problem_id
stringlengths 18
22
| source
stringclasses 1
value | task_type
stringclasses 1
value | in_source_id
stringlengths 13
58
| prompt
stringlengths 1.1k
25.4k
| golden_diff
stringlengths 145
5.13k
| verification_info
stringlengths 582
39.1k
| num_tokens
int64 271
4.1k
| num_tokens_diff
int64 47
1.02k
|
|---|---|---|---|---|---|---|---|---|
gh_patches_debug_35142
|
rasdani/github-patches
|
git_diff
|
Lightning-Universe__lightning-flash-380
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Flash `Trainer.from_argparse_args` not working
## 🐛 Bug
Looks like from_argparse_args isn't working for flash trainer. Likely related to #343
cc @aribornstein
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `flash/core/trainer.py`
Content:
```
1 # Copyright The PyTorch Lightning team.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 import warnings
15 from argparse import ArgumentParser
16 from functools import wraps
17 from typing import Callable, List, Optional, Union
18
19 import torch
20 from pytorch_lightning import LightningDataModule, LightningModule
21 from pytorch_lightning import Trainer as PlTrainer
22 from pytorch_lightning.callbacks import BaseFinetuning
23 from pytorch_lightning.utilities import rank_zero_warn
24 from pytorch_lightning.utilities.argparse import add_argparse_args, get_init_arguments_and_types, parse_env_variables
25 from pytorch_lightning.utilities.exceptions import MisconfigurationException
26 from torch.utils.data import DataLoader
27
28 import flash
29 from flash.core.finetuning import _DEFAULTS_FINETUNE_STRATEGIES, instantiate_default_finetuning_callbacks
30
31
32 def _defaults_from_env_vars(fn: Callable) -> Callable:
33 """Copy of ``pytorch_lightning.trainer.connectors.env_vars_connector._defaults_from_env_vars``. Required to fix
34 build error in readthedocs."""
35
36 @wraps(fn)
37 def insert_env_defaults(self, *args, **kwargs):
38 cls = self.__class__ # get the class
39 if args: # inace any args passed move them to kwargs
40 # parse only the argument names
41 cls_arg_names = [arg[0] for arg in get_init_arguments_and_types(cls)]
42 # convert args to kwargs
43 kwargs.update({k: v for k, v in zip(cls_arg_names, args)})
44 env_variables = vars(parse_env_variables(cls))
45 # update the kwargs by env variables
46 kwargs = dict(list(env_variables.items()) + list(kwargs.items()))
47
48 # all args were already moved to kwargs
49 return fn(self, **kwargs)
50
51 return insert_env_defaults
52
53
54 class Trainer(PlTrainer):
55
56 @_defaults_from_env_vars
57 def __init__(self, *args, **kwargs):
58 if flash._IS_TESTING:
59 if torch.cuda.is_available():
60 kwargs["gpus"] = 1
61 kwargs["max_epochs"] = 3
62 kwargs["limit_train_batches"] = 1.0
63 kwargs["limit_val_batches"] = 1.0
64 kwargs["limit_test_batches"] = 1.0
65 kwargs["fast_dev_run"] = False
66 else:
67 kwargs["fast_dev_run"] = True
68 super().__init__(*args, **kwargs)
69
70 def fit(
71 self,
72 model: LightningModule,
73 train_dataloader: Optional[DataLoader] = None,
74 val_dataloaders: Optional[Union[DataLoader, List[DataLoader]]] = None,
75 datamodule: Optional[LightningDataModule] = None,
76 ):
77 r"""
78 Runs the full optimization routine. Same as :meth:`pytorch_lightning.Trainer.fit`
79
80 Args:
81 datamodule: A instance of :class:`LightningDataModule`.
82
83 model: Model to fit.
84
85 train_dataloader: A Pytorch DataLoader with training samples. If the model has
86 a predefined train_dataloader method this will be skipped.
87
88 val_dataloaders: Either a single Pytorch Dataloader or a list of them, specifying validation samples.
89 If the model has a predefined val_dataloaders method this will be skipped
90 """
91 if any(isinstance(c, BaseFinetuning) for c in self.callbacks):
92 # TODO: if we find a finetuning callback in the trainer should we remove it? or just warn the user?
93 warnings.warn("Warning: You are calling fit(), but your trainer is using a fine-tuning callback")
94 return super().fit(model, train_dataloader, val_dataloaders, datamodule)
95
96 def finetune(
97 self,
98 model: LightningModule,
99 train_dataloader: Optional[DataLoader] = None,
100 val_dataloaders: Optional[Union[DataLoader, List[DataLoader]]] = None,
101 datamodule: Optional[LightningDataModule] = None,
102 strategy: Optional[Union[str, BaseFinetuning]] = None,
103 ):
104 r"""
105
106 Runs the full optimization routine. Same as :meth:`pytorch_lightning.Trainer.fit`, but unfreezes layers
107 of the backbone throughout training layers of the backbone throughout training.
108
109 Args:
110 datamodule: A instance of :class:`LightningDataModule`.
111
112 model: Model to fit.
113
114 train_dataloader: A PyTorch DataLoader with training samples. If the model has
115 a predefined train_dataloader method this will be skipped.
116
117 val_dataloaders: Either a single PyTorch Dataloader or a list of them, specifying validation samples.
118 If the model has a predefined val_dataloaders method this will be skipped
119
120 strategy: Should either be a string or a finetuning callback subclassing
121 :class:`pytorch_lightning.callbacks.BaseFinetuning`.
122
123 Default strategies can be enabled with these strings:
124
125 - ``"no_freeze"``,
126 - ``"freeze"``,
127 - ``"freeze_unfreeze"``,
128 - ``"unfreeze_milestones"``.
129 """
130 self._resolve_callbacks(model, strategy)
131 return super().fit(model, train_dataloader, val_dataloaders, datamodule)
132
133 def _resolve_callbacks(self, model, strategy):
134 """
135 This function is used to select the `BaseFinetuning` to be used for finetuning.
136 """
137 if strategy is not None and not isinstance(strategy, (str, BaseFinetuning)):
138 raise MisconfigurationException(
139 "strategy should be a ``pytorch_lightning.callbacks.BaseFinetuning``"
140 f"callback or a str within {list(_DEFAULTS_FINETUNE_STRATEGIES.keys())}"
141 )
142
143 if isinstance(strategy, BaseFinetuning):
144 callback = [strategy]
145 else:
146 # todo: change to ``configure_callbacks`` when merged to Lightning.
147 model_callback = model.configure_finetune_callback()
148 if len(model_callback) > 1:
149 raise MisconfigurationException(
150 f"{model} configure_finetune_callback should create a list with only 1 callback"
151 )
152 if len(model_callback) == 1:
153 if strategy is not None:
154 rank_zero_warn(
155 "The model contains a default finetune callback. The provided {strategy} will be overriden.\n"
156 " HINT: Provide a `BaseFinetuning` callback as strategy to make it prioritized. ", UserWarning
157 )
158 callback = model_callback
159 else:
160 callback = instantiate_default_finetuning_callbacks(strategy)
161
162 self.callbacks = self._merge_callbacks(self.callbacks, callback)
163
164 @staticmethod
165 def _merge_callbacks(old_callbacks: List, new_callbacks: List) -> List:
166 """
167 This function keeps only 1 instance of each callback type,
168 extending new_callbacks with old_callbacks
169 """
170 if len(new_callbacks) == 0:
171 return old_callbacks
172 new_callbacks_types = set(type(c) for c in new_callbacks)
173 old_callbacks_types = set(type(c) for c in old_callbacks)
174 override_types = new_callbacks_types.intersection(old_callbacks_types)
175 new_callbacks.extend(c for c in old_callbacks if type(c) not in override_types)
176 return new_callbacks
177
178 @classmethod
179 def add_argparse_args(cls, *args, **kwargs) -> ArgumentParser:
180 # the lightning trainer implementation does not support subclasses.
181 # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447
182 return add_argparse_args(PlTrainer, *args, **kwargs)
183
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/flash/core/trainer.py b/flash/core/trainer.py
--- a/flash/core/trainer.py
+++ b/flash/core/trainer.py
@@ -11,8 +11,9 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
+import inspect
import warnings
-from argparse import ArgumentParser
+from argparse import ArgumentParser, Namespace
from functools import wraps
from typing import Callable, List, Optional, Union
@@ -29,6 +30,22 @@
from flash.core.finetuning import _DEFAULTS_FINETUNE_STRATEGIES, instantiate_default_finetuning_callbacks
+def from_argparse_args(cls, args: Union[Namespace, ArgumentParser], **kwargs):
+ """Modified version of ``pytorch_lightning.utilities.argparse.from_argparse_args`` which populates ``valid_kwargs``
+ from ``pytorch_lightning.Trainer``."""
+ if isinstance(args, ArgumentParser):
+ args = cls.parse_argparser(args)
+
+ params = vars(args)
+
+ # we only want to pass in valid PLTrainer args, the rest may be user specific
+ valid_kwargs = inspect.signature(PlTrainer.__init__).parameters
+ trainer_kwargs = dict((name, params[name]) for name in valid_kwargs if name in params)
+ trainer_kwargs.update(**kwargs)
+
+ return cls(**trainer_kwargs)
+
+
def _defaults_from_env_vars(fn: Callable) -> Callable:
"""Copy of ``pytorch_lightning.trainer.connectors.env_vars_connector._defaults_from_env_vars``. Required to fix
build error in readthedocs."""
@@ -180,3 +197,9 @@
# the lightning trainer implementation does not support subclasses.
# context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447
return add_argparse_args(PlTrainer, *args, **kwargs)
+
+ @classmethod
+ def from_argparse_args(cls, args: Union[Namespace, ArgumentParser], **kwargs) -> 'Trainer':
+ # the lightning trainer implementation does not support subclasses.
+ # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447
+ return from_argparse_args(PlTrainer, args, **kwargs)
|
{"golden_diff": "diff --git a/flash/core/trainer.py b/flash/core/trainer.py\n--- a/flash/core/trainer.py\n+++ b/flash/core/trainer.py\n@@ -11,8 +11,9 @@\n # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n # See the License for the specific language governing permissions and\n # limitations under the License.\n+import inspect\n import warnings\n-from argparse import ArgumentParser\n+from argparse import ArgumentParser, Namespace\n from functools import wraps\n from typing import Callable, List, Optional, Union\n \n@@ -29,6 +30,22 @@\n from flash.core.finetuning import _DEFAULTS_FINETUNE_STRATEGIES, instantiate_default_finetuning_callbacks\n \n \n+def from_argparse_args(cls, args: Union[Namespace, ArgumentParser], **kwargs):\n+ \"\"\"Modified version of ``pytorch_lightning.utilities.argparse.from_argparse_args`` which populates ``valid_kwargs``\n+ from ``pytorch_lightning.Trainer``.\"\"\"\n+ if isinstance(args, ArgumentParser):\n+ args = cls.parse_argparser(args)\n+\n+ params = vars(args)\n+\n+ # we only want to pass in valid PLTrainer args, the rest may be user specific\n+ valid_kwargs = inspect.signature(PlTrainer.__init__).parameters\n+ trainer_kwargs = dict((name, params[name]) for name in valid_kwargs if name in params)\n+ trainer_kwargs.update(**kwargs)\n+\n+ return cls(**trainer_kwargs)\n+\n+\n def _defaults_from_env_vars(fn: Callable) -> Callable:\n \"\"\"Copy of ``pytorch_lightning.trainer.connectors.env_vars_connector._defaults_from_env_vars``. Required to fix\n build error in readthedocs.\"\"\"\n@@ -180,3 +197,9 @@\n # the lightning trainer implementation does not support subclasses.\n # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447\n return add_argparse_args(PlTrainer, *args, **kwargs)\n+\n+ @classmethod\n+ def from_argparse_args(cls, args: Union[Namespace, ArgumentParser], **kwargs) -> 'Trainer':\n+ # the lightning trainer implementation does not support subclasses.\n+ # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447\n+ return from_argparse_args(PlTrainer, args, **kwargs)\n", "issue": "Flash `Trainer.from_argparse_args` not working\n## \ud83d\udc1b Bug\r\n\r\nLooks like from_argparse_args isn't working for flash trainer. Likely related to #343\r\n\r\ncc @aribornstein \n", "before_files": [{"content": "# Copyright The PyTorch Lightning team.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nimport warnings\nfrom argparse import ArgumentParser\nfrom functools import wraps\nfrom typing import Callable, List, Optional, Union\n\nimport torch\nfrom pytorch_lightning import LightningDataModule, LightningModule\nfrom pytorch_lightning import Trainer as PlTrainer\nfrom pytorch_lightning.callbacks import BaseFinetuning\nfrom pytorch_lightning.utilities import rank_zero_warn\nfrom pytorch_lightning.utilities.argparse import add_argparse_args, get_init_arguments_and_types, parse_env_variables\nfrom pytorch_lightning.utilities.exceptions import MisconfigurationException\nfrom torch.utils.data import DataLoader\n\nimport flash\nfrom flash.core.finetuning import _DEFAULTS_FINETUNE_STRATEGIES, instantiate_default_finetuning_callbacks\n\n\ndef _defaults_from_env_vars(fn: Callable) -> Callable:\n \"\"\"Copy of ``pytorch_lightning.trainer.connectors.env_vars_connector._defaults_from_env_vars``. Required to fix\n build error in readthedocs.\"\"\"\n\n @wraps(fn)\n def insert_env_defaults(self, *args, **kwargs):\n cls = self.__class__ # get the class\n if args: # inace any args passed move them to kwargs\n # parse only the argument names\n cls_arg_names = [arg[0] for arg in get_init_arguments_and_types(cls)]\n # convert args to kwargs\n kwargs.update({k: v for k, v in zip(cls_arg_names, args)})\n env_variables = vars(parse_env_variables(cls))\n # update the kwargs by env variables\n kwargs = dict(list(env_variables.items()) + list(kwargs.items()))\n\n # all args were already moved to kwargs\n return fn(self, **kwargs)\n\n return insert_env_defaults\n\n\nclass Trainer(PlTrainer):\n\n @_defaults_from_env_vars\n def __init__(self, *args, **kwargs):\n if flash._IS_TESTING:\n if torch.cuda.is_available():\n kwargs[\"gpus\"] = 1\n kwargs[\"max_epochs\"] = 3\n kwargs[\"limit_train_batches\"] = 1.0\n kwargs[\"limit_val_batches\"] = 1.0\n kwargs[\"limit_test_batches\"] = 1.0\n kwargs[\"fast_dev_run\"] = False\n else:\n kwargs[\"fast_dev_run\"] = True\n super().__init__(*args, **kwargs)\n\n def fit(\n self,\n model: LightningModule,\n train_dataloader: Optional[DataLoader] = None,\n val_dataloaders: Optional[Union[DataLoader, List[DataLoader]]] = None,\n datamodule: Optional[LightningDataModule] = None,\n ):\n r\"\"\"\n Runs the full optimization routine. Same as :meth:`pytorch_lightning.Trainer.fit`\n\n Args:\n datamodule: A instance of :class:`LightningDataModule`.\n\n model: Model to fit.\n\n train_dataloader: A Pytorch DataLoader with training samples. If the model has\n a predefined train_dataloader method this will be skipped.\n\n val_dataloaders: Either a single Pytorch Dataloader or a list of them, specifying validation samples.\n If the model has a predefined val_dataloaders method this will be skipped\n \"\"\"\n if any(isinstance(c, BaseFinetuning) for c in self.callbacks):\n # TODO: if we find a finetuning callback in the trainer should we remove it? or just warn the user?\n warnings.warn(\"Warning: You are calling fit(), but your trainer is using a fine-tuning callback\")\n return super().fit(model, train_dataloader, val_dataloaders, datamodule)\n\n def finetune(\n self,\n model: LightningModule,\n train_dataloader: Optional[DataLoader] = None,\n val_dataloaders: Optional[Union[DataLoader, List[DataLoader]]] = None,\n datamodule: Optional[LightningDataModule] = None,\n strategy: Optional[Union[str, BaseFinetuning]] = None,\n ):\n r\"\"\"\n\n Runs the full optimization routine. Same as :meth:`pytorch_lightning.Trainer.fit`, but unfreezes layers\n of the backbone throughout training layers of the backbone throughout training.\n\n Args:\n datamodule: A instance of :class:`LightningDataModule`.\n\n model: Model to fit.\n\n train_dataloader: A PyTorch DataLoader with training samples. If the model has\n a predefined train_dataloader method this will be skipped.\n\n val_dataloaders: Either a single PyTorch Dataloader or a list of them, specifying validation samples.\n If the model has a predefined val_dataloaders method this will be skipped\n\n strategy: Should either be a string or a finetuning callback subclassing\n :class:`pytorch_lightning.callbacks.BaseFinetuning`.\n\n Default strategies can be enabled with these strings:\n\n - ``\"no_freeze\"``,\n - ``\"freeze\"``,\n - ``\"freeze_unfreeze\"``,\n - ``\"unfreeze_milestones\"``.\n \"\"\"\n self._resolve_callbacks(model, strategy)\n return super().fit(model, train_dataloader, val_dataloaders, datamodule)\n\n def _resolve_callbacks(self, model, strategy):\n \"\"\"\n This function is used to select the `BaseFinetuning` to be used for finetuning.\n \"\"\"\n if strategy is not None and not isinstance(strategy, (str, BaseFinetuning)):\n raise MisconfigurationException(\n \"strategy should be a ``pytorch_lightning.callbacks.BaseFinetuning``\"\n f\"callback or a str within {list(_DEFAULTS_FINETUNE_STRATEGIES.keys())}\"\n )\n\n if isinstance(strategy, BaseFinetuning):\n callback = [strategy]\n else:\n # todo: change to ``configure_callbacks`` when merged to Lightning.\n model_callback = model.configure_finetune_callback()\n if len(model_callback) > 1:\n raise MisconfigurationException(\n f\"{model} configure_finetune_callback should create a list with only 1 callback\"\n )\n if len(model_callback) == 1:\n if strategy is not None:\n rank_zero_warn(\n \"The model contains a default finetune callback. The provided {strategy} will be overriden.\\n\"\n \" HINT: Provide a `BaseFinetuning` callback as strategy to make it prioritized. \", UserWarning\n )\n callback = model_callback\n else:\n callback = instantiate_default_finetuning_callbacks(strategy)\n\n self.callbacks = self._merge_callbacks(self.callbacks, callback)\n\n @staticmethod\n def _merge_callbacks(old_callbacks: List, new_callbacks: List) -> List:\n \"\"\"\n This function keeps only 1 instance of each callback type,\n extending new_callbacks with old_callbacks\n \"\"\"\n if len(new_callbacks) == 0:\n return old_callbacks\n new_callbacks_types = set(type(c) for c in new_callbacks)\n old_callbacks_types = set(type(c) for c in old_callbacks)\n override_types = new_callbacks_types.intersection(old_callbacks_types)\n new_callbacks.extend(c for c in old_callbacks if type(c) not in override_types)\n return new_callbacks\n\n @classmethod\n def add_argparse_args(cls, *args, **kwargs) -> ArgumentParser:\n # the lightning trainer implementation does not support subclasses.\n # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447\n return add_argparse_args(PlTrainer, *args, **kwargs)\n", "path": "flash/core/trainer.py"}], "after_files": [{"content": "# Copyright The PyTorch Lightning team.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nimport inspect\nimport warnings\nfrom argparse import ArgumentParser, Namespace\nfrom functools import wraps\nfrom typing import Callable, List, Optional, Union\n\nimport torch\nfrom pytorch_lightning import LightningDataModule, LightningModule\nfrom pytorch_lightning import Trainer as PlTrainer\nfrom pytorch_lightning.callbacks import BaseFinetuning\nfrom pytorch_lightning.utilities import rank_zero_warn\nfrom pytorch_lightning.utilities.argparse import add_argparse_args, get_init_arguments_and_types, parse_env_variables\nfrom pytorch_lightning.utilities.exceptions import MisconfigurationException\nfrom torch.utils.data import DataLoader\n\nimport flash\nfrom flash.core.finetuning import _DEFAULTS_FINETUNE_STRATEGIES, instantiate_default_finetuning_callbacks\n\n\ndef from_argparse_args(cls, args: Union[Namespace, ArgumentParser], **kwargs):\n \"\"\"Modified version of ``pytorch_lightning.utilities.argparse.from_argparse_args`` which populates ``valid_kwargs``\n from ``pytorch_lightning.Trainer``.\"\"\"\n if isinstance(args, ArgumentParser):\n args = cls.parse_argparser(args)\n\n params = vars(args)\n\n # we only want to pass in valid PLTrainer args, the rest may be user specific\n valid_kwargs = inspect.signature(PlTrainer.__init__).parameters\n trainer_kwargs = dict((name, params[name]) for name in valid_kwargs if name in params)\n trainer_kwargs.update(**kwargs)\n\n return cls(**trainer_kwargs)\n\n\ndef _defaults_from_env_vars(fn: Callable) -> Callable:\n \"\"\"Copy of ``pytorch_lightning.trainer.connectors.env_vars_connector._defaults_from_env_vars``. Required to fix\n build error in readthedocs.\"\"\"\n\n @wraps(fn)\n def insert_env_defaults(self, *args, **kwargs):\n cls = self.__class__ # get the class\n if args: # inace any args passed move them to kwargs\n # parse only the argument names\n cls_arg_names = [arg[0] for arg in get_init_arguments_and_types(cls)]\n # convert args to kwargs\n kwargs.update({k: v for k, v in zip(cls_arg_names, args)})\n env_variables = vars(parse_env_variables(cls))\n # update the kwargs by env variables\n kwargs = dict(list(env_variables.items()) + list(kwargs.items()))\n\n # all args were already moved to kwargs\n return fn(self, **kwargs)\n\n return insert_env_defaults\n\n\nclass Trainer(PlTrainer):\n\n @_defaults_from_env_vars\n def __init__(self, *args, **kwargs):\n if flash._IS_TESTING:\n if torch.cuda.is_available():\n kwargs[\"gpus\"] = 1\n kwargs[\"max_epochs\"] = 3\n kwargs[\"limit_train_batches\"] = 1.0\n kwargs[\"limit_val_batches\"] = 1.0\n kwargs[\"limit_test_batches\"] = 1.0\n kwargs[\"fast_dev_run\"] = False\n else:\n kwargs[\"fast_dev_run\"] = True\n super().__init__(*args, **kwargs)\n\n def fit(\n self,\n model: LightningModule,\n train_dataloader: Optional[DataLoader] = None,\n val_dataloaders: Optional[Union[DataLoader, List[DataLoader]]] = None,\n datamodule: Optional[LightningDataModule] = None,\n ):\n r\"\"\"\n Runs the full optimization routine. Same as :meth:`pytorch_lightning.Trainer.fit`\n\n Args:\n datamodule: A instance of :class:`LightningDataModule`.\n\n model: Model to fit.\n\n train_dataloader: A Pytorch DataLoader with training samples. If the model has\n a predefined train_dataloader method this will be skipped.\n\n val_dataloaders: Either a single Pytorch Dataloader or a list of them, specifying validation samples.\n If the model has a predefined val_dataloaders method this will be skipped\n \"\"\"\n if any(isinstance(c, BaseFinetuning) for c in self.callbacks):\n # TODO: if we find a finetuning callback in the trainer should we remove it? or just warn the user?\n warnings.warn(\"Warning: You are calling fit(), but your trainer is using a fine-tuning callback\")\n return super().fit(model, train_dataloader, val_dataloaders, datamodule)\n\n def finetune(\n self,\n model: LightningModule,\n train_dataloader: Optional[DataLoader] = None,\n val_dataloaders: Optional[Union[DataLoader, List[DataLoader]]] = None,\n datamodule: Optional[LightningDataModule] = None,\n strategy: Optional[Union[str, BaseFinetuning]] = None,\n ):\n r\"\"\"\n\n Runs the full optimization routine. Same as :meth:`pytorch_lightning.Trainer.fit`, but unfreezes layers\n of the backbone throughout training layers of the backbone throughout training.\n\n Args:\n datamodule: A instance of :class:`LightningDataModule`.\n\n model: Model to fit.\n\n train_dataloader: A PyTorch DataLoader with training samples. If the model has\n a predefined train_dataloader method this will be skipped.\n\n val_dataloaders: Either a single PyTorch Dataloader or a list of them, specifying validation samples.\n If the model has a predefined val_dataloaders method this will be skipped\n\n strategy: Should either be a string or a finetuning callback subclassing\n :class:`pytorch_lightning.callbacks.BaseFinetuning`.\n\n Default strategies can be enabled with these strings:\n\n - ``\"no_freeze\"``,\n - ``\"freeze\"``,\n - ``\"freeze_unfreeze\"``,\n - ``\"unfreeze_milestones\"``.\n \"\"\"\n self._resolve_callbacks(model, strategy)\n return super().fit(model, train_dataloader, val_dataloaders, datamodule)\n\n def _resolve_callbacks(self, model, strategy):\n \"\"\"\n This function is used to select the `BaseFinetuning` to be used for finetuning.\n \"\"\"\n if strategy is not None and not isinstance(strategy, (str, BaseFinetuning)):\n raise MisconfigurationException(\n \"strategy should be a ``pytorch_lightning.callbacks.BaseFinetuning``\"\n f\"callback or a str within {list(_DEFAULTS_FINETUNE_STRATEGIES.keys())}\"\n )\n\n if isinstance(strategy, BaseFinetuning):\n callback = [strategy]\n else:\n # todo: change to ``configure_callbacks`` when merged to Lightning.\n model_callback = model.configure_finetune_callback()\n if len(model_callback) > 1:\n raise MisconfigurationException(\n f\"{model} configure_finetune_callback should create a list with only 1 callback\"\n )\n if len(model_callback) == 1:\n if strategy is not None:\n rank_zero_warn(\n \"The model contains a default finetune callback. The provided {strategy} will be overriden.\\n\"\n \" HINT: Provide a `BaseFinetuning` callback as strategy to make it prioritized. \", UserWarning\n )\n callback = model_callback\n else:\n callback = instantiate_default_finetuning_callbacks(strategy)\n\n self.callbacks = self._merge_callbacks(self.callbacks, callback)\n\n @staticmethod\n def _merge_callbacks(old_callbacks: List, new_callbacks: List) -> List:\n \"\"\"\n This function keeps only 1 instance of each callback type,\n extending new_callbacks with old_callbacks\n \"\"\"\n if len(new_callbacks) == 0:\n return old_callbacks\n new_callbacks_types = set(type(c) for c in new_callbacks)\n old_callbacks_types = set(type(c) for c in old_callbacks)\n override_types = new_callbacks_types.intersection(old_callbacks_types)\n new_callbacks.extend(c for c in old_callbacks if type(c) not in override_types)\n return new_callbacks\n\n @classmethod\n def add_argparse_args(cls, *args, **kwargs) -> ArgumentParser:\n # the lightning trainer implementation does not support subclasses.\n # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447\n return add_argparse_args(PlTrainer, *args, **kwargs)\n\n @classmethod\n def from_argparse_args(cls, args: Union[Namespace, ArgumentParser], **kwargs) -> 'Trainer':\n # the lightning trainer implementation does not support subclasses.\n # context: https://github.com/PyTorchLightning/lightning-flash/issues/342#issuecomment-848892447\n return from_argparse_args(PlTrainer, args, **kwargs)\n", "path": "flash/core/trainer.py"}]}
| 2,511 | 545 |
gh_patches_debug_34311
|
rasdani/github-patches
|
git_diff
|
bridgecrewio__checkov-2084
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
False positive for CKV_AZURE_43: check storage account name
I'm building my Storage Account names like this
```
name = "${local.saname_prefix}diagnostics${module.tf-var-project.random_id}
```
With https://github.com/bridgecrewio/checkov/pull/429 merged I now get a Check failure on the SA name:
```
Check: CKV_AZURE_43: "Ensure the Storage Account naming rules"
FAILED for resource: azurerm_storage_account.diagnostics
File: /az_diag_sa.tf:8-22
8 | resource "azurerm_storage_account" "diagnostics" {
9 | #checkov:skip=CKV_AZURE_35:Public access is allowed
10 | name = "${local.saname_prefix}diagnostics${module.tf-var-project.random_id}"
````
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `checkov/terraform/checks/resource/azure/StorageAccountName.py`
Content:
```
1 from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck
2 from checkov.common.models.enums import CheckResult, CheckCategories
3 import re
4 from typing import List
5
6 STO_NAME_REGEX = re.compile('^[a-z0-9]{3,24}$')
7
8
9 class StorageAccountName(BaseResourceCheck):
10 def __init__(self):
11 name = "Ensure Storage Accounts adhere to the naming rules"
12 id = "CKV_AZURE_43"
13 supported_resources = ['azurerm_storage_account']
14 categories = [CheckCategories.CONVENTION]
15 super().__init__(name=name, id=id, categories=categories,
16 supported_resources=supported_resources)
17
18 def scan_resource_conf(self, conf):
19 """
20 The Storage Account naming reference:
21 https://docs.microsoft.com/en-us/azure/storage/common/storage-account-overview#naming-storage-accounts
22 :param conf: azurerm_storage_account configuration
23 :return: <CheckResult>
24 """
25 return CheckResult.PASSED if conf.get('name') and re.findall(STO_NAME_REGEX, str(conf['name'][0])) else CheckResult.FAILED
26
27 def get_evaluated_keys(self) -> List[str]:
28 return ['name']
29
30
31 check = StorageAccountName()
32
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/checkov/terraform/checks/resource/azure/StorageAccountName.py b/checkov/terraform/checks/resource/azure/StorageAccountName.py
--- a/checkov/terraform/checks/resource/azure/StorageAccountName.py
+++ b/checkov/terraform/checks/resource/azure/StorageAccountName.py
@@ -1,31 +1,41 @@
+import re
+from typing import List, Dict, Any
+
from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck
from checkov.common.models.enums import CheckResult, CheckCategories
-import re
-from typing import List
-STO_NAME_REGEX = re.compile('^[a-z0-9]{3,24}$')
+STO_NAME_REGEX = re.compile(r"^[a-z0-9]{3,24}$")
+VARIABLE_REFS = ("local.", "module.", "var.")
class StorageAccountName(BaseResourceCheck):
- def __init__(self):
+ def __init__(self) -> None:
name = "Ensure Storage Accounts adhere to the naming rules"
id = "CKV_AZURE_43"
- supported_resources = ['azurerm_storage_account']
+ supported_resources = ["azurerm_storage_account"]
categories = [CheckCategories.CONVENTION]
- super().__init__(name=name, id=id, categories=categories,
- supported_resources=supported_resources)
+ super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)
- def scan_resource_conf(self, conf):
+ def scan_resource_conf(self, conf: Dict[str, Any]) -> CheckResult:
"""
The Storage Account naming reference:
https://docs.microsoft.com/en-us/azure/storage/common/storage-account-overview#naming-storage-accounts
:param conf: azurerm_storage_account configuration
:return: <CheckResult>
"""
- return CheckResult.PASSED if conf.get('name') and re.findall(STO_NAME_REGEX, str(conf['name'][0])) else CheckResult.FAILED
+ name = conf.get("name")
+ if name:
+ name = name[0]
+ if any(x in name for x in VARIABLE_REFS):
+ # in the case we couldn't evaluate the name, just ignore
+ return CheckResult.UNKNOWN
+ if re.findall(STO_NAME_REGEX, str(conf["name"][0])):
+ return CheckResult.PASSED
+
+ return CheckResult.FAILED
def get_evaluated_keys(self) -> List[str]:
- return ['name']
+ return ["name"]
check = StorageAccountName()
|
{"golden_diff": "diff --git a/checkov/terraform/checks/resource/azure/StorageAccountName.py b/checkov/terraform/checks/resource/azure/StorageAccountName.py\n--- a/checkov/terraform/checks/resource/azure/StorageAccountName.py\n+++ b/checkov/terraform/checks/resource/azure/StorageAccountName.py\n@@ -1,31 +1,41 @@\n+import re\n+from typing import List, Dict, Any\n+\n from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck\n from checkov.common.models.enums import CheckResult, CheckCategories\n-import re\n-from typing import List\n \n-STO_NAME_REGEX = re.compile('^[a-z0-9]{3,24}$')\n+STO_NAME_REGEX = re.compile(r\"^[a-z0-9]{3,24}$\")\n+VARIABLE_REFS = (\"local.\", \"module.\", \"var.\")\n \n \n class StorageAccountName(BaseResourceCheck):\n- def __init__(self):\n+ def __init__(self) -> None:\n name = \"Ensure Storage Accounts adhere to the naming rules\"\n id = \"CKV_AZURE_43\"\n- supported_resources = ['azurerm_storage_account']\n+ supported_resources = [\"azurerm_storage_account\"]\n categories = [CheckCategories.CONVENTION]\n- super().__init__(name=name, id=id, categories=categories,\n- supported_resources=supported_resources)\n+ super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n \n- def scan_resource_conf(self, conf):\n+ def scan_resource_conf(self, conf: Dict[str, Any]) -> CheckResult:\n \"\"\"\n The Storage Account naming reference:\n https://docs.microsoft.com/en-us/azure/storage/common/storage-account-overview#naming-storage-accounts\n :param conf: azurerm_storage_account configuration\n :return: <CheckResult>\n \"\"\"\n- return CheckResult.PASSED if conf.get('name') and re.findall(STO_NAME_REGEX, str(conf['name'][0])) else CheckResult.FAILED\n+ name = conf.get(\"name\")\n+ if name:\n+ name = name[0]\n+ if any(x in name for x in VARIABLE_REFS):\n+ # in the case we couldn't evaluate the name, just ignore\n+ return CheckResult.UNKNOWN\n+ if re.findall(STO_NAME_REGEX, str(conf[\"name\"][0])):\n+ return CheckResult.PASSED\n+\n+ return CheckResult.FAILED\n \n def get_evaluated_keys(self) -> List[str]:\n- return ['name']\n+ return [\"name\"]\n \n \n check = StorageAccountName()\n", "issue": "False positive for CKV_AZURE_43: check storage account name\nI'm building my Storage Account names like this\r\n```\r\nname = \"${local.saname_prefix}diagnostics${module.tf-var-project.random_id}\r\n```\r\n\r\nWith https://github.com/bridgecrewio/checkov/pull/429 merged I now get a Check failure on the SA name:\r\n\r\n```\r\nCheck: CKV_AZURE_43: \"Ensure the Storage Account naming rules\"\r\n\tFAILED for resource: azurerm_storage_account.diagnostics\r\n\tFile: /az_diag_sa.tf:8-22\r\n\r\n\t\t8 | resource \"azurerm_storage_account\" \"diagnostics\" {\r\n\t\t9 | #checkov:skip=CKV_AZURE_35:Public access is allowed\r\n\t\t10 | name = \"${local.saname_prefix}diagnostics${module.tf-var-project.random_id}\"\r\n\r\n````\n", "before_files": [{"content": "from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck\nfrom checkov.common.models.enums import CheckResult, CheckCategories\nimport re\nfrom typing import List\n\nSTO_NAME_REGEX = re.compile('^[a-z0-9]{3,24}$')\n\n\nclass StorageAccountName(BaseResourceCheck):\n def __init__(self):\n name = \"Ensure Storage Accounts adhere to the naming rules\"\n id = \"CKV_AZURE_43\"\n supported_resources = ['azurerm_storage_account']\n categories = [CheckCategories.CONVENTION]\n super().__init__(name=name, id=id, categories=categories,\n supported_resources=supported_resources)\n\n def scan_resource_conf(self, conf):\n \"\"\"\n The Storage Account naming reference:\n https://docs.microsoft.com/en-us/azure/storage/common/storage-account-overview#naming-storage-accounts\n :param conf: azurerm_storage_account configuration\n :return: <CheckResult>\n \"\"\"\n return CheckResult.PASSED if conf.get('name') and re.findall(STO_NAME_REGEX, str(conf['name'][0])) else CheckResult.FAILED\n\n def get_evaluated_keys(self) -> List[str]:\n return ['name']\n\n\ncheck = StorageAccountName()\n", "path": "checkov/terraform/checks/resource/azure/StorageAccountName.py"}], "after_files": [{"content": "import re\nfrom typing import List, Dict, Any\n\nfrom checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck\nfrom checkov.common.models.enums import CheckResult, CheckCategories\n\nSTO_NAME_REGEX = re.compile(r\"^[a-z0-9]{3,24}$\")\nVARIABLE_REFS = (\"local.\", \"module.\", \"var.\")\n\n\nclass StorageAccountName(BaseResourceCheck):\n def __init__(self) -> None:\n name = \"Ensure Storage Accounts adhere to the naming rules\"\n id = \"CKV_AZURE_43\"\n supported_resources = [\"azurerm_storage_account\"]\n categories = [CheckCategories.CONVENTION]\n super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n\n def scan_resource_conf(self, conf: Dict[str, Any]) -> CheckResult:\n \"\"\"\n The Storage Account naming reference:\n https://docs.microsoft.com/en-us/azure/storage/common/storage-account-overview#naming-storage-accounts\n :param conf: azurerm_storage_account configuration\n :return: <CheckResult>\n \"\"\"\n name = conf.get(\"name\")\n if name:\n name = name[0]\n if any(x in name for x in VARIABLE_REFS):\n # in the case we couldn't evaluate the name, just ignore\n return CheckResult.UNKNOWN\n if re.findall(STO_NAME_REGEX, str(conf[\"name\"][0])):\n return CheckResult.PASSED\n\n return CheckResult.FAILED\n\n def get_evaluated_keys(self) -> List[str]:\n return [\"name\"]\n\n\ncheck = StorageAccountName()\n", "path": "checkov/terraform/checks/resource/azure/StorageAccountName.py"}]}
| 792 | 571 |
gh_patches_debug_23360
|
rasdani/github-patches
|
git_diff
|
allegro__ralph-3159
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Doc fixes
Some minor doc fixes with a bit of style change
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/ralph/dashboards/management/commands/push_graphs_to_statsd.py`
Content:
```
1 # -*- coding: utf-8 -*-
2 import logging
3 import textwrap
4
5 from django.conf import settings
6 from django.core.management.base import BaseCommand
7 from django.utils.text import slugify
8
9 from ralph.dashboards.models import Graph
10 from ralph.lib.metrics import build_statsd_client
11
12 logger = logging.getLogger(__name__)
13 PREFIX = settings.STATSD_GRAPHS_PREFIX
14 STATSD_PATH = '{}.{{}}.{{}}'.format(PREFIX)
15
16
17 def normalize(s):
18 s = slugify(s)
19 return s.replace('-', '_')
20
21
22 class Command(BaseCommand):
23 """Push to statsd data generated by graphs."""
24 help = textwrap.dedent(__doc__).strip()
25
26 def handle(self, *args, **kwargs):
27 statsd = build_statsd_client(prefix=STATSD_PATH)
28 graphs = Graph.objects.filter(push_to_statsd=True)
29 for graph in graphs:
30 graph_data = graph.get_data()
31 graph_name = normalize(graph.name)
32 for label, value in zip(graph_data['labels'], graph_data['series']):
33 path = STATSD_PATH.format(graph_name, normalize(label))
34 statsd.gauge(path, value)
35
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py b/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py
--- a/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py
+++ b/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py
@@ -10,8 +10,6 @@
from ralph.lib.metrics import build_statsd_client
logger = logging.getLogger(__name__)
-PREFIX = settings.STATSD_GRAPHS_PREFIX
-STATSD_PATH = '{}.{{}}.{{}}'.format(PREFIX)
def normalize(s):
@@ -24,11 +22,11 @@
help = textwrap.dedent(__doc__).strip()
def handle(self, *args, **kwargs):
- statsd = build_statsd_client(prefix=STATSD_PATH)
+ statsd = build_statsd_client(prefix=settings.STATSD_GRAPHS_PREFIX)
graphs = Graph.objects.filter(push_to_statsd=True)
for graph in graphs:
graph_data = graph.get_data()
graph_name = normalize(graph.name)
for label, value in zip(graph_data['labels'], graph_data['series']):
- path = STATSD_PATH.format(graph_name, normalize(label))
+ path = '.'.join((graph_name, normalize(label)))
statsd.gauge(path, value)
|
{"golden_diff": "diff --git a/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py b/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py\n--- a/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py\n+++ b/src/ralph/dashboards/management/commands/push_graphs_to_statsd.py\n@@ -10,8 +10,6 @@\n from ralph.lib.metrics import build_statsd_client\n \n logger = logging.getLogger(__name__)\n-PREFIX = settings.STATSD_GRAPHS_PREFIX\n-STATSD_PATH = '{}.{{}}.{{}}'.format(PREFIX)\n \n \n def normalize(s):\n@@ -24,11 +22,11 @@\n help = textwrap.dedent(__doc__).strip()\n \n def handle(self, *args, **kwargs):\n- statsd = build_statsd_client(prefix=STATSD_PATH)\n+ statsd = build_statsd_client(prefix=settings.STATSD_GRAPHS_PREFIX)\n graphs = Graph.objects.filter(push_to_statsd=True)\n for graph in graphs:\n graph_data = graph.get_data()\n graph_name = normalize(graph.name)\n for label, value in zip(graph_data['labels'], graph_data['series']):\n- path = STATSD_PATH.format(graph_name, normalize(label))\n+ path = '.'.join((graph_name, normalize(label)))\n statsd.gauge(path, value)\n", "issue": "Doc fixes\nSome minor doc fixes with a bit of style change\n\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\nimport logging\nimport textwrap\n\nfrom django.conf import settings\nfrom django.core.management.base import BaseCommand\nfrom django.utils.text import slugify\n\nfrom ralph.dashboards.models import Graph\nfrom ralph.lib.metrics import build_statsd_client\n\nlogger = logging.getLogger(__name__)\nPREFIX = settings.STATSD_GRAPHS_PREFIX\nSTATSD_PATH = '{}.{{}}.{{}}'.format(PREFIX)\n\n\ndef normalize(s):\n s = slugify(s)\n return s.replace('-', '_')\n\n\nclass Command(BaseCommand):\n \"\"\"Push to statsd data generated by graphs.\"\"\"\n help = textwrap.dedent(__doc__).strip()\n\n def handle(self, *args, **kwargs):\n statsd = build_statsd_client(prefix=STATSD_PATH)\n graphs = Graph.objects.filter(push_to_statsd=True)\n for graph in graphs:\n graph_data = graph.get_data()\n graph_name = normalize(graph.name)\n for label, value in zip(graph_data['labels'], graph_data['series']):\n path = STATSD_PATH.format(graph_name, normalize(label))\n statsd.gauge(path, value)\n", "path": "src/ralph/dashboards/management/commands/push_graphs_to_statsd.py"}], "after_files": [{"content": "# -*- coding: utf-8 -*-\nimport logging\nimport textwrap\n\nfrom django.conf import settings\nfrom django.core.management.base import BaseCommand\nfrom django.utils.text import slugify\n\nfrom ralph.dashboards.models import Graph\nfrom ralph.lib.metrics import build_statsd_client\n\nlogger = logging.getLogger(__name__)\n\n\ndef normalize(s):\n s = slugify(s)\n return s.replace('-', '_')\n\n\nclass Command(BaseCommand):\n \"\"\"Push to statsd data generated by graphs.\"\"\"\n help = textwrap.dedent(__doc__).strip()\n\n def handle(self, *args, **kwargs):\n statsd = build_statsd_client(prefix=settings.STATSD_GRAPHS_PREFIX)\n graphs = Graph.objects.filter(push_to_statsd=True)\n for graph in graphs:\n graph_data = graph.get_data()\n graph_name = normalize(graph.name)\n for label, value in zip(graph_data['labels'], graph_data['series']):\n path = '.'.join((graph_name, normalize(label)))\n statsd.gauge(path, value)\n", "path": "src/ralph/dashboards/management/commands/push_graphs_to_statsd.py"}]}
| 594 | 313 |
gh_patches_debug_14848
|
rasdani/github-patches
|
git_diff
|
MongoEngine__mongoengine-1858
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
select_related() ConnectionError
Hi,
I am having an interesting situation. We have been using MongoEngine in our project for a good few years now and this issue appeared out of nowhere (no update, no change to the code).
Calling `select_related()` on the results of a query raises a `mongoengine.connection.ConnectionError: You have not defined a default connection` Exception
The call that causes the issue:
```credentials = Credential.objects(id__in=ids).select_related()```
I noticed that I am getting the exception only the first time time I call `select_related()` and only on this object. Any subsequent calls (on the same collection) work as expected.
While trying to debug, I got to this:
```
> /usr/local/lib/python2.7/dist-packages/mongoengine/dereference.py(129)_fetch_objects()
127 object_map = {}
128 for collection, dbrefs in self.reference_map.iteritems():
--> 129 if hasattr(collection, 'objects'): # We have a document class for the refs
130 col_name = collection._get_collection_name()
131 refs = [dbref for dbref in dbrefs
ipdb> collection
<class 'insights.models.company.Company'>
ipdb> hasattr(collection, 'objects')
False
ipdb> hasattr(collection, 'objects')
True
```
Can this be caused by some lazy loading or some configuration issue?
Thank you!
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `mongoengine/dereference.py`
Content:
```
1 from bson import DBRef, SON
2 import six
3
4 from mongoengine.base import (BaseDict, BaseList, EmbeddedDocumentList,
5 TopLevelDocumentMetaclass, get_document)
6 from mongoengine.base.datastructures import LazyReference
7 from mongoengine.connection import get_db
8 from mongoengine.document import Document, EmbeddedDocument
9 from mongoengine.fields import DictField, ListField, MapField, ReferenceField
10 from mongoengine.queryset import QuerySet
11
12
13 class DeReference(object):
14 def __call__(self, items, max_depth=1, instance=None, name=None):
15 """
16 Cheaply dereferences the items to a set depth.
17 Also handles the conversion of complex data types.
18
19 :param items: The iterable (dict, list, queryset) to be dereferenced.
20 :param max_depth: The maximum depth to recurse to
21 :param instance: The owning instance used for tracking changes by
22 :class:`~mongoengine.base.ComplexBaseField`
23 :param name: The name of the field, used for tracking changes by
24 :class:`~mongoengine.base.ComplexBaseField`
25 :param get: A boolean determining if being called by __get__
26 """
27 if items is None or isinstance(items, six.string_types):
28 return items
29
30 # cheapest way to convert a queryset to a list
31 # list(queryset) uses a count() query to determine length
32 if isinstance(items, QuerySet):
33 items = [i for i in items]
34
35 self.max_depth = max_depth
36 doc_type = None
37
38 if instance and isinstance(instance, (Document, EmbeddedDocument,
39 TopLevelDocumentMetaclass)):
40 doc_type = instance._fields.get(name)
41 while hasattr(doc_type, 'field'):
42 doc_type = doc_type.field
43
44 if isinstance(doc_type, ReferenceField):
45 field = doc_type
46 doc_type = doc_type.document_type
47 is_list = not hasattr(items, 'items')
48
49 if is_list and all([i.__class__ == doc_type for i in items]):
50 return items
51 elif not is_list and all(
52 [i.__class__ == doc_type for i in items.values()]):
53 return items
54 elif not field.dbref:
55 if not hasattr(items, 'items'):
56
57 def _get_items(items):
58 new_items = []
59 for v in items:
60 if isinstance(v, list):
61 new_items.append(_get_items(v))
62 elif not isinstance(v, (DBRef, Document)):
63 new_items.append(field.to_python(v))
64 else:
65 new_items.append(v)
66 return new_items
67
68 items = _get_items(items)
69 else:
70 items = {
71 k: (v if isinstance(v, (DBRef, Document))
72 else field.to_python(v))
73 for k, v in items.iteritems()
74 }
75
76 self.reference_map = self._find_references(items)
77 self.object_map = self._fetch_objects(doc_type=doc_type)
78 return self._attach_objects(items, 0, instance, name)
79
80 def _find_references(self, items, depth=0):
81 """
82 Recursively finds all db references to be dereferenced
83
84 :param items: The iterable (dict, list, queryset)
85 :param depth: The current depth of recursion
86 """
87 reference_map = {}
88 if not items or depth >= self.max_depth:
89 return reference_map
90
91 # Determine the iterator to use
92 if isinstance(items, dict):
93 iterator = items.values()
94 else:
95 iterator = items
96
97 # Recursively find dbreferences
98 depth += 1
99 for item in iterator:
100 if isinstance(item, (Document, EmbeddedDocument)):
101 for field_name, field in item._fields.iteritems():
102 v = item._data.get(field_name, None)
103 if isinstance(v, LazyReference):
104 # LazyReference inherits DBRef but should not be dereferenced here !
105 continue
106 elif isinstance(v, DBRef):
107 reference_map.setdefault(field.document_type, set()).add(v.id)
108 elif isinstance(v, (dict, SON)) and '_ref' in v:
109 reference_map.setdefault(get_document(v['_cls']), set()).add(v['_ref'].id)
110 elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:
111 field_cls = getattr(getattr(field, 'field', None), 'document_type', None)
112 references = self._find_references(v, depth)
113 for key, refs in references.iteritems():
114 if isinstance(field_cls, (Document, TopLevelDocumentMetaclass)):
115 key = field_cls
116 reference_map.setdefault(key, set()).update(refs)
117 elif isinstance(item, LazyReference):
118 # LazyReference inherits DBRef but should not be dereferenced here !
119 continue
120 elif isinstance(item, DBRef):
121 reference_map.setdefault(item.collection, set()).add(item.id)
122 elif isinstance(item, (dict, SON)) and '_ref' in item:
123 reference_map.setdefault(get_document(item['_cls']), set()).add(item['_ref'].id)
124 elif isinstance(item, (dict, list, tuple)) and depth - 1 <= self.max_depth:
125 references = self._find_references(item, depth - 1)
126 for key, refs in references.iteritems():
127 reference_map.setdefault(key, set()).update(refs)
128
129 return reference_map
130
131 def _fetch_objects(self, doc_type=None):
132 """Fetch all references and convert to their document objects
133 """
134 object_map = {}
135 for collection, dbrefs in self.reference_map.iteritems():
136 if hasattr(collection, 'objects'): # We have a document class for the refs
137 col_name = collection._get_collection_name()
138 refs = [dbref for dbref in dbrefs
139 if (col_name, dbref) not in object_map]
140 references = collection.objects.in_bulk(refs)
141 for key, doc in references.iteritems():
142 object_map[(col_name, key)] = doc
143 else: # Generic reference: use the refs data to convert to document
144 if isinstance(doc_type, (ListField, DictField, MapField,)):
145 continue
146
147 refs = [dbref for dbref in dbrefs
148 if (collection, dbref) not in object_map]
149
150 if doc_type:
151 references = doc_type._get_db()[collection].find({'_id': {'$in': refs}})
152 for ref in references:
153 doc = doc_type._from_son(ref)
154 object_map[(collection, doc.id)] = doc
155 else:
156 references = get_db()[collection].find({'_id': {'$in': refs}})
157 for ref in references:
158 if '_cls' in ref:
159 doc = get_document(ref['_cls'])._from_son(ref)
160 elif doc_type is None:
161 doc = get_document(
162 ''.join(x.capitalize()
163 for x in collection.split('_')))._from_son(ref)
164 else:
165 doc = doc_type._from_son(ref)
166 object_map[(collection, doc.id)] = doc
167 return object_map
168
169 def _attach_objects(self, items, depth=0, instance=None, name=None):
170 """
171 Recursively finds all db references to be dereferenced
172
173 :param items: The iterable (dict, list, queryset)
174 :param depth: The current depth of recursion
175 :param instance: The owning instance used for tracking changes by
176 :class:`~mongoengine.base.ComplexBaseField`
177 :param name: The name of the field, used for tracking changes by
178 :class:`~mongoengine.base.ComplexBaseField`
179 """
180 if not items:
181 if isinstance(items, (BaseDict, BaseList)):
182 return items
183
184 if instance:
185 if isinstance(items, dict):
186 return BaseDict(items, instance, name)
187 else:
188 return BaseList(items, instance, name)
189
190 if isinstance(items, (dict, SON)):
191 if '_ref' in items:
192 return self.object_map.get(
193 (items['_ref'].collection, items['_ref'].id), items)
194 elif '_cls' in items:
195 doc = get_document(items['_cls'])._from_son(items)
196 _cls = doc._data.pop('_cls', None)
197 del items['_cls']
198 doc._data = self._attach_objects(doc._data, depth, doc, None)
199 if _cls is not None:
200 doc._data['_cls'] = _cls
201 return doc
202
203 if not hasattr(items, 'items'):
204 is_list = True
205 list_type = BaseList
206 if isinstance(items, EmbeddedDocumentList):
207 list_type = EmbeddedDocumentList
208 as_tuple = isinstance(items, tuple)
209 iterator = enumerate(items)
210 data = []
211 else:
212 is_list = False
213 iterator = items.iteritems()
214 data = {}
215
216 depth += 1
217 for k, v in iterator:
218 if is_list:
219 data.append(v)
220 else:
221 data[k] = v
222
223 if k in self.object_map and not is_list:
224 data[k] = self.object_map[k]
225 elif isinstance(v, (Document, EmbeddedDocument)):
226 for field_name in v._fields:
227 v = data[k]._data.get(field_name, None)
228 if isinstance(v, DBRef):
229 data[k]._data[field_name] = self.object_map.get(
230 (v.collection, v.id), v)
231 elif isinstance(v, (dict, SON)) and '_ref' in v:
232 data[k]._data[field_name] = self.object_map.get(
233 (v['_ref'].collection, v['_ref'].id), v)
234 elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:
235 item_name = six.text_type('{0}.{1}.{2}').format(name, k, field_name)
236 data[k]._data[field_name] = self._attach_objects(v, depth, instance=instance, name=item_name)
237 elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:
238 item_name = '%s.%s' % (name, k) if name else name
239 data[k] = self._attach_objects(v, depth - 1, instance=instance, name=item_name)
240 elif isinstance(v, DBRef) and hasattr(v, 'id'):
241 data[k] = self.object_map.get((v.collection, v.id), v)
242
243 if instance and name:
244 if is_list:
245 return tuple(data) if as_tuple else list_type(data, instance, name)
246 return BaseDict(data, instance, name)
247 depth += 1
248 return data
249
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/mongoengine/dereference.py b/mongoengine/dereference.py
--- a/mongoengine/dereference.py
+++ b/mongoengine/dereference.py
@@ -133,7 +133,12 @@
"""
object_map = {}
for collection, dbrefs in self.reference_map.iteritems():
- if hasattr(collection, 'objects'): # We have a document class for the refs
+
+ # we use getattr instead of hasattr because as hasattr swallows any exception under python2
+ # so it could hide nasty things without raising exceptions (cfr bug #1688))
+ ref_document_cls_exists = (getattr(collection, 'objects', None) is not None)
+
+ if ref_document_cls_exists:
col_name = collection._get_collection_name()
refs = [dbref for dbref in dbrefs
if (col_name, dbref) not in object_map]
|
{"golden_diff": "diff --git a/mongoengine/dereference.py b/mongoengine/dereference.py\n--- a/mongoengine/dereference.py\n+++ b/mongoengine/dereference.py\n@@ -133,7 +133,12 @@\n \"\"\"\n object_map = {}\n for collection, dbrefs in self.reference_map.iteritems():\n- if hasattr(collection, 'objects'): # We have a document class for the refs\n+\n+ # we use getattr instead of hasattr because as hasattr swallows any exception under python2\n+ # so it could hide nasty things without raising exceptions (cfr bug #1688))\n+ ref_document_cls_exists = (getattr(collection, 'objects', None) is not None)\n+\n+ if ref_document_cls_exists:\n col_name = collection._get_collection_name()\n refs = [dbref for dbref in dbrefs\n if (col_name, dbref) not in object_map]\n", "issue": "select_related() ConnectionError \nHi,\r\n\r\nI am having an interesting situation. We have been using MongoEngine in our project for a good few years now and this issue appeared out of nowhere (no update, no change to the code).\r\n\r\nCalling `select_related()` on the results of a query raises a `mongoengine.connection.ConnectionError: You have not defined a default connection` Exception\r\n\r\nThe call that causes the issue:\r\n```credentials = Credential.objects(id__in=ids).select_related()```\r\n\r\nI noticed that I am getting the exception only the first time time I call `select_related()` and only on this object. Any subsequent calls (on the same collection) work as expected. \r\n\r\nWhile trying to debug, I got to this:\r\n```\r\n> /usr/local/lib/python2.7/dist-packages/mongoengine/dereference.py(129)_fetch_objects()\r\n 127 object_map = {}\r\n 128 for collection, dbrefs in self.reference_map.iteritems():\r\n--> 129 if hasattr(collection, 'objects'): # We have a document class for the refs\r\n 130 col_name = collection._get_collection_name()\r\n 131 refs = [dbref for dbref in dbrefs\r\n\r\nipdb> collection\r\n<class 'insights.models.company.Company'>\r\nipdb> hasattr(collection, 'objects')\r\nFalse\r\nipdb> hasattr(collection, 'objects')\r\nTrue\r\n```\r\n\r\nCan this be caused by some lazy loading or some configuration issue?\r\n\r\nThank you!\n", "before_files": [{"content": "from bson import DBRef, SON\nimport six\n\nfrom mongoengine.base import (BaseDict, BaseList, EmbeddedDocumentList,\n TopLevelDocumentMetaclass, get_document)\nfrom mongoengine.base.datastructures import LazyReference\nfrom mongoengine.connection import get_db\nfrom mongoengine.document import Document, EmbeddedDocument\nfrom mongoengine.fields import DictField, ListField, MapField, ReferenceField\nfrom mongoengine.queryset import QuerySet\n\n\nclass DeReference(object):\n def __call__(self, items, max_depth=1, instance=None, name=None):\n \"\"\"\n Cheaply dereferences the items to a set depth.\n Also handles the conversion of complex data types.\n\n :param items: The iterable (dict, list, queryset) to be dereferenced.\n :param max_depth: The maximum depth to recurse to\n :param instance: The owning instance used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n :param name: The name of the field, used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n :param get: A boolean determining if being called by __get__\n \"\"\"\n if items is None or isinstance(items, six.string_types):\n return items\n\n # cheapest way to convert a queryset to a list\n # list(queryset) uses a count() query to determine length\n if isinstance(items, QuerySet):\n items = [i for i in items]\n\n self.max_depth = max_depth\n doc_type = None\n\n if instance and isinstance(instance, (Document, EmbeddedDocument,\n TopLevelDocumentMetaclass)):\n doc_type = instance._fields.get(name)\n while hasattr(doc_type, 'field'):\n doc_type = doc_type.field\n\n if isinstance(doc_type, ReferenceField):\n field = doc_type\n doc_type = doc_type.document_type\n is_list = not hasattr(items, 'items')\n\n if is_list and all([i.__class__ == doc_type for i in items]):\n return items\n elif not is_list and all(\n [i.__class__ == doc_type for i in items.values()]):\n return items\n elif not field.dbref:\n if not hasattr(items, 'items'):\n\n def _get_items(items):\n new_items = []\n for v in items:\n if isinstance(v, list):\n new_items.append(_get_items(v))\n elif not isinstance(v, (DBRef, Document)):\n new_items.append(field.to_python(v))\n else:\n new_items.append(v)\n return new_items\n\n items = _get_items(items)\n else:\n items = {\n k: (v if isinstance(v, (DBRef, Document))\n else field.to_python(v))\n for k, v in items.iteritems()\n }\n\n self.reference_map = self._find_references(items)\n self.object_map = self._fetch_objects(doc_type=doc_type)\n return self._attach_objects(items, 0, instance, name)\n\n def _find_references(self, items, depth=0):\n \"\"\"\n Recursively finds all db references to be dereferenced\n\n :param items: The iterable (dict, list, queryset)\n :param depth: The current depth of recursion\n \"\"\"\n reference_map = {}\n if not items or depth >= self.max_depth:\n return reference_map\n\n # Determine the iterator to use\n if isinstance(items, dict):\n iterator = items.values()\n else:\n iterator = items\n\n # Recursively find dbreferences\n depth += 1\n for item in iterator:\n if isinstance(item, (Document, EmbeddedDocument)):\n for field_name, field in item._fields.iteritems():\n v = item._data.get(field_name, None)\n if isinstance(v, LazyReference):\n # LazyReference inherits DBRef but should not be dereferenced here !\n continue\n elif isinstance(v, DBRef):\n reference_map.setdefault(field.document_type, set()).add(v.id)\n elif isinstance(v, (dict, SON)) and '_ref' in v:\n reference_map.setdefault(get_document(v['_cls']), set()).add(v['_ref'].id)\n elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:\n field_cls = getattr(getattr(field, 'field', None), 'document_type', None)\n references = self._find_references(v, depth)\n for key, refs in references.iteritems():\n if isinstance(field_cls, (Document, TopLevelDocumentMetaclass)):\n key = field_cls\n reference_map.setdefault(key, set()).update(refs)\n elif isinstance(item, LazyReference):\n # LazyReference inherits DBRef but should not be dereferenced here !\n continue\n elif isinstance(item, DBRef):\n reference_map.setdefault(item.collection, set()).add(item.id)\n elif isinstance(item, (dict, SON)) and '_ref' in item:\n reference_map.setdefault(get_document(item['_cls']), set()).add(item['_ref'].id)\n elif isinstance(item, (dict, list, tuple)) and depth - 1 <= self.max_depth:\n references = self._find_references(item, depth - 1)\n for key, refs in references.iteritems():\n reference_map.setdefault(key, set()).update(refs)\n\n return reference_map\n\n def _fetch_objects(self, doc_type=None):\n \"\"\"Fetch all references and convert to their document objects\n \"\"\"\n object_map = {}\n for collection, dbrefs in self.reference_map.iteritems():\n if hasattr(collection, 'objects'): # We have a document class for the refs\n col_name = collection._get_collection_name()\n refs = [dbref for dbref in dbrefs\n if (col_name, dbref) not in object_map]\n references = collection.objects.in_bulk(refs)\n for key, doc in references.iteritems():\n object_map[(col_name, key)] = doc\n else: # Generic reference: use the refs data to convert to document\n if isinstance(doc_type, (ListField, DictField, MapField,)):\n continue\n\n refs = [dbref for dbref in dbrefs\n if (collection, dbref) not in object_map]\n\n if doc_type:\n references = doc_type._get_db()[collection].find({'_id': {'$in': refs}})\n for ref in references:\n doc = doc_type._from_son(ref)\n object_map[(collection, doc.id)] = doc\n else:\n references = get_db()[collection].find({'_id': {'$in': refs}})\n for ref in references:\n if '_cls' in ref:\n doc = get_document(ref['_cls'])._from_son(ref)\n elif doc_type is None:\n doc = get_document(\n ''.join(x.capitalize()\n for x in collection.split('_')))._from_son(ref)\n else:\n doc = doc_type._from_son(ref)\n object_map[(collection, doc.id)] = doc\n return object_map\n\n def _attach_objects(self, items, depth=0, instance=None, name=None):\n \"\"\"\n Recursively finds all db references to be dereferenced\n\n :param items: The iterable (dict, list, queryset)\n :param depth: The current depth of recursion\n :param instance: The owning instance used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n :param name: The name of the field, used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n \"\"\"\n if not items:\n if isinstance(items, (BaseDict, BaseList)):\n return items\n\n if instance:\n if isinstance(items, dict):\n return BaseDict(items, instance, name)\n else:\n return BaseList(items, instance, name)\n\n if isinstance(items, (dict, SON)):\n if '_ref' in items:\n return self.object_map.get(\n (items['_ref'].collection, items['_ref'].id), items)\n elif '_cls' in items:\n doc = get_document(items['_cls'])._from_son(items)\n _cls = doc._data.pop('_cls', None)\n del items['_cls']\n doc._data = self._attach_objects(doc._data, depth, doc, None)\n if _cls is not None:\n doc._data['_cls'] = _cls\n return doc\n\n if not hasattr(items, 'items'):\n is_list = True\n list_type = BaseList\n if isinstance(items, EmbeddedDocumentList):\n list_type = EmbeddedDocumentList\n as_tuple = isinstance(items, tuple)\n iterator = enumerate(items)\n data = []\n else:\n is_list = False\n iterator = items.iteritems()\n data = {}\n\n depth += 1\n for k, v in iterator:\n if is_list:\n data.append(v)\n else:\n data[k] = v\n\n if k in self.object_map and not is_list:\n data[k] = self.object_map[k]\n elif isinstance(v, (Document, EmbeddedDocument)):\n for field_name in v._fields:\n v = data[k]._data.get(field_name, None)\n if isinstance(v, DBRef):\n data[k]._data[field_name] = self.object_map.get(\n (v.collection, v.id), v)\n elif isinstance(v, (dict, SON)) and '_ref' in v:\n data[k]._data[field_name] = self.object_map.get(\n (v['_ref'].collection, v['_ref'].id), v)\n elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:\n item_name = six.text_type('{0}.{1}.{2}').format(name, k, field_name)\n data[k]._data[field_name] = self._attach_objects(v, depth, instance=instance, name=item_name)\n elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:\n item_name = '%s.%s' % (name, k) if name else name\n data[k] = self._attach_objects(v, depth - 1, instance=instance, name=item_name)\n elif isinstance(v, DBRef) and hasattr(v, 'id'):\n data[k] = self.object_map.get((v.collection, v.id), v)\n\n if instance and name:\n if is_list:\n return tuple(data) if as_tuple else list_type(data, instance, name)\n return BaseDict(data, instance, name)\n depth += 1\n return data\n", "path": "mongoengine/dereference.py"}], "after_files": [{"content": "from bson import DBRef, SON\nimport six\n\nfrom mongoengine.base import (BaseDict, BaseList, EmbeddedDocumentList,\n TopLevelDocumentMetaclass, get_document)\nfrom mongoengine.base.datastructures import LazyReference\nfrom mongoengine.connection import get_db\nfrom mongoengine.document import Document, EmbeddedDocument\nfrom mongoengine.fields import DictField, ListField, MapField, ReferenceField\nfrom mongoengine.queryset import QuerySet\n\n\nclass DeReference(object):\n def __call__(self, items, max_depth=1, instance=None, name=None):\n \"\"\"\n Cheaply dereferences the items to a set depth.\n Also handles the conversion of complex data types.\n\n :param items: The iterable (dict, list, queryset) to be dereferenced.\n :param max_depth: The maximum depth to recurse to\n :param instance: The owning instance used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n :param name: The name of the field, used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n :param get: A boolean determining if being called by __get__\n \"\"\"\n if items is None or isinstance(items, six.string_types):\n return items\n\n # cheapest way to convert a queryset to a list\n # list(queryset) uses a count() query to determine length\n if isinstance(items, QuerySet):\n items = [i for i in items]\n\n self.max_depth = max_depth\n doc_type = None\n\n if instance and isinstance(instance, (Document, EmbeddedDocument,\n TopLevelDocumentMetaclass)):\n doc_type = instance._fields.get(name)\n while hasattr(doc_type, 'field'):\n doc_type = doc_type.field\n\n if isinstance(doc_type, ReferenceField):\n field = doc_type\n doc_type = doc_type.document_type\n is_list = not hasattr(items, 'items')\n\n if is_list and all([i.__class__ == doc_type for i in items]):\n return items\n elif not is_list and all(\n [i.__class__ == doc_type for i in items.values()]):\n return items\n elif not field.dbref:\n if not hasattr(items, 'items'):\n\n def _get_items(items):\n new_items = []\n for v in items:\n if isinstance(v, list):\n new_items.append(_get_items(v))\n elif not isinstance(v, (DBRef, Document)):\n new_items.append(field.to_python(v))\n else:\n new_items.append(v)\n return new_items\n\n items = _get_items(items)\n else:\n items = {\n k: (v if isinstance(v, (DBRef, Document))\n else field.to_python(v))\n for k, v in items.iteritems()\n }\n\n self.reference_map = self._find_references(items)\n self.object_map = self._fetch_objects(doc_type=doc_type)\n return self._attach_objects(items, 0, instance, name)\n\n def _find_references(self, items, depth=0):\n \"\"\"\n Recursively finds all db references to be dereferenced\n\n :param items: The iterable (dict, list, queryset)\n :param depth: The current depth of recursion\n \"\"\"\n reference_map = {}\n if not items or depth >= self.max_depth:\n return reference_map\n\n # Determine the iterator to use\n if isinstance(items, dict):\n iterator = items.values()\n else:\n iterator = items\n\n # Recursively find dbreferences\n depth += 1\n for item in iterator:\n if isinstance(item, (Document, EmbeddedDocument)):\n for field_name, field in item._fields.iteritems():\n v = item._data.get(field_name, None)\n if isinstance(v, LazyReference):\n # LazyReference inherits DBRef but should not be dereferenced here !\n continue\n elif isinstance(v, DBRef):\n reference_map.setdefault(field.document_type, set()).add(v.id)\n elif isinstance(v, (dict, SON)) and '_ref' in v:\n reference_map.setdefault(get_document(v['_cls']), set()).add(v['_ref'].id)\n elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:\n field_cls = getattr(getattr(field, 'field', None), 'document_type', None)\n references = self._find_references(v, depth)\n for key, refs in references.iteritems():\n if isinstance(field_cls, (Document, TopLevelDocumentMetaclass)):\n key = field_cls\n reference_map.setdefault(key, set()).update(refs)\n elif isinstance(item, LazyReference):\n # LazyReference inherits DBRef but should not be dereferenced here !\n continue\n elif isinstance(item, DBRef):\n reference_map.setdefault(item.collection, set()).add(item.id)\n elif isinstance(item, (dict, SON)) and '_ref' in item:\n reference_map.setdefault(get_document(item['_cls']), set()).add(item['_ref'].id)\n elif isinstance(item, (dict, list, tuple)) and depth - 1 <= self.max_depth:\n references = self._find_references(item, depth - 1)\n for key, refs in references.iteritems():\n reference_map.setdefault(key, set()).update(refs)\n\n return reference_map\n\n def _fetch_objects(self, doc_type=None):\n \"\"\"Fetch all references and convert to their document objects\n \"\"\"\n object_map = {}\n for collection, dbrefs in self.reference_map.iteritems():\n\n # we use getattr instead of hasattr because as hasattr swallows any exception under python2\n # so it could hide nasty things without raising exceptions (cfr bug #1688))\n ref_document_cls_exists = (getattr(collection, 'objects', None) is not None)\n\n if ref_document_cls_exists:\n col_name = collection._get_collection_name()\n refs = [dbref for dbref in dbrefs\n if (col_name, dbref) not in object_map]\n references = collection.objects.in_bulk(refs)\n for key, doc in references.iteritems():\n object_map[(col_name, key)] = doc\n else: # Generic reference: use the refs data to convert to document\n if isinstance(doc_type, (ListField, DictField, MapField,)):\n continue\n\n refs = [dbref for dbref in dbrefs\n if (collection, dbref) not in object_map]\n\n if doc_type:\n references = doc_type._get_db()[collection].find({'_id': {'$in': refs}})\n for ref in references:\n doc = doc_type._from_son(ref)\n object_map[(collection, doc.id)] = doc\n else:\n references = get_db()[collection].find({'_id': {'$in': refs}})\n for ref in references:\n if '_cls' in ref:\n doc = get_document(ref['_cls'])._from_son(ref)\n elif doc_type is None:\n doc = get_document(\n ''.join(x.capitalize()\n for x in collection.split('_')))._from_son(ref)\n else:\n doc = doc_type._from_son(ref)\n object_map[(collection, doc.id)] = doc\n return object_map\n\n def _attach_objects(self, items, depth=0, instance=None, name=None):\n \"\"\"\n Recursively finds all db references to be dereferenced\n\n :param items: The iterable (dict, list, queryset)\n :param depth: The current depth of recursion\n :param instance: The owning instance used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n :param name: The name of the field, used for tracking changes by\n :class:`~mongoengine.base.ComplexBaseField`\n \"\"\"\n if not items:\n if isinstance(items, (BaseDict, BaseList)):\n return items\n\n if instance:\n if isinstance(items, dict):\n return BaseDict(items, instance, name)\n else:\n return BaseList(items, instance, name)\n\n if isinstance(items, (dict, SON)):\n if '_ref' in items:\n return self.object_map.get(\n (items['_ref'].collection, items['_ref'].id), items)\n elif '_cls' in items:\n doc = get_document(items['_cls'])._from_son(items)\n _cls = doc._data.pop('_cls', None)\n del items['_cls']\n doc._data = self._attach_objects(doc._data, depth, doc, None)\n if _cls is not None:\n doc._data['_cls'] = _cls\n return doc\n\n if not hasattr(items, 'items'):\n is_list = True\n list_type = BaseList\n if isinstance(items, EmbeddedDocumentList):\n list_type = EmbeddedDocumentList\n as_tuple = isinstance(items, tuple)\n iterator = enumerate(items)\n data = []\n else:\n is_list = False\n iterator = items.iteritems()\n data = {}\n\n depth += 1\n for k, v in iterator:\n if is_list:\n data.append(v)\n else:\n data[k] = v\n\n if k in self.object_map and not is_list:\n data[k] = self.object_map[k]\n elif isinstance(v, (Document, EmbeddedDocument)):\n for field_name in v._fields:\n v = data[k]._data.get(field_name, None)\n if isinstance(v, DBRef):\n data[k]._data[field_name] = self.object_map.get(\n (v.collection, v.id), v)\n elif isinstance(v, (dict, SON)) and '_ref' in v:\n data[k]._data[field_name] = self.object_map.get(\n (v['_ref'].collection, v['_ref'].id), v)\n elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:\n item_name = six.text_type('{0}.{1}.{2}').format(name, k, field_name)\n data[k]._data[field_name] = self._attach_objects(v, depth, instance=instance, name=item_name)\n elif isinstance(v, (dict, list, tuple)) and depth <= self.max_depth:\n item_name = '%s.%s' % (name, k) if name else name\n data[k] = self._attach_objects(v, depth - 1, instance=instance, name=item_name)\n elif isinstance(v, DBRef) and hasattr(v, 'id'):\n data[k] = self.object_map.get((v.collection, v.id), v)\n\n if instance and name:\n if is_list:\n return tuple(data) if as_tuple else list_type(data, instance, name)\n return BaseDict(data, instance, name)\n depth += 1\n return data\n", "path": "mongoengine/dereference.py"}]}
| 3,469 | 203 |
gh_patches_debug_23048
|
rasdani/github-patches
|
git_diff
|
cupy__cupy-5759
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
`cupy.concatenate()` misses arguments `dtype` and `casting`
Refs:
- NumPy: https://numpy.org/doc/stable/reference/generated/numpy.concatenate.html
- CuPy: https://docs.cupy.dev/en/stable/reference/generated/cupy.concatenate.html
The `dtype` argument is needed by the Array API standard (#5698, #4789).
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `cupy/_manipulation/join.py`
Content:
```
1 import cupy
2 from cupy import _core
3
4
5 def column_stack(tup):
6 """Stacks 1-D and 2-D arrays as columns into a 2-D array.
7
8 A 1-D array is first converted to a 2-D column array. Then, the 2-D arrays
9 are concatenated along the second axis.
10
11 Args:
12 tup (sequence of arrays): 1-D or 2-D arrays to be stacked.
13
14 Returns:
15 cupy.ndarray: A new 2-D array of stacked columns.
16
17 .. seealso:: :func:`numpy.column_stack`
18
19 """
20 if any(not isinstance(a, cupy.ndarray) for a in tup):
21 raise TypeError('Only cupy arrays can be column stacked')
22
23 lst = list(tup)
24 for i, a in enumerate(lst):
25 if a.ndim == 1:
26 a = a[:, cupy.newaxis]
27 lst[i] = a
28 elif a.ndim != 2:
29 raise ValueError(
30 'Only 1 or 2 dimensional arrays can be column stacked')
31
32 return concatenate(lst, axis=1)
33
34
35 def concatenate(tup, axis=0, out=None):
36 """Joins arrays along an axis.
37
38 Args:
39 tup (sequence of arrays): Arrays to be joined. All of these should have
40 same dimensionalities except the specified axis.
41 axis (int or None): The axis to join arrays along.
42 If axis is None, arrays are flattened before use.
43 Default is 0.
44 out (cupy.ndarray): Output array.
45
46 Returns:
47 cupy.ndarray: Joined array.
48
49 .. seealso:: :func:`numpy.concatenate`
50
51 """
52 if axis is None:
53 tup = [m.ravel() for m in tup]
54 axis = 0
55 return _core.concatenate_method(tup, axis, out)
56
57
58 def dstack(tup):
59 """Stacks arrays along the third axis.
60
61 Args:
62 tup (sequence of arrays): Arrays to be stacked. Each array is converted
63 by :func:`cupy.atleast_3d` before stacking.
64
65 Returns:
66 cupy.ndarray: Stacked array.
67
68 .. seealso:: :func:`numpy.dstack`
69
70 """
71 return concatenate([cupy.atleast_3d(m) for m in tup], 2)
72
73
74 def hstack(tup):
75 """Stacks arrays horizontally.
76
77 If an input array has one dimension, then the array is treated as a
78 horizontal vector and stacked along the first axis. Otherwise, the array is
79 stacked along the second axis.
80
81 Args:
82 tup (sequence of arrays): Arrays to be stacked.
83
84 Returns:
85 cupy.ndarray: Stacked array.
86
87 .. seealso:: :func:`numpy.hstack`
88
89 """
90 arrs = [cupy.atleast_1d(a) for a in tup]
91 axis = 1
92 if arrs[0].ndim == 1:
93 axis = 0
94 return concatenate(arrs, axis)
95
96
97 def vstack(tup):
98 """Stacks arrays vertically.
99
100 If an input array has one dimension, then the array is treated as a
101 horizontal vector and stacked along the additional axis at the head.
102 Otherwise, the array is stacked along the first axis.
103
104 Args:
105 tup (sequence of arrays): Arrays to be stacked. Each array is converted
106 by :func:`cupy.atleast_2d` before stacking.
107
108 Returns:
109 cupy.ndarray: Stacked array.
110
111 .. seealso:: :func:`numpy.dstack`
112
113 """
114 return concatenate([cupy.atleast_2d(m) for m in tup], 0)
115
116
117 def stack(tup, axis=0, out=None):
118 """Stacks arrays along a new axis.
119
120 Args:
121 tup (sequence of arrays): Arrays to be stacked.
122 axis (int): Axis along which the arrays are stacked.
123 out (cupy.ndarray): Output array.
124
125 Returns:
126 cupy.ndarray: Stacked array.
127
128 .. seealso:: :func:`numpy.stack`
129 """
130 return concatenate([cupy.expand_dims(x, axis) for x in tup], axis, out)
131
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/cupy/_manipulation/join.py b/cupy/_manipulation/join.py
--- a/cupy/_manipulation/join.py
+++ b/cupy/_manipulation/join.py
@@ -32,7 +32,7 @@
return concatenate(lst, axis=1)
-def concatenate(tup, axis=0, out=None):
+def concatenate(tup, axis=0, out=None, *, dtype=None, casting='same_kind'):
"""Joins arrays along an axis.
Args:
@@ -42,6 +42,11 @@
If axis is None, arrays are flattened before use.
Default is 0.
out (cupy.ndarray): Output array.
+ dtype (str or dtype): If provided, the destination array will have this
+ dtype. Cannot be provided together with ``out``.
+ casting ({‘no’, ‘equiv’, ‘safe’, ‘same_kind’, ‘unsafe’}, optional):
+ Controls what kind of data casting may occur. Defaults to
+ ``'same_kind'``.
Returns:
cupy.ndarray: Joined array.
@@ -52,7 +57,7 @@
if axis is None:
tup = [m.ravel() for m in tup]
axis = 0
- return _core.concatenate_method(tup, axis, out)
+ return _core.concatenate_method(tup, axis, out, dtype, casting)
def dstack(tup):
|
{"golden_diff": "diff --git a/cupy/_manipulation/join.py b/cupy/_manipulation/join.py\n--- a/cupy/_manipulation/join.py\n+++ b/cupy/_manipulation/join.py\n@@ -32,7 +32,7 @@\n return concatenate(lst, axis=1)\n \n \n-def concatenate(tup, axis=0, out=None):\n+def concatenate(tup, axis=0, out=None, *, dtype=None, casting='same_kind'):\n \"\"\"Joins arrays along an axis.\n \n Args:\n@@ -42,6 +42,11 @@\n If axis is None, arrays are flattened before use.\n Default is 0.\n out (cupy.ndarray): Output array.\n+ dtype (str or dtype): If provided, the destination array will have this\n+ dtype. Cannot be provided together with ``out``.\n+ casting ({\u2018no\u2019, \u2018equiv\u2019, \u2018safe\u2019, \u2018same_kind\u2019, \u2018unsafe\u2019}, optional):\n+ Controls what kind of data casting may occur. Defaults to\n+ ``'same_kind'``.\n \n Returns:\n cupy.ndarray: Joined array.\n@@ -52,7 +57,7 @@\n if axis is None:\n tup = [m.ravel() for m in tup]\n axis = 0\n- return _core.concatenate_method(tup, axis, out)\n+ return _core.concatenate_method(tup, axis, out, dtype, casting)\n \n \n def dstack(tup):\n", "issue": "`cupy.concatenate()` misses arguments `dtype` and `casting`\nRefs:\r\n- NumPy: https://numpy.org/doc/stable/reference/generated/numpy.concatenate.html\r\n- CuPy: https://docs.cupy.dev/en/stable/reference/generated/cupy.concatenate.html\r\n\r\nThe `dtype` argument is needed by the Array API standard (#5698, #4789).\n", "before_files": [{"content": "import cupy\nfrom cupy import _core\n\n\ndef column_stack(tup):\n \"\"\"Stacks 1-D and 2-D arrays as columns into a 2-D array.\n\n A 1-D array is first converted to a 2-D column array. Then, the 2-D arrays\n are concatenated along the second axis.\n\n Args:\n tup (sequence of arrays): 1-D or 2-D arrays to be stacked.\n\n Returns:\n cupy.ndarray: A new 2-D array of stacked columns.\n\n .. seealso:: :func:`numpy.column_stack`\n\n \"\"\"\n if any(not isinstance(a, cupy.ndarray) for a in tup):\n raise TypeError('Only cupy arrays can be column stacked')\n\n lst = list(tup)\n for i, a in enumerate(lst):\n if a.ndim == 1:\n a = a[:, cupy.newaxis]\n lst[i] = a\n elif a.ndim != 2:\n raise ValueError(\n 'Only 1 or 2 dimensional arrays can be column stacked')\n\n return concatenate(lst, axis=1)\n\n\ndef concatenate(tup, axis=0, out=None):\n \"\"\"Joins arrays along an axis.\n\n Args:\n tup (sequence of arrays): Arrays to be joined. All of these should have\n same dimensionalities except the specified axis.\n axis (int or None): The axis to join arrays along.\n If axis is None, arrays are flattened before use.\n Default is 0.\n out (cupy.ndarray): Output array.\n\n Returns:\n cupy.ndarray: Joined array.\n\n .. seealso:: :func:`numpy.concatenate`\n\n \"\"\"\n if axis is None:\n tup = [m.ravel() for m in tup]\n axis = 0\n return _core.concatenate_method(tup, axis, out)\n\n\ndef dstack(tup):\n \"\"\"Stacks arrays along the third axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked. Each array is converted\n by :func:`cupy.atleast_3d` before stacking.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.dstack`\n\n \"\"\"\n return concatenate([cupy.atleast_3d(m) for m in tup], 2)\n\n\ndef hstack(tup):\n \"\"\"Stacks arrays horizontally.\n\n If an input array has one dimension, then the array is treated as a\n horizontal vector and stacked along the first axis. Otherwise, the array is\n stacked along the second axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.hstack`\n\n \"\"\"\n arrs = [cupy.atleast_1d(a) for a in tup]\n axis = 1\n if arrs[0].ndim == 1:\n axis = 0\n return concatenate(arrs, axis)\n\n\ndef vstack(tup):\n \"\"\"Stacks arrays vertically.\n\n If an input array has one dimension, then the array is treated as a\n horizontal vector and stacked along the additional axis at the head.\n Otherwise, the array is stacked along the first axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked. Each array is converted\n by :func:`cupy.atleast_2d` before stacking.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.dstack`\n\n \"\"\"\n return concatenate([cupy.atleast_2d(m) for m in tup], 0)\n\n\ndef stack(tup, axis=0, out=None):\n \"\"\"Stacks arrays along a new axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked.\n axis (int): Axis along which the arrays are stacked.\n out (cupy.ndarray): Output array.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.stack`\n \"\"\"\n return concatenate([cupy.expand_dims(x, axis) for x in tup], axis, out)\n", "path": "cupy/_manipulation/join.py"}], "after_files": [{"content": "import cupy\nfrom cupy import _core\n\n\ndef column_stack(tup):\n \"\"\"Stacks 1-D and 2-D arrays as columns into a 2-D array.\n\n A 1-D array is first converted to a 2-D column array. Then, the 2-D arrays\n are concatenated along the second axis.\n\n Args:\n tup (sequence of arrays): 1-D or 2-D arrays to be stacked.\n\n Returns:\n cupy.ndarray: A new 2-D array of stacked columns.\n\n .. seealso:: :func:`numpy.column_stack`\n\n \"\"\"\n if any(not isinstance(a, cupy.ndarray) for a in tup):\n raise TypeError('Only cupy arrays can be column stacked')\n\n lst = list(tup)\n for i, a in enumerate(lst):\n if a.ndim == 1:\n a = a[:, cupy.newaxis]\n lst[i] = a\n elif a.ndim != 2:\n raise ValueError(\n 'Only 1 or 2 dimensional arrays can be column stacked')\n\n return concatenate(lst, axis=1)\n\n\ndef concatenate(tup, axis=0, out=None, *, dtype=None, casting='same_kind'):\n \"\"\"Joins arrays along an axis.\n\n Args:\n tup (sequence of arrays): Arrays to be joined. All of these should have\n same dimensionalities except the specified axis.\n axis (int or None): The axis to join arrays along.\n If axis is None, arrays are flattened before use.\n Default is 0.\n out (cupy.ndarray): Output array.\n dtype (str or dtype): If provided, the destination array will have this\n dtype. Cannot be provided together with ``out``.\n casting ({\u2018no\u2019, \u2018equiv\u2019, \u2018safe\u2019, \u2018same_kind\u2019, \u2018unsafe\u2019}, optional):\n Controls what kind of data casting may occur. Defaults to\n ``'same_kind'``.\n\n Returns:\n cupy.ndarray: Joined array.\n\n .. seealso:: :func:`numpy.concatenate`\n\n \"\"\"\n if axis is None:\n tup = [m.ravel() for m in tup]\n axis = 0\n return _core.concatenate_method(tup, axis, out, dtype, casting)\n\n\ndef dstack(tup):\n \"\"\"Stacks arrays along the third axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked. Each array is converted\n by :func:`cupy.atleast_3d` before stacking.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.dstack`\n\n \"\"\"\n return concatenate([cupy.atleast_3d(m) for m in tup], 2)\n\n\ndef hstack(tup):\n \"\"\"Stacks arrays horizontally.\n\n If an input array has one dimension, then the array is treated as a\n horizontal vector and stacked along the first axis. Otherwise, the array is\n stacked along the second axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.hstack`\n\n \"\"\"\n arrs = [cupy.atleast_1d(a) for a in tup]\n axis = 1\n if arrs[0].ndim == 1:\n axis = 0\n return concatenate(arrs, axis)\n\n\ndef vstack(tup):\n \"\"\"Stacks arrays vertically.\n\n If an input array has one dimension, then the array is treated as a\n horizontal vector and stacked along the additional axis at the head.\n Otherwise, the array is stacked along the first axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked. Each array is converted\n by :func:`cupy.atleast_2d` before stacking.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.dstack`\n\n \"\"\"\n return concatenate([cupy.atleast_2d(m) for m in tup], 0)\n\n\ndef stack(tup, axis=0, out=None):\n \"\"\"Stacks arrays along a new axis.\n\n Args:\n tup (sequence of arrays): Arrays to be stacked.\n axis (int): Axis along which the arrays are stacked.\n out (cupy.ndarray): Output array.\n\n Returns:\n cupy.ndarray: Stacked array.\n\n .. seealso:: :func:`numpy.stack`\n \"\"\"\n return concatenate([cupy.expand_dims(x, axis) for x in tup], axis, out)\n", "path": "cupy/_manipulation/join.py"}]}
| 1,538 | 322 |
gh_patches_debug_25497
|
rasdani/github-patches
|
git_diff
|
tensorflow__addons-2048
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Deprecate GELU
Per https://github.com/tensorflow/community/pull/252, oonce https://github.com/tensorflow/tensorflow/pull/41178 merges we'll need to deprecate our GELU for versions of TensorFlow that include it within core.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `tensorflow_addons/layers/gelu.py`
Content:
```
1 # Copyright 2019 The TensorFlow Authors. All Rights Reserved.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 # ==============================================================================
15 """Implements GELU activation."""
16
17 import tensorflow as tf
18 from tensorflow_addons.activations import gelu
19 from typeguard import typechecked
20
21
22 @tf.keras.utils.register_keras_serializable(package="Addons")
23 class GELU(tf.keras.layers.Layer):
24 """Gaussian Error Linear Unit.
25
26 A smoother version of ReLU generally used
27 in the BERT or BERT architecture based models.
28 Original paper: https://arxiv.org/abs/1606.08415
29
30 Input shape:
31 Arbitrary. Use the keyword argument `input_shape`
32 (tuple of integers, does not include the samples axis)
33 when using this layer as the first layer in a model.
34
35 Output shape:
36 Same shape as the input.
37 """
38
39 @typechecked
40 def __init__(self, approximate: bool = True, **kwargs):
41 super().__init__(**kwargs)
42 self.approximate = approximate
43 self.supports_masking = True
44
45 def call(self, inputs):
46 return gelu(inputs, approximate=self.approximate)
47
48 def get_config(self):
49 config = {"approximate": self.approximate}
50 base_config = super().get_config()
51 return {**base_config, **config}
52
53 def compute_output_shape(self, input_shape):
54 return input_shape
55
```
Path: `tensorflow_addons/activations/gelu.py`
Content:
```
1 # Copyright 2019 The TensorFlow Authors. All Rights Reserved.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 # ==============================================================================
15
16 import tensorflow as tf
17 import math
18 import warnings
19
20 from tensorflow_addons.utils import types
21 from tensorflow_addons.utils.resource_loader import LazySO
22 from tensorflow_addons import options
23
24 _activation_so = LazySO("custom_ops/activations/_activation_ops.so")
25
26
27 @tf.keras.utils.register_keras_serializable(package="Addons")
28 def gelu(x: types.TensorLike, approximate: bool = True) -> tf.Tensor:
29 """Gaussian Error Linear Unit.
30
31 Computes gaussian error linear:
32 `0.5 * x * (1 + tanh(sqrt(2 / pi) * (x + 0.044715 * x^3)))` or
33 `x * P(X <= x) = 0.5 * x * (1 + erf(x / sqrt(2)))`, where P(X) ~ N(0, 1),
34 depending on whether approximation is enabled.
35
36 See [Gaussian Error Linear Units (GELUs)](https://arxiv.org/abs/1606.08415)
37 and [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805).
38
39 Args:
40 x: A `Tensor`. Must be one of the following types:
41 `float16`, `float32`, `float64`.
42 approximate: bool, whether to enable approximation.
43 Returns:
44 A `Tensor`. Has the same type as `x`.
45 """
46 x = tf.convert_to_tensor(x)
47
48 if not options.TF_ADDONS_PY_OPS:
49 try:
50 return _gelu_custom_op(x, approximate)
51 except tf.errors.NotFoundError:
52 options.warn_fallback("gelu")
53
54 return _gelu_py(x, approximate)
55
56
57 def _gelu_custom_op(x, approximate):
58 warnings.warn(
59 "The activations custom ops are deprecated and will be removed in TensorFlow Addons "
60 "v0.12.0. \nPlease use the pure python version of Gelu instead by using the "
61 "`TF_ADDONS_PY_OPS` flag. \nFor more info about this flag, see "
62 "https://github.com/tensorflow/addons#gpucpu-custom-ops ",
63 DeprecationWarning,
64 )
65 return _activation_so.ops.addons_gelu(x, approximate)
66
67
68 @tf.RegisterGradient("Addons>Gelu")
69 def _gelu_grad(op, grad):
70 return _activation_so.ops.addons_gelu_grad(
71 grad, op.inputs[0], op.get_attr("approximate")
72 )
73
74
75 def _gelu_py(x: types.TensorLike, approximate: bool = True) -> tf.Tensor:
76 x = tf.convert_to_tensor(x)
77 if approximate:
78 pi = tf.cast(math.pi, x.dtype)
79 coeff = tf.cast(0.044715, x.dtype)
80 return 0.5 * x * (1.0 + tf.tanh(tf.sqrt(2.0 / pi) * (x + coeff * tf.pow(x, 3))))
81 else:
82 return 0.5 * x * (1.0 + tf.math.erf(x / tf.cast(tf.sqrt(2.0), x.dtype)))
83
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/tensorflow_addons/activations/gelu.py b/tensorflow_addons/activations/gelu.py
--- a/tensorflow_addons/activations/gelu.py
+++ b/tensorflow_addons/activations/gelu.py
@@ -43,6 +43,12 @@
Returns:
A `Tensor`. Has the same type as `x`.
"""
+ warnings.warn(
+ "gelu activation has been migrated to core TensorFlow, "
+ "and will be deprecated in Addons 0.12.",
+ DeprecationWarning,
+ )
+
x = tf.convert_to_tensor(x)
if not options.TF_ADDONS_PY_OPS:
diff --git a/tensorflow_addons/layers/gelu.py b/tensorflow_addons/layers/gelu.py
--- a/tensorflow_addons/layers/gelu.py
+++ b/tensorflow_addons/layers/gelu.py
@@ -14,6 +14,8 @@
# ==============================================================================
"""Implements GELU activation."""
+import warnings
+
import tensorflow as tf
from tensorflow_addons.activations import gelu
from typeguard import typechecked
@@ -38,6 +40,12 @@
@typechecked
def __init__(self, approximate: bool = True, **kwargs):
+ warnings.warn(
+ "gelu activation has been migrated to core TensorFlow, "
+ "and will be deprecated in Addons 0.12.",
+ DeprecationWarning,
+ )
+
super().__init__(**kwargs)
self.approximate = approximate
self.supports_masking = True
|
{"golden_diff": "diff --git a/tensorflow_addons/activations/gelu.py b/tensorflow_addons/activations/gelu.py\n--- a/tensorflow_addons/activations/gelu.py\n+++ b/tensorflow_addons/activations/gelu.py\n@@ -43,6 +43,12 @@\n Returns:\n A `Tensor`. Has the same type as `x`.\n \"\"\"\n+ warnings.warn(\n+ \"gelu activation has been migrated to core TensorFlow, \"\n+ \"and will be deprecated in Addons 0.12.\",\n+ DeprecationWarning,\n+ )\n+\n x = tf.convert_to_tensor(x)\n \n if not options.TF_ADDONS_PY_OPS:\ndiff --git a/tensorflow_addons/layers/gelu.py b/tensorflow_addons/layers/gelu.py\n--- a/tensorflow_addons/layers/gelu.py\n+++ b/tensorflow_addons/layers/gelu.py\n@@ -14,6 +14,8 @@\n # ==============================================================================\n \"\"\"Implements GELU activation.\"\"\"\n \n+import warnings\n+\n import tensorflow as tf\n from tensorflow_addons.activations import gelu\n from typeguard import typechecked\n@@ -38,6 +40,12 @@\n \n @typechecked\n def __init__(self, approximate: bool = True, **kwargs):\n+ warnings.warn(\n+ \"gelu activation has been migrated to core TensorFlow, \"\n+ \"and will be deprecated in Addons 0.12.\",\n+ DeprecationWarning,\n+ )\n+\n super().__init__(**kwargs)\n self.approximate = approximate\n self.supports_masking = True\n", "issue": "Deprecate GELU \nPer https://github.com/tensorflow/community/pull/252, oonce https://github.com/tensorflow/tensorflow/pull/41178 merges we'll need to deprecate our GELU for versions of TensorFlow that include it within core.\n", "before_files": [{"content": "# Copyright 2019 The TensorFlow Authors. All Rights Reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n# ==============================================================================\n\"\"\"Implements GELU activation.\"\"\"\n\nimport tensorflow as tf\nfrom tensorflow_addons.activations import gelu\nfrom typeguard import typechecked\n\n\[email protected]_keras_serializable(package=\"Addons\")\nclass GELU(tf.keras.layers.Layer):\n \"\"\"Gaussian Error Linear Unit.\n\n A smoother version of ReLU generally used\n in the BERT or BERT architecture based models.\n Original paper: https://arxiv.org/abs/1606.08415\n\n Input shape:\n Arbitrary. Use the keyword argument `input_shape`\n (tuple of integers, does not include the samples axis)\n when using this layer as the first layer in a model.\n\n Output shape:\n Same shape as the input.\n \"\"\"\n\n @typechecked\n def __init__(self, approximate: bool = True, **kwargs):\n super().__init__(**kwargs)\n self.approximate = approximate\n self.supports_masking = True\n\n def call(self, inputs):\n return gelu(inputs, approximate=self.approximate)\n\n def get_config(self):\n config = {\"approximate\": self.approximate}\n base_config = super().get_config()\n return {**base_config, **config}\n\n def compute_output_shape(self, input_shape):\n return input_shape\n", "path": "tensorflow_addons/layers/gelu.py"}, {"content": "# Copyright 2019 The TensorFlow Authors. All Rights Reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n# ==============================================================================\n\nimport tensorflow as tf\nimport math\nimport warnings\n\nfrom tensorflow_addons.utils import types\nfrom tensorflow_addons.utils.resource_loader import LazySO\nfrom tensorflow_addons import options\n\n_activation_so = LazySO(\"custom_ops/activations/_activation_ops.so\")\n\n\[email protected]_keras_serializable(package=\"Addons\")\ndef gelu(x: types.TensorLike, approximate: bool = True) -> tf.Tensor:\n \"\"\"Gaussian Error Linear Unit.\n\n Computes gaussian error linear:\n `0.5 * x * (1 + tanh(sqrt(2 / pi) * (x + 0.044715 * x^3)))` or\n `x * P(X <= x) = 0.5 * x * (1 + erf(x / sqrt(2)))`, where P(X) ~ N(0, 1),\n depending on whether approximation is enabled.\n\n See [Gaussian Error Linear Units (GELUs)](https://arxiv.org/abs/1606.08415)\n and [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805).\n\n Args:\n x: A `Tensor`. Must be one of the following types:\n `float16`, `float32`, `float64`.\n approximate: bool, whether to enable approximation.\n Returns:\n A `Tensor`. Has the same type as `x`.\n \"\"\"\n x = tf.convert_to_tensor(x)\n\n if not options.TF_ADDONS_PY_OPS:\n try:\n return _gelu_custom_op(x, approximate)\n except tf.errors.NotFoundError:\n options.warn_fallback(\"gelu\")\n\n return _gelu_py(x, approximate)\n\n\ndef _gelu_custom_op(x, approximate):\n warnings.warn(\n \"The activations custom ops are deprecated and will be removed in TensorFlow Addons \"\n \"v0.12.0. \\nPlease use the pure python version of Gelu instead by using the \"\n \"`TF_ADDONS_PY_OPS` flag. \\nFor more info about this flag, see \"\n \"https://github.com/tensorflow/addons#gpucpu-custom-ops \",\n DeprecationWarning,\n )\n return _activation_so.ops.addons_gelu(x, approximate)\n\n\[email protected](\"Addons>Gelu\")\ndef _gelu_grad(op, grad):\n return _activation_so.ops.addons_gelu_grad(\n grad, op.inputs[0], op.get_attr(\"approximate\")\n )\n\n\ndef _gelu_py(x: types.TensorLike, approximate: bool = True) -> tf.Tensor:\n x = tf.convert_to_tensor(x)\n if approximate:\n pi = tf.cast(math.pi, x.dtype)\n coeff = tf.cast(0.044715, x.dtype)\n return 0.5 * x * (1.0 + tf.tanh(tf.sqrt(2.0 / pi) * (x + coeff * tf.pow(x, 3))))\n else:\n return 0.5 * x * (1.0 + tf.math.erf(x / tf.cast(tf.sqrt(2.0), x.dtype)))\n", "path": "tensorflow_addons/activations/gelu.py"}], "after_files": [{"content": "# Copyright 2019 The TensorFlow Authors. All Rights Reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n# ==============================================================================\n\"\"\"Implements GELU activation.\"\"\"\n\nimport warnings\n\nimport tensorflow as tf\nfrom tensorflow_addons.activations import gelu\nfrom typeguard import typechecked\n\n\[email protected]_keras_serializable(package=\"Addons\")\nclass GELU(tf.keras.layers.Layer):\n \"\"\"Gaussian Error Linear Unit.\n\n A smoother version of ReLU generally used\n in the BERT or BERT architecture based models.\n Original paper: https://arxiv.org/abs/1606.08415\n\n Input shape:\n Arbitrary. Use the keyword argument `input_shape`\n (tuple of integers, does not include the samples axis)\n when using this layer as the first layer in a model.\n\n Output shape:\n Same shape as the input.\n \"\"\"\n\n @typechecked\n def __init__(self, approximate: bool = True, **kwargs):\n warnings.warn(\n \"gelu activation has been migrated to core TensorFlow, \"\n \"and will be deprecated in Addons 0.12.\",\n DeprecationWarning,\n )\n\n super().__init__(**kwargs)\n self.approximate = approximate\n self.supports_masking = True\n\n def call(self, inputs):\n return gelu(inputs, approximate=self.approximate)\n\n def get_config(self):\n config = {\"approximate\": self.approximate}\n base_config = super().get_config()\n return {**base_config, **config}\n\n def compute_output_shape(self, input_shape):\n return input_shape\n", "path": "tensorflow_addons/layers/gelu.py"}, {"content": "# Copyright 2019 The TensorFlow Authors. All Rights Reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n# ==============================================================================\n\nimport tensorflow as tf\nimport math\nimport warnings\n\nfrom tensorflow_addons.utils import types\nfrom tensorflow_addons.utils.resource_loader import LazySO\nfrom tensorflow_addons import options\n\n_activation_so = LazySO(\"custom_ops/activations/_activation_ops.so\")\n\n\[email protected]_keras_serializable(package=\"Addons\")\ndef gelu(x: types.TensorLike, approximate: bool = True) -> tf.Tensor:\n \"\"\"Gaussian Error Linear Unit.\n\n Computes gaussian error linear:\n `0.5 * x * (1 + tanh(sqrt(2 / pi) * (x + 0.044715 * x^3)))` or\n `x * P(X <= x) = 0.5 * x * (1 + erf(x / sqrt(2)))`, where P(X) ~ N(0, 1),\n depending on whether approximation is enabled.\n\n See [Gaussian Error Linear Units (GELUs)](https://arxiv.org/abs/1606.08415)\n and [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805).\n\n Args:\n x: A `Tensor`. Must be one of the following types:\n `float16`, `float32`, `float64`.\n approximate: bool, whether to enable approximation.\n Returns:\n A `Tensor`. Has the same type as `x`.\n \"\"\"\n warnings.warn(\n \"gelu activation has been migrated to core TensorFlow, \"\n \"and will be deprecated in Addons 0.12.\",\n DeprecationWarning,\n )\n\n x = tf.convert_to_tensor(x)\n\n if not options.TF_ADDONS_PY_OPS:\n try:\n return _gelu_custom_op(x, approximate)\n except tf.errors.NotFoundError:\n options.warn_fallback(\"gelu\")\n\n return _gelu_py(x, approximate)\n\n\ndef _gelu_custom_op(x, approximate):\n warnings.warn(\n \"The activations custom ops are deprecated and will be removed in TensorFlow Addons \"\n \"v0.12.0. \\nPlease use the pure python version of Gelu instead by using the \"\n \"`TF_ADDONS_PY_OPS` flag. \\nFor more info about this flag, see \"\n \"https://github.com/tensorflow/addons#gpucpu-custom-ops \",\n DeprecationWarning,\n )\n return _activation_so.ops.addons_gelu(x, approximate)\n\n\[email protected](\"Addons>Gelu\")\ndef _gelu_grad(op, grad):\n return _activation_so.ops.addons_gelu_grad(\n grad, op.inputs[0], op.get_attr(\"approximate\")\n )\n\n\ndef _gelu_py(x: types.TensorLike, approximate: bool = True) -> tf.Tensor:\n x = tf.convert_to_tensor(x)\n if approximate:\n pi = tf.cast(math.pi, x.dtype)\n coeff = tf.cast(0.044715, x.dtype)\n return 0.5 * x * (1.0 + tf.tanh(tf.sqrt(2.0 / pi) * (x + coeff * tf.pow(x, 3))))\n else:\n return 0.5 * x * (1.0 + tf.math.erf(x / tf.cast(tf.sqrt(2.0), x.dtype)))\n", "path": "tensorflow_addons/activations/gelu.py"}]}
| 1,870 | 364 |
gh_patches_debug_13722
|
rasdani/github-patches
|
git_diff
|
open-telemetry__opentelemetry-python-contrib-935
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Support for pymemcache 2.x and 3.x
The `pymemcache` integration is currently locked to version 1.x. Current version is ~=3.5.
https://github.com/open-telemetry/opentelemetry-python-contrib/blob/0b9e96dae0bfcafa1e0b28dc695e3697fbcf2864/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py#L16
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py`
Content:
```
1 # Copyright The OpenTelemetry Authors
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15
16 _instruments = ("pymemcache ~= 1.3",)
17
```
Path: `opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py`
Content:
```
1 # Copyright The OpenTelemetry Authors
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 # DO NOT EDIT. THIS FILE WAS AUTOGENERATED FROM INSTRUMENTATION PACKAGES.
16 # RUN `python scripts/generate_instrumentation_bootstrap.py` TO REGENERATE.
17
18 libraries = {
19 "aiohttp": {
20 "library": "aiohttp ~= 3.0",
21 "instrumentation": "opentelemetry-instrumentation-aiohttp-client==0.29b0",
22 },
23 "aiopg": {
24 "library": "aiopg >= 0.13.0, < 1.3.0",
25 "instrumentation": "opentelemetry-instrumentation-aiopg==0.29b0",
26 },
27 "asgiref": {
28 "library": "asgiref ~= 3.0",
29 "instrumentation": "opentelemetry-instrumentation-asgi==0.29b0",
30 },
31 "asyncpg": {
32 "library": "asyncpg >= 0.12.0",
33 "instrumentation": "opentelemetry-instrumentation-asyncpg==0.29b0",
34 },
35 "boto": {
36 "library": "boto~=2.0",
37 "instrumentation": "opentelemetry-instrumentation-boto==0.29b0",
38 },
39 "botocore": {
40 "library": "botocore ~= 1.0",
41 "instrumentation": "opentelemetry-instrumentation-botocore==0.29b0",
42 },
43 "celery": {
44 "library": "celery >= 4.0, < 6.0",
45 "instrumentation": "opentelemetry-instrumentation-celery==0.29b0",
46 },
47 "django": {
48 "library": "django >= 1.10",
49 "instrumentation": "opentelemetry-instrumentation-django==0.29b0",
50 },
51 "elasticsearch": {
52 "library": "elasticsearch >= 2.0",
53 "instrumentation": "opentelemetry-instrumentation-elasticsearch==0.29b0",
54 },
55 "falcon": {
56 "library": "falcon >= 2.0.0, < 4.0.0",
57 "instrumentation": "opentelemetry-instrumentation-falcon==0.29b0",
58 },
59 "fastapi": {
60 "library": "fastapi ~= 0.58",
61 "instrumentation": "opentelemetry-instrumentation-fastapi==0.29b0",
62 },
63 "flask": {
64 "library": "flask >= 1.0, < 3.0",
65 "instrumentation": "opentelemetry-instrumentation-flask==0.29b0",
66 },
67 "grpcio": {
68 "library": "grpcio ~= 1.27",
69 "instrumentation": "opentelemetry-instrumentation-grpc==0.29b0",
70 },
71 "httpx": {
72 "library": "httpx >= 0.18.0",
73 "instrumentation": "opentelemetry-instrumentation-httpx==0.29b0",
74 },
75 "jinja2": {
76 "library": "jinja2 >= 2.7, < 4.0",
77 "instrumentation": "opentelemetry-instrumentation-jinja2==0.29b0",
78 },
79 "kafka-python": {
80 "library": "kafka-python >= 2.0",
81 "instrumentation": "opentelemetry-instrumentation-kafka-python==0.29b0",
82 },
83 "mysql-connector-python": {
84 "library": "mysql-connector-python ~= 8.0",
85 "instrumentation": "opentelemetry-instrumentation-mysql==0.29b0",
86 },
87 "pika": {
88 "library": "pika >= 0.12.0",
89 "instrumentation": "opentelemetry-instrumentation-pika==0.29b0",
90 },
91 "psycopg2": {
92 "library": "psycopg2 >= 2.7.3.1",
93 "instrumentation": "opentelemetry-instrumentation-psycopg2==0.29b0",
94 },
95 "pymemcache": {
96 "library": "pymemcache ~= 1.3",
97 "instrumentation": "opentelemetry-instrumentation-pymemcache==0.29b0",
98 },
99 "pymongo": {
100 "library": "pymongo >= 3.1, < 5.0",
101 "instrumentation": "opentelemetry-instrumentation-pymongo==0.29b0",
102 },
103 "PyMySQL": {
104 "library": "PyMySQL < 2",
105 "instrumentation": "opentelemetry-instrumentation-pymysql==0.29b0",
106 },
107 "pyramid": {
108 "library": "pyramid >= 1.7",
109 "instrumentation": "opentelemetry-instrumentation-pyramid==0.29b0",
110 },
111 "redis": {
112 "library": "redis >= 2.6",
113 "instrumentation": "opentelemetry-instrumentation-redis==0.29b0",
114 },
115 "requests": {
116 "library": "requests ~= 2.0",
117 "instrumentation": "opentelemetry-instrumentation-requests==0.29b0",
118 },
119 "scikit-learn": {
120 "library": "scikit-learn ~= 0.24.0",
121 "instrumentation": "opentelemetry-instrumentation-sklearn==0.29b0",
122 },
123 "sqlalchemy": {
124 "library": "sqlalchemy",
125 "instrumentation": "opentelemetry-instrumentation-sqlalchemy==0.29b0",
126 },
127 "starlette": {
128 "library": "starlette ~= 0.13.0",
129 "instrumentation": "opentelemetry-instrumentation-starlette==0.29b0",
130 },
131 "tornado": {
132 "library": "tornado >= 5.1.1",
133 "instrumentation": "opentelemetry-instrumentation-tornado==0.29b0",
134 },
135 "urllib3": {
136 "library": "urllib3 >= 1.0.0, < 2.0.0",
137 "instrumentation": "opentelemetry-instrumentation-urllib3==0.29b0",
138 },
139 }
140 default_instrumentations = [
141 "opentelemetry-instrumentation-aws-lambda==0.29b0",
142 "opentelemetry-instrumentation-dbapi==0.29b0",
143 "opentelemetry-instrumentation-logging==0.29b0",
144 "opentelemetry-instrumentation-sqlite3==0.29b0",
145 "opentelemetry-instrumentation-urllib==0.29b0",
146 "opentelemetry-instrumentation-wsgi==0.29b0",
147 ]
148
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py b/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py
--- a/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py
+++ b/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py
@@ -13,4 +13,4 @@
# limitations under the License.
-_instruments = ("pymemcache ~= 1.3",)
+_instruments = ("pymemcache >= 1.3.5, < 4",)
diff --git a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py
--- a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py
+++ b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py
@@ -93,7 +93,7 @@
"instrumentation": "opentelemetry-instrumentation-psycopg2==0.29b0",
},
"pymemcache": {
- "library": "pymemcache ~= 1.3",
+ "library": "pymemcache >= 1.3.5, < 4",
"instrumentation": "opentelemetry-instrumentation-pymemcache==0.29b0",
},
"pymongo": {
|
{"golden_diff": "diff --git a/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py b/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py\n--- a/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py\n+++ b/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py\n@@ -13,4 +13,4 @@\n # limitations under the License.\n \n \n-_instruments = (\"pymemcache ~= 1.3\",)\n+_instruments = (\"pymemcache >= 1.3.5, < 4\",)\ndiff --git a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py\n--- a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py\n+++ b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py\n@@ -93,7 +93,7 @@\n \"instrumentation\": \"opentelemetry-instrumentation-psycopg2==0.29b0\",\n },\n \"pymemcache\": {\n- \"library\": \"pymemcache ~= 1.3\",\n+ \"library\": \"pymemcache >= 1.3.5, < 4\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymemcache==0.29b0\",\n },\n \"pymongo\": {\n", "issue": "Support for pymemcache 2.x and 3.x\nThe `pymemcache` integration is currently locked to version 1.x. Current version is ~=3.5.\r\n\r\nhttps://github.com/open-telemetry/opentelemetry-python-contrib/blob/0b9e96dae0bfcafa1e0b28dc695e3697fbcf2864/instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py#L16\n", "before_files": [{"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\n_instruments = (\"pymemcache ~= 1.3\",)\n", "path": "instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py"}, {"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n# DO NOT EDIT. THIS FILE WAS AUTOGENERATED FROM INSTRUMENTATION PACKAGES.\n# RUN `python scripts/generate_instrumentation_bootstrap.py` TO REGENERATE.\n\nlibraries = {\n \"aiohttp\": {\n \"library\": \"aiohttp ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiohttp-client==0.29b0\",\n },\n \"aiopg\": {\n \"library\": \"aiopg >= 0.13.0, < 1.3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiopg==0.29b0\",\n },\n \"asgiref\": {\n \"library\": \"asgiref ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-asgi==0.29b0\",\n },\n \"asyncpg\": {\n \"library\": \"asyncpg >= 0.12.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-asyncpg==0.29b0\",\n },\n \"boto\": {\n \"library\": \"boto~=2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-boto==0.29b0\",\n },\n \"botocore\": {\n \"library\": \"botocore ~= 1.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-botocore==0.29b0\",\n },\n \"celery\": {\n \"library\": \"celery >= 4.0, < 6.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-celery==0.29b0\",\n },\n \"django\": {\n \"library\": \"django >= 1.10\",\n \"instrumentation\": \"opentelemetry-instrumentation-django==0.29b0\",\n },\n \"elasticsearch\": {\n \"library\": \"elasticsearch >= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-elasticsearch==0.29b0\",\n },\n \"falcon\": {\n \"library\": \"falcon >= 2.0.0, < 4.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-falcon==0.29b0\",\n },\n \"fastapi\": {\n \"library\": \"fastapi ~= 0.58\",\n \"instrumentation\": \"opentelemetry-instrumentation-fastapi==0.29b0\",\n },\n \"flask\": {\n \"library\": \"flask >= 1.0, < 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-flask==0.29b0\",\n },\n \"grpcio\": {\n \"library\": \"grpcio ~= 1.27\",\n \"instrumentation\": \"opentelemetry-instrumentation-grpc==0.29b0\",\n },\n \"httpx\": {\n \"library\": \"httpx >= 0.18.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-httpx==0.29b0\",\n },\n \"jinja2\": {\n \"library\": \"jinja2 >= 2.7, < 4.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-jinja2==0.29b0\",\n },\n \"kafka-python\": {\n \"library\": \"kafka-python >= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-kafka-python==0.29b0\",\n },\n \"mysql-connector-python\": {\n \"library\": \"mysql-connector-python ~= 8.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-mysql==0.29b0\",\n },\n \"pika\": {\n \"library\": \"pika >= 0.12.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-pika==0.29b0\",\n },\n \"psycopg2\": {\n \"library\": \"psycopg2 >= 2.7.3.1\",\n \"instrumentation\": \"opentelemetry-instrumentation-psycopg2==0.29b0\",\n },\n \"pymemcache\": {\n \"library\": \"pymemcache ~= 1.3\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymemcache==0.29b0\",\n },\n \"pymongo\": {\n \"library\": \"pymongo >= 3.1, < 5.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymongo==0.29b0\",\n },\n \"PyMySQL\": {\n \"library\": \"PyMySQL < 2\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymysql==0.29b0\",\n },\n \"pyramid\": {\n \"library\": \"pyramid >= 1.7\",\n \"instrumentation\": \"opentelemetry-instrumentation-pyramid==0.29b0\",\n },\n \"redis\": {\n \"library\": \"redis >= 2.6\",\n \"instrumentation\": \"opentelemetry-instrumentation-redis==0.29b0\",\n },\n \"requests\": {\n \"library\": \"requests ~= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-requests==0.29b0\",\n },\n \"scikit-learn\": {\n \"library\": \"scikit-learn ~= 0.24.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-sklearn==0.29b0\",\n },\n \"sqlalchemy\": {\n \"library\": \"sqlalchemy\",\n \"instrumentation\": \"opentelemetry-instrumentation-sqlalchemy==0.29b0\",\n },\n \"starlette\": {\n \"library\": \"starlette ~= 0.13.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-starlette==0.29b0\",\n },\n \"tornado\": {\n \"library\": \"tornado >= 5.1.1\",\n \"instrumentation\": \"opentelemetry-instrumentation-tornado==0.29b0\",\n },\n \"urllib3\": {\n \"library\": \"urllib3 >= 1.0.0, < 2.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-urllib3==0.29b0\",\n },\n}\ndefault_instrumentations = [\n \"opentelemetry-instrumentation-aws-lambda==0.29b0\",\n \"opentelemetry-instrumentation-dbapi==0.29b0\",\n \"opentelemetry-instrumentation-logging==0.29b0\",\n \"opentelemetry-instrumentation-sqlite3==0.29b0\",\n \"opentelemetry-instrumentation-urllib==0.29b0\",\n \"opentelemetry-instrumentation-wsgi==0.29b0\",\n]\n", "path": "opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py"}], "after_files": [{"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\n_instruments = (\"pymemcache >= 1.3.5, < 4\",)\n", "path": "instrumentation/opentelemetry-instrumentation-pymemcache/src/opentelemetry/instrumentation/pymemcache/package.py"}, {"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n# DO NOT EDIT. THIS FILE WAS AUTOGENERATED FROM INSTRUMENTATION PACKAGES.\n# RUN `python scripts/generate_instrumentation_bootstrap.py` TO REGENERATE.\n\nlibraries = {\n \"aiohttp\": {\n \"library\": \"aiohttp ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiohttp-client==0.29b0\",\n },\n \"aiopg\": {\n \"library\": \"aiopg >= 0.13.0, < 1.3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiopg==0.29b0\",\n },\n \"asgiref\": {\n \"library\": \"asgiref ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-asgi==0.29b0\",\n },\n \"asyncpg\": {\n \"library\": \"asyncpg >= 0.12.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-asyncpg==0.29b0\",\n },\n \"boto\": {\n \"library\": \"boto~=2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-boto==0.29b0\",\n },\n \"botocore\": {\n \"library\": \"botocore ~= 1.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-botocore==0.29b0\",\n },\n \"celery\": {\n \"library\": \"celery >= 4.0, < 6.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-celery==0.29b0\",\n },\n \"django\": {\n \"library\": \"django >= 1.10\",\n \"instrumentation\": \"opentelemetry-instrumentation-django==0.29b0\",\n },\n \"elasticsearch\": {\n \"library\": \"elasticsearch >= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-elasticsearch==0.29b0\",\n },\n \"falcon\": {\n \"library\": \"falcon >= 2.0.0, < 4.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-falcon==0.29b0\",\n },\n \"fastapi\": {\n \"library\": \"fastapi ~= 0.58\",\n \"instrumentation\": \"opentelemetry-instrumentation-fastapi==0.29b0\",\n },\n \"flask\": {\n \"library\": \"flask >= 1.0, < 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-flask==0.29b0\",\n },\n \"grpcio\": {\n \"library\": \"grpcio ~= 1.27\",\n \"instrumentation\": \"opentelemetry-instrumentation-grpc==0.29b0\",\n },\n \"httpx\": {\n \"library\": \"httpx >= 0.18.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-httpx==0.29b0\",\n },\n \"jinja2\": {\n \"library\": \"jinja2 >= 2.7, < 4.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-jinja2==0.29b0\",\n },\n \"kafka-python\": {\n \"library\": \"kafka-python >= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-kafka-python==0.29b0\",\n },\n \"mysql-connector-python\": {\n \"library\": \"mysql-connector-python ~= 8.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-mysql==0.29b0\",\n },\n \"pika\": {\n \"library\": \"pika >= 0.12.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-pika==0.29b0\",\n },\n \"psycopg2\": {\n \"library\": \"psycopg2 >= 2.7.3.1\",\n \"instrumentation\": \"opentelemetry-instrumentation-psycopg2==0.29b0\",\n },\n \"pymemcache\": {\n \"library\": \"pymemcache >= 1.3.5, < 4\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymemcache==0.29b0\",\n },\n \"pymongo\": {\n \"library\": \"pymongo >= 3.1, < 5.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymongo==0.29b0\",\n },\n \"PyMySQL\": {\n \"library\": \"PyMySQL < 2\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymysql==0.29b0\",\n },\n \"pyramid\": {\n \"library\": \"pyramid >= 1.7\",\n \"instrumentation\": \"opentelemetry-instrumentation-pyramid==0.29b0\",\n },\n \"redis\": {\n \"library\": \"redis >= 2.6\",\n \"instrumentation\": \"opentelemetry-instrumentation-redis==0.29b0\",\n },\n \"requests\": {\n \"library\": \"requests ~= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-requests==0.29b0\",\n },\n \"scikit-learn\": {\n \"library\": \"scikit-learn ~= 0.24.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-sklearn==0.29b0\",\n },\n \"sqlalchemy\": {\n \"library\": \"sqlalchemy\",\n \"instrumentation\": \"opentelemetry-instrumentation-sqlalchemy==0.29b0\",\n },\n \"starlette\": {\n \"library\": \"starlette ~= 0.13.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-starlette==0.29b0\",\n },\n \"tornado\": {\n \"library\": \"tornado >= 5.1.1\",\n \"instrumentation\": \"opentelemetry-instrumentation-tornado==0.29b0\",\n },\n \"urllib3\": {\n \"library\": \"urllib3 >= 1.0.0, < 2.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-urllib3==0.29b0\",\n },\n}\ndefault_instrumentations = [\n \"opentelemetry-instrumentation-aws-lambda==0.29b0\",\n \"opentelemetry-instrumentation-dbapi==0.29b0\",\n \"opentelemetry-instrumentation-logging==0.29b0\",\n \"opentelemetry-instrumentation-sqlite3==0.29b0\",\n \"opentelemetry-instrumentation-urllib==0.29b0\",\n \"opentelemetry-instrumentation-wsgi==0.29b0\",\n]\n", "path": "opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py"}]}
| 2,625 | 365 |
gh_patches_debug_7541
|
rasdani/github-patches
|
git_diff
|
twisted__twisted-12106
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Release 24.1.0 to unbreak users who use the latest PyPy
#12084 is breaking CI for Tahoe-LAFS, so probably is breaking real-world usage for someone somewhere too. So it'd be good to have a release sooner rather than later.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/twisted/_version.py`
Content:
```
1 """
2 Provides Twisted version information.
3 """
4
5 # This file is auto-generated! Do not edit!
6 # Use `python -m incremental.update Twisted` to change this file.
7
8 from incremental import Version
9
10 __version__ = Version("Twisted", 23, 10, 0, post=0)
11 __all__ = ["__version__"]
12
```
Path: `src/twisted/copyright.py`
Content:
```
1 # Copyright (c) Twisted Matrix Laboratories.
2 # See LICENSE for details.
3
4 """
5 Copyright information for Twisted.
6 """
7
8
9 __all__ = ["copyright", "disclaimer", "longversion", "version"]
10
11 from twisted import __version__ as version, version as _longversion
12
13 longversion = str(_longversion)
14
15 copyright = """\
16 Copyright (c) 2001-2023 Twisted Matrix Laboratories.
17 See LICENSE for details."""
18
19 disclaimer = """
20 Twisted, the Framework of Your Internet
21 {}
22
23 Permission is hereby granted, free of charge, to any person obtaining
24 a copy of this software and associated documentation files (the
25 "Software"), to deal in the Software without restriction, including
26 without limitation the rights to use, copy, modify, merge, publish,
27 distribute, sublicense, and/or sell copies of the Software, and to
28 permit persons to whom the Software is furnished to do so, subject to
29 the following conditions:
30
31 The above copyright notice and this permission notice shall be
32 included in all copies or substantial portions of the Software.
33
34 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
35 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
36 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
37 NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
38 LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
39 OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
40 WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
41
42 """.format(
43 copyright,
44 )
45
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/twisted/_version.py b/src/twisted/_version.py
--- a/src/twisted/_version.py
+++ b/src/twisted/_version.py
@@ -7,5 +7,5 @@
from incremental import Version
-__version__ = Version("Twisted", 23, 10, 0, post=0)
+__version__ = Version("Twisted", 24, 3, 0, post=0)
__all__ = ["__version__"]
diff --git a/src/twisted/copyright.py b/src/twisted/copyright.py
--- a/src/twisted/copyright.py
+++ b/src/twisted/copyright.py
@@ -13,7 +13,7 @@
longversion = str(_longversion)
copyright = """\
-Copyright (c) 2001-2023 Twisted Matrix Laboratories.
+Copyright (c) 2001-2024 Twisted Matrix Laboratories.
See LICENSE for details."""
disclaimer = """
|
{"golden_diff": "diff --git a/src/twisted/_version.py b/src/twisted/_version.py\n--- a/src/twisted/_version.py\n+++ b/src/twisted/_version.py\n@@ -7,5 +7,5 @@\n \n from incremental import Version\n \n-__version__ = Version(\"Twisted\", 23, 10, 0, post=0)\n+__version__ = Version(\"Twisted\", 24, 3, 0, post=0)\n __all__ = [\"__version__\"]\ndiff --git a/src/twisted/copyright.py b/src/twisted/copyright.py\n--- a/src/twisted/copyright.py\n+++ b/src/twisted/copyright.py\n@@ -13,7 +13,7 @@\n longversion = str(_longversion)\n \n copyright = \"\"\"\\\n-Copyright (c) 2001-2023 Twisted Matrix Laboratories.\n+Copyright (c) 2001-2024 Twisted Matrix Laboratories.\n See LICENSE for details.\"\"\"\n \n disclaimer = \"\"\"\n", "issue": "Release 24.1.0 to unbreak users who use the latest PyPy\n#12084 is breaking CI for Tahoe-LAFS, so probably is breaking real-world usage for someone somewhere too. So it'd be good to have a release sooner rather than later.\n", "before_files": [{"content": "\"\"\"\nProvides Twisted version information.\n\"\"\"\n\n# This file is auto-generated! Do not edit!\n# Use `python -m incremental.update Twisted` to change this file.\n\nfrom incremental import Version\n\n__version__ = Version(\"Twisted\", 23, 10, 0, post=0)\n__all__ = [\"__version__\"]\n", "path": "src/twisted/_version.py"}, {"content": "# Copyright (c) Twisted Matrix Laboratories.\n# See LICENSE for details.\n\n\"\"\"\nCopyright information for Twisted.\n\"\"\"\n\n\n__all__ = [\"copyright\", \"disclaimer\", \"longversion\", \"version\"]\n\nfrom twisted import __version__ as version, version as _longversion\n\nlongversion = str(_longversion)\n\ncopyright = \"\"\"\\\nCopyright (c) 2001-2023 Twisted Matrix Laboratories.\nSee LICENSE for details.\"\"\"\n\ndisclaimer = \"\"\"\nTwisted, the Framework of Your Internet\n{}\n\nPermission is hereby granted, free of charge, to any person obtaining\na copy of this software and associated documentation files (the\n\"Software\"), to deal in the Software without restriction, including\nwithout limitation the rights to use, copy, modify, merge, publish,\ndistribute, sublicense, and/or sell copies of the Software, and to\npermit persons to whom the Software is furnished to do so, subject to\nthe following conditions:\n\nThe above copyright notice and this permission notice shall be\nincluded in all copies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND,\nEXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF\nMERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND\nNONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE\nLIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION\nOF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION\nWITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\n\"\"\".format(\n copyright,\n)\n", "path": "src/twisted/copyright.py"}], "after_files": [{"content": "\"\"\"\nProvides Twisted version information.\n\"\"\"\n\n# This file is auto-generated! Do not edit!\n# Use `python -m incremental.update Twisted` to change this file.\n\nfrom incremental import Version\n\n__version__ = Version(\"Twisted\", 24, 3, 0, post=0)\n__all__ = [\"__version__\"]\n", "path": "src/twisted/_version.py"}, {"content": "# Copyright (c) Twisted Matrix Laboratories.\n# See LICENSE for details.\n\n\"\"\"\nCopyright information for Twisted.\n\"\"\"\n\n\n__all__ = [\"copyright\", \"disclaimer\", \"longversion\", \"version\"]\n\nfrom twisted import __version__ as version, version as _longversion\n\nlongversion = str(_longversion)\n\ncopyright = \"\"\"\\\nCopyright (c) 2001-2024 Twisted Matrix Laboratories.\nSee LICENSE for details.\"\"\"\n\ndisclaimer = \"\"\"\nTwisted, the Framework of Your Internet\n{}\n\nPermission is hereby granted, free of charge, to any person obtaining\na copy of this software and associated documentation files (the\n\"Software\"), to deal in the Software without restriction, including\nwithout limitation the rights to use, copy, modify, merge, publish,\ndistribute, sublicense, and/or sell copies of the Software, and to\npermit persons to whom the Software is furnished to do so, subject to\nthe following conditions:\n\nThe above copyright notice and this permission notice shall be\nincluded in all copies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND,\nEXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF\nMERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND\nNONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE\nLIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION\nOF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION\nWITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\n\"\"\".format(\n copyright,\n)\n", "path": "src/twisted/copyright.py"}]}
| 838 | 228 |
gh_patches_debug_6887
|
rasdani/github-patches
|
git_diff
|
sherlock-project__sherlock-911
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[site_list.py] change numbering to reduce commit size
letting the markdown renderer do the counting lets us reduce commit size and avoide possible merge conflicts.
---
```
1.
1.
1.
```
renders to:
1.
1.
1.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `site_list.py`
Content:
```
1 """Sherlock: Supported Site Listing
2 This module generates the listing of supported sites
3 which can be found in sites.md
4 It also organizes all the sites in alphanumeric order
5 """
6 import json
7
8 pool = list()
9
10 with open("sherlock/resources/data.json", "r", encoding="utf-8") as data_file:
11 data = json.load(data_file)
12
13 with open("sites.md", "w") as site_file:
14 data_length = len(data)
15 site_file.write(f'## List Of Supported Sites ({data_length} Sites In Total!)\n')
16
17 for social_network in data:
18 url_main = data.get(social_network).get("urlMain")
19 pool.append((social_network, url_main))
20
21 index = 1
22 for social_network, url_main in pool:
23 site_file.write(f'{index}. [{social_network}]({url_main})\n')
24 index = index + 1
25
26
27 sorted_json_data = json.dumps(data, indent=2, sort_keys=True)
28
29 with open("sherlock/resources/data.json", "w") as data_file:
30 data_file.write(sorted_json_data)
31
32 print("Finished updating supported site listing!")
33
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/site_list.py b/site_list.py
--- a/site_list.py
+++ b/site_list.py
@@ -18,11 +18,8 @@
url_main = data.get(social_network).get("urlMain")
pool.append((social_network, url_main))
- index = 1
for social_network, url_main in pool:
- site_file.write(f'{index}. [{social_network}]({url_main})\n')
- index = index + 1
-
+ site_file.write(f'1. [{social_network}]({url_main})\n')
sorted_json_data = json.dumps(data, indent=2, sort_keys=True)
|
{"golden_diff": "diff --git a/site_list.py b/site_list.py\n--- a/site_list.py\n+++ b/site_list.py\n@@ -18,11 +18,8 @@\n url_main = data.get(social_network).get(\"urlMain\")\n pool.append((social_network, url_main))\n \n- index = 1\n for social_network, url_main in pool:\n- site_file.write(f'{index}. [{social_network}]({url_main})\\n')\n- index = index + 1\n-\n+ site_file.write(f'1. [{social_network}]({url_main})\\n')\n \n sorted_json_data = json.dumps(data, indent=2, sort_keys=True)\n", "issue": "[site_list.py] change numbering to reduce commit size\nletting the markdown renderer do the counting lets us reduce commit size and avoide possible merge conflicts.\r\n\r\n---\r\n\r\n```\r\n1.\r\n1.\r\n1.\r\n```\r\nrenders to:\r\n\r\n1.\r\n1.\r\n1.\n", "before_files": [{"content": "\"\"\"Sherlock: Supported Site Listing\nThis module generates the listing of supported sites\nwhich can be found in sites.md\nIt also organizes all the sites in alphanumeric order\n\"\"\"\nimport json\n\npool = list()\n\nwith open(\"sherlock/resources/data.json\", \"r\", encoding=\"utf-8\") as data_file:\n data = json.load(data_file)\n\nwith open(\"sites.md\", \"w\") as site_file:\n data_length = len(data)\n site_file.write(f'## List Of Supported Sites ({data_length} Sites In Total!)\\n')\n\n for social_network in data:\n url_main = data.get(social_network).get(\"urlMain\")\n pool.append((social_network, url_main))\n\n index = 1\n for social_network, url_main in pool:\n site_file.write(f'{index}. [{social_network}]({url_main})\\n')\n index = index + 1\n\n\nsorted_json_data = json.dumps(data, indent=2, sort_keys=True)\n\nwith open(\"sherlock/resources/data.json\", \"w\") as data_file:\n data_file.write(sorted_json_data)\n\nprint(\"Finished updating supported site listing!\")\n", "path": "site_list.py"}], "after_files": [{"content": "\"\"\"Sherlock: Supported Site Listing\nThis module generates the listing of supported sites\nwhich can be found in sites.md\nIt also organizes all the sites in alphanumeric order\n\"\"\"\nimport json\n\npool = list()\n\nwith open(\"sherlock/resources/data.json\", \"r\", encoding=\"utf-8\") as data_file:\n data = json.load(data_file)\n\nwith open(\"sites.md\", \"w\") as site_file:\n data_length = len(data)\n site_file.write(f'## List Of Supported Sites ({data_length} Sites In Total!)\\n')\n\n for social_network in data:\n url_main = data.get(social_network).get(\"urlMain\")\n pool.append((social_network, url_main))\n\n for social_network, url_main in pool:\n site_file.write(f'1. [{social_network}]({url_main})\\n')\n\nsorted_json_data = json.dumps(data, indent=2, sort_keys=True)\n\nwith open(\"sherlock/resources/data.json\", \"w\") as data_file:\n data_file.write(sorted_json_data)\n\nprint(\"Finished updating supported site listing!\")\n", "path": "site_list.py"}]}
| 616 | 147 |
gh_patches_debug_10290
|
rasdani/github-patches
|
git_diff
|
goauthentik__authentik-8139
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
2023.10.6 - "Please select a username" after Azure AD login
**Describe your question/**
Is it now a expected behavior in 2023.10.6 version to ask every user for username input after logging in with azure ad?
In previous versions it was simply authenticating without any prompt, using email address from Azure AD as username.
Now it expects user to input username (and it leads to duplicated accounts, because users with mail as username already exist), and if you enter already existing mail as username it shows error:
I think it can be related to this fix:
https://github.com/goauthentik/authentik/pull/7970
Is it possible somehow to set this username automatically, or revert back to using email address so old user accounts will work again?
**Version and Deployment (please complete the following information):**
- authentik version: 2023.10.6
- Deployment: helm
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `authentik/sources/oauth/types/azure_ad.py`
Content:
```
1 """AzureAD OAuth2 Views"""
2 from typing import Any
3
4 from structlog.stdlib import get_logger
5
6 from authentik.sources.oauth.clients.oauth2 import UserprofileHeaderAuthClient
7 from authentik.sources.oauth.types.oidc import OpenIDConnectOAuth2Callback
8 from authentik.sources.oauth.types.registry import SourceType, registry
9 from authentik.sources.oauth.views.redirect import OAuthRedirect
10
11 LOGGER = get_logger()
12
13
14 class AzureADOAuthRedirect(OAuthRedirect):
15 """Azure AD OAuth2 Redirect"""
16
17 def get_additional_parameters(self, source): # pragma: no cover
18 return {
19 "scope": ["openid", "https://graph.microsoft.com/User.Read"],
20 }
21
22
23 class AzureADOAuthCallback(OpenIDConnectOAuth2Callback):
24 """AzureAD OAuth2 Callback"""
25
26 client_class = UserprofileHeaderAuthClient
27
28 def get_user_enroll_context(
29 self,
30 info: dict[str, Any],
31 ) -> dict[str, Any]:
32 mail = info.get("mail", None) or info.get("otherMails", [None])[0]
33 return {
34 "username": info.get("userPrincipalName"),
35 "email": mail,
36 "name": info.get("displayName"),
37 }
38
39
40 @registry.register()
41 class AzureADType(SourceType):
42 """Azure AD Type definition"""
43
44 callback_view = AzureADOAuthCallback
45 redirect_view = AzureADOAuthRedirect
46 verbose_name = "Azure AD"
47 name = "azuread"
48
49 urls_customizable = True
50
51 authorization_url = "https://login.microsoftonline.com/common/oauth2/v2.0/authorize"
52 access_token_url = "https://login.microsoftonline.com/common/oauth2/v2.0/token" # nosec
53 profile_url = "https://login.microsoftonline.com/common/openid/userinfo"
54 oidc_well_known_url = (
55 "https://login.microsoftonline.com/common/.well-known/openid-configuration"
56 )
57 oidc_jwks_url = "https://login.microsoftonline.com/common/discovery/keys"
58
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/authentik/sources/oauth/types/azure_ad.py b/authentik/sources/oauth/types/azure_ad.py
--- a/authentik/sources/oauth/types/azure_ad.py
+++ b/authentik/sources/oauth/types/azure_ad.py
@@ -50,7 +50,7 @@
authorization_url = "https://login.microsoftonline.com/common/oauth2/v2.0/authorize"
access_token_url = "https://login.microsoftonline.com/common/oauth2/v2.0/token" # nosec
- profile_url = "https://login.microsoftonline.com/common/openid/userinfo"
+ profile_url = "https://graph.microsoft.com/v1.0/me"
oidc_well_known_url = (
"https://login.microsoftonline.com/common/.well-known/openid-configuration"
)
|
{"golden_diff": "diff --git a/authentik/sources/oauth/types/azure_ad.py b/authentik/sources/oauth/types/azure_ad.py\n--- a/authentik/sources/oauth/types/azure_ad.py\n+++ b/authentik/sources/oauth/types/azure_ad.py\n@@ -50,7 +50,7 @@\n \n authorization_url = \"https://login.microsoftonline.com/common/oauth2/v2.0/authorize\"\n access_token_url = \"https://login.microsoftonline.com/common/oauth2/v2.0/token\" # nosec\n- profile_url = \"https://login.microsoftonline.com/common/openid/userinfo\"\n+ profile_url = \"https://graph.microsoft.com/v1.0/me\"\n oidc_well_known_url = (\n \"https://login.microsoftonline.com/common/.well-known/openid-configuration\"\n )\n", "issue": "2023.10.6 - \"Please select a username\" after Azure AD login\n**Describe your question/**\r\n\r\nIs it now a expected behavior in 2023.10.6 version to ask every user for username input after logging in with azure ad?\r\n\r\n\r\nIn previous versions it was simply authenticating without any prompt, using email address from Azure AD as username.\r\n\r\nNow it expects user to input username (and it leads to duplicated accounts, because users with mail as username already exist), and if you enter already existing mail as username it shows error:\r\n\r\n\r\nI think it can be related to this fix:\r\nhttps://github.com/goauthentik/authentik/pull/7970\r\n\r\nIs it possible somehow to set this username automatically, or revert back to using email address so old user accounts will work again?\r\n\r\n**Version and Deployment (please complete the following information):**\r\n\r\n- authentik version: 2023.10.6\r\n- Deployment: helm\r\n\r\n\n", "before_files": [{"content": "\"\"\"AzureAD OAuth2 Views\"\"\"\nfrom typing import Any\n\nfrom structlog.stdlib import get_logger\n\nfrom authentik.sources.oauth.clients.oauth2 import UserprofileHeaderAuthClient\nfrom authentik.sources.oauth.types.oidc import OpenIDConnectOAuth2Callback\nfrom authentik.sources.oauth.types.registry import SourceType, registry\nfrom authentik.sources.oauth.views.redirect import OAuthRedirect\n\nLOGGER = get_logger()\n\n\nclass AzureADOAuthRedirect(OAuthRedirect):\n \"\"\"Azure AD OAuth2 Redirect\"\"\"\n\n def get_additional_parameters(self, source): # pragma: no cover\n return {\n \"scope\": [\"openid\", \"https://graph.microsoft.com/User.Read\"],\n }\n\n\nclass AzureADOAuthCallback(OpenIDConnectOAuth2Callback):\n \"\"\"AzureAD OAuth2 Callback\"\"\"\n\n client_class = UserprofileHeaderAuthClient\n\n def get_user_enroll_context(\n self,\n info: dict[str, Any],\n ) -> dict[str, Any]:\n mail = info.get(\"mail\", None) or info.get(\"otherMails\", [None])[0]\n return {\n \"username\": info.get(\"userPrincipalName\"),\n \"email\": mail,\n \"name\": info.get(\"displayName\"),\n }\n\n\[email protected]()\nclass AzureADType(SourceType):\n \"\"\"Azure AD Type definition\"\"\"\n\n callback_view = AzureADOAuthCallback\n redirect_view = AzureADOAuthRedirect\n verbose_name = \"Azure AD\"\n name = \"azuread\"\n\n urls_customizable = True\n\n authorization_url = \"https://login.microsoftonline.com/common/oauth2/v2.0/authorize\"\n access_token_url = \"https://login.microsoftonline.com/common/oauth2/v2.0/token\" # nosec\n profile_url = \"https://login.microsoftonline.com/common/openid/userinfo\"\n oidc_well_known_url = (\n \"https://login.microsoftonline.com/common/.well-known/openid-configuration\"\n )\n oidc_jwks_url = \"https://login.microsoftonline.com/common/discovery/keys\"\n", "path": "authentik/sources/oauth/types/azure_ad.py"}], "after_files": [{"content": "\"\"\"AzureAD OAuth2 Views\"\"\"\nfrom typing import Any\n\nfrom structlog.stdlib import get_logger\n\nfrom authentik.sources.oauth.clients.oauth2 import UserprofileHeaderAuthClient\nfrom authentik.sources.oauth.types.oidc import OpenIDConnectOAuth2Callback\nfrom authentik.sources.oauth.types.registry import SourceType, registry\nfrom authentik.sources.oauth.views.redirect import OAuthRedirect\n\nLOGGER = get_logger()\n\n\nclass AzureADOAuthRedirect(OAuthRedirect):\n \"\"\"Azure AD OAuth2 Redirect\"\"\"\n\n def get_additional_parameters(self, source): # pragma: no cover\n return {\n \"scope\": [\"openid\", \"https://graph.microsoft.com/User.Read\"],\n }\n\n\nclass AzureADOAuthCallback(OpenIDConnectOAuth2Callback):\n \"\"\"AzureAD OAuth2 Callback\"\"\"\n\n client_class = UserprofileHeaderAuthClient\n\n def get_user_enroll_context(\n self,\n info: dict[str, Any],\n ) -> dict[str, Any]:\n mail = info.get(\"mail\", None) or info.get(\"otherMails\", [None])[0]\n return {\n \"username\": info.get(\"userPrincipalName\"),\n \"email\": mail,\n \"name\": info.get(\"displayName\"),\n }\n\n\[email protected]()\nclass AzureADType(SourceType):\n \"\"\"Azure AD Type definition\"\"\"\n\n callback_view = AzureADOAuthCallback\n redirect_view = AzureADOAuthRedirect\n verbose_name = \"Azure AD\"\n name = \"azuread\"\n\n urls_customizable = True\n\n authorization_url = \"https://login.microsoftonline.com/common/oauth2/v2.0/authorize\"\n access_token_url = \"https://login.microsoftonline.com/common/oauth2/v2.0/token\" # nosec\n profile_url = \"https://graph.microsoft.com/v1.0/me\"\n oidc_well_known_url = (\n \"https://login.microsoftonline.com/common/.well-known/openid-configuration\"\n )\n oidc_jwks_url = \"https://login.microsoftonline.com/common/discovery/keys\"\n", "path": "authentik/sources/oauth/types/azure_ad.py"}]}
| 1,132 | 175 |
gh_patches_debug_9688
|
rasdani/github-patches
|
git_diff
|
googleapis__google-cloud-python-4170
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Spanner: IndexError: pop from empty list when merge_array
```
return merger(lhs, rhs, type_)
File ".../google/cloud/spanner_v1/streamed.py", line 259, in _merge_array
first = rhs.pop(0)
IndexError: pop from empty list
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `spanner/google/cloud/spanner_v1/streamed.py`
Content:
```
1 # Copyright 2016 Google Inc. All rights reserved.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Wrapper for streaming results."""
16
17 from google.protobuf.struct_pb2 import ListValue
18 from google.protobuf.struct_pb2 import Value
19 from google.cloud import exceptions
20 from google.cloud.spanner_v1.proto import type_pb2
21 import six
22
23 # pylint: disable=ungrouped-imports
24 from google.cloud.spanner_v1._helpers import _parse_value_pb
25 # pylint: enable=ungrouped-imports
26
27
28 class StreamedResultSet(object):
29 """Process a sequence of partial result sets into a single set of row data.
30
31 :type response_iterator:
32 :param response_iterator:
33 Iterator yielding
34 :class:`google.cloud.spanner_v1.proto.result_set_pb2.PartialResultSet`
35 instances.
36
37 :type source: :class:`~google.cloud.spanner_v1.snapshot.Snapshot`
38 :param source: Snapshot from which the result set was fetched.
39 """
40 def __init__(self, response_iterator, source=None):
41 self._response_iterator = response_iterator
42 self._rows = [] # Fully-processed rows
43 self._counter = 0 # Counter for processed responses
44 self._metadata = None # Until set from first PRS
45 self._stats = None # Until set from last PRS
46 self._current_row = [] # Accumulated values for incomplete row
47 self._pending_chunk = None # Incomplete value
48 self._source = source # Source snapshot
49
50 @property
51 def rows(self):
52 """Fully-processed rows.
53
54 :rtype: list of row-data lists.
55 :returns: list of completed row data, from proceesd PRS responses.
56 """
57 return self._rows
58
59 @property
60 def fields(self):
61 """Field descriptors for result set columns.
62
63 :rtype: list of :class:`~google.cloud.spanner_v1.proto.type_pb2.Field`
64 :returns: list of fields describing column names / types.
65 """
66 return self._metadata.row_type.fields
67
68 @property
69 def metadata(self):
70 """Result set metadata
71
72 :rtype: :class:`~.result_set_pb2.ResultSetMetadata`
73 :returns: structure describing the results
74 """
75 return self._metadata
76
77 @property
78 def stats(self):
79 """Result set statistics
80
81 :rtype:
82 :class:`~google.cloud.spanner_v1.proto.result_set_pb2.ResultSetStats`
83 :returns: structure describing status about the response
84 """
85 return self._stats
86
87 def _merge_chunk(self, value):
88 """Merge pending chunk with next value.
89
90 :type value: :class:`~google.protobuf.struct_pb2.Value`
91 :param value: continuation of chunked value from previous
92 partial result set.
93
94 :rtype: :class:`~google.protobuf.struct_pb2.Value`
95 :returns: the merged value
96 """
97 current_column = len(self._current_row)
98 field = self.fields[current_column]
99 merged = _merge_by_type(self._pending_chunk, value, field.type)
100 self._pending_chunk = None
101 return merged
102
103 def _merge_values(self, values):
104 """Merge values into rows.
105
106 :type values: list of :class:`~google.protobuf.struct_pb2.Value`
107 :param values: non-chunked values from partial result set.
108 """
109 width = len(self.fields)
110 for value in values:
111 index = len(self._current_row)
112 field = self.fields[index]
113 self._current_row.append(_parse_value_pb(value, field.type))
114 if len(self._current_row) == width:
115 self._rows.append(self._current_row)
116 self._current_row = []
117
118 def consume_next(self):
119 """Consume the next partial result set from the stream.
120
121 Parse the result set into new/existing rows in :attr:`_rows`
122 """
123 response = six.next(self._response_iterator)
124 self._counter += 1
125
126 if self._metadata is None: # first response
127 metadata = self._metadata = response.metadata
128
129 source = self._source
130 if source is not None and source._transaction_id is None:
131 source._transaction_id = metadata.transaction.id
132
133 if response.HasField('stats'): # last response
134 self._stats = response.stats
135
136 values = list(response.values)
137 if self._pending_chunk is not None:
138 values[0] = self._merge_chunk(values[0])
139
140 if response.chunked_value:
141 self._pending_chunk = values.pop()
142
143 self._merge_values(values)
144
145 def consume_all(self):
146 """Consume the streamed responses until there are no more."""
147 while True:
148 try:
149 self.consume_next()
150 except StopIteration:
151 break
152
153 def __iter__(self):
154 iter_rows, self._rows[:] = self._rows[:], ()
155 while True:
156 if not iter_rows:
157 self.consume_next() # raises StopIteration
158 iter_rows, self._rows[:] = self._rows[:], ()
159 while iter_rows:
160 yield iter_rows.pop(0)
161
162 def one(self):
163 """Return exactly one result, or raise an exception.
164
165 :raises: :exc:`NotFound`: If there are no results.
166 :raises: :exc:`ValueError`: If there are multiple results.
167 :raises: :exc:`RuntimeError`: If consumption has already occurred,
168 in whole or in part.
169 """
170 answer = self.one_or_none()
171 if answer is None:
172 raise exceptions.NotFound('No rows matched the given query.')
173 return answer
174
175 def one_or_none(self):
176 """Return exactly one result, or None if there are no results.
177
178 :raises: :exc:`ValueError`: If there are multiple results.
179 :raises: :exc:`RuntimeError`: If consumption has already occurred,
180 in whole or in part.
181 """
182 # Sanity check: Has consumption of this query already started?
183 # If it has, then this is an exception.
184 if self._metadata is not None:
185 raise RuntimeError('Can not call `.one` or `.one_or_none` after '
186 'stream consumption has already started.')
187
188 # Consume the first result of the stream.
189 # If there is no first result, then return None.
190 iterator = iter(self)
191 try:
192 answer = next(iterator)
193 except StopIteration:
194 return None
195
196 # Attempt to consume more. This should no-op; if we get additional
197 # rows, then this is an error case.
198 try:
199 next(iterator)
200 raise ValueError('Expected one result; got more.')
201 except StopIteration:
202 return answer
203
204
205 class Unmergeable(ValueError):
206 """Unable to merge two values.
207
208 :type lhs: :class:`google.protobuf.struct_pb2.Value`
209 :param lhs: pending value to be merged
210
211 :type rhs: :class:`google.protobuf.struct_pb2.Value`
212 :param rhs: remaining value to be merged
213
214 :type type_: :class:`google.cloud.spanner_v1.proto.type_pb2.Type`
215 :param type_: field type of values being merged
216 """
217 def __init__(self, lhs, rhs, type_):
218 message = "Cannot merge %s values: %s %s" % (
219 type_pb2.TypeCode.Name(type_.code), lhs, rhs)
220 super(Unmergeable, self).__init__(message)
221
222
223 def _unmergeable(lhs, rhs, type_):
224 """Helper for '_merge_by_type'."""
225 raise Unmergeable(lhs, rhs, type_)
226
227
228 def _merge_float64(lhs, rhs, type_): # pylint: disable=unused-argument
229 """Helper for '_merge_by_type'."""
230 lhs_kind = lhs.WhichOneof('kind')
231 if lhs_kind == 'string_value':
232 return Value(string_value=lhs.string_value + rhs.string_value)
233 rhs_kind = rhs.WhichOneof('kind')
234 array_continuation = (
235 lhs_kind == 'number_value' and
236 rhs_kind == 'string_value' and
237 rhs.string_value == '')
238 if array_continuation:
239 return lhs
240 raise Unmergeable(lhs, rhs, type_)
241
242
243 def _merge_string(lhs, rhs, type_): # pylint: disable=unused-argument
244 """Helper for '_merge_by_type'."""
245 return Value(string_value=lhs.string_value + rhs.string_value)
246
247
248 _UNMERGEABLE_TYPES = (type_pb2.BOOL,)
249
250
251 def _merge_array(lhs, rhs, type_):
252 """Helper for '_merge_by_type'."""
253 element_type = type_.array_element_type
254 if element_type.code in _UNMERGEABLE_TYPES:
255 # Individual values cannot be merged, just concatenate
256 lhs.list_value.values.extend(rhs.list_value.values)
257 return lhs
258 lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)
259 first = rhs.pop(0)
260 if first.HasField('null_value'): # can't merge
261 lhs.append(first)
262 else:
263 last = lhs.pop()
264 try:
265 merged = _merge_by_type(last, first, element_type)
266 except Unmergeable:
267 lhs.append(last)
268 lhs.append(first)
269 else:
270 lhs.append(merged)
271 return Value(list_value=ListValue(values=(lhs + rhs)))
272
273
274 def _merge_struct(lhs, rhs, type_):
275 """Helper for '_merge_by_type'."""
276 fields = type_.struct_type.fields
277 lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)
278 candidate_type = fields[len(lhs) - 1].type
279 first = rhs.pop(0)
280 if (first.HasField('null_value') or
281 candidate_type.code in _UNMERGEABLE_TYPES):
282 lhs.append(first)
283 else:
284 last = lhs.pop()
285 lhs.append(_merge_by_type(last, first, candidate_type))
286 return Value(list_value=ListValue(values=lhs + rhs))
287
288
289 _MERGE_BY_TYPE = {
290 type_pb2.ARRAY: _merge_array,
291 type_pb2.BOOL: _unmergeable,
292 type_pb2.BYTES: _merge_string,
293 type_pb2.DATE: _merge_string,
294 type_pb2.FLOAT64: _merge_float64,
295 type_pb2.INT64: _merge_string,
296 type_pb2.STRING: _merge_string,
297 type_pb2.STRUCT: _merge_struct,
298 type_pb2.TIMESTAMP: _merge_string,
299 }
300
301
302 def _merge_by_type(lhs, rhs, type_):
303 """Helper for '_merge_chunk'."""
304 merger = _MERGE_BY_TYPE[type_.code]
305 return merger(lhs, rhs, type_)
306
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/spanner/google/cloud/spanner_v1/streamed.py b/spanner/google/cloud/spanner_v1/streamed.py
--- a/spanner/google/cloud/spanner_v1/streamed.py
+++ b/spanner/google/cloud/spanner_v1/streamed.py
@@ -256,6 +256,12 @@
lhs.list_value.values.extend(rhs.list_value.values)
return lhs
lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)
+
+ # Sanity check: If either list is empty, short-circuit.
+ # This is effectively a no-op.
+ if not len(lhs) or not len(rhs):
+ return Value(list_value=ListValue(values=(lhs + rhs)))
+
first = rhs.pop(0)
if first.HasField('null_value'): # can't merge
lhs.append(first)
|
{"golden_diff": "diff --git a/spanner/google/cloud/spanner_v1/streamed.py b/spanner/google/cloud/spanner_v1/streamed.py\n--- a/spanner/google/cloud/spanner_v1/streamed.py\n+++ b/spanner/google/cloud/spanner_v1/streamed.py\n@@ -256,6 +256,12 @@\n lhs.list_value.values.extend(rhs.list_value.values)\n return lhs\n lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)\n+\n+ # Sanity check: If either list is empty, short-circuit.\n+ # This is effectively a no-op.\n+ if not len(lhs) or not len(rhs):\n+ return Value(list_value=ListValue(values=(lhs + rhs)))\n+\n first = rhs.pop(0)\n if first.HasField('null_value'): # can't merge\n lhs.append(first)\n", "issue": "Spanner: IndexError: pop from empty list when merge_array\n```\r\nreturn merger(lhs, rhs, type_)\r\n File \".../google/cloud/spanner_v1/streamed.py\", line 259, in _merge_array\r\n first = rhs.pop(0)\r\nIndexError: pop from empty list\r\n```\n", "before_files": [{"content": "# Copyright 2016 Google Inc. All rights reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Wrapper for streaming results.\"\"\"\n\nfrom google.protobuf.struct_pb2 import ListValue\nfrom google.protobuf.struct_pb2 import Value\nfrom google.cloud import exceptions\nfrom google.cloud.spanner_v1.proto import type_pb2\nimport six\n\n# pylint: disable=ungrouped-imports\nfrom google.cloud.spanner_v1._helpers import _parse_value_pb\n# pylint: enable=ungrouped-imports\n\n\nclass StreamedResultSet(object):\n \"\"\"Process a sequence of partial result sets into a single set of row data.\n\n :type response_iterator:\n :param response_iterator:\n Iterator yielding\n :class:`google.cloud.spanner_v1.proto.result_set_pb2.PartialResultSet`\n instances.\n\n :type source: :class:`~google.cloud.spanner_v1.snapshot.Snapshot`\n :param source: Snapshot from which the result set was fetched.\n \"\"\"\n def __init__(self, response_iterator, source=None):\n self._response_iterator = response_iterator\n self._rows = [] # Fully-processed rows\n self._counter = 0 # Counter for processed responses\n self._metadata = None # Until set from first PRS\n self._stats = None # Until set from last PRS\n self._current_row = [] # Accumulated values for incomplete row\n self._pending_chunk = None # Incomplete value\n self._source = source # Source snapshot\n\n @property\n def rows(self):\n \"\"\"Fully-processed rows.\n\n :rtype: list of row-data lists.\n :returns: list of completed row data, from proceesd PRS responses.\n \"\"\"\n return self._rows\n\n @property\n def fields(self):\n \"\"\"Field descriptors for result set columns.\n\n :rtype: list of :class:`~google.cloud.spanner_v1.proto.type_pb2.Field`\n :returns: list of fields describing column names / types.\n \"\"\"\n return self._metadata.row_type.fields\n\n @property\n def metadata(self):\n \"\"\"Result set metadata\n\n :rtype: :class:`~.result_set_pb2.ResultSetMetadata`\n :returns: structure describing the results\n \"\"\"\n return self._metadata\n\n @property\n def stats(self):\n \"\"\"Result set statistics\n\n :rtype:\n :class:`~google.cloud.spanner_v1.proto.result_set_pb2.ResultSetStats`\n :returns: structure describing status about the response\n \"\"\"\n return self._stats\n\n def _merge_chunk(self, value):\n \"\"\"Merge pending chunk with next value.\n\n :type value: :class:`~google.protobuf.struct_pb2.Value`\n :param value: continuation of chunked value from previous\n partial result set.\n\n :rtype: :class:`~google.protobuf.struct_pb2.Value`\n :returns: the merged value\n \"\"\"\n current_column = len(self._current_row)\n field = self.fields[current_column]\n merged = _merge_by_type(self._pending_chunk, value, field.type)\n self._pending_chunk = None\n return merged\n\n def _merge_values(self, values):\n \"\"\"Merge values into rows.\n\n :type values: list of :class:`~google.protobuf.struct_pb2.Value`\n :param values: non-chunked values from partial result set.\n \"\"\"\n width = len(self.fields)\n for value in values:\n index = len(self._current_row)\n field = self.fields[index]\n self._current_row.append(_parse_value_pb(value, field.type))\n if len(self._current_row) == width:\n self._rows.append(self._current_row)\n self._current_row = []\n\n def consume_next(self):\n \"\"\"Consume the next partial result set from the stream.\n\n Parse the result set into new/existing rows in :attr:`_rows`\n \"\"\"\n response = six.next(self._response_iterator)\n self._counter += 1\n\n if self._metadata is None: # first response\n metadata = self._metadata = response.metadata\n\n source = self._source\n if source is not None and source._transaction_id is None:\n source._transaction_id = metadata.transaction.id\n\n if response.HasField('stats'): # last response\n self._stats = response.stats\n\n values = list(response.values)\n if self._pending_chunk is not None:\n values[0] = self._merge_chunk(values[0])\n\n if response.chunked_value:\n self._pending_chunk = values.pop()\n\n self._merge_values(values)\n\n def consume_all(self):\n \"\"\"Consume the streamed responses until there are no more.\"\"\"\n while True:\n try:\n self.consume_next()\n except StopIteration:\n break\n\n def __iter__(self):\n iter_rows, self._rows[:] = self._rows[:], ()\n while True:\n if not iter_rows:\n self.consume_next() # raises StopIteration\n iter_rows, self._rows[:] = self._rows[:], ()\n while iter_rows:\n yield iter_rows.pop(0)\n\n def one(self):\n \"\"\"Return exactly one result, or raise an exception.\n\n :raises: :exc:`NotFound`: If there are no results.\n :raises: :exc:`ValueError`: If there are multiple results.\n :raises: :exc:`RuntimeError`: If consumption has already occurred,\n in whole or in part.\n \"\"\"\n answer = self.one_or_none()\n if answer is None:\n raise exceptions.NotFound('No rows matched the given query.')\n return answer\n\n def one_or_none(self):\n \"\"\"Return exactly one result, or None if there are no results.\n\n :raises: :exc:`ValueError`: If there are multiple results.\n :raises: :exc:`RuntimeError`: If consumption has already occurred,\n in whole or in part.\n \"\"\"\n # Sanity check: Has consumption of this query already started?\n # If it has, then this is an exception.\n if self._metadata is not None:\n raise RuntimeError('Can not call `.one` or `.one_or_none` after '\n 'stream consumption has already started.')\n\n # Consume the first result of the stream.\n # If there is no first result, then return None.\n iterator = iter(self)\n try:\n answer = next(iterator)\n except StopIteration:\n return None\n\n # Attempt to consume more. This should no-op; if we get additional\n # rows, then this is an error case.\n try:\n next(iterator)\n raise ValueError('Expected one result; got more.')\n except StopIteration:\n return answer\n\n\nclass Unmergeable(ValueError):\n \"\"\"Unable to merge two values.\n\n :type lhs: :class:`google.protobuf.struct_pb2.Value`\n :param lhs: pending value to be merged\n\n :type rhs: :class:`google.protobuf.struct_pb2.Value`\n :param rhs: remaining value to be merged\n\n :type type_: :class:`google.cloud.spanner_v1.proto.type_pb2.Type`\n :param type_: field type of values being merged\n \"\"\"\n def __init__(self, lhs, rhs, type_):\n message = \"Cannot merge %s values: %s %s\" % (\n type_pb2.TypeCode.Name(type_.code), lhs, rhs)\n super(Unmergeable, self).__init__(message)\n\n\ndef _unmergeable(lhs, rhs, type_):\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n raise Unmergeable(lhs, rhs, type_)\n\n\ndef _merge_float64(lhs, rhs, type_): # pylint: disable=unused-argument\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n lhs_kind = lhs.WhichOneof('kind')\n if lhs_kind == 'string_value':\n return Value(string_value=lhs.string_value + rhs.string_value)\n rhs_kind = rhs.WhichOneof('kind')\n array_continuation = (\n lhs_kind == 'number_value' and\n rhs_kind == 'string_value' and\n rhs.string_value == '')\n if array_continuation:\n return lhs\n raise Unmergeable(lhs, rhs, type_)\n\n\ndef _merge_string(lhs, rhs, type_): # pylint: disable=unused-argument\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n return Value(string_value=lhs.string_value + rhs.string_value)\n\n\n_UNMERGEABLE_TYPES = (type_pb2.BOOL,)\n\n\ndef _merge_array(lhs, rhs, type_):\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n element_type = type_.array_element_type\n if element_type.code in _UNMERGEABLE_TYPES:\n # Individual values cannot be merged, just concatenate\n lhs.list_value.values.extend(rhs.list_value.values)\n return lhs\n lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)\n first = rhs.pop(0)\n if first.HasField('null_value'): # can't merge\n lhs.append(first)\n else:\n last = lhs.pop()\n try:\n merged = _merge_by_type(last, first, element_type)\n except Unmergeable:\n lhs.append(last)\n lhs.append(first)\n else:\n lhs.append(merged)\n return Value(list_value=ListValue(values=(lhs + rhs)))\n\n\ndef _merge_struct(lhs, rhs, type_):\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n fields = type_.struct_type.fields\n lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)\n candidate_type = fields[len(lhs) - 1].type\n first = rhs.pop(0)\n if (first.HasField('null_value') or\n candidate_type.code in _UNMERGEABLE_TYPES):\n lhs.append(first)\n else:\n last = lhs.pop()\n lhs.append(_merge_by_type(last, first, candidate_type))\n return Value(list_value=ListValue(values=lhs + rhs))\n\n\n_MERGE_BY_TYPE = {\n type_pb2.ARRAY: _merge_array,\n type_pb2.BOOL: _unmergeable,\n type_pb2.BYTES: _merge_string,\n type_pb2.DATE: _merge_string,\n type_pb2.FLOAT64: _merge_float64,\n type_pb2.INT64: _merge_string,\n type_pb2.STRING: _merge_string,\n type_pb2.STRUCT: _merge_struct,\n type_pb2.TIMESTAMP: _merge_string,\n}\n\n\ndef _merge_by_type(lhs, rhs, type_):\n \"\"\"Helper for '_merge_chunk'.\"\"\"\n merger = _MERGE_BY_TYPE[type_.code]\n return merger(lhs, rhs, type_)\n", "path": "spanner/google/cloud/spanner_v1/streamed.py"}], "after_files": [{"content": "# Copyright 2016 Google Inc. All rights reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Wrapper for streaming results.\"\"\"\n\nfrom google.protobuf.struct_pb2 import ListValue\nfrom google.protobuf.struct_pb2 import Value\nfrom google.cloud import exceptions\nfrom google.cloud.spanner_v1.proto import type_pb2\nimport six\n\n# pylint: disable=ungrouped-imports\nfrom google.cloud.spanner_v1._helpers import _parse_value_pb\n# pylint: enable=ungrouped-imports\n\n\nclass StreamedResultSet(object):\n \"\"\"Process a sequence of partial result sets into a single set of row data.\n\n :type response_iterator:\n :param response_iterator:\n Iterator yielding\n :class:`google.cloud.spanner_v1.proto.result_set_pb2.PartialResultSet`\n instances.\n\n :type source: :class:`~google.cloud.spanner_v1.snapshot.Snapshot`\n :param source: Snapshot from which the result set was fetched.\n \"\"\"\n def __init__(self, response_iterator, source=None):\n self._response_iterator = response_iterator\n self._rows = [] # Fully-processed rows\n self._counter = 0 # Counter for processed responses\n self._metadata = None # Until set from first PRS\n self._stats = None # Until set from last PRS\n self._current_row = [] # Accumulated values for incomplete row\n self._pending_chunk = None # Incomplete value\n self._source = source # Source snapshot\n\n @property\n def rows(self):\n \"\"\"Fully-processed rows.\n\n :rtype: list of row-data lists.\n :returns: list of completed row data, from proceesd PRS responses.\n \"\"\"\n return self._rows\n\n @property\n def fields(self):\n \"\"\"Field descriptors for result set columns.\n\n :rtype: list of :class:`~google.cloud.spanner_v1.proto.type_pb2.Field`\n :returns: list of fields describing column names / types.\n \"\"\"\n return self._metadata.row_type.fields\n\n @property\n def metadata(self):\n \"\"\"Result set metadata\n\n :rtype: :class:`~.result_set_pb2.ResultSetMetadata`\n :returns: structure describing the results\n \"\"\"\n return self._metadata\n\n @property\n def stats(self):\n \"\"\"Result set statistics\n\n :rtype:\n :class:`~google.cloud.spanner_v1.proto.result_set_pb2.ResultSetStats`\n :returns: structure describing status about the response\n \"\"\"\n return self._stats\n\n def _merge_chunk(self, value):\n \"\"\"Merge pending chunk with next value.\n\n :type value: :class:`~google.protobuf.struct_pb2.Value`\n :param value: continuation of chunked value from previous\n partial result set.\n\n :rtype: :class:`~google.protobuf.struct_pb2.Value`\n :returns: the merged value\n \"\"\"\n current_column = len(self._current_row)\n field = self.fields[current_column]\n merged = _merge_by_type(self._pending_chunk, value, field.type)\n self._pending_chunk = None\n return merged\n\n def _merge_values(self, values):\n \"\"\"Merge values into rows.\n\n :type values: list of :class:`~google.protobuf.struct_pb2.Value`\n :param values: non-chunked values from partial result set.\n \"\"\"\n width = len(self.fields)\n for value in values:\n index = len(self._current_row)\n field = self.fields[index]\n self._current_row.append(_parse_value_pb(value, field.type))\n if len(self._current_row) == width:\n self._rows.append(self._current_row)\n self._current_row = []\n\n def consume_next(self):\n \"\"\"Consume the next partial result set from the stream.\n\n Parse the result set into new/existing rows in :attr:`_rows`\n \"\"\"\n response = six.next(self._response_iterator)\n self._counter += 1\n\n if self._metadata is None: # first response\n metadata = self._metadata = response.metadata\n\n source = self._source\n if source is not None and source._transaction_id is None:\n source._transaction_id = metadata.transaction.id\n\n if response.HasField('stats'): # last response\n self._stats = response.stats\n\n values = list(response.values)\n if self._pending_chunk is not None:\n values[0] = self._merge_chunk(values[0])\n\n if response.chunked_value:\n self._pending_chunk = values.pop()\n\n self._merge_values(values)\n\n def consume_all(self):\n \"\"\"Consume the streamed responses until there are no more.\"\"\"\n while True:\n try:\n self.consume_next()\n except StopIteration:\n break\n\n def __iter__(self):\n iter_rows, self._rows[:] = self._rows[:], ()\n while True:\n if not iter_rows:\n self.consume_next() # raises StopIteration\n iter_rows, self._rows[:] = self._rows[:], ()\n while iter_rows:\n yield iter_rows.pop(0)\n\n def one(self):\n \"\"\"Return exactly one result, or raise an exception.\n\n :raises: :exc:`NotFound`: If there are no results.\n :raises: :exc:`ValueError`: If there are multiple results.\n :raises: :exc:`RuntimeError`: If consumption has already occurred,\n in whole or in part.\n \"\"\"\n answer = self.one_or_none()\n if answer is None:\n raise exceptions.NotFound('No rows matched the given query.')\n return answer\n\n def one_or_none(self):\n \"\"\"Return exactly one result, or None if there are no results.\n\n :raises: :exc:`ValueError`: If there are multiple results.\n :raises: :exc:`RuntimeError`: If consumption has already occurred,\n in whole or in part.\n \"\"\"\n # Sanity check: Has consumption of this query already started?\n # If it has, then this is an exception.\n if self._metadata is not None:\n raise RuntimeError('Can not call `.one` or `.one_or_none` after '\n 'stream consumption has already started.')\n\n # Consume the first result of the stream.\n # If there is no first result, then return None.\n iterator = iter(self)\n try:\n answer = next(iterator)\n except StopIteration:\n return None\n\n # Attempt to consume more. This should no-op; if we get additional\n # rows, then this is an error case.\n try:\n next(iterator)\n raise ValueError('Expected one result; got more.')\n except StopIteration:\n return answer\n\n\nclass Unmergeable(ValueError):\n \"\"\"Unable to merge two values.\n\n :type lhs: :class:`google.protobuf.struct_pb2.Value`\n :param lhs: pending value to be merged\n\n :type rhs: :class:`google.protobuf.struct_pb2.Value`\n :param rhs: remaining value to be merged\n\n :type type_: :class:`google.cloud.spanner_v1.proto.type_pb2.Type`\n :param type_: field type of values being merged\n \"\"\"\n def __init__(self, lhs, rhs, type_):\n message = \"Cannot merge %s values: %s %s\" % (\n type_pb2.TypeCode.Name(type_.code), lhs, rhs)\n super(Unmergeable, self).__init__(message)\n\n\ndef _unmergeable(lhs, rhs, type_):\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n raise Unmergeable(lhs, rhs, type_)\n\n\ndef _merge_float64(lhs, rhs, type_): # pylint: disable=unused-argument\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n lhs_kind = lhs.WhichOneof('kind')\n if lhs_kind == 'string_value':\n return Value(string_value=lhs.string_value + rhs.string_value)\n rhs_kind = rhs.WhichOneof('kind')\n array_continuation = (\n lhs_kind == 'number_value' and\n rhs_kind == 'string_value' and\n rhs.string_value == '')\n if array_continuation:\n return lhs\n raise Unmergeable(lhs, rhs, type_)\n\n\ndef _merge_string(lhs, rhs, type_): # pylint: disable=unused-argument\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n return Value(string_value=lhs.string_value + rhs.string_value)\n\n\n_UNMERGEABLE_TYPES = (type_pb2.BOOL,)\n\n\ndef _merge_array(lhs, rhs, type_):\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n element_type = type_.array_element_type\n if element_type.code in _UNMERGEABLE_TYPES:\n # Individual values cannot be merged, just concatenate\n lhs.list_value.values.extend(rhs.list_value.values)\n return lhs\n lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)\n\n # Sanity check: If either list is empty, short-circuit.\n # This is effectively a no-op.\n if not len(lhs) or not len(rhs):\n return Value(list_value=ListValue(values=(lhs + rhs)))\n\n first = rhs.pop(0)\n if first.HasField('null_value'): # can't merge\n lhs.append(first)\n else:\n last = lhs.pop()\n try:\n merged = _merge_by_type(last, first, element_type)\n except Unmergeable:\n lhs.append(last)\n lhs.append(first)\n else:\n lhs.append(merged)\n return Value(list_value=ListValue(values=(lhs + rhs)))\n\n\ndef _merge_struct(lhs, rhs, type_):\n \"\"\"Helper for '_merge_by_type'.\"\"\"\n fields = type_.struct_type.fields\n lhs, rhs = list(lhs.list_value.values), list(rhs.list_value.values)\n candidate_type = fields[len(lhs) - 1].type\n first = rhs.pop(0)\n if (first.HasField('null_value') or\n candidate_type.code in _UNMERGEABLE_TYPES):\n lhs.append(first)\n else:\n last = lhs.pop()\n lhs.append(_merge_by_type(last, first, candidate_type))\n return Value(list_value=ListValue(values=lhs + rhs))\n\n\n_MERGE_BY_TYPE = {\n type_pb2.ARRAY: _merge_array,\n type_pb2.BOOL: _unmergeable,\n type_pb2.BYTES: _merge_string,\n type_pb2.DATE: _merge_string,\n type_pb2.FLOAT64: _merge_float64,\n type_pb2.INT64: _merge_string,\n type_pb2.STRING: _merge_string,\n type_pb2.STRUCT: _merge_struct,\n type_pb2.TIMESTAMP: _merge_string,\n}\n\n\ndef _merge_by_type(lhs, rhs, type_):\n \"\"\"Helper for '_merge_chunk'.\"\"\"\n merger = _MERGE_BY_TYPE[type_.code]\n return merger(lhs, rhs, type_)\n", "path": "spanner/google/cloud/spanner_v1/streamed.py"}]}
| 3,568 | 186 |
gh_patches_debug_15565
|
rasdani/github-patches
|
git_diff
|
deepset-ai__haystack-7796
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[V2.2.0] ChatPromptBuilder is not export
**Describe the bug**
v2.2.0 => ChatPromptBuilder is not export
**Error message**
<img width="1102" alt="image" src="https://github.com/deepset-ai/haystack/assets/15232298/b9372767-42f5-464c-832f-cca38a00cf60">
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `haystack/components/builders/__init__.py`
Content:
```
1 # SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
2 #
3 # SPDX-License-Identifier: Apache-2.0
4
5 from haystack.components.builders.answer_builder import AnswerBuilder
6 from haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder
7 from haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder
8 from haystack.components.builders.prompt_builder import PromptBuilder
9
10 __all__ = ["AnswerBuilder", "PromptBuilder", "DynamicPromptBuilder", "DynamicChatPromptBuilder"]
11
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/haystack/components/builders/__init__.py b/haystack/components/builders/__init__.py
--- a/haystack/components/builders/__init__.py
+++ b/haystack/components/builders/__init__.py
@@ -3,8 +3,9 @@
# SPDX-License-Identifier: Apache-2.0
from haystack.components.builders.answer_builder import AnswerBuilder
+from haystack.components.builders.chat_prompt_builder import ChatPromptBuilder
from haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder
from haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder
from haystack.components.builders.prompt_builder import PromptBuilder
-__all__ = ["AnswerBuilder", "PromptBuilder", "DynamicPromptBuilder", "DynamicChatPromptBuilder"]
+__all__ = ["AnswerBuilder", "PromptBuilder", "DynamicPromptBuilder", "DynamicChatPromptBuilder", "ChatPromptBuilder"]
|
{"golden_diff": "diff --git a/haystack/components/builders/__init__.py b/haystack/components/builders/__init__.py\n--- a/haystack/components/builders/__init__.py\n+++ b/haystack/components/builders/__init__.py\n@@ -3,8 +3,9 @@\n # SPDX-License-Identifier: Apache-2.0\n \n from haystack.components.builders.answer_builder import AnswerBuilder\n+from haystack.components.builders.chat_prompt_builder import ChatPromptBuilder\n from haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder\n from haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder\n from haystack.components.builders.prompt_builder import PromptBuilder\n \n-__all__ = [\"AnswerBuilder\", \"PromptBuilder\", \"DynamicPromptBuilder\", \"DynamicChatPromptBuilder\"]\n+__all__ = [\"AnswerBuilder\", \"PromptBuilder\", \"DynamicPromptBuilder\", \"DynamicChatPromptBuilder\", \"ChatPromptBuilder\"]\n", "issue": "[V2.2.0] ChatPromptBuilder is not export\n**Describe the bug**\r\nv2.2.0 => ChatPromptBuilder is not export\r\n\r\n**Error message**\r\n<img width=\"1102\" alt=\"image\" src=\"https://github.com/deepset-ai/haystack/assets/15232298/b9372767-42f5-464c-832f-cca38a00cf60\">\r\n\r\n\n", "before_files": [{"content": "# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>\n#\n# SPDX-License-Identifier: Apache-2.0\n\nfrom haystack.components.builders.answer_builder import AnswerBuilder\nfrom haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder\nfrom haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder\nfrom haystack.components.builders.prompt_builder import PromptBuilder\n\n__all__ = [\"AnswerBuilder\", \"PromptBuilder\", \"DynamicPromptBuilder\", \"DynamicChatPromptBuilder\"]\n", "path": "haystack/components/builders/__init__.py"}], "after_files": [{"content": "# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>\n#\n# SPDX-License-Identifier: Apache-2.0\n\nfrom haystack.components.builders.answer_builder import AnswerBuilder\nfrom haystack.components.builders.chat_prompt_builder import ChatPromptBuilder\nfrom haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder\nfrom haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder\nfrom haystack.components.builders.prompt_builder import PromptBuilder\n\n__all__ = [\"AnswerBuilder\", \"PromptBuilder\", \"DynamicPromptBuilder\", \"DynamicChatPromptBuilder\", \"ChatPromptBuilder\"]\n", "path": "haystack/components/builders/__init__.py"}]}
| 491 | 185 |
gh_patches_debug_36530
|
rasdani/github-patches
|
git_diff
|
getsentry__sentry-python-541
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
0.12.0 breaks Django function-based middleware
Similar to #504, but a different stack trace:
AttributeError: 'method-wrapper' object has no attribute '__module__'
File "django/core/handlers/exception.py", line 41, in inner
response = get_response(request)
File "functools.py", line 33, in update_wrapper
setattr(wrapper, attr, getattr(wrapped, attr))
According to sentry (kind-of neat how I get this in this case...), the `get_response` object at that point in time is `<sentry_sdk.integrations.django.middleware.AuditMiddleware object at 0x7f37d64d4450>`.
This problem only occurs in 0.12.0 and newer, and with Django 1.11.x
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `sentry_sdk/integrations/django/middleware.py`
Content:
```
1 """
2 Create spans from Django middleware invocations
3 """
4
5 from functools import wraps
6
7 from django import VERSION as DJANGO_VERSION
8
9 from sentry_sdk import Hub
10 from sentry_sdk.utils import ContextVar, transaction_from_function
11
12 from sentry_sdk._types import MYPY
13
14 if MYPY:
15 from typing import Any
16 from typing import Callable
17 from typing import TypeVar
18
19 F = TypeVar("F", bound=Callable[..., Any])
20
21 _import_string_should_wrap_middleware = ContextVar(
22 "import_string_should_wrap_middleware"
23 )
24
25 if DJANGO_VERSION < (1, 7):
26 import_string_name = "import_by_path"
27 else:
28 import_string_name = "import_string"
29
30
31 def patch_django_middlewares():
32 # type: () -> None
33 from django.core.handlers import base
34
35 old_import_string = getattr(base, import_string_name)
36
37 def sentry_patched_import_string(dotted_path):
38 # type: (str) -> Any
39 rv = old_import_string(dotted_path)
40
41 if _import_string_should_wrap_middleware.get(None):
42 rv = _wrap_middleware(rv, dotted_path)
43
44 return rv
45
46 setattr(base, import_string_name, sentry_patched_import_string)
47
48 old_load_middleware = base.BaseHandler.load_middleware
49
50 def sentry_patched_load_middleware(self):
51 # type: (base.BaseHandler) -> Any
52 _import_string_should_wrap_middleware.set(True)
53 try:
54 return old_load_middleware(self)
55 finally:
56 _import_string_should_wrap_middleware.set(False)
57
58 base.BaseHandler.load_middleware = sentry_patched_load_middleware
59
60
61 def _wrap_middleware(middleware, middleware_name):
62 # type: (Any, str) -> Any
63 from sentry_sdk.integrations.django import DjangoIntegration
64
65 def _get_wrapped_method(old_method):
66 # type: (F) -> F
67 @wraps(old_method)
68 def sentry_wrapped_method(*args, **kwargs):
69 # type: (*Any, **Any) -> Any
70 hub = Hub.current
71 integration = hub.get_integration(DjangoIntegration)
72 if integration is None or not integration.middleware_spans:
73 return old_method(*args, **kwargs)
74
75 function_name = transaction_from_function(old_method)
76
77 description = middleware_name
78 function_basename = getattr(old_method, "__name__", None)
79 if function_basename:
80 description = "{}.{}".format(description, function_basename)
81
82 with hub.start_span(
83 op="django.middleware", description=description
84 ) as span:
85 span.set_tag("django.function_name", function_name)
86 span.set_tag("django.middleware_name", middleware_name)
87 return old_method(*args, **kwargs)
88
89 return sentry_wrapped_method # type: ignore
90
91 class SentryWrappingMiddleware(object):
92 def __init__(self, *args, **kwargs):
93 # type: (*Any, **Any) -> None
94 self._inner = middleware(*args, **kwargs)
95 self._call_method = None
96
97 # We need correct behavior for `hasattr()`, which we can only determine
98 # when we have an instance of the middleware we're wrapping.
99 def __getattr__(self, method_name):
100 # type: (str) -> Any
101 if method_name not in (
102 "process_request",
103 "process_view",
104 "process_template_response",
105 "process_response",
106 "process_exception",
107 ):
108 raise AttributeError()
109
110 old_method = getattr(self._inner, method_name)
111 rv = _get_wrapped_method(old_method)
112 self.__dict__[method_name] = rv
113 return rv
114
115 def __call__(self, *args, **kwargs):
116 # type: (*Any, **Any) -> Any
117 f = self._call_method
118 if f is None:
119 self._call_method = f = _get_wrapped_method(self._inner.__call__)
120 return f(*args, **kwargs)
121
122 if hasattr(middleware, "__name__"):
123 SentryWrappingMiddleware.__name__ = middleware.__name__
124
125 return SentryWrappingMiddleware
126
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/sentry_sdk/integrations/django/middleware.py b/sentry_sdk/integrations/django/middleware.py
--- a/sentry_sdk/integrations/django/middleware.py
+++ b/sentry_sdk/integrations/django/middleware.py
@@ -7,7 +7,11 @@
from django import VERSION as DJANGO_VERSION
from sentry_sdk import Hub
-from sentry_sdk.utils import ContextVar, transaction_from_function
+from sentry_sdk.utils import (
+ ContextVar,
+ transaction_from_function,
+ capture_internal_exceptions,
+)
from sentry_sdk._types import MYPY
@@ -64,29 +68,36 @@
def _get_wrapped_method(old_method):
# type: (F) -> F
- @wraps(old_method)
- def sentry_wrapped_method(*args, **kwargs):
- # type: (*Any, **Any) -> Any
- hub = Hub.current
- integration = hub.get_integration(DjangoIntegration)
- if integration is None or not integration.middleware_spans:
- return old_method(*args, **kwargs)
-
- function_name = transaction_from_function(old_method)
-
- description = middleware_name
- function_basename = getattr(old_method, "__name__", None)
- if function_basename:
- description = "{}.{}".format(description, function_basename)
-
- with hub.start_span(
- op="django.middleware", description=description
- ) as span:
- span.set_tag("django.function_name", function_name)
- span.set_tag("django.middleware_name", middleware_name)
- return old_method(*args, **kwargs)
-
- return sentry_wrapped_method # type: ignore
+ with capture_internal_exceptions():
+
+ def sentry_wrapped_method(*args, **kwargs):
+ # type: (*Any, **Any) -> Any
+ hub = Hub.current
+ integration = hub.get_integration(DjangoIntegration)
+ if integration is None or not integration.middleware_spans:
+ return old_method(*args, **kwargs)
+
+ function_name = transaction_from_function(old_method)
+
+ description = middleware_name
+ function_basename = getattr(old_method, "__name__", None)
+ if function_basename:
+ description = "{}.{}".format(description, function_basename)
+
+ with hub.start_span(
+ op="django.middleware", description=description
+ ) as span:
+ span.set_tag("django.function_name", function_name)
+ span.set_tag("django.middleware_name", middleware_name)
+ return old_method(*args, **kwargs)
+
+ try:
+ # fails for __call__ of function on Python 2 (see py2.7-django-1.11)
+ return wraps(old_method)(sentry_wrapped_method) # type: ignore
+ except Exception:
+ return sentry_wrapped_method # type: ignore
+
+ return old_method
class SentryWrappingMiddleware(object):
def __init__(self, *args, **kwargs):
|
{"golden_diff": "diff --git a/sentry_sdk/integrations/django/middleware.py b/sentry_sdk/integrations/django/middleware.py\n--- a/sentry_sdk/integrations/django/middleware.py\n+++ b/sentry_sdk/integrations/django/middleware.py\n@@ -7,7 +7,11 @@\n from django import VERSION as DJANGO_VERSION\n \n from sentry_sdk import Hub\n-from sentry_sdk.utils import ContextVar, transaction_from_function\n+from sentry_sdk.utils import (\n+ ContextVar,\n+ transaction_from_function,\n+ capture_internal_exceptions,\n+)\n \n from sentry_sdk._types import MYPY\n \n@@ -64,29 +68,36 @@\n \n def _get_wrapped_method(old_method):\n # type: (F) -> F\n- @wraps(old_method)\n- def sentry_wrapped_method(*args, **kwargs):\n- # type: (*Any, **Any) -> Any\n- hub = Hub.current\n- integration = hub.get_integration(DjangoIntegration)\n- if integration is None or not integration.middleware_spans:\n- return old_method(*args, **kwargs)\n-\n- function_name = transaction_from_function(old_method)\n-\n- description = middleware_name\n- function_basename = getattr(old_method, \"__name__\", None)\n- if function_basename:\n- description = \"{}.{}\".format(description, function_basename)\n-\n- with hub.start_span(\n- op=\"django.middleware\", description=description\n- ) as span:\n- span.set_tag(\"django.function_name\", function_name)\n- span.set_tag(\"django.middleware_name\", middleware_name)\n- return old_method(*args, **kwargs)\n-\n- return sentry_wrapped_method # type: ignore\n+ with capture_internal_exceptions():\n+\n+ def sentry_wrapped_method(*args, **kwargs):\n+ # type: (*Any, **Any) -> Any\n+ hub = Hub.current\n+ integration = hub.get_integration(DjangoIntegration)\n+ if integration is None or not integration.middleware_spans:\n+ return old_method(*args, **kwargs)\n+\n+ function_name = transaction_from_function(old_method)\n+\n+ description = middleware_name\n+ function_basename = getattr(old_method, \"__name__\", None)\n+ if function_basename:\n+ description = \"{}.{}\".format(description, function_basename)\n+\n+ with hub.start_span(\n+ op=\"django.middleware\", description=description\n+ ) as span:\n+ span.set_tag(\"django.function_name\", function_name)\n+ span.set_tag(\"django.middleware_name\", middleware_name)\n+ return old_method(*args, **kwargs)\n+\n+ try:\n+ # fails for __call__ of function on Python 2 (see py2.7-django-1.11)\n+ return wraps(old_method)(sentry_wrapped_method) # type: ignore\n+ except Exception:\n+ return sentry_wrapped_method # type: ignore\n+\n+ return old_method\n \n class SentryWrappingMiddleware(object):\n def __init__(self, *args, **kwargs):\n", "issue": "0.12.0 breaks Django function-based middleware\nSimilar to #504, but a different stack trace:\r\n\r\n AttributeError: 'method-wrapper' object has no attribute '__module__'\r\n File \"django/core/handlers/exception.py\", line 41, in inner\r\n response = get_response(request)\r\n File \"functools.py\", line 33, in update_wrapper\r\n setattr(wrapper, attr, getattr(wrapped, attr))\r\n\r\nAccording to sentry (kind-of neat how I get this in this case...), the `get_response` object at that point in time is `<sentry_sdk.integrations.django.middleware.AuditMiddleware object at 0x7f37d64d4450>`.\r\n\r\nThis problem only occurs in 0.12.0 and newer, and with Django 1.11.x\n", "before_files": [{"content": "\"\"\"\nCreate spans from Django middleware invocations\n\"\"\"\n\nfrom functools import wraps\n\nfrom django import VERSION as DJANGO_VERSION\n\nfrom sentry_sdk import Hub\nfrom sentry_sdk.utils import ContextVar, transaction_from_function\n\nfrom sentry_sdk._types import MYPY\n\nif MYPY:\n from typing import Any\n from typing import Callable\n from typing import TypeVar\n\n F = TypeVar(\"F\", bound=Callable[..., Any])\n\n_import_string_should_wrap_middleware = ContextVar(\n \"import_string_should_wrap_middleware\"\n)\n\nif DJANGO_VERSION < (1, 7):\n import_string_name = \"import_by_path\"\nelse:\n import_string_name = \"import_string\"\n\n\ndef patch_django_middlewares():\n # type: () -> None\n from django.core.handlers import base\n\n old_import_string = getattr(base, import_string_name)\n\n def sentry_patched_import_string(dotted_path):\n # type: (str) -> Any\n rv = old_import_string(dotted_path)\n\n if _import_string_should_wrap_middleware.get(None):\n rv = _wrap_middleware(rv, dotted_path)\n\n return rv\n\n setattr(base, import_string_name, sentry_patched_import_string)\n\n old_load_middleware = base.BaseHandler.load_middleware\n\n def sentry_patched_load_middleware(self):\n # type: (base.BaseHandler) -> Any\n _import_string_should_wrap_middleware.set(True)\n try:\n return old_load_middleware(self)\n finally:\n _import_string_should_wrap_middleware.set(False)\n\n base.BaseHandler.load_middleware = sentry_patched_load_middleware\n\n\ndef _wrap_middleware(middleware, middleware_name):\n # type: (Any, str) -> Any\n from sentry_sdk.integrations.django import DjangoIntegration\n\n def _get_wrapped_method(old_method):\n # type: (F) -> F\n @wraps(old_method)\n def sentry_wrapped_method(*args, **kwargs):\n # type: (*Any, **Any) -> Any\n hub = Hub.current\n integration = hub.get_integration(DjangoIntegration)\n if integration is None or not integration.middleware_spans:\n return old_method(*args, **kwargs)\n\n function_name = transaction_from_function(old_method)\n\n description = middleware_name\n function_basename = getattr(old_method, \"__name__\", None)\n if function_basename:\n description = \"{}.{}\".format(description, function_basename)\n\n with hub.start_span(\n op=\"django.middleware\", description=description\n ) as span:\n span.set_tag(\"django.function_name\", function_name)\n span.set_tag(\"django.middleware_name\", middleware_name)\n return old_method(*args, **kwargs)\n\n return sentry_wrapped_method # type: ignore\n\n class SentryWrappingMiddleware(object):\n def __init__(self, *args, **kwargs):\n # type: (*Any, **Any) -> None\n self._inner = middleware(*args, **kwargs)\n self._call_method = None\n\n # We need correct behavior for `hasattr()`, which we can only determine\n # when we have an instance of the middleware we're wrapping.\n def __getattr__(self, method_name):\n # type: (str) -> Any\n if method_name not in (\n \"process_request\",\n \"process_view\",\n \"process_template_response\",\n \"process_response\",\n \"process_exception\",\n ):\n raise AttributeError()\n\n old_method = getattr(self._inner, method_name)\n rv = _get_wrapped_method(old_method)\n self.__dict__[method_name] = rv\n return rv\n\n def __call__(self, *args, **kwargs):\n # type: (*Any, **Any) -> Any\n f = self._call_method\n if f is None:\n self._call_method = f = _get_wrapped_method(self._inner.__call__)\n return f(*args, **kwargs)\n\n if hasattr(middleware, \"__name__\"):\n SentryWrappingMiddleware.__name__ = middleware.__name__\n\n return SentryWrappingMiddleware\n", "path": "sentry_sdk/integrations/django/middleware.py"}], "after_files": [{"content": "\"\"\"\nCreate spans from Django middleware invocations\n\"\"\"\n\nfrom functools import wraps\n\nfrom django import VERSION as DJANGO_VERSION\n\nfrom sentry_sdk import Hub\nfrom sentry_sdk.utils import (\n ContextVar,\n transaction_from_function,\n capture_internal_exceptions,\n)\n\nfrom sentry_sdk._types import MYPY\n\nif MYPY:\n from typing import Any\n from typing import Callable\n from typing import TypeVar\n\n F = TypeVar(\"F\", bound=Callable[..., Any])\n\n_import_string_should_wrap_middleware = ContextVar(\n \"import_string_should_wrap_middleware\"\n)\n\nif DJANGO_VERSION < (1, 7):\n import_string_name = \"import_by_path\"\nelse:\n import_string_name = \"import_string\"\n\n\ndef patch_django_middlewares():\n # type: () -> None\n from django.core.handlers import base\n\n old_import_string = getattr(base, import_string_name)\n\n def sentry_patched_import_string(dotted_path):\n # type: (str) -> Any\n rv = old_import_string(dotted_path)\n\n if _import_string_should_wrap_middleware.get(None):\n rv = _wrap_middleware(rv, dotted_path)\n\n return rv\n\n setattr(base, import_string_name, sentry_patched_import_string)\n\n old_load_middleware = base.BaseHandler.load_middleware\n\n def sentry_patched_load_middleware(self):\n # type: (base.BaseHandler) -> Any\n _import_string_should_wrap_middleware.set(True)\n try:\n return old_load_middleware(self)\n finally:\n _import_string_should_wrap_middleware.set(False)\n\n base.BaseHandler.load_middleware = sentry_patched_load_middleware\n\n\ndef _wrap_middleware(middleware, middleware_name):\n # type: (Any, str) -> Any\n from sentry_sdk.integrations.django import DjangoIntegration\n\n def _get_wrapped_method(old_method):\n # type: (F) -> F\n with capture_internal_exceptions():\n\n def sentry_wrapped_method(*args, **kwargs):\n # type: (*Any, **Any) -> Any\n hub = Hub.current\n integration = hub.get_integration(DjangoIntegration)\n if integration is None or not integration.middleware_spans:\n return old_method(*args, **kwargs)\n\n function_name = transaction_from_function(old_method)\n\n description = middleware_name\n function_basename = getattr(old_method, \"__name__\", None)\n if function_basename:\n description = \"{}.{}\".format(description, function_basename)\n\n with hub.start_span(\n op=\"django.middleware\", description=description\n ) as span:\n span.set_tag(\"django.function_name\", function_name)\n span.set_tag(\"django.middleware_name\", middleware_name)\n return old_method(*args, **kwargs)\n\n try:\n # fails for __call__ of function on Python 2 (see py2.7-django-1.11)\n return wraps(old_method)(sentry_wrapped_method) # type: ignore\n except Exception:\n return sentry_wrapped_method # type: ignore\n\n return old_method\n\n class SentryWrappingMiddleware(object):\n def __init__(self, *args, **kwargs):\n # type: (*Any, **Any) -> None\n self._inner = middleware(*args, **kwargs)\n self._call_method = None\n\n # We need correct behavior for `hasattr()`, which we can only determine\n # when we have an instance of the middleware we're wrapping.\n def __getattr__(self, method_name):\n # type: (str) -> Any\n if method_name not in (\n \"process_request\",\n \"process_view\",\n \"process_template_response\",\n \"process_response\",\n \"process_exception\",\n ):\n raise AttributeError()\n\n old_method = getattr(self._inner, method_name)\n rv = _get_wrapped_method(old_method)\n self.__dict__[method_name] = rv\n return rv\n\n def __call__(self, *args, **kwargs):\n # type: (*Any, **Any) -> Any\n f = self._call_method\n if f is None:\n self._call_method = f = _get_wrapped_method(self._inner.__call__)\n return f(*args, **kwargs)\n\n if hasattr(middleware, \"__name__\"):\n SentryWrappingMiddleware.__name__ = middleware.__name__\n\n return SentryWrappingMiddleware\n", "path": "sentry_sdk/integrations/django/middleware.py"}]}
| 1,616 | 672 |
gh_patches_debug_24599
|
rasdani/github-patches
|
git_diff
|
edgedb__edgedb-1207
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Error creating role using CLI tool: please specify an attribute to alter
EdgeDB version: `1.0-alpha.2+dev.505.g5b68ec24`
Steps to reproduce:
```
# edgedb --admin create-role test
Usage: edgedb create-role [OPTIONS] ROLE_NAME
Error: please specify an attribute to alter
```
Command fails with weird error message if `OPTIONS` were no provided, even though they're supposed to be optional according to help message.
It works if 1 or more options are present: `edgedb --admin create-role --allow-login test`
Creating role inside interactive session without options works as expected:
```
modbay_beta> CREATE ROLE test;
CREATE
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `edb/cli/mng.py`
Content:
```
1 #
2 # This source file is part of the EdgeDB open source project.
3 #
4 # Copyright 2008-present MagicStack Inc. and the EdgeDB authors.
5 #
6 # Licensed under the Apache License, Version 2.0 (the "License");
7 # you may not use this file except in compliance with the License.
8 # You may obtain a copy of the License at
9 #
10 # http://www.apache.org/licenses/LICENSE-2.0
11 #
12 # Unless required by applicable law or agreed to in writing, software
13 # distributed under the License is distributed on an "AS IS" BASIS,
14 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 # See the License for the specific language governing permissions and
16 # limitations under the License.
17 #
18
19
20 from __future__ import annotations
21
22 import re
23 import sys
24 import textwrap
25
26 import click
27
28 import edgedb
29
30 from edb.cli import cli
31 from edb.cli import utils
32 from edb.edgeql.quote import quote_literal as ql, quote_ident as qi
33
34
35 @cli.group(help='Modify database configuration')
36 @click.pass_context
37 def configure(ctx):
38 utils.connect(ctx)
39
40
41 @configure.command(context_settings=dict(
42 ignore_unknown_options=True,
43 ))
44 @click.pass_context
45 @click.argument('parameter', type=str)
46 @click.argument('values', nargs=-1, type=click.UNPROCESSED)
47 def insert(ctx, parameter: str, values):
48 if not values:
49 raise click.UsageError(
50 'missing configuration value properties', ctx=ctx)
51
52 try:
53 cfg_obj_name, props = _process_configure_composite_options(
54 ctx, parameter, values)
55 except NotAnObjectError as e:
56 raise click.UsageError(str(e), ctx=ctx) from None
57
58 attrs = []
59
60 for pn, (pval, ptype) in props.items():
61 if ptype.__type__.name == 'schema::ObjectType':
62 pval = f'(INSERT {pval})'
63 else:
64 pval = f'<{ptype.name}>{ql(pval)}'
65
66 attrs.append(f'{qi(pn)} := {pval}')
67
68 attrs = ',\n'.join(attrs)
69
70 qry = textwrap.dedent(f'''\
71 CONFIGURE SYSTEM INSERT {cfg_obj_name} {{
72 {textwrap.indent(attrs, ' ' * 12).strip()}
73 }}
74 ''')
75
76 try:
77 ctx.obj['conn'].execute(qry)
78 except edgedb.EdgeDBError as e:
79 raise click.ClickException(str(e)) from e
80 else:
81 click.echo(ctx.obj['conn']._get_last_status())
82
83
84 @configure.command()
85 @click.pass_context
86 @click.argument('parameter', type=str)
87 @click.argument('value', nargs=-1, type=str)
88 def set(ctx, parameter: str, value):
89 cfg_obj_name, cfg_type, cfg_card = _process_configure_scalar(
90 ctx, parameter, [])
91
92 if cfg_card == 'ONE':
93 if len(value) > 1:
94 raise click.ClickException('too many values', ctx=ctx)
95 value = value[0]
96 val_expr = ql(value)
97 else:
98 val_expr = f'{{{", ".join(ql(v) for v in value)}}}'
99
100 # Canonicalize the values by casting them.
101 vals = ctx.obj['conn'].fetchall(f'''
102 SELECT <str><{cfg_type.name}>{val_expr}
103 ''')
104
105 args = []
106 for val in vals:
107 if cfg_type.is_numeric or cfg_type.is_bool:
108 args.append(val)
109 elif cfg_type.is_str:
110 args.append(ql(val))
111 else:
112 raise click.ClickException(
113 f'cannot set {parameter}: it is not a string, numeric or bool'
114 )
115
116 args_list = ', '.join(args)
117 args_expr = f'{{{args_list}}}'
118
119 qry = textwrap.dedent(f'''
120 CONFIGURE SYSTEM SET {cfg_obj_name} := {args_expr}
121 ''')
122
123 try:
124 ctx.obj['conn'].execute(qry)
125 except edgedb.EdgeDBError as e:
126 raise click.ClickException(str(e)) from e
127 else:
128 click.echo(ctx.obj['conn']._get_last_status())
129
130
131 @configure.command(context_settings=dict(
132 ignore_unknown_options=True,
133 ))
134 @click.pass_context
135 @click.argument('parameter', type=str)
136 @click.argument('values', nargs=-1, type=click.UNPROCESSED)
137 def reset(ctx, parameter: str, values):
138 try:
139 cfg_obj_name, props = _process_configure_composite_options(
140 ctx, parameter, values)
141 except NotAnObjectError:
142 is_scalar = True
143 else:
144 is_scalar = False
145
146 if is_scalar:
147 cfg_obj_name, cfg_type, cfg_card = _process_configure_scalar(
148 ctx, parameter, values)
149
150 qry = f'CONFIGURE SYSTEM RESET {cfg_obj_name}'
151 else:
152 attrs = []
153
154 for pn, (pval, ptype) in props.items():
155 if ptype.__type__.name == 'schema::ObjectType':
156 pval = f'.{pn} IS {pval}'
157 else:
158 pval = f'.{pn} = <{ptype.name}>{ql(pval)}'
159
160 attrs.append(pval)
161
162 if attrs:
163 flt = f"FILTER {' AND '.join(attrs)}"
164 else:
165 flt = ''
166
167 qry = textwrap.dedent(f'''
168 CONFIGURE SYSTEM RESET {cfg_obj_name} {flt}
169 ''')
170
171 try:
172 ctx.obj['conn'].execute(qry)
173 except edgedb.EdgeDBError as e:
174 raise click.ClickException(str(e)) from e
175 else:
176 click.echo(ctx.obj['conn']._get_last_status())
177
178
179 class NotAnObjectError(Exception):
180 pass
181
182
183 def _process_configure_composite_options(ctx, parameter, values):
184 props = {}
185
186 cfg_objects = ctx.obj['conn'].fetchall('''
187 WITH MODULE schema
188 SELECT ObjectType {
189 name
190 } FILTER .name LIKE 'cfg::%'
191 ''')
192
193 cfg_objmap = {}
194
195 for obj in cfg_objects:
196 _, _, obj_name = obj.name.partition('::')
197 cfg_objmap[obj_name] = obj_name
198 cfg_objmap[obj_name.lower()] = obj_name
199
200 cfg_obj_name = cfg_objmap.get(parameter)
201 if not cfg_obj_name:
202 raise NotAnObjectError(
203 f'{parameter} is not a valid configuration object')
204
205 cfg_props = ctx.obj['conn'].fetchall('''
206 WITH
207 MODULE schema,
208 Cfg := (SELECT ObjectType FILTER .name = <str>$typename)
209 SELECT Cfg.pointers {
210 name,
211 target: {name, __type__: {name}}
212 };
213 ''', typename=f'cfg::{cfg_obj_name}')
214
215 cfg_prop_map = {p.name: p.target for p in cfg_props}
216
217 for value in values:
218 v = re.match(r'--(\w+)(?: |=)(.*)', value)
219 if not v:
220 raise click.UsageError(f'unrecognized option: {value}', ctx=ctx)
221
222 propname = v.group(1)
223 propval = v.group(2)
224
225 proptype = cfg_prop_map.get(propname)
226 if proptype is None:
227 raise click.UsageError(
228 f'{propname!r} is not a valid {cfg_obj_name} property',
229 ctx=ctx)
230
231 if propval in cfg_objmap:
232 propval = cfg_objmap[propval]
233
234 props[propname] = (propval, proptype)
235
236 return cfg_obj_name, props
237
238
239 def _process_configure_scalar(ctx, parameter, values):
240 if values:
241 raise click.UsageError(f'unexpected option: {next(iter(values))}')
242
243 cfg_props = ctx.obj['conn'].fetchall('''
244 WITH
245 MODULE schema,
246 Cfg := (SELECT ObjectType FILTER .name = <str>$typename)
247 SELECT Cfg.pointers {
248 name,
249 cardinality,
250 target: {
251 name,
252 __type__: {name},
253 is_numeric := (
254 'std::anyreal' IN
255 Cfg.pointers.target[IS ScalarType].ancestors.name),
256 is_bool := (
257 Cfg.pointers.target.name = 'std::bool'
258 OR 'std::bool' IN
259 Cfg.pointers.target[IS ScalarType].ancestors.name),
260 is_str := (
261 Cfg.pointers.target.name = 'std::str'
262 OR any({'std::str', 'std::anyenum'} IN
263 Cfg.pointers.target[IS ScalarType].ancestors.name)),
264 }
265 } FILTER .name = <str>$propname;
266 ''', typename=f'cfg::Config', propname=parameter)
267
268 if len(cfg_props) == 0:
269 raise click.UsageError(
270 f'{parameter!r} is not a valid configuration parameter',
271 ctx=ctx)
272
273 return parameter, cfg_props[0].target, cfg_props[0].cardinality
274
275
276 def options(options):
277 def _decorator(func):
278 for option in reversed(options):
279 func = option(func)
280 return func
281
282 return _decorator
283
284
285 _role_options = [
286 click.option('--password/--no-password', default=None),
287 click.option('--password-from-stdin', is_flag=True, default=False),
288 ]
289
290
291 def _process_role_options(ctx, password, password_from_stdin):
292 if password is None and password_from_stdin:
293 password = True
294
295 if password is not None:
296 if password:
297 if password_from_stdin:
298 password_value = ql(sys.stdin.readline().strip('\r\n'))
299 elif sys.stdin.isatty():
300 password_value = ql(click.prompt(
301 'Password',
302 hide_input=True,
303 confirmation_prompt=True,
304 type=str,
305 ))
306 else:
307 raise click.UsageError(
308 'input is not a TTY, please use --password-from-stdin '
309 'to provide the password value'
310 )
311 else:
312 password_value = '{}'
313 else:
314 password_value = None
315
316 alters = []
317 if password_value is not None:
318 alters.append(f'SET password := {password_value}')
319
320 if not alters:
321 raise click.UsageError(
322 'please specify an attribute to alter', ctx=ctx,
323 )
324
325 return alters
326
327
328 @cli.command(name='create-superuser-role',
329 help='Create a new database superuser')
330 @click.argument('role-name', type=str)
331 @options(_role_options)
332 @click.pass_context
333 def create_role(ctx, role_name, **kwargs):
334 utils.connect(ctx)
335
336 attrs = ";\n".join(_process_role_options(ctx, **kwargs))
337
338 qry = f'''
339 CREATE SUPERUSER ROLE {qi(role_name)} {{
340 {attrs}
341 }}
342 '''
343
344 try:
345 ctx.obj['conn'].execute(qry)
346 except edgedb.EdgeDBError as e:
347 raise click.ClickException(str(e)) from e
348
349
350 @cli.command(name='alter-role', help='Modify role')
351 @click.argument('role-name', type=str)
352 @options(_role_options)
353 @click.pass_context
354 def alter_role(ctx, role_name, **kwargs):
355 utils.connect(ctx)
356
357 attrs = ";\n".join(_process_role_options(ctx, **kwargs))
358
359 qry = f'''
360 ALTER ROLE {qi(role_name)} {{
361 {attrs}
362 }}
363 '''
364
365 try:
366 ctx.obj['conn'].execute(qry)
367 except edgedb.EdgeDBError as e:
368 raise click.ClickException(str(e)) from e
369
370
371 @cli.command(name='drop-role', help="Remove role")
372 @click.argument('role-name', type=str)
373 @click.pass_context
374 def drop_role(ctx, role_name, **kwargs):
375 utils.connect(ctx)
376 qry = f'''
377 DROP ROLE {qi(role_name)};
378 '''
379
380 try:
381 ctx.obj['conn'].execute(qry)
382 except edgedb.EdgeDBError as e:
383 raise click.ClickException(str(e)) from e
384
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/edb/cli/mng.py b/edb/cli/mng.py
--- a/edb/cli/mng.py
+++ b/edb/cli/mng.py
@@ -288,7 +288,13 @@
]
-def _process_role_options(ctx, password, password_from_stdin):
+def _process_role_options(
+ ctx,
+ password,
+ password_from_stdin,
+ allow_empty=False
+):
+
if password is None and password_from_stdin:
password = True
@@ -318,6 +324,9 @@
alters.append(f'SET password := {password_value}')
if not alters:
+ if allow_empty:
+ return alters
+
raise click.UsageError(
'please specify an attribute to alter', ctx=ctx,
)
@@ -333,12 +342,19 @@
def create_role(ctx, role_name, **kwargs):
utils.connect(ctx)
- attrs = ";\n".join(_process_role_options(ctx, **kwargs))
+ attrs = ";\n".join(_process_role_options(ctx, allow_empty=True, **kwargs))
- qry = f'''
- CREATE SUPERUSER ROLE {qi(role_name)} {{
+ if attrs:
+ formatted_attrs = f'''
+ {{
{attrs}
}}
+ '''
+ else:
+ formatted_attrs = ''
+
+ qry = f'''
+ CREATE SUPERUSER ROLE {qi(role_name)} {formatted_attrs}
'''
try:
|
{"golden_diff": "diff --git a/edb/cli/mng.py b/edb/cli/mng.py\n--- a/edb/cli/mng.py\n+++ b/edb/cli/mng.py\n@@ -288,7 +288,13 @@\n ]\n \n \n-def _process_role_options(ctx, password, password_from_stdin):\n+def _process_role_options(\n+ ctx,\n+ password,\n+ password_from_stdin,\n+ allow_empty=False\n+):\n+\n if password is None and password_from_stdin:\n password = True\n \n@@ -318,6 +324,9 @@\n alters.append(f'SET password := {password_value}')\n \n if not alters:\n+ if allow_empty:\n+ return alters\n+\n raise click.UsageError(\n 'please specify an attribute to alter', ctx=ctx,\n )\n@@ -333,12 +342,19 @@\n def create_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n \n- attrs = \";\\n\".join(_process_role_options(ctx, **kwargs))\n+ attrs = \";\\n\".join(_process_role_options(ctx, allow_empty=True, **kwargs))\n \n- qry = f'''\n- CREATE SUPERUSER ROLE {qi(role_name)} {{\n+ if attrs:\n+ formatted_attrs = f'''\n+ {{\n {attrs}\n }}\n+ '''\n+ else:\n+ formatted_attrs = ''\n+\n+ qry = f'''\n+ CREATE SUPERUSER ROLE {qi(role_name)} {formatted_attrs}\n '''\n \n try:\n", "issue": "Error creating role using CLI tool: please specify an attribute to alter\nEdgeDB version: `1.0-alpha.2+dev.505.g5b68ec24`\r\n\r\nSteps to reproduce:\r\n```\r\n# edgedb --admin create-role test\r\nUsage: edgedb create-role [OPTIONS] ROLE_NAME\r\n\r\nError: please specify an attribute to alter\r\n```\r\nCommand fails with weird error message if `OPTIONS` were no provided, even though they're supposed to be optional according to help message.\r\nIt works if 1 or more options are present: `edgedb --admin create-role --allow-login test`\r\n\r\nCreating role inside interactive session without options works as expected:\r\n```\r\nmodbay_beta> CREATE ROLE test; \r\nCREATE\r\n```\n", "before_files": [{"content": "#\n# This source file is part of the EdgeDB open source project.\n#\n# Copyright 2008-present MagicStack Inc. and the EdgeDB authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\n\n\nfrom __future__ import annotations\n\nimport re\nimport sys\nimport textwrap\n\nimport click\n\nimport edgedb\n\nfrom edb.cli import cli\nfrom edb.cli import utils\nfrom edb.edgeql.quote import quote_literal as ql, quote_ident as qi\n\n\[email protected](help='Modify database configuration')\[email protected]_context\ndef configure(ctx):\n utils.connect(ctx)\n\n\[email protected](context_settings=dict(\n ignore_unknown_options=True,\n))\[email protected]_context\[email protected]('parameter', type=str)\[email protected]('values', nargs=-1, type=click.UNPROCESSED)\ndef insert(ctx, parameter: str, values):\n if not values:\n raise click.UsageError(\n 'missing configuration value properties', ctx=ctx)\n\n try:\n cfg_obj_name, props = _process_configure_composite_options(\n ctx, parameter, values)\n except NotAnObjectError as e:\n raise click.UsageError(str(e), ctx=ctx) from None\n\n attrs = []\n\n for pn, (pval, ptype) in props.items():\n if ptype.__type__.name == 'schema::ObjectType':\n pval = f'(INSERT {pval})'\n else:\n pval = f'<{ptype.name}>{ql(pval)}'\n\n attrs.append(f'{qi(pn)} := {pval}')\n\n attrs = ',\\n'.join(attrs)\n\n qry = textwrap.dedent(f'''\\\n CONFIGURE SYSTEM INSERT {cfg_obj_name} {{\n {textwrap.indent(attrs, ' ' * 12).strip()}\n }}\n ''')\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n else:\n click.echo(ctx.obj['conn']._get_last_status())\n\n\[email protected]()\[email protected]_context\[email protected]('parameter', type=str)\[email protected]('value', nargs=-1, type=str)\ndef set(ctx, parameter: str, value):\n cfg_obj_name, cfg_type, cfg_card = _process_configure_scalar(\n ctx, parameter, [])\n\n if cfg_card == 'ONE':\n if len(value) > 1:\n raise click.ClickException('too many values', ctx=ctx)\n value = value[0]\n val_expr = ql(value)\n else:\n val_expr = f'{{{\", \".join(ql(v) for v in value)}}}'\n\n # Canonicalize the values by casting them.\n vals = ctx.obj['conn'].fetchall(f'''\n SELECT <str><{cfg_type.name}>{val_expr}\n ''')\n\n args = []\n for val in vals:\n if cfg_type.is_numeric or cfg_type.is_bool:\n args.append(val)\n elif cfg_type.is_str:\n args.append(ql(val))\n else:\n raise click.ClickException(\n f'cannot set {parameter}: it is not a string, numeric or bool'\n )\n\n args_list = ', '.join(args)\n args_expr = f'{{{args_list}}}'\n\n qry = textwrap.dedent(f'''\n CONFIGURE SYSTEM SET {cfg_obj_name} := {args_expr}\n ''')\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n else:\n click.echo(ctx.obj['conn']._get_last_status())\n\n\[email protected](context_settings=dict(\n ignore_unknown_options=True,\n))\[email protected]_context\[email protected]('parameter', type=str)\[email protected]('values', nargs=-1, type=click.UNPROCESSED)\ndef reset(ctx, parameter: str, values):\n try:\n cfg_obj_name, props = _process_configure_composite_options(\n ctx, parameter, values)\n except NotAnObjectError:\n is_scalar = True\n else:\n is_scalar = False\n\n if is_scalar:\n cfg_obj_name, cfg_type, cfg_card = _process_configure_scalar(\n ctx, parameter, values)\n\n qry = f'CONFIGURE SYSTEM RESET {cfg_obj_name}'\n else:\n attrs = []\n\n for pn, (pval, ptype) in props.items():\n if ptype.__type__.name == 'schema::ObjectType':\n pval = f'.{pn} IS {pval}'\n else:\n pval = f'.{pn} = <{ptype.name}>{ql(pval)}'\n\n attrs.append(pval)\n\n if attrs:\n flt = f\"FILTER {' AND '.join(attrs)}\"\n else:\n flt = ''\n\n qry = textwrap.dedent(f'''\n CONFIGURE SYSTEM RESET {cfg_obj_name} {flt}\n ''')\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n else:\n click.echo(ctx.obj['conn']._get_last_status())\n\n\nclass NotAnObjectError(Exception):\n pass\n\n\ndef _process_configure_composite_options(ctx, parameter, values):\n props = {}\n\n cfg_objects = ctx.obj['conn'].fetchall('''\n WITH MODULE schema\n SELECT ObjectType {\n name\n } FILTER .name LIKE 'cfg::%'\n ''')\n\n cfg_objmap = {}\n\n for obj in cfg_objects:\n _, _, obj_name = obj.name.partition('::')\n cfg_objmap[obj_name] = obj_name\n cfg_objmap[obj_name.lower()] = obj_name\n\n cfg_obj_name = cfg_objmap.get(parameter)\n if not cfg_obj_name:\n raise NotAnObjectError(\n f'{parameter} is not a valid configuration object')\n\n cfg_props = ctx.obj['conn'].fetchall('''\n WITH\n MODULE schema,\n Cfg := (SELECT ObjectType FILTER .name = <str>$typename)\n SELECT Cfg.pointers {\n name,\n target: {name, __type__: {name}}\n };\n ''', typename=f'cfg::{cfg_obj_name}')\n\n cfg_prop_map = {p.name: p.target for p in cfg_props}\n\n for value in values:\n v = re.match(r'--(\\w+)(?: |=)(.*)', value)\n if not v:\n raise click.UsageError(f'unrecognized option: {value}', ctx=ctx)\n\n propname = v.group(1)\n propval = v.group(2)\n\n proptype = cfg_prop_map.get(propname)\n if proptype is None:\n raise click.UsageError(\n f'{propname!r} is not a valid {cfg_obj_name} property',\n ctx=ctx)\n\n if propval in cfg_objmap:\n propval = cfg_objmap[propval]\n\n props[propname] = (propval, proptype)\n\n return cfg_obj_name, props\n\n\ndef _process_configure_scalar(ctx, parameter, values):\n if values:\n raise click.UsageError(f'unexpected option: {next(iter(values))}')\n\n cfg_props = ctx.obj['conn'].fetchall('''\n WITH\n MODULE schema,\n Cfg := (SELECT ObjectType FILTER .name = <str>$typename)\n SELECT Cfg.pointers {\n name,\n cardinality,\n target: {\n name,\n __type__: {name},\n is_numeric := (\n 'std::anyreal' IN\n Cfg.pointers.target[IS ScalarType].ancestors.name),\n is_bool := (\n Cfg.pointers.target.name = 'std::bool'\n OR 'std::bool' IN\n Cfg.pointers.target[IS ScalarType].ancestors.name),\n is_str := (\n Cfg.pointers.target.name = 'std::str'\n OR any({'std::str', 'std::anyenum'} IN\n Cfg.pointers.target[IS ScalarType].ancestors.name)),\n }\n } FILTER .name = <str>$propname;\n ''', typename=f'cfg::Config', propname=parameter)\n\n if len(cfg_props) == 0:\n raise click.UsageError(\n f'{parameter!r} is not a valid configuration parameter',\n ctx=ctx)\n\n return parameter, cfg_props[0].target, cfg_props[0].cardinality\n\n\ndef options(options):\n def _decorator(func):\n for option in reversed(options):\n func = option(func)\n return func\n\n return _decorator\n\n\n_role_options = [\n click.option('--password/--no-password', default=None),\n click.option('--password-from-stdin', is_flag=True, default=False),\n]\n\n\ndef _process_role_options(ctx, password, password_from_stdin):\n if password is None and password_from_stdin:\n password = True\n\n if password is not None:\n if password:\n if password_from_stdin:\n password_value = ql(sys.stdin.readline().strip('\\r\\n'))\n elif sys.stdin.isatty():\n password_value = ql(click.prompt(\n 'Password',\n hide_input=True,\n confirmation_prompt=True,\n type=str,\n ))\n else:\n raise click.UsageError(\n 'input is not a TTY, please use --password-from-stdin '\n 'to provide the password value'\n )\n else:\n password_value = '{}'\n else:\n password_value = None\n\n alters = []\n if password_value is not None:\n alters.append(f'SET password := {password_value}')\n\n if not alters:\n raise click.UsageError(\n 'please specify an attribute to alter', ctx=ctx,\n )\n\n return alters\n\n\[email protected](name='create-superuser-role',\n help='Create a new database superuser')\[email protected]('role-name', type=str)\n@options(_role_options)\[email protected]_context\ndef create_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n\n attrs = \";\\n\".join(_process_role_options(ctx, **kwargs))\n\n qry = f'''\n CREATE SUPERUSER ROLE {qi(role_name)} {{\n {attrs}\n }}\n '''\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n\n\[email protected](name='alter-role', help='Modify role')\[email protected]('role-name', type=str)\n@options(_role_options)\[email protected]_context\ndef alter_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n\n attrs = \";\\n\".join(_process_role_options(ctx, **kwargs))\n\n qry = f'''\n ALTER ROLE {qi(role_name)} {{\n {attrs}\n }}\n '''\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n\n\[email protected](name='drop-role', help=\"Remove role\")\[email protected]('role-name', type=str)\[email protected]_context\ndef drop_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n qry = f'''\n DROP ROLE {qi(role_name)};\n '''\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n", "path": "edb/cli/mng.py"}], "after_files": [{"content": "#\n# This source file is part of the EdgeDB open source project.\n#\n# Copyright 2008-present MagicStack Inc. and the EdgeDB authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\n\n\nfrom __future__ import annotations\n\nimport re\nimport sys\nimport textwrap\n\nimport click\n\nimport edgedb\n\nfrom edb.cli import cli\nfrom edb.cli import utils\nfrom edb.edgeql.quote import quote_literal as ql, quote_ident as qi\n\n\[email protected](help='Modify database configuration')\[email protected]_context\ndef configure(ctx):\n utils.connect(ctx)\n\n\[email protected](context_settings=dict(\n ignore_unknown_options=True,\n))\[email protected]_context\[email protected]('parameter', type=str)\[email protected]('values', nargs=-1, type=click.UNPROCESSED)\ndef insert(ctx, parameter: str, values):\n if not values:\n raise click.UsageError(\n 'missing configuration value properties', ctx=ctx)\n\n try:\n cfg_obj_name, props = _process_configure_composite_options(\n ctx, parameter, values)\n except NotAnObjectError as e:\n raise click.UsageError(str(e), ctx=ctx) from None\n\n attrs = []\n\n for pn, (pval, ptype) in props.items():\n if ptype.__type__.name == 'schema::ObjectType':\n pval = f'(INSERT {pval})'\n else:\n pval = f'<{ptype.name}>{ql(pval)}'\n\n attrs.append(f'{qi(pn)} := {pval}')\n\n attrs = ',\\n'.join(attrs)\n\n qry = textwrap.dedent(f'''\\\n CONFIGURE SYSTEM INSERT {cfg_obj_name} {{\n {textwrap.indent(attrs, ' ' * 12).strip()}\n }}\n ''')\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n else:\n click.echo(ctx.obj['conn']._get_last_status())\n\n\[email protected]()\[email protected]_context\[email protected]('parameter', type=str)\[email protected]('value', nargs=-1, type=str)\ndef set(ctx, parameter: str, value):\n cfg_obj_name, cfg_type, cfg_card = _process_configure_scalar(\n ctx, parameter, [])\n\n if cfg_card == 'ONE':\n if len(value) > 1:\n raise click.ClickException('too many values', ctx=ctx)\n value = value[0]\n val_expr = ql(value)\n else:\n val_expr = f'{{{\", \".join(ql(v) for v in value)}}}'\n\n # Canonicalize the values by casting them.\n vals = ctx.obj['conn'].fetchall(f'''\n SELECT <str><{cfg_type.name}>{val_expr}\n ''')\n\n args = []\n for val in vals:\n if cfg_type.is_numeric or cfg_type.is_bool:\n args.append(val)\n elif cfg_type.is_str:\n args.append(ql(val))\n else:\n raise click.ClickException(\n f'cannot set {parameter}: it is not a string, numeric or bool'\n )\n\n args_list = ', '.join(args)\n args_expr = f'{{{args_list}}}'\n\n qry = textwrap.dedent(f'''\n CONFIGURE SYSTEM SET {cfg_obj_name} := {args_expr}\n ''')\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n else:\n click.echo(ctx.obj['conn']._get_last_status())\n\n\[email protected](context_settings=dict(\n ignore_unknown_options=True,\n))\[email protected]_context\[email protected]('parameter', type=str)\[email protected]('values', nargs=-1, type=click.UNPROCESSED)\ndef reset(ctx, parameter: str, values):\n try:\n cfg_obj_name, props = _process_configure_composite_options(\n ctx, parameter, values)\n except NotAnObjectError:\n is_scalar = True\n else:\n is_scalar = False\n\n if is_scalar:\n cfg_obj_name, cfg_type, cfg_card = _process_configure_scalar(\n ctx, parameter, values)\n\n qry = f'CONFIGURE SYSTEM RESET {cfg_obj_name}'\n else:\n attrs = []\n\n for pn, (pval, ptype) in props.items():\n if ptype.__type__.name == 'schema::ObjectType':\n pval = f'.{pn} IS {pval}'\n else:\n pval = f'.{pn} = <{ptype.name}>{ql(pval)}'\n\n attrs.append(pval)\n\n if attrs:\n flt = f\"FILTER {' AND '.join(attrs)}\"\n else:\n flt = ''\n\n qry = textwrap.dedent(f'''\n CONFIGURE SYSTEM RESET {cfg_obj_name} {flt}\n ''')\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n else:\n click.echo(ctx.obj['conn']._get_last_status())\n\n\nclass NotAnObjectError(Exception):\n pass\n\n\ndef _process_configure_composite_options(ctx, parameter, values):\n props = {}\n\n cfg_objects = ctx.obj['conn'].fetchall('''\n WITH MODULE schema\n SELECT ObjectType {\n name\n } FILTER .name LIKE 'cfg::%'\n ''')\n\n cfg_objmap = {}\n\n for obj in cfg_objects:\n _, _, obj_name = obj.name.partition('::')\n cfg_objmap[obj_name] = obj_name\n cfg_objmap[obj_name.lower()] = obj_name\n\n cfg_obj_name = cfg_objmap.get(parameter)\n if not cfg_obj_name:\n raise NotAnObjectError(\n f'{parameter} is not a valid configuration object')\n\n cfg_props = ctx.obj['conn'].fetchall('''\n WITH\n MODULE schema,\n Cfg := (SELECT ObjectType FILTER .name = <str>$typename)\n SELECT Cfg.pointers {\n name,\n target: {name, __type__: {name}}\n };\n ''', typename=f'cfg::{cfg_obj_name}')\n\n cfg_prop_map = {p.name: p.target for p in cfg_props}\n\n for value in values:\n v = re.match(r'--(\\w+)(?: |=)(.*)', value)\n if not v:\n raise click.UsageError(f'unrecognized option: {value}', ctx=ctx)\n\n propname = v.group(1)\n propval = v.group(2)\n\n proptype = cfg_prop_map.get(propname)\n if proptype is None:\n raise click.UsageError(\n f'{propname!r} is not a valid {cfg_obj_name} property',\n ctx=ctx)\n\n if propval in cfg_objmap:\n propval = cfg_objmap[propval]\n\n props[propname] = (propval, proptype)\n\n return cfg_obj_name, props\n\n\ndef _process_configure_scalar(ctx, parameter, values):\n if values:\n raise click.UsageError(f'unexpected option: {next(iter(values))}')\n\n cfg_props = ctx.obj['conn'].fetchall('''\n WITH\n MODULE schema,\n Cfg := (SELECT ObjectType FILTER .name = <str>$typename)\n SELECT Cfg.pointers {\n name,\n cardinality,\n target: {\n name,\n __type__: {name},\n is_numeric := (\n 'std::anyreal' IN\n Cfg.pointers.target[IS ScalarType].ancestors.name),\n is_bool := (\n Cfg.pointers.target.name = 'std::bool'\n OR 'std::bool' IN\n Cfg.pointers.target[IS ScalarType].ancestors.name),\n is_str := (\n Cfg.pointers.target.name = 'std::str'\n OR any({'std::str', 'std::anyenum'} IN\n Cfg.pointers.target[IS ScalarType].ancestors.name)),\n }\n } FILTER .name = <str>$propname;\n ''', typename=f'cfg::Config', propname=parameter)\n\n if len(cfg_props) == 0:\n raise click.UsageError(\n f'{parameter!r} is not a valid configuration parameter',\n ctx=ctx)\n\n return parameter, cfg_props[0].target, cfg_props[0].cardinality\n\n\ndef options(options):\n def _decorator(func):\n for option in reversed(options):\n func = option(func)\n return func\n\n return _decorator\n\n\n_role_options = [\n click.option('--password/--no-password', default=None),\n click.option('--password-from-stdin', is_flag=True, default=False),\n]\n\n\ndef _process_role_options(\n ctx,\n password,\n password_from_stdin,\n allow_empty=False\n):\n\n if password is None and password_from_stdin:\n password = True\n\n if password is not None:\n if password:\n if password_from_stdin:\n password_value = ql(sys.stdin.readline().strip('\\r\\n'))\n elif sys.stdin.isatty():\n password_value = ql(click.prompt(\n 'Password',\n hide_input=True,\n confirmation_prompt=True,\n type=str,\n ))\n else:\n raise click.UsageError(\n 'input is not a TTY, please use --password-from-stdin '\n 'to provide the password value'\n )\n else:\n password_value = '{}'\n else:\n password_value = None\n\n alters = []\n if password_value is not None:\n alters.append(f'SET password := {password_value}')\n\n if not alters:\n if allow_empty:\n return alters\n\n raise click.UsageError(\n 'please specify an attribute to alter', ctx=ctx,\n )\n\n return alters\n\n\[email protected](name='create-superuser-role',\n help='Create a new database superuser')\[email protected]('role-name', type=str)\n@options(_role_options)\[email protected]_context\ndef create_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n\n attrs = \";\\n\".join(_process_role_options(ctx, allow_empty=True, **kwargs))\n\n if attrs:\n formatted_attrs = f'''\n {{\n {attrs}\n }}\n '''\n else:\n formatted_attrs = ''\n\n qry = f'''\n CREATE SUPERUSER ROLE {qi(role_name)} {formatted_attrs}\n '''\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n\n\[email protected](name='alter-role', help='Modify role')\[email protected]('role-name', type=str)\n@options(_role_options)\[email protected]_context\ndef alter_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n\n attrs = \";\\n\".join(_process_role_options(ctx, **kwargs))\n\n qry = f'''\n ALTER ROLE {qi(role_name)} {{\n {attrs}\n }}\n '''\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n\n\[email protected](name='drop-role', help=\"Remove role\")\[email protected]('role-name', type=str)\[email protected]_context\ndef drop_role(ctx, role_name, **kwargs):\n utils.connect(ctx)\n qry = f'''\n DROP ROLE {qi(role_name)};\n '''\n\n try:\n ctx.obj['conn'].execute(qry)\n except edgedb.EdgeDBError as e:\n raise click.ClickException(str(e)) from e\n", "path": "edb/cli/mng.py"}]}
| 4,062 | 333 |
gh_patches_debug_28409
|
rasdani/github-patches
|
git_diff
|
mampfes__hacs_waste_collection_schedule-182
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
recycleapp_be not working for some addresses
when I enter my address into the configuration.yaml I receive this error on restart:
```
fetch failed for source Recycle!: Traceback (most recent call last): File "/config/custom_components/waste_collection_schedule/waste_collection_schedule/scraper.py",
line 116, in fetch entries = self._source.fetch() File "/config/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py",
line 79, in fetch entries.append(Collection(date, item["fraction"]["name"]["en"])) KeyError: 'name'
```
when I use the example address or some other addresses everything works fine. Is it a problem with my city? Because other addresses of this city also don't work, even though those addresses work on [Recycle!](https://recycleapp.be/home).
this is what I have in configuration.yaml
```
waste_collection_schedule:
sources:
- name: recycleapp_be
args:
postcode: 3001
street: Waversebaan
house_number: 276
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py`
Content:
```
1 import logging
2 from datetime import datetime, timedelta
3
4 import requests
5 from waste_collection_schedule import Collection # type: ignore[attr-defined]
6
7 TITLE = "Recycle!"
8 DESCRIPTION = "Source for RecycleApp.be"
9 URL = "https://www.recycleapp.be"
10 TEST_CASES = {
11 "1140 Evere, Bazellaan 1": {
12 "postcode": 1140,
13 "street": "Bazellaan",
14 "house_number": 1,
15 }
16 }
17
18 _LOGGER = logging.getLogger(__name__)
19
20
21 class Source:
22 def __init__(self, postcode, street, house_number):
23 self._postcode = postcode
24 self._street = street
25 self._house_number = house_number
26
27 def fetch(self):
28 url = "https://recycleapp.be/api/app/v1"
29 headers = {
30 "x-secret": "Crgja3EGWe8jdapyr4EEoMBgZACYYjRRcRpaMQrLDW9HJBvmgkfGQyYqLgeXPavAGvnJqkV87PBB2b8zx43q46sUgzqio4yRZbABhtKeagkVKypTEDjKfPgGycjLyJTtLHYpzwJgp4YmmCuJZN9ZmJY8CGEoFs8MKfdJpU9RjkEVfngmmk2LYD4QzFegLNKUbcCeAdEW",
31 "x-consumer": "recycleapp.be",
32 "User-Agent": "",
33 "Authorization": "",
34 }
35 r = requests.get(f"{url}/access-token", headers=headers)
36 headers["Authorization"] = r.json()["accessToken"]
37
38 params = {"q": self._postcode}
39 r = requests.get(f"{url}/zipcodes", params=params, headers=headers)
40 if r.status_code != 200:
41 _LOGGER.error("Get zip code failed")
42 return []
43 zipcodeId = r.json()["items"][0]["id"]
44
45 params = {"q": self._street, "zipcodes": zipcodeId}
46 r = requests.get(f"{url}/streets", params=params, headers=headers)
47 if r.status_code != 200:
48 _LOGGER.error("Get street id failed")
49 return []
50
51 for item in r.json()["items"]:
52 if item["name"] == self._street:
53 streetId = item["id"]
54 if streetId is None:
55 streetId = r.json()["items"][0]["id"]
56
57 now = datetime.now()
58 fromDate = now.strftime("%Y-%m-%d")
59 untilDate = (now + timedelta(days=365)).strftime("%Y-%m-%d")
60 params = {
61 "zipcodeId": zipcodeId,
62 "streetId": streetId,
63 "houseNumber": self._house_number,
64 "fromDate": fromDate,
65 "untilDate": untilDate,
66 # "size":100,
67 }
68 r = requests.get(f"{url}/collections", params=params, headers=headers)
69 if r.status_code != 200:
70 _LOGGER.error("Get data failed")
71 return []
72
73 entries = []
74 for item in r.json()["items"]:
75 if "exception" in item and "replacedBy" in item["exception"]:
76 continue
77
78 date = datetime.strptime(item["timestamp"], "%Y-%m-%dT%H:%M:%S.000Z").date()
79 entries.append(Collection(date, item["fraction"]["name"]["en"]))
80 return entries
81
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py b/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py
--- a/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py
+++ b/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py
@@ -12,17 +12,29 @@
"postcode": 1140,
"street": "Bazellaan",
"house_number": 1,
- }
+ },
+ "3001, Waversebaan 276 with events": {
+ "postcode": 3001,
+ "street": "Waversebaan",
+ "house_number": 276,
+ },
+ "3001, Waversebaan 276 without events": {
+ "postcode": 3001,
+ "street": "Waversebaan",
+ "house_number": 276,
+ "add_events": False,
+ },
}
_LOGGER = logging.getLogger(__name__)
class Source:
- def __init__(self, postcode, street, house_number):
+ def __init__(self, postcode, street, house_number, add_events=True):
self._postcode = postcode
self._street = street
self._house_number = house_number
+ self._add_events = add_events
def fetch(self):
url = "https://recycleapp.be/api/app/v1"
@@ -76,5 +88,9 @@
continue
date = datetime.strptime(item["timestamp"], "%Y-%m-%dT%H:%M:%S.000Z").date()
- entries.append(Collection(date, item["fraction"]["name"]["en"]))
+ if item["type"] == "collection":
+ entries.append(Collection(date, item["fraction"]["name"]["en"]))
+ elif item["type"] == "event" and self._add_events:
+ entries.append(Collection(date, item["event"]["title"]["en"]))
+
return entries
|
{"golden_diff": "diff --git a/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py b/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py\n--- a/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py\n+++ b/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py\n@@ -12,17 +12,29 @@\n \"postcode\": 1140,\n \"street\": \"Bazellaan\",\n \"house_number\": 1,\n- }\n+ },\n+ \"3001, Waversebaan 276 with events\": {\n+ \"postcode\": 3001,\n+ \"street\": \"Waversebaan\",\n+ \"house_number\": 276,\n+ },\n+ \"3001, Waversebaan 276 without events\": {\n+ \"postcode\": 3001,\n+ \"street\": \"Waversebaan\",\n+ \"house_number\": 276,\n+ \"add_events\": False,\n+ },\n }\n \n _LOGGER = logging.getLogger(__name__)\n \n \n class Source:\n- def __init__(self, postcode, street, house_number):\n+ def __init__(self, postcode, street, house_number, add_events=True):\n self._postcode = postcode\n self._street = street\n self._house_number = house_number\n+ self._add_events = add_events\n \n def fetch(self):\n url = \"https://recycleapp.be/api/app/v1\"\n@@ -76,5 +88,9 @@\n continue\n \n date = datetime.strptime(item[\"timestamp\"], \"%Y-%m-%dT%H:%M:%S.000Z\").date()\n- entries.append(Collection(date, item[\"fraction\"][\"name\"][\"en\"]))\n+ if item[\"type\"] == \"collection\":\n+ entries.append(Collection(date, item[\"fraction\"][\"name\"][\"en\"]))\n+ elif item[\"type\"] == \"event\" and self._add_events:\n+ entries.append(Collection(date, item[\"event\"][\"title\"][\"en\"]))\n+\n return entries\n", "issue": "recycleapp_be not working for some addresses\nwhen I enter my address into the configuration.yaml I receive this error on restart:\r\n```\r\nfetch failed for source Recycle!: Traceback (most recent call last): File \"/config/custom_components/waste_collection_schedule/waste_collection_schedule/scraper.py\", \r\nline 116, in fetch entries = self._source.fetch() File \"/config/custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py\", \r\nline 79, in fetch entries.append(Collection(date, item[\"fraction\"][\"name\"][\"en\"])) KeyError: 'name'\r\n```\r\nwhen I use the example address or some other addresses everything works fine. Is it a problem with my city? Because other addresses of this city also don't work, even though those addresses work on [Recycle!](https://recycleapp.be/home).\r\nthis is what I have in configuration.yaml\r\n```\r\nwaste_collection_schedule:\r\n sources:\r\n - name: recycleapp_be\r\n args:\r\n postcode: 3001\r\n street: Waversebaan\r\n house_number: 276\r\n```\n", "before_files": [{"content": "import logging\nfrom datetime import datetime, timedelta\n\nimport requests\nfrom waste_collection_schedule import Collection # type: ignore[attr-defined]\n\nTITLE = \"Recycle!\"\nDESCRIPTION = \"Source for RecycleApp.be\"\nURL = \"https://www.recycleapp.be\"\nTEST_CASES = {\n \"1140 Evere, Bazellaan 1\": {\n \"postcode\": 1140,\n \"street\": \"Bazellaan\",\n \"house_number\": 1,\n }\n}\n\n_LOGGER = logging.getLogger(__name__)\n\n\nclass Source:\n def __init__(self, postcode, street, house_number):\n self._postcode = postcode\n self._street = street\n self._house_number = house_number\n\n def fetch(self):\n url = \"https://recycleapp.be/api/app/v1\"\n headers = {\n \"x-secret\": \"Crgja3EGWe8jdapyr4EEoMBgZACYYjRRcRpaMQrLDW9HJBvmgkfGQyYqLgeXPavAGvnJqkV87PBB2b8zx43q46sUgzqio4yRZbABhtKeagkVKypTEDjKfPgGycjLyJTtLHYpzwJgp4YmmCuJZN9ZmJY8CGEoFs8MKfdJpU9RjkEVfngmmk2LYD4QzFegLNKUbcCeAdEW\",\n \"x-consumer\": \"recycleapp.be\",\n \"User-Agent\": \"\",\n \"Authorization\": \"\",\n }\n r = requests.get(f\"{url}/access-token\", headers=headers)\n headers[\"Authorization\"] = r.json()[\"accessToken\"]\n\n params = {\"q\": self._postcode}\n r = requests.get(f\"{url}/zipcodes\", params=params, headers=headers)\n if r.status_code != 200:\n _LOGGER.error(\"Get zip code failed\")\n return []\n zipcodeId = r.json()[\"items\"][0][\"id\"]\n\n params = {\"q\": self._street, \"zipcodes\": zipcodeId}\n r = requests.get(f\"{url}/streets\", params=params, headers=headers)\n if r.status_code != 200:\n _LOGGER.error(\"Get street id failed\")\n return []\n\n for item in r.json()[\"items\"]:\n if item[\"name\"] == self._street:\n streetId = item[\"id\"]\n if streetId is None:\n streetId = r.json()[\"items\"][0][\"id\"]\n\n now = datetime.now()\n fromDate = now.strftime(\"%Y-%m-%d\")\n untilDate = (now + timedelta(days=365)).strftime(\"%Y-%m-%d\")\n params = {\n \"zipcodeId\": zipcodeId,\n \"streetId\": streetId,\n \"houseNumber\": self._house_number,\n \"fromDate\": fromDate,\n \"untilDate\": untilDate,\n # \"size\":100,\n }\n r = requests.get(f\"{url}/collections\", params=params, headers=headers)\n if r.status_code != 200:\n _LOGGER.error(\"Get data failed\")\n return []\n\n entries = []\n for item in r.json()[\"items\"]:\n if \"exception\" in item and \"replacedBy\" in item[\"exception\"]:\n continue\n\n date = datetime.strptime(item[\"timestamp\"], \"%Y-%m-%dT%H:%M:%S.000Z\").date()\n entries.append(Collection(date, item[\"fraction\"][\"name\"][\"en\"]))\n return entries\n", "path": "custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py"}], "after_files": [{"content": "import logging\nfrom datetime import datetime, timedelta\n\nimport requests\nfrom waste_collection_schedule import Collection # type: ignore[attr-defined]\n\nTITLE = \"Recycle!\"\nDESCRIPTION = \"Source for RecycleApp.be\"\nURL = \"https://www.recycleapp.be\"\nTEST_CASES = {\n \"1140 Evere, Bazellaan 1\": {\n \"postcode\": 1140,\n \"street\": \"Bazellaan\",\n \"house_number\": 1,\n },\n \"3001, Waversebaan 276 with events\": {\n \"postcode\": 3001,\n \"street\": \"Waversebaan\",\n \"house_number\": 276,\n },\n \"3001, Waversebaan 276 without events\": {\n \"postcode\": 3001,\n \"street\": \"Waversebaan\",\n \"house_number\": 276,\n \"add_events\": False,\n },\n}\n\n_LOGGER = logging.getLogger(__name__)\n\n\nclass Source:\n def __init__(self, postcode, street, house_number, add_events=True):\n self._postcode = postcode\n self._street = street\n self._house_number = house_number\n self._add_events = add_events\n\n def fetch(self):\n url = \"https://recycleapp.be/api/app/v1\"\n headers = {\n \"x-secret\": \"Crgja3EGWe8jdapyr4EEoMBgZACYYjRRcRpaMQrLDW9HJBvmgkfGQyYqLgeXPavAGvnJqkV87PBB2b8zx43q46sUgzqio4yRZbABhtKeagkVKypTEDjKfPgGycjLyJTtLHYpzwJgp4YmmCuJZN9ZmJY8CGEoFs8MKfdJpU9RjkEVfngmmk2LYD4QzFegLNKUbcCeAdEW\",\n \"x-consumer\": \"recycleapp.be\",\n \"User-Agent\": \"\",\n \"Authorization\": \"\",\n }\n r = requests.get(f\"{url}/access-token\", headers=headers)\n headers[\"Authorization\"] = r.json()[\"accessToken\"]\n\n params = {\"q\": self._postcode}\n r = requests.get(f\"{url}/zipcodes\", params=params, headers=headers)\n if r.status_code != 200:\n _LOGGER.error(\"Get zip code failed\")\n return []\n zipcodeId = r.json()[\"items\"][0][\"id\"]\n\n params = {\"q\": self._street, \"zipcodes\": zipcodeId}\n r = requests.get(f\"{url}/streets\", params=params, headers=headers)\n if r.status_code != 200:\n _LOGGER.error(\"Get street id failed\")\n return []\n\n for item in r.json()[\"items\"]:\n if item[\"name\"] == self._street:\n streetId = item[\"id\"]\n if streetId is None:\n streetId = r.json()[\"items\"][0][\"id\"]\n\n now = datetime.now()\n fromDate = now.strftime(\"%Y-%m-%d\")\n untilDate = (now + timedelta(days=365)).strftime(\"%Y-%m-%d\")\n params = {\n \"zipcodeId\": zipcodeId,\n \"streetId\": streetId,\n \"houseNumber\": self._house_number,\n \"fromDate\": fromDate,\n \"untilDate\": untilDate,\n # \"size\":100,\n }\n r = requests.get(f\"{url}/collections\", params=params, headers=headers)\n if r.status_code != 200:\n _LOGGER.error(\"Get data failed\")\n return []\n\n entries = []\n for item in r.json()[\"items\"]:\n if \"exception\" in item and \"replacedBy\" in item[\"exception\"]:\n continue\n\n date = datetime.strptime(item[\"timestamp\"], \"%Y-%m-%dT%H:%M:%S.000Z\").date()\n if item[\"type\"] == \"collection\":\n entries.append(Collection(date, item[\"fraction\"][\"name\"][\"en\"]))\n elif item[\"type\"] == \"event\" and self._add_events:\n entries.append(Collection(date, item[\"event\"][\"title\"][\"en\"]))\n\n return entries\n", "path": "custom_components/waste_collection_schedule/waste_collection_schedule/source/recycleapp_be.py"}]}
| 1,434 | 466 |
gh_patches_debug_31901
|
rasdani/github-patches
|
git_diff
|
fidals__shopelectro-753
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Add sending mail action for given orders to admin panel
We have got connection issue with smtp and didn't notify 5 client
https://sentry.fidals.com/fidals/shopelectro/issues/36/
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `shopelectro/admin.py`
Content:
```
1 from django.contrib import admin
2 from django.contrib.admin.widgets import FilteredSelectMultiple
3 from django.contrib.redirects.models import Redirect
4 from django.db import models as django_models
5 from django.urls import reverse
6 from django.utils.html import format_html
7 from django.utils.translation import ugettext_lazy as _
8
9 from django_select2.forms import ModelSelect2Widget
10
11 from ecommerce.models import Position
12 from pages.models import CustomPage, FlatPage, PageTemplate
13 from generic_admin import inlines, mixins, models, sites
14
15 from shopelectro import models as se_models
16 from shopelectro.views.admin import TableEditor
17
18
19 class SEAdminSite(sites.SiteWithTableEditor):
20
21 site_header = 'Shopelectro administration'
22 table_editor_view = TableEditor
23
24
25 def prepare_has_filter_queryset(value, db_table, queryset):
26 if not value:
27 return
28
29 query = '{}__tags__isnull'.format(db_table)
30
31 # Use brackets, because `Explicit is better than implicit`.
32 return queryset.filter(**{query: value != 'yes'})
33
34
35 class HasTagsFilter(admin.SimpleListFilter):
36
37 product_model = se_models.Product
38 title = _('has tags')
39 parameter_name = 'has_tags'
40
41 def lookups(self, request, model_admin):
42 return (
43 ('yes', _('Has tags')),
44 ('no', _('Has no tags')),
45 )
46
47 def queryset(self, request, queryset):
48 return prepare_has_filter_queryset(
49 self.value(),
50 self.product_model._meta.db_table,
51 queryset
52 )
53
54
55 class HasCategoryFilter(admin.SimpleListFilter):
56
57 product_model = se_models.Product
58 title = _('has category')
59 parameter_name = 'has_category'
60
61 def lookups(self, request, model_admin):
62 return (
63 ('yes', _('Has category')),
64 ('no', _('Has no category')),
65 )
66
67 def queryset(self, request, queryset):
68 return prepare_has_filter_queryset(
69 self.value(),
70 self.product_model._meta.db_table,
71 queryset
72 )
73
74
75 class TagInline(admin.StackedInline):
76
77 model = se_models.Tag
78 extra = 0
79
80
81 class CategoryInline(inlines.CategoryInline):
82
83 model = se_models.Category
84
85 fieldsets = ((None, {
86 'classes': ('primary-chars', ),
87 'fields': (
88 ('name', 'id'),
89 ('parent', 'correct_parent_id'),
90 )
91 }),)
92
93
94 class ProductInline(inlines.ProductInline):
95
96 model = se_models.Product
97
98 formfield_overrides = {
99 django_models.ManyToManyField: {
100 'widget': FilteredSelectMultiple(verbose_name='Tags', is_stacked=False)
101 },
102 }
103
104 fieldsets = ((None, {
105 'classes': ('primary-chars', ),
106 'fields': (
107 ('name', 'id', 'vendor_code'),
108 ('category', 'correct_category_id'),
109 ('price', 'in_stock'),
110 'is_popular',
111 ('purchase_price', 'wholesale_small'),
112 ('wholesale_medium', 'wholesale_large'),
113 'tags',
114 )
115 }),)
116
117 def formfield_for_dbfield(self, db_field, **kwargs):
118 if db_field.name == 'category':
119 kwargs['widget'] = ModelSelect2Widget(
120 model=se_models.Category,
121 search_fields=[
122 'name__icontains',
123 'pk__startswith',
124 ],
125 )
126 return super(ProductInline, self).formfield_for_dbfield(
127 db_field,
128 **kwargs,
129 )
130
131
132 class PositionInline(admin.StackedInline):
133
134 model = Position
135
136
137 class CategoryPageAdmin(models.CategoryPageAdmin):
138
139 add = True
140 delete = False
141 inlines = [CategoryInline, inlines.ImageInline]
142
143 def get_queryset(self, request):
144 return (
145 super(CategoryPageAdmin, self)
146 .get_queryset(request)
147 .select_related('shopelectro_category')
148 )
149
150
151 class ProductPageAdmin(models.ProductPageAdmin):
152
153 add = False
154 delete = False
155 category_page_model = se_models.CategoryPage
156 list_filter = [*models.ProductPageAdmin.list_filter, HasTagsFilter, HasCategoryFilter]
157 inlines = [ProductInline, inlines.ImageInline]
158 search_fields = [
159 'shopelectro_product__vendor_code', 'name', 'slug',
160 ]
161
162 def model_id(self, obj):
163 return obj.model.vendor_code
164
165 model_id.short_description = _('Vendor code')
166 model_id.admin_order_field = 'shopelectro_product__vendor_code'
167
168 def get_queryset(self, request):
169 return (
170 super(ProductPageAdmin, self)
171 .get_queryset(request)
172 .select_related('shopelectro_product')
173 )
174
175
176 class ProductFeedbackPageAdmin(admin.ModelAdmin):
177
178 add = False
179 delete = False
180 list_filter = ['rating']
181 list_display = ['rating', 'name', 'dignities', 'limitations', 'general', 'links']
182
183 def links(self, obj):
184 return format_html(
185 '''
186 <a href="{url}" class="field-link" title="Посмотреть на сайте" target="_blank">
187 <i class="fa fa-link" aria-hidden="true"></i>
188 </a>
189 '''.format(url=obj.product.url))
190
191 links.short_description = _('Link')
192
193 def get_queryset(self, request):
194 return (
195 super(ProductFeedbackPageAdmin, self)
196 .get_queryset(request)
197 .select_related('product')
198 )
199
200
201 class TagGroupAdmin(admin.ModelAdmin):
202
203 list_display = ['id', 'name', 'position', 'count_tags']
204 list_display_links = ['name']
205
206 inlines = [TagInline]
207
208 def get_queryset(self, request):
209 return super(TagGroupAdmin, self).get_queryset(request).prefetch_related('tags')
210
211 def count_tags(self, obj):
212 return obj.tags.count()
213
214
215 class TagAdmin(admin.ModelAdmin):
216
217 search_fields = ['id', 'name']
218 list_display = ['id', 'name', 'position', 'custom_group']
219 list_display_links = ['name']
220
221 def get_queryset(self, request):
222 return super(TagAdmin, self).get_queryset(request).prefetch_related('group')
223
224 def custom_group(self, obj):
225 group = obj.group
226
227 return format_html(
228 '<a href="{url}">{group}</a>',
229 group=group,
230 url=reverse('admin:shopelectro_taggroup_change', args=(group.id, ))
231 )
232
233 custom_group.admin_order_field = 'group'
234 custom_group.short_description = _('Group')
235
236
237 class OrderAdmin(mixins.PermissionsControl):
238
239 add = False
240 inlines = [PositionInline]
241 list_display = ['id_', 'name', 'email', 'phone', 'total_price', 'payment_type', 'paid']
242 search_fields = ['name', 'email', 'phone']
243 list_display_links = ['name']
244
245 def id_(self, obj):
246 return obj.fake_order_number
247
248
249 se_admin = SEAdminSite(name='se_admin')
250 se_admin.register(CustomPage, models.CustomPageAdmin)
251 se_admin.register(FlatPage, models.FlatPageAdmin)
252 se_admin.register(PageTemplate, models.CustomPageTemplateAdmin)
253
254 se_admin.register(se_models.CategoryPage, CategoryPageAdmin)
255 se_admin.register(se_models.Order, OrderAdmin)
256 se_admin.register(se_models.ProductPage, ProductPageAdmin)
257 se_admin.register(se_models.ProductFeedback, ProductFeedbackPageAdmin)
258 se_admin.register(se_models.TagGroup, TagGroupAdmin)
259 se_admin.register(se_models.Tag, TagAdmin)
260
261 se_admin.register(Redirect)
262
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/shopelectro/admin.py b/shopelectro/admin.py
--- a/shopelectro/admin.py
+++ b/shopelectro/admin.py
@@ -1,3 +1,4 @@
+from django.conf import settings
from django.contrib import admin
from django.contrib.admin.widgets import FilteredSelectMultiple
from django.contrib.redirects.models import Redirect
@@ -8,6 +9,7 @@
from django_select2.forms import ModelSelect2Widget
+from ecommerce import mailer
from ecommerce.models import Position
from pages.models import CustomPage, FlatPage, PageTemplate
from generic_admin import inlines, mixins, models, sites
@@ -234,6 +236,27 @@
custom_group.short_description = _('Group')
+def send_order_emails(admin_model, request, order_qs):
+ for order in order_qs:
+ context = {'shop': settings.SHOP}
+ if order.email:
+ mailer.send_order(
+ subject=settings.EMAIL_SUBJECTS['order'],
+ order=order,
+ extra_context=context,
+ )
+ else:
+ mailer.send_order(
+ subject=settings.EMAIL_SUBJECTS['one_click'],
+ order=order,
+ to_customer=False,
+ extra_context=context,
+ )
+
+
+send_order_emails.short_description = _('Sends email notifications about placed orders')
+
+
class OrderAdmin(mixins.PermissionsControl):
add = False
@@ -241,6 +264,7 @@
list_display = ['id_', 'name', 'email', 'phone', 'total_price', 'payment_type', 'paid']
search_fields = ['name', 'email', 'phone']
list_display_links = ['name']
+ actions = [send_order_emails]
def id_(self, obj):
return obj.fake_order_number
|
{"golden_diff": "diff --git a/shopelectro/admin.py b/shopelectro/admin.py\n--- a/shopelectro/admin.py\n+++ b/shopelectro/admin.py\n@@ -1,3 +1,4 @@\n+from django.conf import settings\n from django.contrib import admin\n from django.contrib.admin.widgets import FilteredSelectMultiple\n from django.contrib.redirects.models import Redirect\n@@ -8,6 +9,7 @@\n \n from django_select2.forms import ModelSelect2Widget\n \n+from ecommerce import mailer\n from ecommerce.models import Position\n from pages.models import CustomPage, FlatPage, PageTemplate\n from generic_admin import inlines, mixins, models, sites\n@@ -234,6 +236,27 @@\n custom_group.short_description = _('Group')\n \n \n+def send_order_emails(admin_model, request, order_qs):\n+ for order in order_qs:\n+ context = {'shop': settings.SHOP}\n+ if order.email:\n+ mailer.send_order(\n+ subject=settings.EMAIL_SUBJECTS['order'],\n+ order=order,\n+ extra_context=context,\n+ )\n+ else:\n+ mailer.send_order(\n+ subject=settings.EMAIL_SUBJECTS['one_click'],\n+ order=order,\n+ to_customer=False,\n+ extra_context=context,\n+ )\n+\n+\n+send_order_emails.short_description = _('Sends email notifications about placed orders')\n+\n+\n class OrderAdmin(mixins.PermissionsControl):\n \n add = False\n@@ -241,6 +264,7 @@\n list_display = ['id_', 'name', 'email', 'phone', 'total_price', 'payment_type', 'paid']\n search_fields = ['name', 'email', 'phone']\n list_display_links = ['name']\n+ actions = [send_order_emails]\n \n def id_(self, obj):\n return obj.fake_order_number\n", "issue": "Add sending mail action for given orders to admin panel\nWe have got connection issue with smtp and didn't notify 5 client\r\nhttps://sentry.fidals.com/fidals/shopelectro/issues/36/\n", "before_files": [{"content": "from django.contrib import admin\nfrom django.contrib.admin.widgets import FilteredSelectMultiple\nfrom django.contrib.redirects.models import Redirect\nfrom django.db import models as django_models\nfrom django.urls import reverse\nfrom django.utils.html import format_html\nfrom django.utils.translation import ugettext_lazy as _\n\nfrom django_select2.forms import ModelSelect2Widget\n\nfrom ecommerce.models import Position\nfrom pages.models import CustomPage, FlatPage, PageTemplate\nfrom generic_admin import inlines, mixins, models, sites\n\nfrom shopelectro import models as se_models\nfrom shopelectro.views.admin import TableEditor\n\n\nclass SEAdminSite(sites.SiteWithTableEditor):\n\n site_header = 'Shopelectro administration'\n table_editor_view = TableEditor\n\n\ndef prepare_has_filter_queryset(value, db_table, queryset):\n if not value:\n return\n\n query = '{}__tags__isnull'.format(db_table)\n\n # Use brackets, because `Explicit is better than implicit`.\n return queryset.filter(**{query: value != 'yes'})\n\n\nclass HasTagsFilter(admin.SimpleListFilter):\n\n product_model = se_models.Product\n title = _('has tags')\n parameter_name = 'has_tags'\n\n def lookups(self, request, model_admin):\n return (\n ('yes', _('Has tags')),\n ('no', _('Has no tags')),\n )\n\n def queryset(self, request, queryset):\n return prepare_has_filter_queryset(\n self.value(),\n self.product_model._meta.db_table,\n queryset\n )\n\n\nclass HasCategoryFilter(admin.SimpleListFilter):\n\n product_model = se_models.Product\n title = _('has category')\n parameter_name = 'has_category'\n\n def lookups(self, request, model_admin):\n return (\n ('yes', _('Has category')),\n ('no', _('Has no category')),\n )\n\n def queryset(self, request, queryset):\n return prepare_has_filter_queryset(\n self.value(),\n self.product_model._meta.db_table,\n queryset\n )\n\n\nclass TagInline(admin.StackedInline):\n\n model = se_models.Tag\n extra = 0\n\n\nclass CategoryInline(inlines.CategoryInline):\n\n model = se_models.Category\n\n fieldsets = ((None, {\n 'classes': ('primary-chars', ),\n 'fields': (\n ('name', 'id'),\n ('parent', 'correct_parent_id'),\n )\n }),)\n\n\nclass ProductInline(inlines.ProductInline):\n\n model = se_models.Product\n\n formfield_overrides = {\n django_models.ManyToManyField: {\n 'widget': FilteredSelectMultiple(verbose_name='Tags', is_stacked=False)\n },\n }\n\n fieldsets = ((None, {\n 'classes': ('primary-chars', ),\n 'fields': (\n ('name', 'id', 'vendor_code'),\n ('category', 'correct_category_id'),\n ('price', 'in_stock'),\n 'is_popular',\n ('purchase_price', 'wholesale_small'),\n ('wholesale_medium', 'wholesale_large'),\n 'tags',\n )\n }),)\n\n def formfield_for_dbfield(self, db_field, **kwargs):\n if db_field.name == 'category':\n kwargs['widget'] = ModelSelect2Widget(\n model=se_models.Category,\n search_fields=[\n 'name__icontains',\n 'pk__startswith',\n ],\n )\n return super(ProductInline, self).formfield_for_dbfield(\n db_field,\n **kwargs,\n )\n\n\nclass PositionInline(admin.StackedInline):\n\n model = Position\n\n\nclass CategoryPageAdmin(models.CategoryPageAdmin):\n\n add = True\n delete = False\n inlines = [CategoryInline, inlines.ImageInline]\n\n def get_queryset(self, request):\n return (\n super(CategoryPageAdmin, self)\n .get_queryset(request)\n .select_related('shopelectro_category')\n )\n\n\nclass ProductPageAdmin(models.ProductPageAdmin):\n\n add = False\n delete = False\n category_page_model = se_models.CategoryPage\n list_filter = [*models.ProductPageAdmin.list_filter, HasTagsFilter, HasCategoryFilter]\n inlines = [ProductInline, inlines.ImageInline]\n search_fields = [\n 'shopelectro_product__vendor_code', 'name', 'slug',\n ]\n\n def model_id(self, obj):\n return obj.model.vendor_code\n\n model_id.short_description = _('Vendor code')\n model_id.admin_order_field = 'shopelectro_product__vendor_code'\n\n def get_queryset(self, request):\n return (\n super(ProductPageAdmin, self)\n .get_queryset(request)\n .select_related('shopelectro_product')\n )\n\n\nclass ProductFeedbackPageAdmin(admin.ModelAdmin):\n\n add = False\n delete = False\n list_filter = ['rating']\n list_display = ['rating', 'name', 'dignities', 'limitations', 'general', 'links']\n\n def links(self, obj):\n return format_html(\n '''\n <a href=\"{url}\" class=\"field-link\" title=\"\u041f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u043d\u0430 \u0441\u0430\u0439\u0442\u0435\" target=\"_blank\">\n <i class=\"fa fa-link\" aria-hidden=\"true\"></i>\n </a>\n '''.format(url=obj.product.url))\n\n links.short_description = _('Link')\n\n def get_queryset(self, request):\n return (\n super(ProductFeedbackPageAdmin, self)\n .get_queryset(request)\n .select_related('product')\n )\n\n\nclass TagGroupAdmin(admin.ModelAdmin):\n\n list_display = ['id', 'name', 'position', 'count_tags']\n list_display_links = ['name']\n\n inlines = [TagInline]\n\n def get_queryset(self, request):\n return super(TagGroupAdmin, self).get_queryset(request).prefetch_related('tags')\n\n def count_tags(self, obj):\n return obj.tags.count()\n\n\nclass TagAdmin(admin.ModelAdmin):\n\n search_fields = ['id', 'name']\n list_display = ['id', 'name', 'position', 'custom_group']\n list_display_links = ['name']\n\n def get_queryset(self, request):\n return super(TagAdmin, self).get_queryset(request).prefetch_related('group')\n\n def custom_group(self, obj):\n group = obj.group\n\n return format_html(\n '<a href=\"{url}\">{group}</a>',\n group=group,\n url=reverse('admin:shopelectro_taggroup_change', args=(group.id, ))\n )\n\n custom_group.admin_order_field = 'group'\n custom_group.short_description = _('Group')\n\n\nclass OrderAdmin(mixins.PermissionsControl):\n\n add = False\n inlines = [PositionInline]\n list_display = ['id_', 'name', 'email', 'phone', 'total_price', 'payment_type', 'paid']\n search_fields = ['name', 'email', 'phone']\n list_display_links = ['name']\n\n def id_(self, obj):\n return obj.fake_order_number\n\n\nse_admin = SEAdminSite(name='se_admin')\nse_admin.register(CustomPage, models.CustomPageAdmin)\nse_admin.register(FlatPage, models.FlatPageAdmin)\nse_admin.register(PageTemplate, models.CustomPageTemplateAdmin)\n\nse_admin.register(se_models.CategoryPage, CategoryPageAdmin)\nse_admin.register(se_models.Order, OrderAdmin)\nse_admin.register(se_models.ProductPage, ProductPageAdmin)\nse_admin.register(se_models.ProductFeedback, ProductFeedbackPageAdmin)\nse_admin.register(se_models.TagGroup, TagGroupAdmin)\nse_admin.register(se_models.Tag, TagAdmin)\n\nse_admin.register(Redirect)\n", "path": "shopelectro/admin.py"}], "after_files": [{"content": "from django.conf import settings\nfrom django.contrib import admin\nfrom django.contrib.admin.widgets import FilteredSelectMultiple\nfrom django.contrib.redirects.models import Redirect\nfrom django.db import models as django_models\nfrom django.urls import reverse\nfrom django.utils.html import format_html\nfrom django.utils.translation import ugettext_lazy as _\n\nfrom django_select2.forms import ModelSelect2Widget\n\nfrom ecommerce import mailer\nfrom ecommerce.models import Position\nfrom pages.models import CustomPage, FlatPage, PageTemplate\nfrom generic_admin import inlines, mixins, models, sites\n\nfrom shopelectro import models as se_models\nfrom shopelectro.views.admin import TableEditor\n\n\nclass SEAdminSite(sites.SiteWithTableEditor):\n\n site_header = 'Shopelectro administration'\n table_editor_view = TableEditor\n\n\ndef prepare_has_filter_queryset(value, db_table, queryset):\n if not value:\n return\n\n query = '{}__tags__isnull'.format(db_table)\n\n # Use brackets, because `Explicit is better than implicit`.\n return queryset.filter(**{query: value != 'yes'})\n\n\nclass HasTagsFilter(admin.SimpleListFilter):\n\n product_model = se_models.Product\n title = _('has tags')\n parameter_name = 'has_tags'\n\n def lookups(self, request, model_admin):\n return (\n ('yes', _('Has tags')),\n ('no', _('Has no tags')),\n )\n\n def queryset(self, request, queryset):\n return prepare_has_filter_queryset(\n self.value(),\n self.product_model._meta.db_table,\n queryset\n )\n\n\nclass HasCategoryFilter(admin.SimpleListFilter):\n\n product_model = se_models.Product\n title = _('has category')\n parameter_name = 'has_category'\n\n def lookups(self, request, model_admin):\n return (\n ('yes', _('Has category')),\n ('no', _('Has no category')),\n )\n\n def queryset(self, request, queryset):\n return prepare_has_filter_queryset(\n self.value(),\n self.product_model._meta.db_table,\n queryset\n )\n\n\nclass TagInline(admin.StackedInline):\n\n model = se_models.Tag\n extra = 0\n\n\nclass CategoryInline(inlines.CategoryInline):\n\n model = se_models.Category\n\n fieldsets = ((None, {\n 'classes': ('primary-chars', ),\n 'fields': (\n ('name', 'id'),\n ('parent', 'correct_parent_id'),\n )\n }),)\n\n\nclass ProductInline(inlines.ProductInline):\n\n model = se_models.Product\n\n formfield_overrides = {\n django_models.ManyToManyField: {\n 'widget': FilteredSelectMultiple(verbose_name='Tags', is_stacked=False)\n },\n }\n\n fieldsets = ((None, {\n 'classes': ('primary-chars', ),\n 'fields': (\n ('name', 'id', 'vendor_code'),\n ('category', 'correct_category_id'),\n ('price', 'in_stock'),\n 'is_popular',\n ('purchase_price', 'wholesale_small'),\n ('wholesale_medium', 'wholesale_large'),\n 'tags',\n )\n }),)\n\n def formfield_for_dbfield(self, db_field, **kwargs):\n if db_field.name == 'category':\n kwargs['widget'] = ModelSelect2Widget(\n model=se_models.Category,\n search_fields=[\n 'name__icontains',\n 'pk__startswith',\n ],\n )\n return super(ProductInline, self).formfield_for_dbfield(\n db_field,\n **kwargs,\n )\n\n\nclass PositionInline(admin.StackedInline):\n\n model = Position\n\n\nclass CategoryPageAdmin(models.CategoryPageAdmin):\n\n add = True\n delete = False\n inlines = [CategoryInline, inlines.ImageInline]\n\n def get_queryset(self, request):\n return (\n super(CategoryPageAdmin, self)\n .get_queryset(request)\n .select_related('shopelectro_category')\n )\n\n\nclass ProductPageAdmin(models.ProductPageAdmin):\n\n add = False\n delete = False\n category_page_model = se_models.CategoryPage\n list_filter = [*models.ProductPageAdmin.list_filter, HasTagsFilter, HasCategoryFilter]\n inlines = [ProductInline, inlines.ImageInline]\n search_fields = [\n 'shopelectro_product__vendor_code', 'name', 'slug',\n ]\n\n def model_id(self, obj):\n return obj.model.vendor_code\n\n model_id.short_description = _('Vendor code')\n model_id.admin_order_field = 'shopelectro_product__vendor_code'\n\n def get_queryset(self, request):\n return (\n super(ProductPageAdmin, self)\n .get_queryset(request)\n .select_related('shopelectro_product')\n )\n\n\nclass ProductFeedbackPageAdmin(admin.ModelAdmin):\n\n add = False\n delete = False\n list_filter = ['rating']\n list_display = ['rating', 'name', 'dignities', 'limitations', 'general', 'links']\n\n def links(self, obj):\n return format_html(\n '''\n <a href=\"{url}\" class=\"field-link\" title=\"\u041f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u043d\u0430 \u0441\u0430\u0439\u0442\u0435\" target=\"_blank\">\n <i class=\"fa fa-link\" aria-hidden=\"true\"></i>\n </a>\n '''.format(url=obj.product.url))\n\n links.short_description = _('Link')\n\n def get_queryset(self, request):\n return (\n super(ProductFeedbackPageAdmin, self)\n .get_queryset(request)\n .select_related('product')\n )\n\n\nclass TagGroupAdmin(admin.ModelAdmin):\n\n list_display = ['id', 'name', 'position', 'count_tags']\n list_display_links = ['name']\n\n inlines = [TagInline]\n\n def get_queryset(self, request):\n return super(TagGroupAdmin, self).get_queryset(request).prefetch_related('tags')\n\n def count_tags(self, obj):\n return obj.tags.count()\n\n\nclass TagAdmin(admin.ModelAdmin):\n\n search_fields = ['id', 'name']\n list_display = ['id', 'name', 'position', 'custom_group']\n list_display_links = ['name']\n\n def get_queryset(self, request):\n return super(TagAdmin, self).get_queryset(request).prefetch_related('group')\n\n def custom_group(self, obj):\n group = obj.group\n\n return format_html(\n '<a href=\"{url}\">{group}</a>',\n group=group,\n url=reverse('admin:shopelectro_taggroup_change', args=(group.id, ))\n )\n\n custom_group.admin_order_field = 'group'\n custom_group.short_description = _('Group')\n\n\ndef send_order_emails(admin_model, request, order_qs):\n for order in order_qs:\n context = {'shop': settings.SHOP}\n if order.email:\n mailer.send_order(\n subject=settings.EMAIL_SUBJECTS['order'],\n order=order,\n extra_context=context,\n )\n else:\n mailer.send_order(\n subject=settings.EMAIL_SUBJECTS['one_click'],\n order=order,\n to_customer=False,\n extra_context=context,\n )\n\n\nsend_order_emails.short_description = _('Sends email notifications about placed orders')\n\n\nclass OrderAdmin(mixins.PermissionsControl):\n\n add = False\n inlines = [PositionInline]\n list_display = ['id_', 'name', 'email', 'phone', 'total_price', 'payment_type', 'paid']\n search_fields = ['name', 'email', 'phone']\n list_display_links = ['name']\n actions = [send_order_emails]\n\n def id_(self, obj):\n return obj.fake_order_number\n\n\nse_admin = SEAdminSite(name='se_admin')\nse_admin.register(CustomPage, models.CustomPageAdmin)\nse_admin.register(FlatPage, models.FlatPageAdmin)\nse_admin.register(PageTemplate, models.CustomPageTemplateAdmin)\n\nse_admin.register(se_models.CategoryPage, CategoryPageAdmin)\nse_admin.register(se_models.Order, OrderAdmin)\nse_admin.register(se_models.ProductPage, ProductPageAdmin)\nse_admin.register(se_models.ProductFeedback, ProductFeedbackPageAdmin)\nse_admin.register(se_models.TagGroup, TagGroupAdmin)\nse_admin.register(se_models.Tag, TagAdmin)\n\nse_admin.register(Redirect)\n", "path": "shopelectro/admin.py"}]}
| 2,616 | 401 |
gh_patches_debug_27458
|
rasdani/github-patches
|
git_diff
|
pyinstaller__pyinstaller-4889
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Py3.6: Unable to find .../site-packages/importlib_resources/version.txt"
Hello,
On latest version of pyinstaller, the hook for importlib_resource seems to look for a non existing version.txt file. It is not provided by the latest version 1.2.0 of the backport: https://gitlab.com/python-devs/importlib_resources
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `PyInstaller/hooks/hook-importlib_resources.py`
Content:
```
1 #-----------------------------------------------------------------------------
2 # Copyright (c) 2019-2020, PyInstaller Development Team.
3 #
4 # Distributed under the terms of the GNU General Public License (version 2
5 # or later) with exception for distributing the bootloader.
6 #
7 # The full license is in the file COPYING.txt, distributed with this software.
8 #
9 # SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)
10 #-----------------------------------------------------------------------------
11 """
12 `importlib_resources` is a backport of the 3.7+ module `importlib.resources`
13 """
14
15 import os
16 from PyInstaller.compat import is_py37
17 from PyInstaller.utils.hooks import get_module_file_attribute
18
19 # Include the version.txt file, used to set __version__
20 res_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))
21 datas = [
22 (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),
23 ]
24
25 # Replicate the module's version checks to exclude unused modules.
26 if is_py37:
27 # Stdlib now has the implmentation of this, so the backports
28 # aren't used at all
29 excludedmodules = [
30 'importlib_resources._py2',
31 'importlib_resources._py3',
32 ]
33 else:
34 excludedmodules = ['importlib_resources._py2']
35
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/PyInstaller/hooks/hook-importlib_resources.py b/PyInstaller/hooks/hook-importlib_resources.py
--- a/PyInstaller/hooks/hook-importlib_resources.py
+++ b/PyInstaller/hooks/hook-importlib_resources.py
@@ -9,26 +9,25 @@
# SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)
#-----------------------------------------------------------------------------
"""
-`importlib_resources` is a backport of the 3.7+ module `importlib.resources`
+`importlib_resources` is a backport of the 3.9+ module `importlib.resources`
"""
import os
-from PyInstaller.compat import is_py37
-from PyInstaller.utils.hooks import get_module_file_attribute
+from PyInstaller.utils.hooks import get_module_file_attribute, \
+ is_module_satisfies, copy_metadata
-# Include the version.txt file, used to set __version__
-res_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))
-datas = [
- (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),
-]
-
-# Replicate the module's version checks to exclude unused modules.
-if is_py37:
- # Stdlib now has the implmentation of this, so the backports
- # aren't used at all
- excludedmodules = [
- 'importlib_resources._py2',
- 'importlib_resources._py3',
- ]
+if is_module_satisfies("importlib_resources >= 1.2.0"):
+ # since 1.2.0 importlib.metadata is used
+ datas = copy_metadata('importlib_resources')
else:
- excludedmodules = ['importlib_resources._py2']
+ # include the version.txt file, used to set __version__
+ res_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))
+ datas = [
+ (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),
+ ]
+
+if is_module_satisfies("importlib_resources >= 1.3.1"):
+ hiddenimports = ['importlib_resources.trees']
+
+# this is only required for python2 support
+excludedimports = ['importlib_resources._py2']
|
{"golden_diff": "diff --git a/PyInstaller/hooks/hook-importlib_resources.py b/PyInstaller/hooks/hook-importlib_resources.py\n--- a/PyInstaller/hooks/hook-importlib_resources.py\n+++ b/PyInstaller/hooks/hook-importlib_resources.py\n@@ -9,26 +9,25 @@\n # SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)\n #-----------------------------------------------------------------------------\n \"\"\"\n-`importlib_resources` is a backport of the 3.7+ module `importlib.resources`\n+`importlib_resources` is a backport of the 3.9+ module `importlib.resources`\n \"\"\"\n \n import os\n-from PyInstaller.compat import is_py37\n-from PyInstaller.utils.hooks import get_module_file_attribute\n+from PyInstaller.utils.hooks import get_module_file_attribute, \\\n+ is_module_satisfies, copy_metadata\n \n-# Include the version.txt file, used to set __version__\n-res_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))\n-datas = [\n- (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),\n-]\n-\n-# Replicate the module's version checks to exclude unused modules.\n-if is_py37:\n- # Stdlib now has the implmentation of this, so the backports\n- # aren't used at all\n- excludedmodules = [\n- 'importlib_resources._py2',\n- 'importlib_resources._py3',\n- ]\n+if is_module_satisfies(\"importlib_resources >= 1.2.0\"):\n+ # since 1.2.0 importlib.metadata is used\n+ datas = copy_metadata('importlib_resources')\n else:\n- excludedmodules = ['importlib_resources._py2']\n+ # include the version.txt file, used to set __version__\n+ res_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))\n+ datas = [\n+ (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),\n+ ]\n+\n+if is_module_satisfies(\"importlib_resources >= 1.3.1\"):\n+ hiddenimports = ['importlib_resources.trees']\n+\n+# this is only required for python2 support\n+excludedimports = ['importlib_resources._py2']\n", "issue": "Py3.6: Unable to find .../site-packages/importlib_resources/version.txt\"\nHello,\r\n\r\nOn latest version of pyinstaller, the hook for importlib_resource seems to look for a non existing version.txt file. It is not provided by the latest version 1.2.0 of the backport: https://gitlab.com/python-devs/importlib_resources\n", "before_files": [{"content": "#-----------------------------------------------------------------------------\n# Copyright (c) 2019-2020, PyInstaller Development Team.\n#\n# Distributed under the terms of the GNU General Public License (version 2\n# or later) with exception for distributing the bootloader.\n#\n# The full license is in the file COPYING.txt, distributed with this software.\n#\n# SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)\n#-----------------------------------------------------------------------------\n\"\"\"\n`importlib_resources` is a backport of the 3.7+ module `importlib.resources`\n\"\"\"\n\nimport os\nfrom PyInstaller.compat import is_py37\nfrom PyInstaller.utils.hooks import get_module_file_attribute\n\n# Include the version.txt file, used to set __version__\nres_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))\ndatas = [\n (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),\n]\n\n# Replicate the module's version checks to exclude unused modules.\nif is_py37:\n # Stdlib now has the implmentation of this, so the backports\n # aren't used at all\n excludedmodules = [\n 'importlib_resources._py2',\n 'importlib_resources._py3',\n ]\nelse:\n excludedmodules = ['importlib_resources._py2']\n", "path": "PyInstaller/hooks/hook-importlib_resources.py"}], "after_files": [{"content": "#-----------------------------------------------------------------------------\n# Copyright (c) 2019-2020, PyInstaller Development Team.\n#\n# Distributed under the terms of the GNU General Public License (version 2\n# or later) with exception for distributing the bootloader.\n#\n# The full license is in the file COPYING.txt, distributed with this software.\n#\n# SPDX-License-Identifier: (GPL-2.0-or-later WITH Bootloader-exception)\n#-----------------------------------------------------------------------------\n\"\"\"\n`importlib_resources` is a backport of the 3.9+ module `importlib.resources`\n\"\"\"\n\nimport os\nfrom PyInstaller.utils.hooks import get_module_file_attribute, \\\n is_module_satisfies, copy_metadata\n\nif is_module_satisfies(\"importlib_resources >= 1.2.0\"):\n # since 1.2.0 importlib.metadata is used\n datas = copy_metadata('importlib_resources')\nelse:\n # include the version.txt file, used to set __version__\n res_loc = os.path.dirname(get_module_file_attribute('importlib_resources'))\n datas = [\n (os.path.join(res_loc, 'version.txt'), 'importlib_resources'),\n ]\n\nif is_module_satisfies(\"importlib_resources >= 1.3.1\"):\n hiddenimports = ['importlib_resources.trees']\n\n# this is only required for python2 support\nexcludedimports = ['importlib_resources._py2']\n", "path": "PyInstaller/hooks/hook-importlib_resources.py"}]}
| 676 | 491 |
gh_patches_debug_27546
|
rasdani/github-patches
|
git_diff
|
TheAlgorithms__Python-10822
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Improve our test coverage
### Feature description
Many of our existing algorithm files have little to no unit testing. This is problematic because this can easily let bugs slip through. We want some assurance that the code we currently have is correct and functional. We welcome all contributors to open PRs to help us add tests to our codebase.
### How to find low-coverage files
Go to the Actions tab in this repository and find the most recent **build** workflow run. Open the logs under "Run Tests" and scroll down until you find the section on code coverage:
```
---------- coverage: platform linux, python 3.12.0-final-0 -----------
Name Stmts Miss Cover Missing
-----------------------------------------------------------------------------------------------------------
quantum/q_fourier_transform.py 30 30 0% 14-93
scripts/validate_solutions.py 54 54 0% 2-94
strings/min_cost_string_conversion.py 78 75 4% 20-57, 61-75, 79-129
...
```
The "Cover" column tells you what percentage of the lines in that file are covered by tests. We want to increase this percentage for existing files. Find a file with low coverage percentage that you wish to write tests for, add doctests for each function, and open a PR with your changes. You do not need to have a perfect coverage percentage, but all functions should have doctests.
Some files will naturally be hard to write tests for. For example, the file may be poorly written because they lack any functions. Other files might be how-tos, meaning they simply demonstrate how to use an existing library's functions rather than implementing the algorithm themselves. Ignore these kinds of files, as they will need to be rewritten eventually. Furthermore, ignore files in the `web_programming` and `project_euler` directories. Web programming files are inherently hard to test and Project Euler files have their own validation workflow, so don't worry about their test coverage.
_**When you open your PR, put "Contributes to #9943" in the PR description.**_ Do not use the word "fixes", "resolves", or "closes". This issue is an ongoing one, and your PR will not single-handedly resolve this issue.
### How to add doctests
A doctest is a unit test that is contained within the documentation comment (docstring) for a function. Here is an example of what doctests look like within a docstring:
```py
def add(a: int, b: int) -> int:
"""
Adds two non-negative numbers.
>>> add(1, 1)
2
>>> add(2, 5)
7
>>> add(1, 0)
1
>>> add(-1, -1)
Traceback (most recent last):
...
ValueError: Numbers must be non-negative
"""
```
For every function in the file you choose, you should write doctests like the ones shown above in its docstring. If a function doesn't have a docstring, add one. Your doctests should be comprehensive but not excessive: you should write just enough tests to cover all basic cases as well as all edge cases (e.g., negative numbers, empty lists, etc).
Do not simply run a function on some example inputs and put its output as the expected output for a doctest. This assumes that the function is implemented correctly when it might not be. Verify independently that your doctests and their expected outputs are correct. **Your PR will not be merged if it has failing tests.** If you happen to discover a bug while writing doctests, please fix it.
_**Please read our [contributing guidelines](https://github.com/TheAlgorithms/Python/blob/master/CONTRIBUTING.md) before you contribute.**_
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `maths/binomial_coefficient.py`
Content:
```
1 def binomial_coefficient(n: int, r: int) -> int:
2 """
3 Find binomial coefficient using pascals triangle.
4
5 >>> binomial_coefficient(10, 5)
6 252
7 """
8 c = [0 for i in range(r + 1)]
9 # nc0 = 1
10 c[0] = 1
11 for i in range(1, n + 1):
12 # to compute current row from previous row.
13 j = min(i, r)
14 while j > 0:
15 c[j] += c[j - 1]
16 j -= 1
17 return c[r]
18
19
20 print(binomial_coefficient(n=10, r=5))
21
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/maths/binomial_coefficient.py b/maths/binomial_coefficient.py
--- a/maths/binomial_coefficient.py
+++ b/maths/binomial_coefficient.py
@@ -1,10 +1,48 @@
def binomial_coefficient(n: int, r: int) -> int:
"""
- Find binomial coefficient using pascals triangle.
+ Find binomial coefficient using Pascal's triangle.
+
+ Calculate C(n, r) using Pascal's triangle.
+
+ :param n: The total number of items.
+ :param r: The number of items to choose.
+ :return: The binomial coefficient C(n, r).
>>> binomial_coefficient(10, 5)
252
+ >>> binomial_coefficient(10, 0)
+ 1
+ >>> binomial_coefficient(0, 10)
+ 1
+ >>> binomial_coefficient(10, 10)
+ 1
+ >>> binomial_coefficient(5, 2)
+ 10
+ >>> binomial_coefficient(5, 6)
+ 0
+ >>> binomial_coefficient(3, 5)
+ 0
+ >>> binomial_coefficient(-2, 3)
+ Traceback (most recent call last):
+ ...
+ ValueError: n and r must be non-negative integers
+ >>> binomial_coefficient(5, -1)
+ Traceback (most recent call last):
+ ...
+ ValueError: n and r must be non-negative integers
+ >>> binomial_coefficient(10.1, 5)
+ Traceback (most recent call last):
+ ...
+ TypeError: 'float' object cannot be interpreted as an integer
+ >>> binomial_coefficient(10, 5.1)
+ Traceback (most recent call last):
+ ...
+ TypeError: 'float' object cannot be interpreted as an integer
"""
+ if n < 0 or r < 0:
+ raise ValueError("n and r must be non-negative integers")
+ if 0 in (n, r):
+ return 1
c = [0 for i in range(r + 1)]
# nc0 = 1
c[0] = 1
@@ -17,4 +55,8 @@
return c[r]
-print(binomial_coefficient(n=10, r=5))
+if __name__ == "__main__":
+ from doctest import testmod
+
+ testmod()
+ print(binomial_coefficient(n=10, r=5))
|
{"golden_diff": "diff --git a/maths/binomial_coefficient.py b/maths/binomial_coefficient.py\n--- a/maths/binomial_coefficient.py\n+++ b/maths/binomial_coefficient.py\n@@ -1,10 +1,48 @@\n def binomial_coefficient(n: int, r: int) -> int:\n \"\"\"\n- Find binomial coefficient using pascals triangle.\n+ Find binomial coefficient using Pascal's triangle.\n+\n+ Calculate C(n, r) using Pascal's triangle.\n+\n+ :param n: The total number of items.\n+ :param r: The number of items to choose.\n+ :return: The binomial coefficient C(n, r).\n \n >>> binomial_coefficient(10, 5)\n 252\n+ >>> binomial_coefficient(10, 0)\n+ 1\n+ >>> binomial_coefficient(0, 10)\n+ 1\n+ >>> binomial_coefficient(10, 10)\n+ 1\n+ >>> binomial_coefficient(5, 2)\n+ 10\n+ >>> binomial_coefficient(5, 6)\n+ 0\n+ >>> binomial_coefficient(3, 5)\n+ 0\n+ >>> binomial_coefficient(-2, 3)\n+ Traceback (most recent call last):\n+ ...\n+ ValueError: n and r must be non-negative integers\n+ >>> binomial_coefficient(5, -1)\n+ Traceback (most recent call last):\n+ ...\n+ ValueError: n and r must be non-negative integers\n+ >>> binomial_coefficient(10.1, 5)\n+ Traceback (most recent call last):\n+ ...\n+ TypeError: 'float' object cannot be interpreted as an integer\n+ >>> binomial_coefficient(10, 5.1)\n+ Traceback (most recent call last):\n+ ...\n+ TypeError: 'float' object cannot be interpreted as an integer\n \"\"\"\n+ if n < 0 or r < 0:\n+ raise ValueError(\"n and r must be non-negative integers\")\n+ if 0 in (n, r):\n+ return 1\n c = [0 for i in range(r + 1)]\n # nc0 = 1\n c[0] = 1\n@@ -17,4 +55,8 @@\n return c[r]\n \n \n-print(binomial_coefficient(n=10, r=5))\n+if __name__ == \"__main__\":\n+ from doctest import testmod\n+\n+ testmod()\n+ print(binomial_coefficient(n=10, r=5))\n", "issue": "Improve our test coverage\n### Feature description\r\n\r\nMany of our existing algorithm files have little to no unit testing. This is problematic because this can easily let bugs slip through. We want some assurance that the code we currently have is correct and functional. We welcome all contributors to open PRs to help us add tests to our codebase.\r\n\r\n### How to find low-coverage files\r\n\r\nGo to the Actions tab in this repository and find the most recent **build** workflow run. Open the logs under \"Run Tests\" and scroll down until you find the section on code coverage:\r\n```\r\n---------- coverage: platform linux, python 3.12.0-final-0 -----------\r\nName Stmts Miss Cover Missing\r\n-----------------------------------------------------------------------------------------------------------\r\nquantum/q_fourier_transform.py 30 30 0% 14-93\r\nscripts/validate_solutions.py 54 54 0% 2-94\r\nstrings/min_cost_string_conversion.py 78 75 4% 20-57, 61-75, 79-129\r\n...\r\n```\r\nThe \"Cover\" column tells you what percentage of the lines in that file are covered by tests. We want to increase this percentage for existing files. Find a file with low coverage percentage that you wish to write tests for, add doctests for each function, and open a PR with your changes. You do not need to have a perfect coverage percentage, but all functions should have doctests.\r\n\r\nSome files will naturally be hard to write tests for. For example, the file may be poorly written because they lack any functions. Other files might be how-tos, meaning they simply demonstrate how to use an existing library's functions rather than implementing the algorithm themselves. Ignore these kinds of files, as they will need to be rewritten eventually. Furthermore, ignore files in the `web_programming` and `project_euler` directories. Web programming files are inherently hard to test and Project Euler files have their own validation workflow, so don't worry about their test coverage.\r\n\r\n_**When you open your PR, put \"Contributes to #9943\" in the PR description.**_ Do not use the word \"fixes\", \"resolves\", or \"closes\". This issue is an ongoing one, and your PR will not single-handedly resolve this issue.\r\n\r\n### How to add doctests\r\n\r\nA doctest is a unit test that is contained within the documentation comment (docstring) for a function. Here is an example of what doctests look like within a docstring:\r\n```py\r\ndef add(a: int, b: int) -> int:\r\n \"\"\"\r\n Adds two non-negative numbers.\r\n >>> add(1, 1)\r\n 2\r\n >>> add(2, 5)\r\n 7\r\n >>> add(1, 0)\r\n 1\r\n >>> add(-1, -1)\r\n Traceback (most recent last):\r\n ...\r\n ValueError: Numbers must be non-negative\r\n \"\"\"\r\n```\r\nFor every function in the file you choose, you should write doctests like the ones shown above in its docstring. If a function doesn't have a docstring, add one. Your doctests should be comprehensive but not excessive: you should write just enough tests to cover all basic cases as well as all edge cases (e.g., negative numbers, empty lists, etc).\r\n\r\nDo not simply run a function on some example inputs and put its output as the expected output for a doctest. This assumes that the function is implemented correctly when it might not be. Verify independently that your doctests and their expected outputs are correct. **Your PR will not be merged if it has failing tests.** If you happen to discover a bug while writing doctests, please fix it.\r\n\r\n_**Please read our [contributing guidelines](https://github.com/TheAlgorithms/Python/blob/master/CONTRIBUTING.md) before you contribute.**_\n", "before_files": [{"content": "def binomial_coefficient(n: int, r: int) -> int:\n \"\"\"\n Find binomial coefficient using pascals triangle.\n\n >>> binomial_coefficient(10, 5)\n 252\n \"\"\"\n c = [0 for i in range(r + 1)]\n # nc0 = 1\n c[0] = 1\n for i in range(1, n + 1):\n # to compute current row from previous row.\n j = min(i, r)\n while j > 0:\n c[j] += c[j - 1]\n j -= 1\n return c[r]\n\n\nprint(binomial_coefficient(n=10, r=5))\n", "path": "maths/binomial_coefficient.py"}], "after_files": [{"content": "def binomial_coefficient(n: int, r: int) -> int:\n \"\"\"\n Find binomial coefficient using Pascal's triangle.\n\n Calculate C(n, r) using Pascal's triangle.\n\n :param n: The total number of items.\n :param r: The number of items to choose.\n :return: The binomial coefficient C(n, r).\n\n >>> binomial_coefficient(10, 5)\n 252\n >>> binomial_coefficient(10, 0)\n 1\n >>> binomial_coefficient(0, 10)\n 1\n >>> binomial_coefficient(10, 10)\n 1\n >>> binomial_coefficient(5, 2)\n 10\n >>> binomial_coefficient(5, 6)\n 0\n >>> binomial_coefficient(3, 5)\n 0\n >>> binomial_coefficient(-2, 3)\n Traceback (most recent call last):\n ...\n ValueError: n and r must be non-negative integers\n >>> binomial_coefficient(5, -1)\n Traceback (most recent call last):\n ...\n ValueError: n and r must be non-negative integers\n >>> binomial_coefficient(10.1, 5)\n Traceback (most recent call last):\n ...\n TypeError: 'float' object cannot be interpreted as an integer\n >>> binomial_coefficient(10, 5.1)\n Traceback (most recent call last):\n ...\n TypeError: 'float' object cannot be interpreted as an integer\n \"\"\"\n if n < 0 or r < 0:\n raise ValueError(\"n and r must be non-negative integers\")\n if 0 in (n, r):\n return 1\n c = [0 for i in range(r + 1)]\n # nc0 = 1\n c[0] = 1\n for i in range(1, n + 1):\n # to compute current row from previous row.\n j = min(i, r)\n while j > 0:\n c[j] += c[j - 1]\n j -= 1\n return c[r]\n\n\nif __name__ == \"__main__\":\n from doctest import testmod\n\n testmod()\n print(binomial_coefficient(n=10, r=5))\n", "path": "maths/binomial_coefficient.py"}]}
| 1,293 | 595 |
gh_patches_debug_16578
|
rasdani/github-patches
|
git_diff
|
doccano__doccano-1668
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Pagination of the project list
When fetching projects in the project list page, is it intentional that all projects are fetched at once even though there is pagination?
Endpoint of project list fetching: `/v1/projects`
When there are a lot of projects, it takes a long time to display them.
Your Environment
---------
doccano v1.5.5
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `backend/api/views/project.py`
Content:
```
1 from django.conf import settings
2 from rest_framework import generics, status
3 from rest_framework.permissions import IsAdminUser, IsAuthenticated
4 from rest_framework.response import Response
5
6 from members.permissions import IsProjectAdmin, IsProjectStaffAndReadOnly
7
8 from ..models import Project
9 from ..serializers import ProjectPolymorphicSerializer
10
11
12 class ProjectList(generics.ListCreateAPIView):
13 serializer_class = ProjectPolymorphicSerializer
14 pagination_class = None
15
16 def get_permissions(self):
17 if self.request.method == 'GET':
18 self.permission_classes = [IsAuthenticated, ]
19 else:
20 self.permission_classes = [IsAuthenticated & IsAdminUser]
21 return super().get_permissions()
22
23 def get_queryset(self):
24 return Project.objects.filter(role_mappings__user=self.request.user)
25
26 def perform_create(self, serializer):
27 serializer.save(created_by=self.request.user)
28
29 def delete(self, request, *args, **kwargs):
30 delete_ids = request.data['ids']
31 projects = Project.objects.filter(
32 role_mappings__user=self.request.user,
33 role_mappings__role__name=settings.ROLE_PROJECT_ADMIN,
34 pk__in=delete_ids
35 )
36 # Todo: I want to use bulk delete.
37 # But it causes the constraint error.
38 # See https://github.com/django-polymorphic/django-polymorphic/issues/229
39 for project in projects:
40 project.delete()
41 return Response(status=status.HTTP_204_NO_CONTENT)
42
43
44 class ProjectDetail(generics.RetrieveUpdateDestroyAPIView):
45 queryset = Project.objects.all()
46 serializer_class = ProjectPolymorphicSerializer
47 lookup_url_kwarg = 'project_id'
48 permission_classes = [IsAuthenticated & (IsProjectAdmin | IsProjectStaffAndReadOnly)]
49
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/backend/api/views/project.py b/backend/api/views/project.py
--- a/backend/api/views/project.py
+++ b/backend/api/views/project.py
@@ -1,5 +1,6 @@
from django.conf import settings
-from rest_framework import generics, status
+from django_filters.rest_framework import DjangoFilterBackend
+from rest_framework import filters, generics, status
from rest_framework.permissions import IsAdminUser, IsAuthenticated
from rest_framework.response import Response
@@ -11,7 +12,8 @@
class ProjectList(generics.ListCreateAPIView):
serializer_class = ProjectPolymorphicSerializer
- pagination_class = None
+ filter_backends = (DjangoFilterBackend, filters.SearchFilter, filters.OrderingFilter)
+ search_fields = ('name', 'description')
def get_permissions(self):
if self.request.method == 'GET':
|
{"golden_diff": "diff --git a/backend/api/views/project.py b/backend/api/views/project.py\n--- a/backend/api/views/project.py\n+++ b/backend/api/views/project.py\n@@ -1,5 +1,6 @@\n from django.conf import settings\n-from rest_framework import generics, status\n+from django_filters.rest_framework import DjangoFilterBackend\n+from rest_framework import filters, generics, status\n from rest_framework.permissions import IsAdminUser, IsAuthenticated\n from rest_framework.response import Response\n \n@@ -11,7 +12,8 @@\n \n class ProjectList(generics.ListCreateAPIView):\n serializer_class = ProjectPolymorphicSerializer\n- pagination_class = None\n+ filter_backends = (DjangoFilterBackend, filters.SearchFilter, filters.OrderingFilter)\n+ search_fields = ('name', 'description')\n \n def get_permissions(self):\n if self.request.method == 'GET':\n", "issue": "Pagination of the project list\nWhen fetching projects in the project list page, is it intentional that all projects are fetched at once even though there is pagination?\r\n\r\nEndpoint of project list fetching: `/v1/projects`\r\n\r\nWhen there are a lot of projects, it takes a long time to display them.\r\n\r\nYour Environment\r\n---------\r\ndoccano v1.5.5\n", "before_files": [{"content": "from django.conf import settings\nfrom rest_framework import generics, status\nfrom rest_framework.permissions import IsAdminUser, IsAuthenticated\nfrom rest_framework.response import Response\n\nfrom members.permissions import IsProjectAdmin, IsProjectStaffAndReadOnly\n\nfrom ..models import Project\nfrom ..serializers import ProjectPolymorphicSerializer\n\n\nclass ProjectList(generics.ListCreateAPIView):\n serializer_class = ProjectPolymorphicSerializer\n pagination_class = None\n\n def get_permissions(self):\n if self.request.method == 'GET':\n self.permission_classes = [IsAuthenticated, ]\n else:\n self.permission_classes = [IsAuthenticated & IsAdminUser]\n return super().get_permissions()\n\n def get_queryset(self):\n return Project.objects.filter(role_mappings__user=self.request.user)\n\n def perform_create(self, serializer):\n serializer.save(created_by=self.request.user)\n\n def delete(self, request, *args, **kwargs):\n delete_ids = request.data['ids']\n projects = Project.objects.filter(\n role_mappings__user=self.request.user,\n role_mappings__role__name=settings.ROLE_PROJECT_ADMIN,\n pk__in=delete_ids\n )\n # Todo: I want to use bulk delete.\n # But it causes the constraint error.\n # See https://github.com/django-polymorphic/django-polymorphic/issues/229\n for project in projects:\n project.delete()\n return Response(status=status.HTTP_204_NO_CONTENT)\n\n\nclass ProjectDetail(generics.RetrieveUpdateDestroyAPIView):\n queryset = Project.objects.all()\n serializer_class = ProjectPolymorphicSerializer\n lookup_url_kwarg = 'project_id'\n permission_classes = [IsAuthenticated & (IsProjectAdmin | IsProjectStaffAndReadOnly)]\n", "path": "backend/api/views/project.py"}], "after_files": [{"content": "from django.conf import settings\nfrom django_filters.rest_framework import DjangoFilterBackend\nfrom rest_framework import filters, generics, status\nfrom rest_framework.permissions import IsAdminUser, IsAuthenticated\nfrom rest_framework.response import Response\n\nfrom members.permissions import IsProjectAdmin, IsProjectStaffAndReadOnly\n\nfrom ..models import Project\nfrom ..serializers import ProjectPolymorphicSerializer\n\n\nclass ProjectList(generics.ListCreateAPIView):\n serializer_class = ProjectPolymorphicSerializer\n filter_backends = (DjangoFilterBackend, filters.SearchFilter, filters.OrderingFilter)\n search_fields = ('name', 'description')\n\n def get_permissions(self):\n if self.request.method == 'GET':\n self.permission_classes = [IsAuthenticated, ]\n else:\n self.permission_classes = [IsAuthenticated & IsAdminUser]\n return super().get_permissions()\n\n def get_queryset(self):\n return Project.objects.filter(role_mappings__user=self.request.user)\n\n def perform_create(self, serializer):\n serializer.save(created_by=self.request.user)\n\n def delete(self, request, *args, **kwargs):\n delete_ids = request.data['ids']\n projects = Project.objects.filter(\n role_mappings__user=self.request.user,\n role_mappings__role__name=settings.ROLE_PROJECT_ADMIN,\n pk__in=delete_ids\n )\n # Todo: I want to use bulk delete.\n # But it causes the constraint error.\n # See https://github.com/django-polymorphic/django-polymorphic/issues/229\n for project in projects:\n project.delete()\n return Response(status=status.HTTP_204_NO_CONTENT)\n\n\nclass ProjectDetail(generics.RetrieveUpdateDestroyAPIView):\n queryset = Project.objects.all()\n serializer_class = ProjectPolymorphicSerializer\n lookup_url_kwarg = 'project_id'\n permission_classes = [IsAuthenticated & (IsProjectAdmin | IsProjectStaffAndReadOnly)]\n", "path": "backend/api/views/project.py"}]}
| 792 | 185 |
gh_patches_debug_38925
|
rasdani/github-patches
|
git_diff
|
sktime__sktime-5942
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[BUG] TDistribution pdf does not consider location/scale
**Describe the bug**
The location/scale (mu/sigma) are not considered at all in methods: pdf, log_pdf, cdf or ppf
For example, the case pdf:
```
def pdf(self, x):
"""Probability density function."""
d = self.loc[x.index, x.columns]
pdf_arr = gamma((d._df + 1) / 2)
pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))
pdf_arr = pdf_arr * (1 + x**2 / d._df) ** (-(d._df + 1) / 2)
return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)
```
Here, in line 6, instead of x**2 one should use ((x - d._mu)/d._sigma)**2
sktime version 0.25.1
[BUG] TDistribution computes incorrectly variance
**Describe the bug**
TDistribution does not use scale (sigma) for variance computation
```
def var(self):
...
df_arr = self._df.copy()
df_arr = df_arr.astype(np.float32)
df_arr[df_arr <= 2] = np.inf
mask = (df_arr > 2) & (df_arr != np.inf)
df_arr[mask] = df_arr[mask] / (df_arr[mask] - 2)
return pd.DataFrame(df_arr, index=self.index, columns=self.columns)
```
one should correct the previous to last line to:
```
df_arr[mask] = self._sigma** 2 * df_arr[mask] / (df_arr[mask] - 2)
```
sktime version 0.25.1
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `sktime/proba/t.py`
Content:
```
1 # copyright: sktime developers, BSD-3-Clause License (see LICENSE file)
2 """Student's t-distribution."""
3
4 __author__ = ["Alex-JG3"]
5
6 import numpy as np
7 import pandas as pd
8 from scipy.special import betaincinv, gamma, hyp2f1, loggamma
9
10 from sktime.proba.base import BaseDistribution
11
12
13 class TDistribution(BaseDistribution):
14 """Student's t-distribution (sktime native).
15
16 Parameters
17 ----------
18 mean : float or array of float (1D or 2D)
19 mean of the t-distribution distribution
20 sd : float or array of float (1D or 2D), must be positive
21 standard deviation of the t-distribution distribution
22 df : float or array of float (1D or 2D), must be positive
23 Degrees of freedom of the t-distribution
24 index : pd.Index, optional, default = RangeIndex
25 columns : pd.Index, optional, default = RangeIndex
26
27 Example
28 -------
29 >>> from sktime.proba.t import TDistribution
30
31 >>> n = TDistribution(mu=[[0, 1], [2, 3], [4, 5]], sigma=1, df=10)
32 """
33
34 _tags = {
35 "authors": ["Alex-JG3"],
36 "maintainers": ["Alex-JG3"],
37 "capabilities:approx": ["pdfnorm", "energy"],
38 "capabilities:exact": ["mean", "var", "pdf", "log_pdf", "cdf", "ppf"],
39 "distr:measuretype": "continuous",
40 }
41
42 def __init__(self, mu, sigma, df=1, index=None, columns=None):
43 self.mu = mu
44 self.sigma = sigma
45 self.df = df
46 self.index = index
47 self.columns = columns
48
49 self._mu, self._sigma, self._df = self._get_bc_params(
50 self.mu, self.sigma, self.df
51 )
52 shape = self._mu.shape
53
54 if index is None:
55 index = pd.RangeIndex(shape[0])
56
57 if columns is None:
58 columns = pd.RangeIndex(shape[1])
59
60 super().__init__(index=index, columns=columns)
61
62 def mean(self):
63 r"""Return expected value of the distribution.
64
65 Let :math:`X` be a random variable with the distribution of `self`.
66 Returns the expectation :math:`\mathbb{E}[X]`. The expectation,
67 :math:`\mathbb{E}[X]`, as infinite if :math:`\nu \le 1`.
68
69 Returns
70 -------
71 pd.DataFrame with same rows, columns as `self`
72 expected value of distribution (entry-wise)
73 """
74 mean_arr = self._mu.copy()
75 if (self._df <= 1).any():
76 mean_arr = mean_arr.astype(np.float32)
77 mean_arr[self._df <= 1] = np.inf
78 return pd.DataFrame(mean_arr, index=self.index, columns=self.columns)
79
80 def var(self):
81 r"""Return element/entry-wise variance of the distribution.
82
83 Let :math:`X` be a random variable with the distribution of `self`.
84 Returns,
85
86 .. math::
87 \mathbb{V}[X] = \begin{cases}
88 \frac{\nu}{\nu - 2} & \text{if} \nu > 2, \\
89 \infty & \text{if} \nu \le 2, \\
90 \begin{cases}
91
92 Where :math:`\nu` is the degrees of freedom of the t-distribution.
93
94 Returns
95 -------
96 pd.DataFrame with same rows, columns as `self`
97 variance of distribution (entry-wise)
98 """
99 df_arr = self._df.copy()
100 df_arr = df_arr.astype(np.float32)
101 df_arr[df_arr <= 2] = np.inf
102 mask = (df_arr > 2) & (df_arr != np.inf)
103 df_arr[mask] = df_arr[mask] / (df_arr[mask] - 2)
104 return pd.DataFrame(df_arr, index=self.index, columns=self.columns)
105
106 def pdf(self, x):
107 """Probability density function."""
108 d = self.loc[x.index, x.columns]
109 pdf_arr = gamma((d._df + 1) / 2)
110 pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))
111 pdf_arr = pdf_arr * (1 + x**2 / d._df) ** (-(d._df + 1) / 2)
112 return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)
113
114 def log_pdf(self, x):
115 """Logarithmic probability density function."""
116 d = self.loc[x.index, x.columns]
117 lpdf_arr = loggamma((d._df + 1) / 2)
118 lpdf_arr = lpdf_arr - 0.5 * np.log(d._df * np.pi)
119 lpdf_arr = lpdf_arr - loggamma(d._df / 2)
120 lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(1 + x**2 / d._df)
121 return pd.DataFrame(lpdf_arr, index=x.index, columns=x.columns)
122
123 def cdf(self, x):
124 """Cumulative distribution function."""
125 d = self.loc[x.index, x.columns]
126 cdf_arr = x * gamma((d._df + 1) / 2)
127 cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x**2) / d._df)
128 cdf_arr = 0.5 + cdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))
129 return pd.DataFrame(cdf_arr, index=x.index, columns=x.columns)
130
131 def ppf(self, p):
132 """Quantile function = percent point function = inverse cdf."""
133 d = self.loc[p.index, p.columns]
134 ppf_arr = p.to_numpy(copy=True)
135 ppf_arr[p.values == 0.5] = 0.0
136 ppf_arr[p.values <= 0] = -np.inf
137 ppf_arr[p.values >= 1] = np.inf
138
139 mask1 = (p.values < 0.5) & (p.values > 0)
140 mask2 = (p.values < 1) & (p.values > 0.5)
141 ppf_arr[mask1] = 1 / betaincinv(0.5 * d._df[mask1], 0.5, 2 * ppf_arr[mask1])
142 ppf_arr[mask2] = 1 / betaincinv(
143 0.5 * d._df[mask2], 0.5, 2 * (1 - ppf_arr[mask2])
144 )
145 ppf_arr[mask1 | mask2] = np.sqrt(ppf_arr[mask1 | mask2] - 1)
146 ppf_arr[mask1 | mask2] = np.sqrt(d._df[mask1 | mask2]) * ppf_arr[mask1 | mask2]
147 ppf_arr[mask1] = -ppf_arr[mask1]
148 return pd.DataFrame(ppf_arr, index=p.index, columns=p.columns)
149
150 @classmethod
151 def get_test_params(cls, parameter_set="default"):
152 """Return testing parameter settings for the estimator."""
153 params1 = {"mu": [[0, 1], [2, 3], [4, 5]], "sigma": 1}
154 params2 = {
155 "mu": 0,
156 "sigma": 1,
157 "index": pd.Index([1, 2, 5]),
158 "columns": pd.Index(["a", "b"]),
159 }
160 return [params1, params2]
161
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/sktime/proba/t.py b/sktime/proba/t.py
--- a/sktime/proba/t.py
+++ b/sktime/proba/t.py
@@ -100,7 +100,7 @@
df_arr = df_arr.astype(np.float32)
df_arr[df_arr <= 2] = np.inf
mask = (df_arr > 2) & (df_arr != np.inf)
- df_arr[mask] = df_arr[mask] / (df_arr[mask] - 2)
+ df_arr[mask] = self._sigma[mask] ** 2 * df_arr[mask] / (df_arr[mask] - 2)
return pd.DataFrame(df_arr, index=self.index, columns=self.columns)
def pdf(self, x):
@@ -108,7 +108,10 @@
d = self.loc[x.index, x.columns]
pdf_arr = gamma((d._df + 1) / 2)
pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))
- pdf_arr = pdf_arr * (1 + x**2 / d._df) ** (-(d._df + 1) / 2)
+ pdf_arr = pdf_arr * (1 + ((x - d._mu) / d._sigma) ** 2 / d._df) ** (
+ -(d._df + 1) / 2
+ )
+ pdf_arr = pdf_arr / d._sigma
return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)
def log_pdf(self, x):
@@ -117,14 +120,18 @@
lpdf_arr = loggamma((d._df + 1) / 2)
lpdf_arr = lpdf_arr - 0.5 * np.log(d._df * np.pi)
lpdf_arr = lpdf_arr - loggamma(d._df / 2)
- lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(1 + x**2 / d._df)
+ lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(
+ 1 + ((x - d._mu) / d._sigma) ** 2 / d._df
+ )
+ lpdf_arr = lpdf_arr - np.log(d._sigma)
return pd.DataFrame(lpdf_arr, index=x.index, columns=x.columns)
def cdf(self, x):
"""Cumulative distribution function."""
d = self.loc[x.index, x.columns]
- cdf_arr = x * gamma((d._df + 1) / 2)
- cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x**2) / d._df)
+ x_ = (x - d._mu) / d._sigma
+ cdf_arr = x_ * gamma((d._df + 1) / 2)
+ cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x_**2) / d._df)
cdf_arr = 0.5 + cdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))
return pd.DataFrame(cdf_arr, index=x.index, columns=x.columns)
@@ -145,6 +152,7 @@
ppf_arr[mask1 | mask2] = np.sqrt(ppf_arr[mask1 | mask2] - 1)
ppf_arr[mask1 | mask2] = np.sqrt(d._df[mask1 | mask2]) * ppf_arr[mask1 | mask2]
ppf_arr[mask1] = -ppf_arr[mask1]
+ ppf_arr = d._sigma * ppf_arr + d._mu
return pd.DataFrame(ppf_arr, index=p.index, columns=p.columns)
@classmethod
|
{"golden_diff": "diff --git a/sktime/proba/t.py b/sktime/proba/t.py\n--- a/sktime/proba/t.py\n+++ b/sktime/proba/t.py\n@@ -100,7 +100,7 @@\n df_arr = df_arr.astype(np.float32)\n df_arr[df_arr <= 2] = np.inf\n mask = (df_arr > 2) & (df_arr != np.inf)\n- df_arr[mask] = df_arr[mask] / (df_arr[mask] - 2)\n+ df_arr[mask] = self._sigma[mask] ** 2 * df_arr[mask] / (df_arr[mask] - 2)\n return pd.DataFrame(df_arr, index=self.index, columns=self.columns)\n \n def pdf(self, x):\n@@ -108,7 +108,10 @@\n d = self.loc[x.index, x.columns]\n pdf_arr = gamma((d._df + 1) / 2)\n pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\n- pdf_arr = pdf_arr * (1 + x**2 / d._df) ** (-(d._df + 1) / 2)\n+ pdf_arr = pdf_arr * (1 + ((x - d._mu) / d._sigma) ** 2 / d._df) ** (\n+ -(d._df + 1) / 2\n+ )\n+ pdf_arr = pdf_arr / d._sigma\n return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)\n \n def log_pdf(self, x):\n@@ -117,14 +120,18 @@\n lpdf_arr = loggamma((d._df + 1) / 2)\n lpdf_arr = lpdf_arr - 0.5 * np.log(d._df * np.pi)\n lpdf_arr = lpdf_arr - loggamma(d._df / 2)\n- lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(1 + x**2 / d._df)\n+ lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(\n+ 1 + ((x - d._mu) / d._sigma) ** 2 / d._df\n+ )\n+ lpdf_arr = lpdf_arr - np.log(d._sigma)\n return pd.DataFrame(lpdf_arr, index=x.index, columns=x.columns)\n \n def cdf(self, x):\n \"\"\"Cumulative distribution function.\"\"\"\n d = self.loc[x.index, x.columns]\n- cdf_arr = x * gamma((d._df + 1) / 2)\n- cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x**2) / d._df)\n+ x_ = (x - d._mu) / d._sigma\n+ cdf_arr = x_ * gamma((d._df + 1) / 2)\n+ cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x_**2) / d._df)\n cdf_arr = 0.5 + cdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\n return pd.DataFrame(cdf_arr, index=x.index, columns=x.columns)\n \n@@ -145,6 +152,7 @@\n ppf_arr[mask1 | mask2] = np.sqrt(ppf_arr[mask1 | mask2] - 1)\n ppf_arr[mask1 | mask2] = np.sqrt(d._df[mask1 | mask2]) * ppf_arr[mask1 | mask2]\n ppf_arr[mask1] = -ppf_arr[mask1]\n+ ppf_arr = d._sigma * ppf_arr + d._mu\n return pd.DataFrame(ppf_arr, index=p.index, columns=p.columns)\n \n @classmethod\n", "issue": "[BUG] TDistribution pdf does not consider location/scale\n**Describe the bug**\r\nThe location/scale (mu/sigma) are not considered at all in methods: pdf, log_pdf, cdf or ppf\r\n\r\nFor example, the case pdf:\r\n\r\n``` \r\ndef pdf(self, x):\r\n \"\"\"Probability density function.\"\"\"\r\n d = self.loc[x.index, x.columns]\r\n pdf_arr = gamma((d._df + 1) / 2)\r\n pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\r\n pdf_arr = pdf_arr * (1 + x**2 / d._df) ** (-(d._df + 1) / 2)\r\n return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)\r\n```\r\n\r\nHere, in line 6, instead of x**2 one should use ((x - d._mu)/d._sigma)**2\r\n\r\n\r\nsktime version 0.25.1\r\n\r\n\n[BUG] TDistribution computes incorrectly variance \n**Describe the bug**\r\n\r\nTDistribution does not use scale (sigma) for variance computation\r\n\r\n``` \r\ndef var(self):\r\n...\r\n df_arr = self._df.copy()\r\n df_arr = df_arr.astype(np.float32)\r\n df_arr[df_arr <= 2] = np.inf\r\n mask = (df_arr > 2) & (df_arr != np.inf)\r\n df_arr[mask] = df_arr[mask] / (df_arr[mask] - 2)\r\n return pd.DataFrame(df_arr, index=self.index, columns=self.columns)\r\n```\r\n\r\none should correct the previous to last line to:\r\n\r\n```\r\ndf_arr[mask] = self._sigma** 2 * df_arr[mask] / (df_arr[mask] - 2)\r\n```\r\n\r\nsktime version 0.25.1\n", "before_files": [{"content": "# copyright: sktime developers, BSD-3-Clause License (see LICENSE file)\n\"\"\"Student's t-distribution.\"\"\"\n\n__author__ = [\"Alex-JG3\"]\n\nimport numpy as np\nimport pandas as pd\nfrom scipy.special import betaincinv, gamma, hyp2f1, loggamma\n\nfrom sktime.proba.base import BaseDistribution\n\n\nclass TDistribution(BaseDistribution):\n \"\"\"Student's t-distribution (sktime native).\n\n Parameters\n ----------\n mean : float or array of float (1D or 2D)\n mean of the t-distribution distribution\n sd : float or array of float (1D or 2D), must be positive\n standard deviation of the t-distribution distribution\n df : float or array of float (1D or 2D), must be positive\n Degrees of freedom of the t-distribution\n index : pd.Index, optional, default = RangeIndex\n columns : pd.Index, optional, default = RangeIndex\n\n Example\n -------\n >>> from sktime.proba.t import TDistribution\n\n >>> n = TDistribution(mu=[[0, 1], [2, 3], [4, 5]], sigma=1, df=10)\n \"\"\"\n\n _tags = {\n \"authors\": [\"Alex-JG3\"],\n \"maintainers\": [\"Alex-JG3\"],\n \"capabilities:approx\": [\"pdfnorm\", \"energy\"],\n \"capabilities:exact\": [\"mean\", \"var\", \"pdf\", \"log_pdf\", \"cdf\", \"ppf\"],\n \"distr:measuretype\": \"continuous\",\n }\n\n def __init__(self, mu, sigma, df=1, index=None, columns=None):\n self.mu = mu\n self.sigma = sigma\n self.df = df\n self.index = index\n self.columns = columns\n\n self._mu, self._sigma, self._df = self._get_bc_params(\n self.mu, self.sigma, self.df\n )\n shape = self._mu.shape\n\n if index is None:\n index = pd.RangeIndex(shape[0])\n\n if columns is None:\n columns = pd.RangeIndex(shape[1])\n\n super().__init__(index=index, columns=columns)\n\n def mean(self):\n r\"\"\"Return expected value of the distribution.\n\n Let :math:`X` be a random variable with the distribution of `self`.\n Returns the expectation :math:`\\mathbb{E}[X]`. The expectation,\n :math:`\\mathbb{E}[X]`, as infinite if :math:`\\nu \\le 1`.\n\n Returns\n -------\n pd.DataFrame with same rows, columns as `self`\n expected value of distribution (entry-wise)\n \"\"\"\n mean_arr = self._mu.copy()\n if (self._df <= 1).any():\n mean_arr = mean_arr.astype(np.float32)\n mean_arr[self._df <= 1] = np.inf\n return pd.DataFrame(mean_arr, index=self.index, columns=self.columns)\n\n def var(self):\n r\"\"\"Return element/entry-wise variance of the distribution.\n\n Let :math:`X` be a random variable with the distribution of `self`.\n Returns,\n\n .. math::\n \\mathbb{V}[X] = \\begin{cases}\n \\frac{\\nu}{\\nu - 2} & \\text{if} \\nu > 2, \\\\\n \\infty & \\text{if} \\nu \\le 2, \\\\\n \\begin{cases}\n\n Where :math:`\\nu` is the degrees of freedom of the t-distribution.\n\n Returns\n -------\n pd.DataFrame with same rows, columns as `self`\n variance of distribution (entry-wise)\n \"\"\"\n df_arr = self._df.copy()\n df_arr = df_arr.astype(np.float32)\n df_arr[df_arr <= 2] = np.inf\n mask = (df_arr > 2) & (df_arr != np.inf)\n df_arr[mask] = df_arr[mask] / (df_arr[mask] - 2)\n return pd.DataFrame(df_arr, index=self.index, columns=self.columns)\n\n def pdf(self, x):\n \"\"\"Probability density function.\"\"\"\n d = self.loc[x.index, x.columns]\n pdf_arr = gamma((d._df + 1) / 2)\n pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\n pdf_arr = pdf_arr * (1 + x**2 / d._df) ** (-(d._df + 1) / 2)\n return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)\n\n def log_pdf(self, x):\n \"\"\"Logarithmic probability density function.\"\"\"\n d = self.loc[x.index, x.columns]\n lpdf_arr = loggamma((d._df + 1) / 2)\n lpdf_arr = lpdf_arr - 0.5 * np.log(d._df * np.pi)\n lpdf_arr = lpdf_arr - loggamma(d._df / 2)\n lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(1 + x**2 / d._df)\n return pd.DataFrame(lpdf_arr, index=x.index, columns=x.columns)\n\n def cdf(self, x):\n \"\"\"Cumulative distribution function.\"\"\"\n d = self.loc[x.index, x.columns]\n cdf_arr = x * gamma((d._df + 1) / 2)\n cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x**2) / d._df)\n cdf_arr = 0.5 + cdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\n return pd.DataFrame(cdf_arr, index=x.index, columns=x.columns)\n\n def ppf(self, p):\n \"\"\"Quantile function = percent point function = inverse cdf.\"\"\"\n d = self.loc[p.index, p.columns]\n ppf_arr = p.to_numpy(copy=True)\n ppf_arr[p.values == 0.5] = 0.0\n ppf_arr[p.values <= 0] = -np.inf\n ppf_arr[p.values >= 1] = np.inf\n\n mask1 = (p.values < 0.5) & (p.values > 0)\n mask2 = (p.values < 1) & (p.values > 0.5)\n ppf_arr[mask1] = 1 / betaincinv(0.5 * d._df[mask1], 0.5, 2 * ppf_arr[mask1])\n ppf_arr[mask2] = 1 / betaincinv(\n 0.5 * d._df[mask2], 0.5, 2 * (1 - ppf_arr[mask2])\n )\n ppf_arr[mask1 | mask2] = np.sqrt(ppf_arr[mask1 | mask2] - 1)\n ppf_arr[mask1 | mask2] = np.sqrt(d._df[mask1 | mask2]) * ppf_arr[mask1 | mask2]\n ppf_arr[mask1] = -ppf_arr[mask1]\n return pd.DataFrame(ppf_arr, index=p.index, columns=p.columns)\n\n @classmethod\n def get_test_params(cls, parameter_set=\"default\"):\n \"\"\"Return testing parameter settings for the estimator.\"\"\"\n params1 = {\"mu\": [[0, 1], [2, 3], [4, 5]], \"sigma\": 1}\n params2 = {\n \"mu\": 0,\n \"sigma\": 1,\n \"index\": pd.Index([1, 2, 5]),\n \"columns\": pd.Index([\"a\", \"b\"]),\n }\n return [params1, params2]\n", "path": "sktime/proba/t.py"}], "after_files": [{"content": "# copyright: sktime developers, BSD-3-Clause License (see LICENSE file)\n\"\"\"Student's t-distribution.\"\"\"\n\n__author__ = [\"Alex-JG3\"]\n\nimport numpy as np\nimport pandas as pd\nfrom scipy.special import betaincinv, gamma, hyp2f1, loggamma\n\nfrom sktime.proba.base import BaseDistribution\n\n\nclass TDistribution(BaseDistribution):\n \"\"\"Student's t-distribution (sktime native).\n\n Parameters\n ----------\n mean : float or array of float (1D or 2D)\n mean of the t-distribution distribution\n sd : float or array of float (1D or 2D), must be positive\n standard deviation of the t-distribution distribution\n df : float or array of float (1D or 2D), must be positive\n Degrees of freedom of the t-distribution\n index : pd.Index, optional, default = RangeIndex\n columns : pd.Index, optional, default = RangeIndex\n\n Example\n -------\n >>> from sktime.proba.t import TDistribution\n\n >>> n = TDistribution(mu=[[0, 1], [2, 3], [4, 5]], sigma=1, df=10)\n \"\"\"\n\n _tags = {\n \"authors\": [\"Alex-JG3\"],\n \"maintainers\": [\"Alex-JG3\"],\n \"capabilities:approx\": [\"pdfnorm\", \"energy\"],\n \"capabilities:exact\": [\"mean\", \"var\", \"pdf\", \"log_pdf\", \"cdf\", \"ppf\"],\n \"distr:measuretype\": \"continuous\",\n }\n\n def __init__(self, mu, sigma, df=1, index=None, columns=None):\n self.mu = mu\n self.sigma = sigma\n self.df = df\n self.index = index\n self.columns = columns\n\n self._mu, self._sigma, self._df = self._get_bc_params(\n self.mu, self.sigma, self.df\n )\n shape = self._mu.shape\n\n if index is None:\n index = pd.RangeIndex(shape[0])\n\n if columns is None:\n columns = pd.RangeIndex(shape[1])\n\n super().__init__(index=index, columns=columns)\n\n def mean(self):\n r\"\"\"Return expected value of the distribution.\n\n Let :math:`X` be a random variable with the distribution of `self`.\n Returns the expectation :math:`\\mathbb{E}[X]`. The expectation,\n :math:`\\mathbb{E}[X]`, as infinite if :math:`\\nu \\le 1`.\n\n Returns\n -------\n pd.DataFrame with same rows, columns as `self`\n expected value of distribution (entry-wise)\n \"\"\"\n mean_arr = self._mu.copy()\n if (self._df <= 1).any():\n mean_arr = mean_arr.astype(np.float32)\n mean_arr[self._df <= 1] = np.inf\n return pd.DataFrame(mean_arr, index=self.index, columns=self.columns)\n\n def var(self):\n r\"\"\"Return element/entry-wise variance of the distribution.\n\n Let :math:`X` be a random variable with the distribution of `self`.\n Returns,\n\n .. math::\n \\mathbb{V}[X] = \\begin{cases}\n \\frac{\\nu}{\\nu - 2} & \\text{if} \\nu > 2, \\\\\n \\infty & \\text{if} \\nu \\le 2, \\\\\n \\begin{cases}\n\n Where :math:`\\nu` is the degrees of freedom of the t-distribution.\n\n Returns\n -------\n pd.DataFrame with same rows, columns as `self`\n variance of distribution (entry-wise)\n \"\"\"\n df_arr = self._df.copy()\n df_arr = df_arr.astype(np.float32)\n df_arr[df_arr <= 2] = np.inf\n mask = (df_arr > 2) & (df_arr != np.inf)\n df_arr[mask] = self._sigma[mask] ** 2 * df_arr[mask] / (df_arr[mask] - 2)\n return pd.DataFrame(df_arr, index=self.index, columns=self.columns)\n\n def pdf(self, x):\n \"\"\"Probability density function.\"\"\"\n d = self.loc[x.index, x.columns]\n pdf_arr = gamma((d._df + 1) / 2)\n pdf_arr = pdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\n pdf_arr = pdf_arr * (1 + ((x - d._mu) / d._sigma) ** 2 / d._df) ** (\n -(d._df + 1) / 2\n )\n pdf_arr = pdf_arr / d._sigma\n return pd.DataFrame(pdf_arr, index=x.index, columns=x.columns)\n\n def log_pdf(self, x):\n \"\"\"Logarithmic probability density function.\"\"\"\n d = self.loc[x.index, x.columns]\n lpdf_arr = loggamma((d._df + 1) / 2)\n lpdf_arr = lpdf_arr - 0.5 * np.log(d._df * np.pi)\n lpdf_arr = lpdf_arr - loggamma(d._df / 2)\n lpdf_arr = lpdf_arr - ((d._df + 1) / 2) * np.log(\n 1 + ((x - d._mu) / d._sigma) ** 2 / d._df\n )\n lpdf_arr = lpdf_arr - np.log(d._sigma)\n return pd.DataFrame(lpdf_arr, index=x.index, columns=x.columns)\n\n def cdf(self, x):\n \"\"\"Cumulative distribution function.\"\"\"\n d = self.loc[x.index, x.columns]\n x_ = (x - d._mu) / d._sigma\n cdf_arr = x_ * gamma((d._df + 1) / 2)\n cdf_arr = cdf_arr * hyp2f1(0.5, (d._df + 1) / 2, 3 / 2, -(x_**2) / d._df)\n cdf_arr = 0.5 + cdf_arr / (np.sqrt(np.pi * d._df) * gamma(d._df / 2))\n return pd.DataFrame(cdf_arr, index=x.index, columns=x.columns)\n\n def ppf(self, p):\n \"\"\"Quantile function = percent point function = inverse cdf.\"\"\"\n d = self.loc[p.index, p.columns]\n ppf_arr = p.to_numpy(copy=True)\n ppf_arr[p.values == 0.5] = 0.0\n ppf_arr[p.values <= 0] = -np.inf\n ppf_arr[p.values >= 1] = np.inf\n\n mask1 = (p.values < 0.5) & (p.values > 0)\n mask2 = (p.values < 1) & (p.values > 0.5)\n ppf_arr[mask1] = 1 / betaincinv(0.5 * d._df[mask1], 0.5, 2 * ppf_arr[mask1])\n ppf_arr[mask2] = 1 / betaincinv(\n 0.5 * d._df[mask2], 0.5, 2 * (1 - ppf_arr[mask2])\n )\n ppf_arr[mask1 | mask2] = np.sqrt(ppf_arr[mask1 | mask2] - 1)\n ppf_arr[mask1 | mask2] = np.sqrt(d._df[mask1 | mask2]) * ppf_arr[mask1 | mask2]\n ppf_arr[mask1] = -ppf_arr[mask1]\n ppf_arr = d._sigma * ppf_arr + d._mu\n return pd.DataFrame(ppf_arr, index=p.index, columns=p.columns)\n\n @classmethod\n def get_test_params(cls, parameter_set=\"default\"):\n \"\"\"Return testing parameter settings for the estimator.\"\"\"\n params1 = {\"mu\": [[0, 1], [2, 3], [4, 5]], \"sigma\": 1}\n params2 = {\n \"mu\": 0,\n \"sigma\": 1,\n \"index\": pd.Index([1, 2, 5]),\n \"columns\": pd.Index([\"a\", \"b\"]),\n }\n return [params1, params2]\n", "path": "sktime/proba/t.py"}]}
| 2,747 | 915 |
gh_patches_debug_27773
|
rasdani/github-patches
|
git_diff
|
pypa__pip-12569
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Show 'home-page' project URL when Home-Page metadata value is not set
### What's the problem this feature will solve?
When installing a pyproject.toml-only project, the `Home-Page` metadata won't be set (as there's no way to specify it: PEP 621 only maps to `Project-Url`). This means `pip show` won't provide any URL to the user.
### Describe the solution you'd like
If `Home-Page` is not set, instead select one of the project URLs (if present), with the following order of preference:
* Home-page
* Homepage
* homepage
* Source
* fallback: the first project-URL in the metadata
### Alternative Solutions
`pip show -v` shows all project URLs, but that still shows an empty `Home-page:` field
### Additional context
Project URLs were included in `pip show -v` in #10827
### Code of Conduct
- [X] I agree to follow the [PSF Code of Conduct](https://www.python.org/psf/conduct/).
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/pip/_internal/commands/show.py`
Content:
```
1 import logging
2 from optparse import Values
3 from typing import Generator, Iterable, Iterator, List, NamedTuple, Optional
4
5 from pip._vendor.packaging.utils import canonicalize_name
6
7 from pip._internal.cli.base_command import Command
8 from pip._internal.cli.status_codes import ERROR, SUCCESS
9 from pip._internal.metadata import BaseDistribution, get_default_environment
10 from pip._internal.utils.misc import write_output
11
12 logger = logging.getLogger(__name__)
13
14
15 class ShowCommand(Command):
16 """
17 Show information about one or more installed packages.
18
19 The output is in RFC-compliant mail header format.
20 """
21
22 usage = """
23 %prog [options] <package> ..."""
24 ignore_require_venv = True
25
26 def add_options(self) -> None:
27 self.cmd_opts.add_option(
28 "-f",
29 "--files",
30 dest="files",
31 action="store_true",
32 default=False,
33 help="Show the full list of installed files for each package.",
34 )
35
36 self.parser.insert_option_group(0, self.cmd_opts)
37
38 def run(self, options: Values, args: List[str]) -> int:
39 if not args:
40 logger.warning("ERROR: Please provide a package name or names.")
41 return ERROR
42 query = args
43
44 results = search_packages_info(query)
45 if not print_results(
46 results, list_files=options.files, verbose=options.verbose
47 ):
48 return ERROR
49 return SUCCESS
50
51
52 class _PackageInfo(NamedTuple):
53 name: str
54 version: str
55 location: str
56 editable_project_location: Optional[str]
57 requires: List[str]
58 required_by: List[str]
59 installer: str
60 metadata_version: str
61 classifiers: List[str]
62 summary: str
63 homepage: str
64 project_urls: List[str]
65 author: str
66 author_email: str
67 license: str
68 entry_points: List[str]
69 files: Optional[List[str]]
70
71
72 def search_packages_info(query: List[str]) -> Generator[_PackageInfo, None, None]:
73 """
74 Gather details from installed distributions. Print distribution name,
75 version, location, and installed files. Installed files requires a
76 pip generated 'installed-files.txt' in the distributions '.egg-info'
77 directory.
78 """
79 env = get_default_environment()
80
81 installed = {dist.canonical_name: dist for dist in env.iter_all_distributions()}
82 query_names = [canonicalize_name(name) for name in query]
83 missing = sorted(
84 [name for name, pkg in zip(query, query_names) if pkg not in installed]
85 )
86 if missing:
87 logger.warning("Package(s) not found: %s", ", ".join(missing))
88
89 def _get_requiring_packages(current_dist: BaseDistribution) -> Iterator[str]:
90 return (
91 dist.metadata["Name"] or "UNKNOWN"
92 for dist in installed.values()
93 if current_dist.canonical_name
94 in {canonicalize_name(d.name) for d in dist.iter_dependencies()}
95 )
96
97 for query_name in query_names:
98 try:
99 dist = installed[query_name]
100 except KeyError:
101 continue
102
103 requires = sorted(
104 # Avoid duplicates in requirements (e.g. due to environment markers).
105 {req.name for req in dist.iter_dependencies()},
106 key=str.lower,
107 )
108 required_by = sorted(_get_requiring_packages(dist), key=str.lower)
109
110 try:
111 entry_points_text = dist.read_text("entry_points.txt")
112 entry_points = entry_points_text.splitlines(keepends=False)
113 except FileNotFoundError:
114 entry_points = []
115
116 files_iter = dist.iter_declared_entries()
117 if files_iter is None:
118 files: Optional[List[str]] = None
119 else:
120 files = sorted(files_iter)
121
122 metadata = dist.metadata
123
124 yield _PackageInfo(
125 name=dist.raw_name,
126 version=str(dist.version),
127 location=dist.location or "",
128 editable_project_location=dist.editable_project_location,
129 requires=requires,
130 required_by=required_by,
131 installer=dist.installer,
132 metadata_version=dist.metadata_version or "",
133 classifiers=metadata.get_all("Classifier", []),
134 summary=metadata.get("Summary", ""),
135 homepage=metadata.get("Home-page", ""),
136 project_urls=metadata.get_all("Project-URL", []),
137 author=metadata.get("Author", ""),
138 author_email=metadata.get("Author-email", ""),
139 license=metadata.get("License", ""),
140 entry_points=entry_points,
141 files=files,
142 )
143
144
145 def print_results(
146 distributions: Iterable[_PackageInfo],
147 list_files: bool,
148 verbose: bool,
149 ) -> bool:
150 """
151 Print the information from installed distributions found.
152 """
153 results_printed = False
154 for i, dist in enumerate(distributions):
155 results_printed = True
156 if i > 0:
157 write_output("---")
158
159 write_output("Name: %s", dist.name)
160 write_output("Version: %s", dist.version)
161 write_output("Summary: %s", dist.summary)
162 write_output("Home-page: %s", dist.homepage)
163 write_output("Author: %s", dist.author)
164 write_output("Author-email: %s", dist.author_email)
165 write_output("License: %s", dist.license)
166 write_output("Location: %s", dist.location)
167 if dist.editable_project_location is not None:
168 write_output(
169 "Editable project location: %s", dist.editable_project_location
170 )
171 write_output("Requires: %s", ", ".join(dist.requires))
172 write_output("Required-by: %s", ", ".join(dist.required_by))
173
174 if verbose:
175 write_output("Metadata-Version: %s", dist.metadata_version)
176 write_output("Installer: %s", dist.installer)
177 write_output("Classifiers:")
178 for classifier in dist.classifiers:
179 write_output(" %s", classifier)
180 write_output("Entry-points:")
181 for entry in dist.entry_points:
182 write_output(" %s", entry.strip())
183 write_output("Project-URLs:")
184 for project_url in dist.project_urls:
185 write_output(" %s", project_url)
186 if list_files:
187 write_output("Files:")
188 if dist.files is None:
189 write_output("Cannot locate RECORD or installed-files.txt")
190 else:
191 for line in dist.files:
192 write_output(" %s", line.strip())
193 return results_printed
194
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/pip/_internal/commands/show.py b/src/pip/_internal/commands/show.py
--- a/src/pip/_internal/commands/show.py
+++ b/src/pip/_internal/commands/show.py
@@ -121,6 +121,22 @@
metadata = dist.metadata
+ project_urls = metadata.get_all("Project-URL", [])
+ homepage = metadata.get("Home-page", "")
+ if not homepage:
+ # It's common that there is a "homepage" Project-URL, but Home-page
+ # remains unset (especially as PEP 621 doesn't surface the field).
+ #
+ # This logic was taken from PyPI's codebase.
+ for url in project_urls:
+ url_label, url = url.split(",", maxsplit=1)
+ normalized_label = (
+ url_label.casefold().replace("-", "").replace("_", "").strip()
+ )
+ if normalized_label == "homepage":
+ homepage = url.strip()
+ break
+
yield _PackageInfo(
name=dist.raw_name,
version=str(dist.version),
@@ -132,8 +148,8 @@
metadata_version=dist.metadata_version or "",
classifiers=metadata.get_all("Classifier", []),
summary=metadata.get("Summary", ""),
- homepage=metadata.get("Home-page", ""),
- project_urls=metadata.get_all("Project-URL", []),
+ homepage=homepage,
+ project_urls=project_urls,
author=metadata.get("Author", ""),
author_email=metadata.get("Author-email", ""),
license=metadata.get("License", ""),
|
{"golden_diff": "diff --git a/src/pip/_internal/commands/show.py b/src/pip/_internal/commands/show.py\n--- a/src/pip/_internal/commands/show.py\n+++ b/src/pip/_internal/commands/show.py\n@@ -121,6 +121,22 @@\n \n metadata = dist.metadata\n \n+ project_urls = metadata.get_all(\"Project-URL\", [])\n+ homepage = metadata.get(\"Home-page\", \"\")\n+ if not homepage:\n+ # It's common that there is a \"homepage\" Project-URL, but Home-page\n+ # remains unset (especially as PEP 621 doesn't surface the field).\n+ #\n+ # This logic was taken from PyPI's codebase.\n+ for url in project_urls:\n+ url_label, url = url.split(\",\", maxsplit=1)\n+ normalized_label = (\n+ url_label.casefold().replace(\"-\", \"\").replace(\"_\", \"\").strip()\n+ )\n+ if normalized_label == \"homepage\":\n+ homepage = url.strip()\n+ break\n+\n yield _PackageInfo(\n name=dist.raw_name,\n version=str(dist.version),\n@@ -132,8 +148,8 @@\n metadata_version=dist.metadata_version or \"\",\n classifiers=metadata.get_all(\"Classifier\", []),\n summary=metadata.get(\"Summary\", \"\"),\n- homepage=metadata.get(\"Home-page\", \"\"),\n- project_urls=metadata.get_all(\"Project-URL\", []),\n+ homepage=homepage,\n+ project_urls=project_urls,\n author=metadata.get(\"Author\", \"\"),\n author_email=metadata.get(\"Author-email\", \"\"),\n license=metadata.get(\"License\", \"\"),\n", "issue": "Show 'home-page' project URL when Home-Page metadata value is not set\n### What's the problem this feature will solve?\n\nWhen installing a pyproject.toml-only project, the `Home-Page` metadata won't be set (as there's no way to specify it: PEP 621 only maps to `Project-Url`). This means `pip show` won't provide any URL to the user.\n\n### Describe the solution you'd like\n\nIf `Home-Page` is not set, instead select one of the project URLs (if present), with the following order of preference:\r\n* Home-page\r\n* Homepage\r\n* homepage\r\n* Source\r\n* fallback: the first project-URL in the metadata\n\n### Alternative Solutions\n\n`pip show -v` shows all project URLs, but that still shows an empty `Home-page:` field\n\n### Additional context\n\nProject URLs were included in `pip show -v` in #10827\n\n### Code of Conduct\n\n- [X] I agree to follow the [PSF Code of Conduct](https://www.python.org/psf/conduct/).\n", "before_files": [{"content": "import logging\nfrom optparse import Values\nfrom typing import Generator, Iterable, Iterator, List, NamedTuple, Optional\n\nfrom pip._vendor.packaging.utils import canonicalize_name\n\nfrom pip._internal.cli.base_command import Command\nfrom pip._internal.cli.status_codes import ERROR, SUCCESS\nfrom pip._internal.metadata import BaseDistribution, get_default_environment\nfrom pip._internal.utils.misc import write_output\n\nlogger = logging.getLogger(__name__)\n\n\nclass ShowCommand(Command):\n \"\"\"\n Show information about one or more installed packages.\n\n The output is in RFC-compliant mail header format.\n \"\"\"\n\n usage = \"\"\"\n %prog [options] <package> ...\"\"\"\n ignore_require_venv = True\n\n def add_options(self) -> None:\n self.cmd_opts.add_option(\n \"-f\",\n \"--files\",\n dest=\"files\",\n action=\"store_true\",\n default=False,\n help=\"Show the full list of installed files for each package.\",\n )\n\n self.parser.insert_option_group(0, self.cmd_opts)\n\n def run(self, options: Values, args: List[str]) -> int:\n if not args:\n logger.warning(\"ERROR: Please provide a package name or names.\")\n return ERROR\n query = args\n\n results = search_packages_info(query)\n if not print_results(\n results, list_files=options.files, verbose=options.verbose\n ):\n return ERROR\n return SUCCESS\n\n\nclass _PackageInfo(NamedTuple):\n name: str\n version: str\n location: str\n editable_project_location: Optional[str]\n requires: List[str]\n required_by: List[str]\n installer: str\n metadata_version: str\n classifiers: List[str]\n summary: str\n homepage: str\n project_urls: List[str]\n author: str\n author_email: str\n license: str\n entry_points: List[str]\n files: Optional[List[str]]\n\n\ndef search_packages_info(query: List[str]) -> Generator[_PackageInfo, None, None]:\n \"\"\"\n Gather details from installed distributions. Print distribution name,\n version, location, and installed files. Installed files requires a\n pip generated 'installed-files.txt' in the distributions '.egg-info'\n directory.\n \"\"\"\n env = get_default_environment()\n\n installed = {dist.canonical_name: dist for dist in env.iter_all_distributions()}\n query_names = [canonicalize_name(name) for name in query]\n missing = sorted(\n [name for name, pkg in zip(query, query_names) if pkg not in installed]\n )\n if missing:\n logger.warning(\"Package(s) not found: %s\", \", \".join(missing))\n\n def _get_requiring_packages(current_dist: BaseDistribution) -> Iterator[str]:\n return (\n dist.metadata[\"Name\"] or \"UNKNOWN\"\n for dist in installed.values()\n if current_dist.canonical_name\n in {canonicalize_name(d.name) for d in dist.iter_dependencies()}\n )\n\n for query_name in query_names:\n try:\n dist = installed[query_name]\n except KeyError:\n continue\n\n requires = sorted(\n # Avoid duplicates in requirements (e.g. due to environment markers).\n {req.name for req in dist.iter_dependencies()},\n key=str.lower,\n )\n required_by = sorted(_get_requiring_packages(dist), key=str.lower)\n\n try:\n entry_points_text = dist.read_text(\"entry_points.txt\")\n entry_points = entry_points_text.splitlines(keepends=False)\n except FileNotFoundError:\n entry_points = []\n\n files_iter = dist.iter_declared_entries()\n if files_iter is None:\n files: Optional[List[str]] = None\n else:\n files = sorted(files_iter)\n\n metadata = dist.metadata\n\n yield _PackageInfo(\n name=dist.raw_name,\n version=str(dist.version),\n location=dist.location or \"\",\n editable_project_location=dist.editable_project_location,\n requires=requires,\n required_by=required_by,\n installer=dist.installer,\n metadata_version=dist.metadata_version or \"\",\n classifiers=metadata.get_all(\"Classifier\", []),\n summary=metadata.get(\"Summary\", \"\"),\n homepage=metadata.get(\"Home-page\", \"\"),\n project_urls=metadata.get_all(\"Project-URL\", []),\n author=metadata.get(\"Author\", \"\"),\n author_email=metadata.get(\"Author-email\", \"\"),\n license=metadata.get(\"License\", \"\"),\n entry_points=entry_points,\n files=files,\n )\n\n\ndef print_results(\n distributions: Iterable[_PackageInfo],\n list_files: bool,\n verbose: bool,\n) -> bool:\n \"\"\"\n Print the information from installed distributions found.\n \"\"\"\n results_printed = False\n for i, dist in enumerate(distributions):\n results_printed = True\n if i > 0:\n write_output(\"---\")\n\n write_output(\"Name: %s\", dist.name)\n write_output(\"Version: %s\", dist.version)\n write_output(\"Summary: %s\", dist.summary)\n write_output(\"Home-page: %s\", dist.homepage)\n write_output(\"Author: %s\", dist.author)\n write_output(\"Author-email: %s\", dist.author_email)\n write_output(\"License: %s\", dist.license)\n write_output(\"Location: %s\", dist.location)\n if dist.editable_project_location is not None:\n write_output(\n \"Editable project location: %s\", dist.editable_project_location\n )\n write_output(\"Requires: %s\", \", \".join(dist.requires))\n write_output(\"Required-by: %s\", \", \".join(dist.required_by))\n\n if verbose:\n write_output(\"Metadata-Version: %s\", dist.metadata_version)\n write_output(\"Installer: %s\", dist.installer)\n write_output(\"Classifiers:\")\n for classifier in dist.classifiers:\n write_output(\" %s\", classifier)\n write_output(\"Entry-points:\")\n for entry in dist.entry_points:\n write_output(\" %s\", entry.strip())\n write_output(\"Project-URLs:\")\n for project_url in dist.project_urls:\n write_output(\" %s\", project_url)\n if list_files:\n write_output(\"Files:\")\n if dist.files is None:\n write_output(\"Cannot locate RECORD or installed-files.txt\")\n else:\n for line in dist.files:\n write_output(\" %s\", line.strip())\n return results_printed\n", "path": "src/pip/_internal/commands/show.py"}], "after_files": [{"content": "import logging\nfrom optparse import Values\nfrom typing import Generator, Iterable, Iterator, List, NamedTuple, Optional\n\nfrom pip._vendor.packaging.utils import canonicalize_name\n\nfrom pip._internal.cli.base_command import Command\nfrom pip._internal.cli.status_codes import ERROR, SUCCESS\nfrom pip._internal.metadata import BaseDistribution, get_default_environment\nfrom pip._internal.utils.misc import write_output\n\nlogger = logging.getLogger(__name__)\n\n\nclass ShowCommand(Command):\n \"\"\"\n Show information about one or more installed packages.\n\n The output is in RFC-compliant mail header format.\n \"\"\"\n\n usage = \"\"\"\n %prog [options] <package> ...\"\"\"\n ignore_require_venv = True\n\n def add_options(self) -> None:\n self.cmd_opts.add_option(\n \"-f\",\n \"--files\",\n dest=\"files\",\n action=\"store_true\",\n default=False,\n help=\"Show the full list of installed files for each package.\",\n )\n\n self.parser.insert_option_group(0, self.cmd_opts)\n\n def run(self, options: Values, args: List[str]) -> int:\n if not args:\n logger.warning(\"ERROR: Please provide a package name or names.\")\n return ERROR\n query = args\n\n results = search_packages_info(query)\n if not print_results(\n results, list_files=options.files, verbose=options.verbose\n ):\n return ERROR\n return SUCCESS\n\n\nclass _PackageInfo(NamedTuple):\n name: str\n version: str\n location: str\n editable_project_location: Optional[str]\n requires: List[str]\n required_by: List[str]\n installer: str\n metadata_version: str\n classifiers: List[str]\n summary: str\n homepage: str\n project_urls: List[str]\n author: str\n author_email: str\n license: str\n entry_points: List[str]\n files: Optional[List[str]]\n\n\ndef search_packages_info(query: List[str]) -> Generator[_PackageInfo, None, None]:\n \"\"\"\n Gather details from installed distributions. Print distribution name,\n version, location, and installed files. Installed files requires a\n pip generated 'installed-files.txt' in the distributions '.egg-info'\n directory.\n \"\"\"\n env = get_default_environment()\n\n installed = {dist.canonical_name: dist for dist in env.iter_all_distributions()}\n query_names = [canonicalize_name(name) for name in query]\n missing = sorted(\n [name for name, pkg in zip(query, query_names) if pkg not in installed]\n )\n if missing:\n logger.warning(\"Package(s) not found: %s\", \", \".join(missing))\n\n def _get_requiring_packages(current_dist: BaseDistribution) -> Iterator[str]:\n return (\n dist.metadata[\"Name\"] or \"UNKNOWN\"\n for dist in installed.values()\n if current_dist.canonical_name\n in {canonicalize_name(d.name) for d in dist.iter_dependencies()}\n )\n\n for query_name in query_names:\n try:\n dist = installed[query_name]\n except KeyError:\n continue\n\n requires = sorted(\n # Avoid duplicates in requirements (e.g. due to environment markers).\n {req.name for req in dist.iter_dependencies()},\n key=str.lower,\n )\n required_by = sorted(_get_requiring_packages(dist), key=str.lower)\n\n try:\n entry_points_text = dist.read_text(\"entry_points.txt\")\n entry_points = entry_points_text.splitlines(keepends=False)\n except FileNotFoundError:\n entry_points = []\n\n files_iter = dist.iter_declared_entries()\n if files_iter is None:\n files: Optional[List[str]] = None\n else:\n files = sorted(files_iter)\n\n metadata = dist.metadata\n\n project_urls = metadata.get_all(\"Project-URL\", [])\n homepage = metadata.get(\"Home-page\", \"\")\n if not homepage:\n # It's common that there is a \"homepage\" Project-URL, but Home-page\n # remains unset (especially as PEP 621 doesn't surface the field).\n #\n # This logic was taken from PyPI's codebase.\n for url in project_urls:\n url_label, url = url.split(\",\", maxsplit=1)\n normalized_label = (\n url_label.casefold().replace(\"-\", \"\").replace(\"_\", \"\").strip()\n )\n if normalized_label == \"homepage\":\n homepage = url.strip()\n break\n\n yield _PackageInfo(\n name=dist.raw_name,\n version=str(dist.version),\n location=dist.location or \"\",\n editable_project_location=dist.editable_project_location,\n requires=requires,\n required_by=required_by,\n installer=dist.installer,\n metadata_version=dist.metadata_version or \"\",\n classifiers=metadata.get_all(\"Classifier\", []),\n summary=metadata.get(\"Summary\", \"\"),\n homepage=homepage,\n project_urls=project_urls,\n author=metadata.get(\"Author\", \"\"),\n author_email=metadata.get(\"Author-email\", \"\"),\n license=metadata.get(\"License\", \"\"),\n entry_points=entry_points,\n files=files,\n )\n\n\ndef print_results(\n distributions: Iterable[_PackageInfo],\n list_files: bool,\n verbose: bool,\n) -> bool:\n \"\"\"\n Print the information from installed distributions found.\n \"\"\"\n results_printed = False\n for i, dist in enumerate(distributions):\n results_printed = True\n if i > 0:\n write_output(\"---\")\n\n write_output(\"Name: %s\", dist.name)\n write_output(\"Version: %s\", dist.version)\n write_output(\"Summary: %s\", dist.summary)\n write_output(\"Home-page: %s\", dist.homepage)\n write_output(\"Author: %s\", dist.author)\n write_output(\"Author-email: %s\", dist.author_email)\n write_output(\"License: %s\", dist.license)\n write_output(\"Location: %s\", dist.location)\n if dist.editable_project_location is not None:\n write_output(\n \"Editable project location: %s\", dist.editable_project_location\n )\n write_output(\"Requires: %s\", \", \".join(dist.requires))\n write_output(\"Required-by: %s\", \", \".join(dist.required_by))\n\n if verbose:\n write_output(\"Metadata-Version: %s\", dist.metadata_version)\n write_output(\"Installer: %s\", dist.installer)\n write_output(\"Classifiers:\")\n for classifier in dist.classifiers:\n write_output(\" %s\", classifier)\n write_output(\"Entry-points:\")\n for entry in dist.entry_points:\n write_output(\" %s\", entry.strip())\n write_output(\"Project-URLs:\")\n for project_url in dist.project_urls:\n write_output(\" %s\", project_url)\n if list_files:\n write_output(\"Files:\")\n if dist.files is None:\n write_output(\"Cannot locate RECORD or installed-files.txt\")\n else:\n for line in dist.files:\n write_output(\" %s\", line.strip())\n return results_printed\n", "path": "src/pip/_internal/commands/show.py"}]}
| 2,337 | 357 |
gh_patches_debug_42271
|
rasdani/github-patches
|
git_diff
|
google__flax-2204
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
codediff section not respecting html container
In the new `sphinx_book_theme` our custom `codediff` directive is rendering its content outside the container, overflowing until the end of the page. As shown in this screenshot, it appear to be rendered underneath the `contents` section because its not respecting its section boundaries:
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `docs/conf.py`
Content:
```
1 # Copyright 2022 The Flax Authors.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Configuration file for the Sphinx documentation builder."""
16
17
18 # This file only contains a selection of the most common options. For a full
19 # list see the documentation:
20 # https://www.sphinx-doc.org/en/master/usage/configuration.html
21
22 # -- Path setup --------------------------------------------------------------
23
24 # If extensions (or modules to document with autodoc) are in another directory,
25 # add these directories to sys.path here. If the directory is relative to the
26 # documentation root, use os.path.abspath to make it absolute, like shown here.
27 #
28 # import os
29 # import sys
30 # sys.path.insert(0, os.path.abspath('.'))
31
32 import os
33 import sys
34 sys.path.insert(0, os.path.abspath('..'))
35 # Include local extension.
36 sys.path.append(os.path.abspath('./_ext'))
37
38 # patch sphinx
39 import docs.conf_sphinx_patch
40 # -- Project information -----------------------------------------------------
41
42 project = 'Flax'
43 copyright = '2020, The Flax authors' # pylint: disable=redefined-builtin
44 author = 'The Flax authors'
45
46
47 # -- General configuration ---------------------------------------------------
48
49 # Add any Sphinx extension module names here, as strings. They can be
50 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
51 # ones.
52 extensions = [
53 'sphinx.ext.autodoc',
54 'sphinx.ext.autosummary',
55 'sphinx.ext.autosectionlabel',
56 'sphinx.ext.doctest',
57 'sphinx.ext.intersphinx',
58 'sphinx.ext.mathjax',
59 'sphinx.ext.napoleon',
60 'sphinx.ext.viewcode',
61 'myst_nb',
62 'codediff',
63 'sphinx_markdown_tables'
64 ]
65
66 # Add any paths that contain templates here, relative to this directory.
67 templates_path = ['_templates']
68
69 # List of patterns, relative to source directory, that match files and
70 # directories to ignore when looking for source files.
71 # This pattern also affects html_static_path and html_extra_path.
72 exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
73
74 # The suffix(es) of source filenames.
75 # Note: important to list ipynb before md here: we have both md and ipynb
76 # copies of each notebook, and myst will choose which to convert based on
77 # the order in the source_suffix list. Notebooks which are not executed have
78 # outputs stored in ipynb but not in md, so we must convert the ipynb.
79 source_suffix = ['.rst', '.ipynb', '.md']
80
81 autosummary_generate = True
82
83 master_doc = 'index'
84
85 autodoc_typehints = 'none'
86
87
88 # -- Options for HTML output -------------------------------------------------
89
90 # The theme to use for HTML and HTML Help pages. See the documentation for
91 # a list of builtin themes.
92 #
93 html_theme = 'sphinx_book_theme'
94 # html_style = 'css/flax_theme.css'
95
96 # The name of an image file (relative to this directory) to place at the top
97 # of the sidebar.
98 html_logo = './flax.png'
99
100 # Add any paths that contain custom static files (such as style sheets) here,
101 # relative to this directory. They are copied after the builtin static files,
102 # so a file named "default.css" will overwrite the builtin "default.css".
103 html_static_path = ['_static']
104
105 html_theme_options = {
106 "repository_url": "https://github.com/google/flax",
107 "use_repository_button": True, # add a "link to repository" button
108 "use_issues_button": False, # add an "Open an Issue" button
109 "path_to_docs": "docs", # used to compute the path to launch notebooks in colab
110 "launch_buttons": {
111 "colab_url": "https://colab.research.google.com/",
112 },
113 }
114
115 # -- Options for myst ----------------------------------------------
116 # Notebook cell execution timeout; defaults to 30.
117 nb_execution_timeout = 100
118 # List of patterns, relative to source directory, that match notebook
119 # files that will not be executed.
120 nb_execution_excludepatterns = [
121 'notebooks/annotated_mnist.ipynb', # <-- times out
122 ]
123 # raise exceptions on execution so CI can catch errors
124 nb_execution_allow_errors = False
125 nb_execution_raise_on_error = True
126
127 # -- Extension configuration -------------------------------------------------
128
129 # Tell sphinx-autodoc-typehints to generate stub parameter annotations including
130 # types, even if the parameters aren't explicitly documented.
131 always_document_param_types = True
132
```
Path: `docs/_ext/codediff.py`
Content:
```
1 # Copyright 2022 The Flax Authors.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Sphinx directive for creating code diff tables.
16
17 Use directive as follows:
18
19 .. codediff::
20 :title_left: <LEFT_CODE_BLOCK_TITLE>
21 :title_right: <RIGHT_CODE_BLOCK_TITLE>
22
23 <CODE_BLOCK_LEFT>
24 ---
25 <CODE_BLOCK_RIGHT>
26
27 In order to highlight a line of code, prepend it with "#!".
28 """
29 import itertools
30
31 from docutils import nodes
32 from docutils.parsers.rst import directives
33 from docutils.statemachine import ViewList
34
35 import sphinx
36 from sphinx.util.docutils import SphinxDirective
37
38
39 class CodeDiffParser:
40
41 def parse(self, lines, title_left='Base', title_right='Diff', code_sep='---'):
42 if code_sep not in lines:
43 raise ValueError('Code separator not found! Code snippets should be '
44 f'separated by {code_sep}.')
45 idx = lines.index(code_sep)
46 code_left = self._code_block(lines[0: idx])
47 test_code = lines[idx+1:]
48 code_right = self._code_block(test_code)
49
50 self.max_left = max(len(x) for x in code_left + [title_left])
51 self.max_right = max(len(x) for x in code_right + [title_right])
52
53 output = [
54 self._hline(),
55 self._table_row(title_left, title_right),
56 self._hline(),
57 ]
58
59 for l, r in itertools.zip_longest(code_left, code_right, fillvalue=''):
60 output += [self._table_row(l, r)]
61
62 return output + [self._hline()], test_code
63
64 def _code_block(self, lines):
65 """Creates a codeblock."""
66 # Remove right trailing whitespace so we can detect the comments.
67 lines = [x.rstrip() for x in lines]
68 highlight = lambda x: x.endswith('#!')
69 code = map(lambda x: x[:-2].rstrip() if highlight(x) else x, lines)
70 highlights = [i + 1 for i in range(len(lines)) if highlight(lines[i])]
71 highlights = ','.join(str(i) for i in highlights)
72
73 directive = ['.. code-block:: python']
74 if highlights:
75 directive += [f' :emphasize-lines: {highlights}']
76
77 # Indent code and add empty line so the code is picked up by the directive.
78 return directive + [''] + list(map(lambda x: ' ' + x, code))
79
80 def _hline(self):
81 return '+' + '-'*(self.max_left+2) + '+' + '-'*(self.max_right+2) + '+'
82
83 def _rfill(self, text, max_len):
84 return text + ' ' * (max_len-len(text))
85
86 def _table_row(self, left, right):
87 text_left = self._rfill(left, self.max_left)
88 text_right = self._rfill(right, self.max_right)
89 return '| ' + text_left + ' | ' + text_right + ' |'
90
91
92 class CodeDiffDirective(SphinxDirective):
93 has_content = True
94 option_spec = {
95 'title_left': directives.unchanged,
96 'title_right': directives.unchanged,
97 'code_sep': directives.unchanged,
98 }
99
100 def run(self):
101 table_code, test_code = CodeDiffParser().parse(
102 list(self.content), **self.options)
103
104 # Create a test node as a comment node so it won't show up in the docs.
105 # We add attribute "testnodetype" so it is be picked up by the doctest
106 # builder. This functionality is not officially documented but can be found
107 # in the source code:
108 # https://github.com/sphinx-doc/sphinx/blob/3.x/sphinx/ext/doctest.py
109 # (search for 'testnodetype').
110 test_code = '\n'.join(test_code)
111 test_node = nodes.comment(test_code, test_code, testnodetype='testcode')
112 # Set the source info so the error message is correct when testing.
113 self.set_source_info(test_node)
114 test_node['options'] = {}
115 test_node['language'] = 'python3'
116
117 # The table node is the side-by-side diff view that will be shown on RTD.
118 table_node = nodes.paragraph()
119 self.content = ViewList(table_code, self.content.parent)
120 self.state.nested_parse(self.content, self.content_offset, table_node)
121
122 return [table_node, test_node]
123
124
125 def setup(app):
126 app.add_directive('codediff', CodeDiffDirective)
127
128 return {
129 'version': sphinx.__display_version__,
130 'parallel_read_safe': True,
131 'parallel_write_safe': True,
132 }
133
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/docs/_ext/codediff.py b/docs/_ext/codediff.py
--- a/docs/_ext/codediff.py
+++ b/docs/_ext/codediff.py
@@ -24,9 +24,10 @@
---
<CODE_BLOCK_RIGHT>
-In order to highlight a line of code, prepend it with "#!".
+In order to highlight a line of code, append "#!" to it.
"""
import itertools
+from typing import List, Tuple
from docutils import nodes
from docutils.parsers.rst import directives
@@ -35,10 +36,14 @@
import sphinx
from sphinx.util.docutils import SphinxDirective
+MISSING = object()
class CodeDiffParser:
- def parse(self, lines, title_left='Base', title_right='Diff', code_sep='---'):
+ def parse(
+ self, lines, title_left='Base', title_right='Diff', code_sep='---', sync=MISSING):
+ sync = sync is not MISSING
+
if code_sep not in lines:
raise ValueError('Code separator not found! Code snippets should be '
f'separated by {code_sep}.')
@@ -47,19 +52,10 @@
test_code = lines[idx+1:]
code_right = self._code_block(test_code)
- self.max_left = max(len(x) for x in code_left + [title_left])
- self.max_right = max(len(x) for x in code_right + [title_right])
-
- output = [
- self._hline(),
- self._table_row(title_left, title_right),
- self._hline(),
- ]
+ output = self._tabs(
+ (title_left, code_left), (title_right, code_right), sync=sync)
- for l, r in itertools.zip_longest(code_left, code_right, fillvalue=''):
- output += [self._table_row(l, r)]
-
- return output + [self._hline()], test_code
+ return output, test_code
def _code_block(self, lines):
"""Creates a codeblock."""
@@ -77,17 +73,20 @@
# Indent code and add empty line so the code is picked up by the directive.
return directive + [''] + list(map(lambda x: ' ' + x, code))
- def _hline(self):
- return '+' + '-'*(self.max_left+2) + '+' + '-'*(self.max_right+2) + '+'
-
- def _rfill(self, text, max_len):
- return text + ' ' * (max_len-len(text))
+ def _tabs(self, *contents: Tuple[str, List[str]], sync):
+ output = ['.. tab-set::'] + [' ']
+
+ for title, content in contents:
+ output += [f' .. tab-item:: {title}']
+
+ if sync:
+ key = title.strip()
+ output += [f' :sync: {key}']
- def _table_row(self, left, right):
- text_left = self._rfill(left, self.max_left)
- text_right = self._rfill(right, self.max_right)
- return '| ' + text_left + ' | ' + text_right + ' |'
+ output += [' ']
+ output += [' ' + line for line in content]
+ return output
class CodeDiffDirective(SphinxDirective):
has_content = True
@@ -95,6 +94,7 @@
'title_left': directives.unchanged,
'title_right': directives.unchanged,
'code_sep': directives.unchanged,
+ 'sync': directives.flag,
}
def run(self):
diff --git a/docs/conf.py b/docs/conf.py
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -60,7 +60,7 @@
'sphinx.ext.viewcode',
'myst_nb',
'codediff',
- 'sphinx_markdown_tables'
+ 'sphinx_design',
]
# Add any paths that contain templates here, relative to this directory.
@@ -91,7 +91,7 @@
# a list of builtin themes.
#
html_theme = 'sphinx_book_theme'
-# html_style = 'css/flax_theme.css'
+html_css_files = ["css/flax_theme.css"]
# The name of an image file (relative to this directory) to place at the top
# of the sidebar.
|
{"golden_diff": "diff --git a/docs/_ext/codediff.py b/docs/_ext/codediff.py\n--- a/docs/_ext/codediff.py\n+++ b/docs/_ext/codediff.py\n@@ -24,9 +24,10 @@\n ---\n <CODE_BLOCK_RIGHT>\n \n-In order to highlight a line of code, prepend it with \"#!\".\n+In order to highlight a line of code, append \"#!\" to it.\n \"\"\"\n import itertools\n+from typing import List, Tuple\n \n from docutils import nodes\n from docutils.parsers.rst import directives\n@@ -35,10 +36,14 @@\n import sphinx\n from sphinx.util.docutils import SphinxDirective\n \n+MISSING = object()\n \n class CodeDiffParser:\n \n- def parse(self, lines, title_left='Base', title_right='Diff', code_sep='---'):\n+ def parse(\n+ self, lines, title_left='Base', title_right='Diff', code_sep='---', sync=MISSING):\n+ sync = sync is not MISSING\n+\n if code_sep not in lines:\n raise ValueError('Code separator not found! Code snippets should be '\n f'separated by {code_sep}.')\n@@ -47,19 +52,10 @@\n test_code = lines[idx+1:]\n code_right = self._code_block(test_code)\n \n- self.max_left = max(len(x) for x in code_left + [title_left])\n- self.max_right = max(len(x) for x in code_right + [title_right])\n-\n- output = [\n- self._hline(),\n- self._table_row(title_left, title_right),\n- self._hline(),\n- ]\n+ output = self._tabs(\n+ (title_left, code_left), (title_right, code_right), sync=sync)\n \n- for l, r in itertools.zip_longest(code_left, code_right, fillvalue=''):\n- output += [self._table_row(l, r)]\n-\n- return output + [self._hline()], test_code\n+ return output, test_code\n \n def _code_block(self, lines):\n \"\"\"Creates a codeblock.\"\"\"\n@@ -77,17 +73,20 @@\n # Indent code and add empty line so the code is picked up by the directive.\n return directive + [''] + list(map(lambda x: ' ' + x, code))\n \n- def _hline(self):\n- return '+' + '-'*(self.max_left+2) + '+' + '-'*(self.max_right+2) + '+'\n-\n- def _rfill(self, text, max_len):\n- return text + ' ' * (max_len-len(text))\n+ def _tabs(self, *contents: Tuple[str, List[str]], sync):\n+ output = ['.. tab-set::'] + [' ']\n+ \n+ for title, content in contents:\n+ output += [f' .. tab-item:: {title}']\n+ \n+ if sync:\n+ key = title.strip()\n+ output += [f' :sync: {key}']\n \n- def _table_row(self, left, right):\n- text_left = self._rfill(left, self.max_left)\n- text_right = self._rfill(right, self.max_right)\n- return '| ' + text_left + ' | ' + text_right + ' |'\n+ output += [' ']\n+ output += [' ' + line for line in content]\n \n+ return output\n \n class CodeDiffDirective(SphinxDirective):\n has_content = True\n@@ -95,6 +94,7 @@\n 'title_left': directives.unchanged,\n 'title_right': directives.unchanged,\n 'code_sep': directives.unchanged,\n+ 'sync': directives.flag,\n }\n \n def run(self):\ndiff --git a/docs/conf.py b/docs/conf.py\n--- a/docs/conf.py\n+++ b/docs/conf.py\n@@ -60,7 +60,7 @@\n 'sphinx.ext.viewcode',\n 'myst_nb',\n 'codediff',\n- 'sphinx_markdown_tables'\n+ 'sphinx_design',\n ]\n \n # Add any paths that contain templates here, relative to this directory.\n@@ -91,7 +91,7 @@\n # a list of builtin themes.\n #\n html_theme = 'sphinx_book_theme'\n-# html_style = 'css/flax_theme.css'\n+html_css_files = [\"css/flax_theme.css\"]\n \n # The name of an image file (relative to this directory) to place at the top\n # of the sidebar.\n", "issue": "codediff section not respecting html container \nIn the new `sphinx_book_theme` our custom `codediff` directive is rendering its content outside the container, overflowing until the end of the page. As shown in this screenshot, it appear to be rendered underneath the `contents` section because its not respecting its section boundaries:\r\n\r\n\r\n\r\n\n", "before_files": [{"content": "# Copyright 2022 The Flax Authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Configuration file for the Sphinx documentation builder.\"\"\"\n\n\n# This file only contains a selection of the most common options. For a full\n# list see the documentation:\n# https://www.sphinx-doc.org/en/master/usage/configuration.html\n\n# -- Path setup --------------------------------------------------------------\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\n#\n# import os\n# import sys\n# sys.path.insert(0, os.path.abspath('.'))\n\nimport os\nimport sys\nsys.path.insert(0, os.path.abspath('..'))\n# Include local extension.\nsys.path.append(os.path.abspath('./_ext'))\n\n# patch sphinx\nimport docs.conf_sphinx_patch\n# -- Project information -----------------------------------------------------\n\nproject = 'Flax'\ncopyright = '2020, The Flax authors' # pylint: disable=redefined-builtin\nauthor = 'The Flax authors'\n\n\n# -- General configuration ---------------------------------------------------\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom\n# ones.\nextensions = [\n 'sphinx.ext.autodoc',\n 'sphinx.ext.autosummary',\n 'sphinx.ext.autosectionlabel',\n 'sphinx.ext.doctest',\n 'sphinx.ext.intersphinx',\n 'sphinx.ext.mathjax',\n 'sphinx.ext.napoleon',\n 'sphinx.ext.viewcode',\n 'myst_nb',\n 'codediff',\n 'sphinx_markdown_tables'\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = ['_templates']\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This pattern also affects html_static_path and html_extra_path.\nexclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']\n\n# The suffix(es) of source filenames.\n# Note: important to list ipynb before md here: we have both md and ipynb\n# copies of each notebook, and myst will choose which to convert based on\n# the order in the source_suffix list. Notebooks which are not executed have\n# outputs stored in ipynb but not in md, so we must convert the ipynb.\nsource_suffix = ['.rst', '.ipynb', '.md']\n\nautosummary_generate = True\n\nmaster_doc = 'index'\n\nautodoc_typehints = 'none'\n\n\n# -- Options for HTML output -------------------------------------------------\n\n# The theme to use for HTML and HTML Help pages. See the documentation for\n# a list of builtin themes.\n#\nhtml_theme = 'sphinx_book_theme'\n# html_style = 'css/flax_theme.css'\n\n# The name of an image file (relative to this directory) to place at the top\n# of the sidebar.\nhtml_logo = './flax.png'\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = ['_static']\n\nhtml_theme_options = {\n \"repository_url\": \"https://github.com/google/flax\",\n \"use_repository_button\": True, # add a \"link to repository\" button\n \"use_issues_button\": False, # add an \"Open an Issue\" button\n \"path_to_docs\": \"docs\", # used to compute the path to launch notebooks in colab\n \"launch_buttons\": {\n \"colab_url\": \"https://colab.research.google.com/\",\n },\n}\n\n# -- Options for myst ----------------------------------------------\n# Notebook cell execution timeout; defaults to 30.\nnb_execution_timeout = 100\n# List of patterns, relative to source directory, that match notebook\n# files that will not be executed.\nnb_execution_excludepatterns = [\n 'notebooks/annotated_mnist.ipynb', # <-- times out \n]\n# raise exceptions on execution so CI can catch errors\nnb_execution_allow_errors = False\nnb_execution_raise_on_error = True\n\n# -- Extension configuration -------------------------------------------------\n\n# Tell sphinx-autodoc-typehints to generate stub parameter annotations including\n# types, even if the parameters aren't explicitly documented.\nalways_document_param_types = True\n", "path": "docs/conf.py"}, {"content": "# Copyright 2022 The Flax Authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Sphinx directive for creating code diff tables.\n\nUse directive as follows:\n\n.. codediff::\n :title_left: <LEFT_CODE_BLOCK_TITLE>\n :title_right: <RIGHT_CODE_BLOCK_TITLE>\n\n <CODE_BLOCK_LEFT>\n ---\n <CODE_BLOCK_RIGHT>\n\nIn order to highlight a line of code, prepend it with \"#!\".\n\"\"\"\nimport itertools\n\nfrom docutils import nodes\nfrom docutils.parsers.rst import directives\nfrom docutils.statemachine import ViewList\n\nimport sphinx\nfrom sphinx.util.docutils import SphinxDirective\n\n\nclass CodeDiffParser:\n\n def parse(self, lines, title_left='Base', title_right='Diff', code_sep='---'):\n if code_sep not in lines:\n raise ValueError('Code separator not found! Code snippets should be '\n f'separated by {code_sep}.')\n idx = lines.index(code_sep)\n code_left = self._code_block(lines[0: idx])\n test_code = lines[idx+1:]\n code_right = self._code_block(test_code)\n\n self.max_left = max(len(x) for x in code_left + [title_left])\n self.max_right = max(len(x) for x in code_right + [title_right])\n\n output = [\n self._hline(),\n self._table_row(title_left, title_right),\n self._hline(),\n ]\n\n for l, r in itertools.zip_longest(code_left, code_right, fillvalue=''):\n output += [self._table_row(l, r)]\n\n return output + [self._hline()], test_code\n\n def _code_block(self, lines):\n \"\"\"Creates a codeblock.\"\"\"\n # Remove right trailing whitespace so we can detect the comments.\n lines = [x.rstrip() for x in lines]\n highlight = lambda x: x.endswith('#!')\n code = map(lambda x: x[:-2].rstrip() if highlight(x) else x, lines)\n highlights = [i + 1 for i in range(len(lines)) if highlight(lines[i])]\n highlights = ','.join(str(i) for i in highlights)\n\n directive = ['.. code-block:: python']\n if highlights:\n directive += [f' :emphasize-lines: {highlights}']\n\n # Indent code and add empty line so the code is picked up by the directive.\n return directive + [''] + list(map(lambda x: ' ' + x, code))\n\n def _hline(self):\n return '+' + '-'*(self.max_left+2) + '+' + '-'*(self.max_right+2) + '+'\n\n def _rfill(self, text, max_len):\n return text + ' ' * (max_len-len(text))\n\n def _table_row(self, left, right):\n text_left = self._rfill(left, self.max_left)\n text_right = self._rfill(right, self.max_right)\n return '| ' + text_left + ' | ' + text_right + ' |'\n\n\nclass CodeDiffDirective(SphinxDirective):\n has_content = True\n option_spec = {\n 'title_left': directives.unchanged,\n 'title_right': directives.unchanged,\n 'code_sep': directives.unchanged,\n }\n\n def run(self):\n table_code, test_code = CodeDiffParser().parse(\n list(self.content), **self.options)\n\n # Create a test node as a comment node so it won't show up in the docs.\n # We add attribute \"testnodetype\" so it is be picked up by the doctest\n # builder. This functionality is not officially documented but can be found\n # in the source code:\n # https://github.com/sphinx-doc/sphinx/blob/3.x/sphinx/ext/doctest.py\n # (search for 'testnodetype').\n test_code = '\\n'.join(test_code)\n test_node = nodes.comment(test_code, test_code, testnodetype='testcode')\n # Set the source info so the error message is correct when testing.\n self.set_source_info(test_node)\n test_node['options'] = {}\n test_node['language'] = 'python3'\n\n # The table node is the side-by-side diff view that will be shown on RTD.\n table_node = nodes.paragraph()\n self.content = ViewList(table_code, self.content.parent)\n self.state.nested_parse(self.content, self.content_offset, table_node)\n\n return [table_node, test_node]\n\n\ndef setup(app):\n app.add_directive('codediff', CodeDiffDirective)\n\n return {\n 'version': sphinx.__display_version__,\n 'parallel_read_safe': True,\n 'parallel_write_safe': True,\n }\n", "path": "docs/_ext/codediff.py"}], "after_files": [{"content": "# Copyright 2022 The Flax Authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Configuration file for the Sphinx documentation builder.\"\"\"\n\n\n# This file only contains a selection of the most common options. For a full\n# list see the documentation:\n# https://www.sphinx-doc.org/en/master/usage/configuration.html\n\n# -- Path setup --------------------------------------------------------------\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\n#\n# import os\n# import sys\n# sys.path.insert(0, os.path.abspath('.'))\n\nimport os\nimport sys\nsys.path.insert(0, os.path.abspath('..'))\n# Include local extension.\nsys.path.append(os.path.abspath('./_ext'))\n\n# patch sphinx\nimport docs.conf_sphinx_patch\n# -- Project information -----------------------------------------------------\n\nproject = 'Flax'\ncopyright = '2020, The Flax authors' # pylint: disable=redefined-builtin\nauthor = 'The Flax authors'\n\n\n# -- General configuration ---------------------------------------------------\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom\n# ones.\nextensions = [\n 'sphinx.ext.autodoc',\n 'sphinx.ext.autosummary',\n 'sphinx.ext.autosectionlabel',\n 'sphinx.ext.doctest',\n 'sphinx.ext.intersphinx',\n 'sphinx.ext.mathjax',\n 'sphinx.ext.napoleon',\n 'sphinx.ext.viewcode',\n 'myst_nb',\n 'codediff',\n 'sphinx_design',\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = ['_templates']\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This pattern also affects html_static_path and html_extra_path.\nexclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']\n\n# The suffix(es) of source filenames.\n# Note: important to list ipynb before md here: we have both md and ipynb\n# copies of each notebook, and myst will choose which to convert based on\n# the order in the source_suffix list. Notebooks which are not executed have\n# outputs stored in ipynb but not in md, so we must convert the ipynb.\nsource_suffix = ['.rst', '.ipynb', '.md']\n\nautosummary_generate = True\n\nmaster_doc = 'index'\n\nautodoc_typehints = 'none'\n\n\n# -- Options for HTML output -------------------------------------------------\n\n# The theme to use for HTML and HTML Help pages. See the documentation for\n# a list of builtin themes.\n#\nhtml_theme = 'sphinx_book_theme'\nhtml_css_files = [\"css/flax_theme.css\"]\n\n# The name of an image file (relative to this directory) to place at the top\n# of the sidebar.\nhtml_logo = './flax.png'\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = ['_static']\n\nhtml_theme_options = {\n \"repository_url\": \"https://github.com/google/flax\",\n \"use_repository_button\": True, # add a \"link to repository\" button\n \"use_issues_button\": False, # add an \"Open an Issue\" button\n \"path_to_docs\": \"docs\", # used to compute the path to launch notebooks in colab\n \"launch_buttons\": {\n \"colab_url\": \"https://colab.research.google.com/\",\n },\n}\n\n# -- Options for myst ----------------------------------------------\n# Notebook cell execution timeout; defaults to 30.\nnb_execution_timeout = 100\n# List of patterns, relative to source directory, that match notebook\n# files that will not be executed.\nnb_execution_excludepatterns = [\n 'notebooks/annotated_mnist.ipynb', # <-- times out \n]\n# raise exceptions on execution so CI can catch errors\nnb_execution_allow_errors = False\nnb_execution_raise_on_error = True\n\n# -- Extension configuration -------------------------------------------------\n\n# Tell sphinx-autodoc-typehints to generate stub parameter annotations including\n# types, even if the parameters aren't explicitly documented.\nalways_document_param_types = True\n", "path": "docs/conf.py"}, {"content": "# Copyright 2022 The Flax Authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Sphinx directive for creating code diff tables.\n\nUse directive as follows:\n\n.. codediff::\n :title_left: <LEFT_CODE_BLOCK_TITLE>\n :title_right: <RIGHT_CODE_BLOCK_TITLE>\n\n <CODE_BLOCK_LEFT>\n ---\n <CODE_BLOCK_RIGHT>\n\nIn order to highlight a line of code, append \"#!\" to it.\n\"\"\"\nimport itertools\nfrom typing import List, Tuple\n\nfrom docutils import nodes\nfrom docutils.parsers.rst import directives\nfrom docutils.statemachine import ViewList\n\nimport sphinx\nfrom sphinx.util.docutils import SphinxDirective\n\nMISSING = object()\n\nclass CodeDiffParser:\n\n def parse(\n self, lines, title_left='Base', title_right='Diff', code_sep='---', sync=MISSING):\n sync = sync is not MISSING\n\n if code_sep not in lines:\n raise ValueError('Code separator not found! Code snippets should be '\n f'separated by {code_sep}.')\n idx = lines.index(code_sep)\n code_left = self._code_block(lines[0: idx])\n test_code = lines[idx+1:]\n code_right = self._code_block(test_code)\n\n output = self._tabs(\n (title_left, code_left), (title_right, code_right), sync=sync)\n\n return output, test_code\n\n def _code_block(self, lines):\n \"\"\"Creates a codeblock.\"\"\"\n # Remove right trailing whitespace so we can detect the comments.\n lines = [x.rstrip() for x in lines]\n highlight = lambda x: x.endswith('#!')\n code = map(lambda x: x[:-2].rstrip() if highlight(x) else x, lines)\n highlights = [i + 1 for i in range(len(lines)) if highlight(lines[i])]\n highlights = ','.join(str(i) for i in highlights)\n\n directive = ['.. code-block:: python']\n if highlights:\n directive += [f' :emphasize-lines: {highlights}']\n\n # Indent code and add empty line so the code is picked up by the directive.\n return directive + [''] + list(map(lambda x: ' ' + x, code))\n\n def _tabs(self, *contents: Tuple[str, List[str]], sync):\n output = ['.. tab-set::'] + [' ']\n \n for title, content in contents:\n output += [f' .. tab-item:: {title}']\n \n if sync:\n key = title.strip()\n output += [f' :sync: {key}']\n\n output += [' ']\n output += [' ' + line for line in content]\n\n return output\n\nclass CodeDiffDirective(SphinxDirective):\n has_content = True\n option_spec = {\n 'title_left': directives.unchanged,\n 'title_right': directives.unchanged,\n 'code_sep': directives.unchanged,\n 'sync': directives.flag,\n }\n\n def run(self):\n table_code, test_code = CodeDiffParser().parse(\n list(self.content), **self.options)\n\n # Create a test node as a comment node so it won't show up in the docs.\n # We add attribute \"testnodetype\" so it is be picked up by the doctest\n # builder. This functionality is not officially documented but can be found\n # in the source code:\n # https://github.com/sphinx-doc/sphinx/blob/3.x/sphinx/ext/doctest.py\n # (search for 'testnodetype').\n test_code = '\\n'.join(test_code)\n test_node = nodes.comment(test_code, test_code, testnodetype='testcode')\n # Set the source info so the error message is correct when testing.\n self.set_source_info(test_node)\n test_node['options'] = {}\n test_node['language'] = 'python3'\n\n # The table node is the side-by-side diff view that will be shown on RTD.\n table_node = nodes.paragraph()\n self.content = ViewList(table_code, self.content.parent)\n self.state.nested_parse(self.content, self.content_offset, table_node)\n\n return [table_node, test_node]\n\n\ndef setup(app):\n app.add_directive('codediff', CodeDiffDirective)\n\n return {\n 'version': sphinx.__display_version__,\n 'parallel_read_safe': True,\n 'parallel_write_safe': True,\n }\n", "path": "docs/_ext/codediff.py"}]}
| 3,221 | 1,007 |
gh_patches_debug_20614
|
rasdani/github-patches
|
git_diff
|
pytorch__examples-1189
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Add `save_model` arg to `mnist_hogwild` example
Currently the example doesn't support the `--save_model` argument like the other examples
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `mnist_hogwild/main.py`
Content:
```
1 from __future__ import print_function
2 import argparse
3 import torch
4 import torch.nn as nn
5 import torch.nn.functional as F
6 import torch.multiprocessing as mp
7 from torch.utils.data.sampler import Sampler
8 from torchvision import datasets, transforms
9
10 from train import train, test
11
12 # Training settings
13 parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
14 parser.add_argument('--batch-size', type=int, default=64, metavar='N',
15 help='input batch size for training (default: 64)')
16 parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
17 help='input batch size for testing (default: 1000)')
18 parser.add_argument('--epochs', type=int, default=10, metavar='N',
19 help='number of epochs to train (default: 10)')
20 parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
21 help='learning rate (default: 0.01)')
22 parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
23 help='SGD momentum (default: 0.5)')
24 parser.add_argument('--seed', type=int, default=1, metavar='S',
25 help='random seed (default: 1)')
26 parser.add_argument('--log-interval', type=int, default=10, metavar='N',
27 help='how many batches to wait before logging training status')
28 parser.add_argument('--num-processes', type=int, default=2, metavar='N',
29 help='how many training processes to use (default: 2)')
30 parser.add_argument('--cuda', action='store_true', default=False,
31 help='enables CUDA training')
32 parser.add_argument('--mps', action='store_true', default=False,
33 help='enables macOS GPU training')
34 parser.add_argument('--dry-run', action='store_true', default=False,
35 help='quickly check a single pass')
36
37 class Net(nn.Module):
38 def __init__(self):
39 super(Net, self).__init__()
40 self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
41 self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
42 self.conv2_drop = nn.Dropout2d()
43 self.fc1 = nn.Linear(320, 50)
44 self.fc2 = nn.Linear(50, 10)
45
46 def forward(self, x):
47 x = F.relu(F.max_pool2d(self.conv1(x), 2))
48 x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
49 x = x.view(-1, 320)
50 x = F.relu(self.fc1(x))
51 x = F.dropout(x, training=self.training)
52 x = self.fc2(x)
53 return F.log_softmax(x, dim=1)
54
55
56 if __name__ == '__main__':
57 args = parser.parse_args()
58
59 use_cuda = args.cuda and torch.cuda.is_available()
60 use_mps = args.mps and torch.backends.mps.is_available()
61 if use_cuda:
62 device = torch.device("cuda")
63 elif use_mps:
64 device = torch.device("mps")
65 else:
66 device = torch.device("cpu")
67
68 transform=transforms.Compose([
69 transforms.ToTensor(),
70 transforms.Normalize((0.1307,), (0.3081,))
71 ])
72 dataset1 = datasets.MNIST('../data', train=True, download=True,
73 transform=transform)
74 dataset2 = datasets.MNIST('../data', train=False,
75 transform=transform)
76 kwargs = {'batch_size': args.batch_size,
77 'shuffle': True}
78 if use_cuda:
79 kwargs.update({'num_workers': 1,
80 'pin_memory': True,
81 })
82
83 torch.manual_seed(args.seed)
84 mp.set_start_method('spawn', force=True)
85
86 model = Net().to(device)
87 model.share_memory() # gradients are allocated lazily, so they are not shared here
88
89 processes = []
90 for rank in range(args.num_processes):
91 p = mp.Process(target=train, args=(rank, args, model, device,
92 dataset1, kwargs))
93 # We first train the model across `num_processes` processes
94 p.start()
95 processes.append(p)
96 for p in processes:
97 p.join()
98
99 # Once training is complete, we can test the model
100 test(args, model, device, dataset2, kwargs)
101
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/mnist_hogwild/main.py b/mnist_hogwild/main.py
--- a/mnist_hogwild/main.py
+++ b/mnist_hogwild/main.py
@@ -30,7 +30,9 @@
parser.add_argument('--cuda', action='store_true', default=False,
help='enables CUDA training')
parser.add_argument('--mps', action='store_true', default=False,
- help='enables macOS GPU training')
+ help='enables macOS GPU training')
+parser.add_argument('--save_model', action='store_true', default=False,
+ help='save the trained model to state_dict')
parser.add_argument('--dry-run', action='store_true', default=False,
help='quickly check a single pass')
@@ -96,5 +98,8 @@
for p in processes:
p.join()
+ if args.save_model:
+ torch.save(model.state_dict(), "MNIST_hogwild.pt")
+
# Once training is complete, we can test the model
test(args, model, device, dataset2, kwargs)
|
{"golden_diff": "diff --git a/mnist_hogwild/main.py b/mnist_hogwild/main.py\n--- a/mnist_hogwild/main.py\n+++ b/mnist_hogwild/main.py\n@@ -30,7 +30,9 @@\n parser.add_argument('--cuda', action='store_true', default=False,\n help='enables CUDA training')\n parser.add_argument('--mps', action='store_true', default=False,\n- help='enables macOS GPU training')\n+ help='enables macOS GPU training')\n+parser.add_argument('--save_model', action='store_true', default=False,\n+ help='save the trained model to state_dict')\n parser.add_argument('--dry-run', action='store_true', default=False,\n help='quickly check a single pass')\n \n@@ -96,5 +98,8 @@\n for p in processes:\n p.join()\n \n+ if args.save_model:\n+ torch.save(model.state_dict(), \"MNIST_hogwild.pt\")\n+\n # Once training is complete, we can test the model\n test(args, model, device, dataset2, kwargs)\n", "issue": "Add `save_model` arg to `mnist_hogwild` example\nCurrently the example doesn't support the `--save_model` argument like the other examples\r\n\n", "before_files": [{"content": "from __future__ import print_function\nimport argparse\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.multiprocessing as mp\nfrom torch.utils.data.sampler import Sampler\nfrom torchvision import datasets, transforms\n\nfrom train import train, test\n\n# Training settings\nparser = argparse.ArgumentParser(description='PyTorch MNIST Example')\nparser.add_argument('--batch-size', type=int, default=64, metavar='N',\n help='input batch size for training (default: 64)')\nparser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',\n help='input batch size for testing (default: 1000)')\nparser.add_argument('--epochs', type=int, default=10, metavar='N',\n help='number of epochs to train (default: 10)')\nparser.add_argument('--lr', type=float, default=0.01, metavar='LR',\n help='learning rate (default: 0.01)')\nparser.add_argument('--momentum', type=float, default=0.5, metavar='M',\n help='SGD momentum (default: 0.5)')\nparser.add_argument('--seed', type=int, default=1, metavar='S',\n help='random seed (default: 1)')\nparser.add_argument('--log-interval', type=int, default=10, metavar='N',\n help='how many batches to wait before logging training status')\nparser.add_argument('--num-processes', type=int, default=2, metavar='N',\n help='how many training processes to use (default: 2)')\nparser.add_argument('--cuda', action='store_true', default=False,\n help='enables CUDA training')\nparser.add_argument('--mps', action='store_true', default=False,\n help='enables macOS GPU training')\nparser.add_argument('--dry-run', action='store_true', default=False,\n help='quickly check a single pass')\n\nclass Net(nn.Module):\n def __init__(self):\n super(Net, self).__init__()\n self.conv1 = nn.Conv2d(1, 10, kernel_size=5)\n self.conv2 = nn.Conv2d(10, 20, kernel_size=5)\n self.conv2_drop = nn.Dropout2d()\n self.fc1 = nn.Linear(320, 50)\n self.fc2 = nn.Linear(50, 10)\n\n def forward(self, x):\n x = F.relu(F.max_pool2d(self.conv1(x), 2))\n x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))\n x = x.view(-1, 320)\n x = F.relu(self.fc1(x))\n x = F.dropout(x, training=self.training)\n x = self.fc2(x)\n return F.log_softmax(x, dim=1)\n\n\nif __name__ == '__main__':\n args = parser.parse_args()\n\n use_cuda = args.cuda and torch.cuda.is_available()\n use_mps = args.mps and torch.backends.mps.is_available()\n if use_cuda:\n device = torch.device(\"cuda\")\n elif use_mps:\n device = torch.device(\"mps\")\n else:\n device = torch.device(\"cpu\")\n\n transform=transforms.Compose([\n transforms.ToTensor(),\n transforms.Normalize((0.1307,), (0.3081,))\n ])\n dataset1 = datasets.MNIST('../data', train=True, download=True,\n transform=transform)\n dataset2 = datasets.MNIST('../data', train=False,\n transform=transform)\n kwargs = {'batch_size': args.batch_size,\n 'shuffle': True}\n if use_cuda:\n kwargs.update({'num_workers': 1,\n 'pin_memory': True,\n })\n\n torch.manual_seed(args.seed)\n mp.set_start_method('spawn', force=True)\n\n model = Net().to(device)\n model.share_memory() # gradients are allocated lazily, so they are not shared here\n\n processes = []\n for rank in range(args.num_processes):\n p = mp.Process(target=train, args=(rank, args, model, device,\n dataset1, kwargs))\n # We first train the model across `num_processes` processes\n p.start()\n processes.append(p)\n for p in processes:\n p.join()\n\n # Once training is complete, we can test the model\n test(args, model, device, dataset2, kwargs)\n", "path": "mnist_hogwild/main.py"}], "after_files": [{"content": "from __future__ import print_function\nimport argparse\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.multiprocessing as mp\nfrom torch.utils.data.sampler import Sampler\nfrom torchvision import datasets, transforms\n\nfrom train import train, test\n\n# Training settings\nparser = argparse.ArgumentParser(description='PyTorch MNIST Example')\nparser.add_argument('--batch-size', type=int, default=64, metavar='N',\n help='input batch size for training (default: 64)')\nparser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',\n help='input batch size for testing (default: 1000)')\nparser.add_argument('--epochs', type=int, default=10, metavar='N',\n help='number of epochs to train (default: 10)')\nparser.add_argument('--lr', type=float, default=0.01, metavar='LR',\n help='learning rate (default: 0.01)')\nparser.add_argument('--momentum', type=float, default=0.5, metavar='M',\n help='SGD momentum (default: 0.5)')\nparser.add_argument('--seed', type=int, default=1, metavar='S',\n help='random seed (default: 1)')\nparser.add_argument('--log-interval', type=int, default=10, metavar='N',\n help='how many batches to wait before logging training status')\nparser.add_argument('--num-processes', type=int, default=2, metavar='N',\n help='how many training processes to use (default: 2)')\nparser.add_argument('--cuda', action='store_true', default=False,\n help='enables CUDA training')\nparser.add_argument('--mps', action='store_true', default=False,\n help='enables macOS GPU training')\nparser.add_argument('--save_model', action='store_true', default=False,\n help='save the trained model to state_dict')\nparser.add_argument('--dry-run', action='store_true', default=False,\n help='quickly check a single pass')\n\nclass Net(nn.Module):\n def __init__(self):\n super(Net, self).__init__()\n self.conv1 = nn.Conv2d(1, 10, kernel_size=5)\n self.conv2 = nn.Conv2d(10, 20, kernel_size=5)\n self.conv2_drop = nn.Dropout2d()\n self.fc1 = nn.Linear(320, 50)\n self.fc2 = nn.Linear(50, 10)\n\n def forward(self, x):\n x = F.relu(F.max_pool2d(self.conv1(x), 2))\n x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))\n x = x.view(-1, 320)\n x = F.relu(self.fc1(x))\n x = F.dropout(x, training=self.training)\n x = self.fc2(x)\n return F.log_softmax(x, dim=1)\n\n\nif __name__ == '__main__':\n args = parser.parse_args()\n\n use_cuda = args.cuda and torch.cuda.is_available()\n use_mps = args.mps and torch.backends.mps.is_available()\n if use_cuda:\n device = torch.device(\"cuda\")\n elif use_mps:\n device = torch.device(\"mps\")\n else:\n device = torch.device(\"cpu\")\n\n transform=transforms.Compose([\n transforms.ToTensor(),\n transforms.Normalize((0.1307,), (0.3081,))\n ])\n dataset1 = datasets.MNIST('../data', train=True, download=True,\n transform=transform)\n dataset2 = datasets.MNIST('../data', train=False,\n transform=transform)\n kwargs = {'batch_size': args.batch_size,\n 'shuffle': True}\n if use_cuda:\n kwargs.update({'num_workers': 1,\n 'pin_memory': True,\n })\n\n torch.manual_seed(args.seed)\n mp.set_start_method('spawn', force=True)\n\n model = Net().to(device)\n model.share_memory() # gradients are allocated lazily, so they are not shared here\n\n processes = []\n for rank in range(args.num_processes):\n p = mp.Process(target=train, args=(rank, args, model, device,\n dataset1, kwargs))\n # We first train the model across `num_processes` processes\n p.start()\n processes.append(p)\n for p in processes:\n p.join()\n\n if args.save_model:\n torch.save(model.state_dict(), \"MNIST_hogwild.pt\")\n\n # Once training is complete, we can test the model\n test(args, model, device, dataset2, kwargs)\n", "path": "mnist_hogwild/main.py"}]}
| 1,460 | 235 |
gh_patches_debug_33732
|
rasdani/github-patches
|
git_diff
|
qtile__qtile-1883
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
widget.Pacman needs a non existing file:'checkupdates'
```
2020-03-30 07:09:12,582 ERROR libqtile base.py:worker():L478 problem polling to update widget pacman
Traceback (most recent call last):
File "/home/parsrch/.local/lib/python3.8/site-packages/libqtile/widget/base.py", line 474, in worker
text = self.poll()
File "/home/parsrch/.local/lib/python3.8/site-packages/libqtile/widget/pacman.py", line 49, in poll
pacman = self.call_process(['checkupdates'])
File "/home/parsrch/.local/lib/python3.8/site-packages/libqtile/widget/base.py", line 266, in call_process
output = subprocess.check_output(command, **kwargs)
File "/usr/lib/python3.8/subprocess.py", line 411, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
File "/usr/lib/python3.8/subprocess.py", line 489, in run
with Popen(*popenargs, **kwargs) as process:
File "/usr/lib/python3.8/subprocess.py", line 854, in __init__
self._execute_child(args, executable, preexec_fn, close_fds,
File "/usr/lib/python3.8/subprocess.py", line 1702, in _execute_child
raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'checkupdates'
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `libqtile/widget/pacman.py`
Content:
```
1 # -*- coding:utf-8 -*-
2 #
3 # Copyright (C) 2012, Maximilian Köhl <[email protected]>
4 #
5 # This program is free software: you can redistribute it and/or modify
6 # it under the terms of the GNU General Public License as published by
7 # the Free Software Foundation, either version 3 of the License, or
8 # (at your option) any later version.
9 #
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
14 #
15 # You should have received a copy of the GNU General Public License
16 # along with this program. If not, see <http://www.gnu.org/licenses/>.
17
18 import subprocess
19
20 from libqtile.log_utils import logger
21 from libqtile.widget import base
22
23
24 class Pacman(base.ThreadedPollText):
25 """Shows number of available updates
26
27 Needs the pacman package manager installed. So will only work in Arch Linux
28 installation.
29 """
30 orientations = base.ORIENTATION_HORIZONTAL
31 defaults = [
32 ('unavailable', 'ffffff', 'Unavailable Color - no updates.'),
33 ('execute', None, 'Command to execute on click'),
34 ('update_interval', 60, "The update interval."),
35 ]
36
37 def __init__(self, **config):
38 logger.warning("Pacman is deprecated, please use CheckUpdates")
39 base.ThreadedPollText.__init__(self, **config)
40 self.add_defaults(Pacman.defaults)
41
42 def draw(self):
43 if self.text == '0':
44 self.layout.colour = self.unavailable
45 else:
46 self.layout.colour = self.foreground
47 base.ThreadedPollText.draw(self)
48
49 def poll(self):
50 pacman = self.call_process(['checkupdates'])
51 return str(len(pacman.splitlines()))
52
53 def button_press(self, x, y, button):
54 base.ThreadedPollText.button_press(self, x, y, button)
55 if button == 1 and self.execute is not None:
56 subprocess.Popen([self.execute], shell=True)
57
```
Path: `libqtile/widget/__init__.py`
Content:
```
1 # Copyright (c) 2014 Rock Neurotiko
2 # Copyright (c) 2014 roger
3 # Copyright (c) 2015 David R. Andersen
4 #
5 # Permission is hereby granted, free of charge, to any person obtaining a copy
6 # of this software and associated documentation files (the "Software"), to deal
7 # in the Software without restriction, including without limitation the rights
8 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 # copies of the Software, and to permit persons to whom the Software is
10 # furnished to do so, subject to the following conditions:
11 #
12 # The above copyright notice and this permission notice shall be included in
13 # all copies or substantial portions of the Software.
14 #
15 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 # SOFTWARE.
22
23 from libqtile.utils import safe_import as safe_import_
24 # only directly import widgets that do not have any third party dependencies
25 # other than those required by qtile, otherwise use the same import function
26 from libqtile.widget.base import Mirror # noqa: F401
27 from libqtile.widget.chord import Chord # noqa: F401
28 from libqtile.widget.clock import Clock # noqa: F401
29 from libqtile.widget.currentlayout import ( # noqa: F401
30 CurrentLayout,
31 CurrentLayoutIcon,
32 )
33 from libqtile.widget.groupbox import AGroupBox, GroupBox # noqa: F401
34 from libqtile.widget.import_error import make_error
35 from libqtile.widget.prompt import Prompt # noqa: F401
36 from libqtile.widget.quick_exit import QuickExit # noqa: F401
37 from libqtile.widget.systray import Systray # noqa: F401
38 from libqtile.widget.textbox import TextBox # noqa: F401
39 from libqtile.widget.windowname import WindowName # noqa: F401
40
41
42 def safe_import(module_name, class_name):
43 safe_import_(
44 (".widget", module_name), class_name, globals(), fallback=make_error
45 )
46
47
48 safe_import("backlight", "Backlight")
49 safe_import("battery", ["Battery", "BatteryIcon"])
50 safe_import("currentscreen", "CurrentScreen")
51 safe_import("debuginfo", "DebugInfo")
52 safe_import(
53 "graph",
54 [
55 "CPUGraph",
56 "MemoryGraph",
57 "SwapGraph",
58 "NetGraph",
59 "HDDGraph",
60 "HDDBusyGraph",
61 ],
62 )
63 safe_import("maildir", "Maildir")
64 safe_import("notify", "Notify")
65 safe_import("sensors", "ThermalSensor")
66 safe_import("sep", "Sep")
67 safe_import("she", "She")
68 safe_import("spacer", "Spacer")
69 safe_import("generic_poll_text", ["GenPollText", "GenPollUrl"])
70 safe_import("volume", "Volume")
71 safe_import("windowtabs", "WindowTabs")
72 safe_import("keyboardlayout", "KeyboardLayout")
73 safe_import("df", "DF")
74 safe_import("image", "Image")
75 safe_import("gmail_checker", "GmailChecker")
76 safe_import("clipboard", "Clipboard")
77 safe_import("countdown", "Countdown")
78 safe_import("tasklist", "TaskList")
79 safe_import("pacman", "Pacman")
80 safe_import("launchbar", "LaunchBar")
81 safe_import("canto", "Canto")
82 safe_import("mpriswidget", "Mpris")
83 safe_import("mpris2widget", "Mpris2")
84 safe_import("mpd2widget", "Mpd2")
85 safe_import("yahoo_weather", "YahooWeather")
86 safe_import("bitcoin_ticker", "BitcoinTicker")
87 safe_import("wlan", "Wlan")
88 safe_import("khal_calendar", "KhalCalendar")
89 safe_import("imapwidget", "ImapWidget")
90 safe_import("net", "Net")
91 safe_import("keyboardkbdd", "KeyboardKbdd")
92 safe_import("cmus", "Cmus")
93 safe_import("wallpaper", "Wallpaper")
94 safe_import("check_updates", "CheckUpdates")
95 safe_import("moc", "Moc")
96 safe_import("memory", "Memory")
97 safe_import("cpu", "CPU")
98 safe_import("idlerpg", "IdleRPG")
99 safe_import("pomodoro", "Pomodoro")
100 safe_import("stock_ticker", "StockTicker")
101 safe_import("caps_num_lock_indicator", "CapsNumLockIndicator")
102 safe_import("quick_exit", "QuickExit")
103 safe_import("pulse_volume", "PulseVolume")
104 safe_import("chord", "Chord")
105
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/libqtile/widget/__init__.py b/libqtile/widget/__init__.py
--- a/libqtile/widget/__init__.py
+++ b/libqtile/widget/__init__.py
@@ -76,7 +76,6 @@
safe_import("clipboard", "Clipboard")
safe_import("countdown", "Countdown")
safe_import("tasklist", "TaskList")
-safe_import("pacman", "Pacman")
safe_import("launchbar", "LaunchBar")
safe_import("canto", "Canto")
safe_import("mpriswidget", "Mpris")
diff --git a/libqtile/widget/pacman.py b/libqtile/widget/pacman.py
deleted file mode 100644
--- a/libqtile/widget/pacman.py
+++ /dev/null
@@ -1,56 +0,0 @@
-# -*- coding:utf-8 -*-
-#
-# Copyright (C) 2012, Maximilian Köhl <[email protected]>
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-import subprocess
-
-from libqtile.log_utils import logger
-from libqtile.widget import base
-
-
-class Pacman(base.ThreadedPollText):
- """Shows number of available updates
-
- Needs the pacman package manager installed. So will only work in Arch Linux
- installation.
- """
- orientations = base.ORIENTATION_HORIZONTAL
- defaults = [
- ('unavailable', 'ffffff', 'Unavailable Color - no updates.'),
- ('execute', None, 'Command to execute on click'),
- ('update_interval', 60, "The update interval."),
- ]
-
- def __init__(self, **config):
- logger.warning("Pacman is deprecated, please use CheckUpdates")
- base.ThreadedPollText.__init__(self, **config)
- self.add_defaults(Pacman.defaults)
-
- def draw(self):
- if self.text == '0':
- self.layout.colour = self.unavailable
- else:
- self.layout.colour = self.foreground
- base.ThreadedPollText.draw(self)
-
- def poll(self):
- pacman = self.call_process(['checkupdates'])
- return str(len(pacman.splitlines()))
-
- def button_press(self, x, y, button):
- base.ThreadedPollText.button_press(self, x, y, button)
- if button == 1 and self.execute is not None:
- subprocess.Popen([self.execute], shell=True)
|
{"golden_diff": "diff --git a/libqtile/widget/__init__.py b/libqtile/widget/__init__.py\n--- a/libqtile/widget/__init__.py\n+++ b/libqtile/widget/__init__.py\n@@ -76,7 +76,6 @@\n safe_import(\"clipboard\", \"Clipboard\")\n safe_import(\"countdown\", \"Countdown\")\n safe_import(\"tasklist\", \"TaskList\")\n-safe_import(\"pacman\", \"Pacman\")\n safe_import(\"launchbar\", \"LaunchBar\")\n safe_import(\"canto\", \"Canto\")\n safe_import(\"mpriswidget\", \"Mpris\")\ndiff --git a/libqtile/widget/pacman.py b/libqtile/widget/pacman.py\ndeleted file mode 100644\n--- a/libqtile/widget/pacman.py\n+++ /dev/null\n@@ -1,56 +0,0 @@\n-# -*- coding:utf-8 -*-\n-#\n-# Copyright (C) 2012, Maximilian K\u00f6hl <[email protected]>\n-#\n-# This program is free software: you can redistribute it and/or modify\n-# it under the terms of the GNU General Public License as published by\n-# the Free Software Foundation, either version 3 of the License, or\n-# (at your option) any later version.\n-#\n-# This program is distributed in the hope that it will be useful,\n-# but WITHOUT ANY WARRANTY; without even the implied warranty of\n-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n-# GNU General Public License for more details.\n-#\n-# You should have received a copy of the GNU General Public License\n-# along with this program. If not, see <http://www.gnu.org/licenses/>.\n-\n-import subprocess\n-\n-from libqtile.log_utils import logger\n-from libqtile.widget import base\n-\n-\n-class Pacman(base.ThreadedPollText):\n- \"\"\"Shows number of available updates\n-\n- Needs the pacman package manager installed. So will only work in Arch Linux\n- installation.\n- \"\"\"\n- orientations = base.ORIENTATION_HORIZONTAL\n- defaults = [\n- ('unavailable', 'ffffff', 'Unavailable Color - no updates.'),\n- ('execute', None, 'Command to execute on click'),\n- ('update_interval', 60, \"The update interval.\"),\n- ]\n-\n- def __init__(self, **config):\n- logger.warning(\"Pacman is deprecated, please use CheckUpdates\")\n- base.ThreadedPollText.__init__(self, **config)\n- self.add_defaults(Pacman.defaults)\n-\n- def draw(self):\n- if self.text == '0':\n- self.layout.colour = self.unavailable\n- else:\n- self.layout.colour = self.foreground\n- base.ThreadedPollText.draw(self)\n-\n- def poll(self):\n- pacman = self.call_process(['checkupdates'])\n- return str(len(pacman.splitlines()))\n-\n- def button_press(self, x, y, button):\n- base.ThreadedPollText.button_press(self, x, y, button)\n- if button == 1 and self.execute is not None:\n- subprocess.Popen([self.execute], shell=True)\n", "issue": "widget.Pacman needs a non existing file:'checkupdates'\n```\r\n2020-03-30 07:09:12,582 ERROR libqtile base.py:worker():L478 problem polling to update widget pacman\r\nTraceback (most recent call last):\r\n File \"/home/parsrch/.local/lib/python3.8/site-packages/libqtile/widget/base.py\", line 474, in worker\r\n text = self.poll()\r\n File \"/home/parsrch/.local/lib/python3.8/site-packages/libqtile/widget/pacman.py\", line 49, in poll\r\n pacman = self.call_process(['checkupdates'])\r\n File \"/home/parsrch/.local/lib/python3.8/site-packages/libqtile/widget/base.py\", line 266, in call_process\r\n output = subprocess.check_output(command, **kwargs)\r\n File \"/usr/lib/python3.8/subprocess.py\", line 411, in check_output\r\n return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,\r\n File \"/usr/lib/python3.8/subprocess.py\", line 489, in run\r\n with Popen(*popenargs, **kwargs) as process:\r\n File \"/usr/lib/python3.8/subprocess.py\", line 854, in __init__\r\n self._execute_child(args, executable, preexec_fn, close_fds,\r\n File \"/usr/lib/python3.8/subprocess.py\", line 1702, in _execute_child\r\n raise child_exception_type(errno_num, err_msg, err_filename)\r\nFileNotFoundError: [Errno 2] No such file or directory: 'checkupdates'\r\n```\n", "before_files": [{"content": "# -*- coding:utf-8 -*-\n#\n# Copyright (C) 2012, Maximilian K\u00f6hl <[email protected]>\n#\n# This program is free software: you can redistribute it and/or modify\n# it under the terms of the GNU General Public License as published by\n# the Free Software Foundation, either version 3 of the License, or\n# (at your option) any later version.\n#\n# This program is distributed in the hope that it will be useful,\n# but WITHOUT ANY WARRANTY; without even the implied warranty of\n# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n# GNU General Public License for more details.\n#\n# You should have received a copy of the GNU General Public License\n# along with this program. If not, see <http://www.gnu.org/licenses/>.\n\nimport subprocess\n\nfrom libqtile.log_utils import logger\nfrom libqtile.widget import base\n\n\nclass Pacman(base.ThreadedPollText):\n \"\"\"Shows number of available updates\n\n Needs the pacman package manager installed. So will only work in Arch Linux\n installation.\n \"\"\"\n orientations = base.ORIENTATION_HORIZONTAL\n defaults = [\n ('unavailable', 'ffffff', 'Unavailable Color - no updates.'),\n ('execute', None, 'Command to execute on click'),\n ('update_interval', 60, \"The update interval.\"),\n ]\n\n def __init__(self, **config):\n logger.warning(\"Pacman is deprecated, please use CheckUpdates\")\n base.ThreadedPollText.__init__(self, **config)\n self.add_defaults(Pacman.defaults)\n\n def draw(self):\n if self.text == '0':\n self.layout.colour = self.unavailable\n else:\n self.layout.colour = self.foreground\n base.ThreadedPollText.draw(self)\n\n def poll(self):\n pacman = self.call_process(['checkupdates'])\n return str(len(pacman.splitlines()))\n\n def button_press(self, x, y, button):\n base.ThreadedPollText.button_press(self, x, y, button)\n if button == 1 and self.execute is not None:\n subprocess.Popen([self.execute], shell=True)\n", "path": "libqtile/widget/pacman.py"}, {"content": "# Copyright (c) 2014 Rock Neurotiko\n# Copyright (c) 2014 roger\n# Copyright (c) 2015 David R. Andersen\n#\n# Permission is hereby granted, free of charge, to any person obtaining a copy\n# of this software and associated documentation files (the \"Software\"), to deal\n# in the Software without restriction, including without limitation the rights\n# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\n# copies of the Software, and to permit persons to whom the Software is\n# furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice shall be included in\n# all copies or substantial portions of the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\n# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\n# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\n# SOFTWARE.\n\nfrom libqtile.utils import safe_import as safe_import_\n# only directly import widgets that do not have any third party dependencies\n# other than those required by qtile, otherwise use the same import function\nfrom libqtile.widget.base import Mirror # noqa: F401\nfrom libqtile.widget.chord import Chord # noqa: F401\nfrom libqtile.widget.clock import Clock # noqa: F401\nfrom libqtile.widget.currentlayout import ( # noqa: F401\n CurrentLayout,\n CurrentLayoutIcon,\n)\nfrom libqtile.widget.groupbox import AGroupBox, GroupBox # noqa: F401\nfrom libqtile.widget.import_error import make_error\nfrom libqtile.widget.prompt import Prompt # noqa: F401\nfrom libqtile.widget.quick_exit import QuickExit # noqa: F401\nfrom libqtile.widget.systray import Systray # noqa: F401\nfrom libqtile.widget.textbox import TextBox # noqa: F401\nfrom libqtile.widget.windowname import WindowName # noqa: F401\n\n\ndef safe_import(module_name, class_name):\n safe_import_(\n (\".widget\", module_name), class_name, globals(), fallback=make_error\n )\n\n\nsafe_import(\"backlight\", \"Backlight\")\nsafe_import(\"battery\", [\"Battery\", \"BatteryIcon\"])\nsafe_import(\"currentscreen\", \"CurrentScreen\")\nsafe_import(\"debuginfo\", \"DebugInfo\")\nsafe_import(\n \"graph\",\n [\n \"CPUGraph\",\n \"MemoryGraph\",\n \"SwapGraph\",\n \"NetGraph\",\n \"HDDGraph\",\n \"HDDBusyGraph\",\n ],\n)\nsafe_import(\"maildir\", \"Maildir\")\nsafe_import(\"notify\", \"Notify\")\nsafe_import(\"sensors\", \"ThermalSensor\")\nsafe_import(\"sep\", \"Sep\")\nsafe_import(\"she\", \"She\")\nsafe_import(\"spacer\", \"Spacer\")\nsafe_import(\"generic_poll_text\", [\"GenPollText\", \"GenPollUrl\"])\nsafe_import(\"volume\", \"Volume\")\nsafe_import(\"windowtabs\", \"WindowTabs\")\nsafe_import(\"keyboardlayout\", \"KeyboardLayout\")\nsafe_import(\"df\", \"DF\")\nsafe_import(\"image\", \"Image\")\nsafe_import(\"gmail_checker\", \"GmailChecker\")\nsafe_import(\"clipboard\", \"Clipboard\")\nsafe_import(\"countdown\", \"Countdown\")\nsafe_import(\"tasklist\", \"TaskList\")\nsafe_import(\"pacman\", \"Pacman\")\nsafe_import(\"launchbar\", \"LaunchBar\")\nsafe_import(\"canto\", \"Canto\")\nsafe_import(\"mpriswidget\", \"Mpris\")\nsafe_import(\"mpris2widget\", \"Mpris2\")\nsafe_import(\"mpd2widget\", \"Mpd2\")\nsafe_import(\"yahoo_weather\", \"YahooWeather\")\nsafe_import(\"bitcoin_ticker\", \"BitcoinTicker\")\nsafe_import(\"wlan\", \"Wlan\")\nsafe_import(\"khal_calendar\", \"KhalCalendar\")\nsafe_import(\"imapwidget\", \"ImapWidget\")\nsafe_import(\"net\", \"Net\")\nsafe_import(\"keyboardkbdd\", \"KeyboardKbdd\")\nsafe_import(\"cmus\", \"Cmus\")\nsafe_import(\"wallpaper\", \"Wallpaper\")\nsafe_import(\"check_updates\", \"CheckUpdates\")\nsafe_import(\"moc\", \"Moc\")\nsafe_import(\"memory\", \"Memory\")\nsafe_import(\"cpu\", \"CPU\")\nsafe_import(\"idlerpg\", \"IdleRPG\")\nsafe_import(\"pomodoro\", \"Pomodoro\")\nsafe_import(\"stock_ticker\", \"StockTicker\")\nsafe_import(\"caps_num_lock_indicator\", \"CapsNumLockIndicator\")\nsafe_import(\"quick_exit\", \"QuickExit\")\nsafe_import(\"pulse_volume\", \"PulseVolume\")\nsafe_import(\"chord\", \"Chord\")\n", "path": "libqtile/widget/__init__.py"}], "after_files": [{"content": null, "path": "libqtile/widget/pacman.py"}, {"content": "# Copyright (c) 2014 Rock Neurotiko\n# Copyright (c) 2014 roger\n# Copyright (c) 2015 David R. Andersen\n#\n# Permission is hereby granted, free of charge, to any person obtaining a copy\n# of this software and associated documentation files (the \"Software\"), to deal\n# in the Software without restriction, including without limitation the rights\n# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\n# copies of the Software, and to permit persons to whom the Software is\n# furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice shall be included in\n# all copies or substantial portions of the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\n# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\n# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\n# SOFTWARE.\n\nfrom libqtile.utils import safe_import as safe_import_\n# only directly import widgets that do not have any third party dependencies\n# other than those required by qtile, otherwise use the same import function\nfrom libqtile.widget.base import Mirror # noqa: F401\nfrom libqtile.widget.chord import Chord # noqa: F401\nfrom libqtile.widget.clock import Clock # noqa: F401\nfrom libqtile.widget.currentlayout import ( # noqa: F401\n CurrentLayout,\n CurrentLayoutIcon,\n)\nfrom libqtile.widget.groupbox import AGroupBox, GroupBox # noqa: F401\nfrom libqtile.widget.import_error import make_error\nfrom libqtile.widget.prompt import Prompt # noqa: F401\nfrom libqtile.widget.quick_exit import QuickExit # noqa: F401\nfrom libqtile.widget.systray import Systray # noqa: F401\nfrom libqtile.widget.textbox import TextBox # noqa: F401\nfrom libqtile.widget.windowname import WindowName # noqa: F401\n\n\ndef safe_import(module_name, class_name):\n safe_import_(\n (\".widget\", module_name), class_name, globals(), fallback=make_error\n )\n\n\nsafe_import(\"backlight\", \"Backlight\")\nsafe_import(\"battery\", [\"Battery\", \"BatteryIcon\"])\nsafe_import(\"currentscreen\", \"CurrentScreen\")\nsafe_import(\"debuginfo\", \"DebugInfo\")\nsafe_import(\n \"graph\",\n [\n \"CPUGraph\",\n \"MemoryGraph\",\n \"SwapGraph\",\n \"NetGraph\",\n \"HDDGraph\",\n \"HDDBusyGraph\",\n ],\n)\nsafe_import(\"maildir\", \"Maildir\")\nsafe_import(\"notify\", \"Notify\")\nsafe_import(\"sensors\", \"ThermalSensor\")\nsafe_import(\"sep\", \"Sep\")\nsafe_import(\"she\", \"She\")\nsafe_import(\"spacer\", \"Spacer\")\nsafe_import(\"generic_poll_text\", [\"GenPollText\", \"GenPollUrl\"])\nsafe_import(\"volume\", \"Volume\")\nsafe_import(\"windowtabs\", \"WindowTabs\")\nsafe_import(\"keyboardlayout\", \"KeyboardLayout\")\nsafe_import(\"df\", \"DF\")\nsafe_import(\"image\", \"Image\")\nsafe_import(\"gmail_checker\", \"GmailChecker\")\nsafe_import(\"clipboard\", \"Clipboard\")\nsafe_import(\"countdown\", \"Countdown\")\nsafe_import(\"tasklist\", \"TaskList\")\nsafe_import(\"launchbar\", \"LaunchBar\")\nsafe_import(\"canto\", \"Canto\")\nsafe_import(\"mpriswidget\", \"Mpris\")\nsafe_import(\"mpris2widget\", \"Mpris2\")\nsafe_import(\"mpd2widget\", \"Mpd2\")\nsafe_import(\"yahoo_weather\", \"YahooWeather\")\nsafe_import(\"bitcoin_ticker\", \"BitcoinTicker\")\nsafe_import(\"wlan\", \"Wlan\")\nsafe_import(\"khal_calendar\", \"KhalCalendar\")\nsafe_import(\"imapwidget\", \"ImapWidget\")\nsafe_import(\"net\", \"Net\")\nsafe_import(\"keyboardkbdd\", \"KeyboardKbdd\")\nsafe_import(\"cmus\", \"Cmus\")\nsafe_import(\"wallpaper\", \"Wallpaper\")\nsafe_import(\"check_updates\", \"CheckUpdates\")\nsafe_import(\"moc\", \"Moc\")\nsafe_import(\"memory\", \"Memory\")\nsafe_import(\"cpu\", \"CPU\")\nsafe_import(\"idlerpg\", \"IdleRPG\")\nsafe_import(\"pomodoro\", \"Pomodoro\")\nsafe_import(\"stock_ticker\", \"StockTicker\")\nsafe_import(\"caps_num_lock_indicator\", \"CapsNumLockIndicator\")\nsafe_import(\"quick_exit\", \"QuickExit\")\nsafe_import(\"pulse_volume\", \"PulseVolume\")\nsafe_import(\"chord\", \"Chord\")\n", "path": "libqtile/widget/__init__.py"}]}
| 2,493 | 686 |
gh_patches_debug_5067
|
rasdani/github-patches
|
git_diff
|
jupyterhub__jupyterhub-1111
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Passwords beginning or ending with a whitespace are not supported
Due to POST argument stripping, passwords with a beginning or ending whitespace are not allowed.
**How to reproduce the issue**
Set up a user password with an ending or beginning whitespace.
**What you expected to happen**
The user should be allowed to login with the password, given that the password should be any complicated sequence of characters the user can reproduce.
**What actually happens**
The user is denied access, because the LoginHandler will strip all posted values before considering the password for authentication (line 81, get_argument has a default "strip=True")
**Share what version of JupyterHub you are using**
HEAD (006488fc749923851df97d47d8850bdf5fd157cf)
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `jupyterhub/handlers/login.py`
Content:
```
1 """HTTP Handlers for the hub server"""
2
3 # Copyright (c) Jupyter Development Team.
4 # Distributed under the terms of the Modified BSD License.
5
6 from urllib.parse import urlparse
7
8 from tornado.escape import url_escape
9 from tornado import gen
10 from tornado.httputil import url_concat
11
12 from .base import BaseHandler
13
14
15 class LogoutHandler(BaseHandler):
16 """Log a user out by clearing their login cookie."""
17 def get(self):
18 user = self.get_current_user()
19 if user:
20 self.log.info("User logged out: %s", user.name)
21 self.clear_login_cookie()
22 self.statsd.incr('logout')
23 if self.authenticator.auto_login:
24 self.render('logout.html')
25 else:
26 self.redirect(self.settings['login_url'], permanent=False)
27
28
29 class LoginHandler(BaseHandler):
30 """Render the login page."""
31
32 def _render(self, login_error=None, username=None):
33 return self.render_template('login.html',
34 next=url_escape(self.get_argument('next', default='')),
35 username=username,
36 login_error=login_error,
37 custom_html=self.authenticator.custom_html,
38 login_url=self.settings['login_url'],
39 authenticator_login_url=self.authenticator.login_url(self.hub.server.base_url),
40 )
41
42 def get(self):
43 self.statsd.incr('login.request')
44 next_url = self.get_argument('next', '')
45 if (next_url + '/').startswith('%s://%s/' % (self.request.protocol, self.request.host)):
46 # treat absolute URLs for our host as absolute paths:
47 next_url = urlparse(next_url).path
48 elif not next_url.startswith('/'):
49 # disallow non-absolute next URLs (e.g. full URLs to other hosts)
50 next_url = ''
51 user = self.get_current_user()
52 if user:
53 if not next_url:
54 if user.running:
55 next_url = user.url
56 else:
57 next_url = self.hub.server.base_url
58 # set new login cookie
59 # because single-user cookie may have been cleared or incorrect
60 self.set_login_cookie(self.get_current_user())
61 self.redirect(next_url, permanent=False)
62 else:
63 if self.authenticator.auto_login:
64 auto_login_url = self.authenticator.login_url(self.hub.server.base_url)
65 if auto_login_url == self.settings['login_url']:
66 self.authenticator.auto_login = False
67 self.log.warning("Authenticator.auto_login cannot be used without a custom login_url")
68 else:
69 if next_url:
70 auto_login_url = url_concat(auto_login_url, {'next': next_url})
71 self.redirect(auto_login_url)
72 return
73 username = self.get_argument('username', default='')
74 self.finish(self._render(username=username))
75
76 @gen.coroutine
77 def post(self):
78 # parse the arguments dict
79 data = {}
80 for arg in self.request.arguments:
81 data[arg] = self.get_argument(arg)
82
83 auth_timer = self.statsd.timer('login.authenticate').start()
84 username = yield self.authenticate(data)
85 auth_timer.stop(send=False)
86
87 if username:
88 self.statsd.incr('login.success')
89 self.statsd.timing('login.authenticate.success', auth_timer.ms)
90 user = self.user_from_username(username)
91 already_running = False
92 if user.spawner:
93 status = yield user.spawner.poll()
94 already_running = (status == None)
95 if not already_running and not user.spawner.options_form:
96 yield self.spawn_single_user(user)
97 self.set_login_cookie(user)
98 next_url = self.get_argument('next', default='')
99 if not next_url.startswith('/'):
100 next_url = ''
101 next_url = next_url or self.hub.server.base_url
102 self.redirect(next_url)
103 self.log.info("User logged in: %s", username)
104 else:
105 self.statsd.incr('login.failure')
106 self.statsd.timing('login.authenticate.failure', auth_timer.ms)
107 self.log.debug("Failed login for %s", data.get('username', 'unknown user'))
108 html = self._render(
109 login_error='Invalid username or password',
110 username=username,
111 )
112 self.finish(html)
113
114
115 # /login renders the login page or the "Login with..." link,
116 # so it should always be registered.
117 # /logout clears cookies.
118 default_handlers = [
119 (r"/login", LoginHandler),
120 (r"/logout", LogoutHandler),
121 ]
122
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/jupyterhub/handlers/login.py b/jupyterhub/handlers/login.py
--- a/jupyterhub/handlers/login.py
+++ b/jupyterhub/handlers/login.py
@@ -78,7 +78,7 @@
# parse the arguments dict
data = {}
for arg in self.request.arguments:
- data[arg] = self.get_argument(arg)
+ data[arg] = self.get_argument(arg, strip=False)
auth_timer = self.statsd.timer('login.authenticate').start()
username = yield self.authenticate(data)
|
{"golden_diff": "diff --git a/jupyterhub/handlers/login.py b/jupyterhub/handlers/login.py\n--- a/jupyterhub/handlers/login.py\n+++ b/jupyterhub/handlers/login.py\n@@ -78,7 +78,7 @@\n # parse the arguments dict\n data = {}\n for arg in self.request.arguments:\n- data[arg] = self.get_argument(arg)\n+ data[arg] = self.get_argument(arg, strip=False)\n \n auth_timer = self.statsd.timer('login.authenticate').start()\n username = yield self.authenticate(data)\n", "issue": "Passwords beginning or ending with a whitespace are not supported\nDue to POST argument stripping, passwords with a beginning or ending whitespace are not allowed.\r\n\r\n**How to reproduce the issue**\r\nSet up a user password with an ending or beginning whitespace.\r\n\r\n**What you expected to happen**\r\nThe user should be allowed to login with the password, given that the password should be any complicated sequence of characters the user can reproduce.\r\n\r\n**What actually happens**\r\nThe user is denied access, because the LoginHandler will strip all posted values before considering the password for authentication (line 81, get_argument has a default \"strip=True\")\r\n\r\n**Share what version of JupyterHub you are using**\r\nHEAD (006488fc749923851df97d47d8850bdf5fd157cf)\r\n\r\n\r\n\n", "before_files": [{"content": "\"\"\"HTTP Handlers for the hub server\"\"\"\n\n# Copyright (c) Jupyter Development Team.\n# Distributed under the terms of the Modified BSD License.\n\nfrom urllib.parse import urlparse\n\nfrom tornado.escape import url_escape\nfrom tornado import gen\nfrom tornado.httputil import url_concat\n\nfrom .base import BaseHandler\n\n\nclass LogoutHandler(BaseHandler):\n \"\"\"Log a user out by clearing their login cookie.\"\"\"\n def get(self):\n user = self.get_current_user()\n if user:\n self.log.info(\"User logged out: %s\", user.name)\n self.clear_login_cookie()\n self.statsd.incr('logout')\n if self.authenticator.auto_login:\n self.render('logout.html')\n else:\n self.redirect(self.settings['login_url'], permanent=False)\n\n\nclass LoginHandler(BaseHandler):\n \"\"\"Render the login page.\"\"\"\n\n def _render(self, login_error=None, username=None):\n return self.render_template('login.html',\n next=url_escape(self.get_argument('next', default='')),\n username=username,\n login_error=login_error,\n custom_html=self.authenticator.custom_html,\n login_url=self.settings['login_url'],\n authenticator_login_url=self.authenticator.login_url(self.hub.server.base_url),\n )\n\n def get(self):\n self.statsd.incr('login.request')\n next_url = self.get_argument('next', '')\n if (next_url + '/').startswith('%s://%s/' % (self.request.protocol, self.request.host)):\n # treat absolute URLs for our host as absolute paths:\n next_url = urlparse(next_url).path\n elif not next_url.startswith('/'):\n # disallow non-absolute next URLs (e.g. full URLs to other hosts)\n next_url = ''\n user = self.get_current_user()\n if user:\n if not next_url:\n if user.running:\n next_url = user.url\n else:\n next_url = self.hub.server.base_url\n # set new login cookie\n # because single-user cookie may have been cleared or incorrect\n self.set_login_cookie(self.get_current_user())\n self.redirect(next_url, permanent=False)\n else:\n if self.authenticator.auto_login:\n auto_login_url = self.authenticator.login_url(self.hub.server.base_url)\n if auto_login_url == self.settings['login_url']:\n self.authenticator.auto_login = False\n self.log.warning(\"Authenticator.auto_login cannot be used without a custom login_url\")\n else:\n if next_url:\n auto_login_url = url_concat(auto_login_url, {'next': next_url})\n self.redirect(auto_login_url)\n return\n username = self.get_argument('username', default='')\n self.finish(self._render(username=username))\n\n @gen.coroutine\n def post(self):\n # parse the arguments dict\n data = {}\n for arg in self.request.arguments:\n data[arg] = self.get_argument(arg)\n\n auth_timer = self.statsd.timer('login.authenticate').start()\n username = yield self.authenticate(data)\n auth_timer.stop(send=False)\n\n if username:\n self.statsd.incr('login.success')\n self.statsd.timing('login.authenticate.success', auth_timer.ms)\n user = self.user_from_username(username)\n already_running = False\n if user.spawner:\n status = yield user.spawner.poll()\n already_running = (status == None)\n if not already_running and not user.spawner.options_form:\n yield self.spawn_single_user(user)\n self.set_login_cookie(user)\n next_url = self.get_argument('next', default='')\n if not next_url.startswith('/'):\n next_url = ''\n next_url = next_url or self.hub.server.base_url\n self.redirect(next_url)\n self.log.info(\"User logged in: %s\", username)\n else:\n self.statsd.incr('login.failure')\n self.statsd.timing('login.authenticate.failure', auth_timer.ms)\n self.log.debug(\"Failed login for %s\", data.get('username', 'unknown user'))\n html = self._render(\n login_error='Invalid username or password',\n username=username,\n )\n self.finish(html)\n\n\n# /login renders the login page or the \"Login with...\" link,\n# so it should always be registered.\n# /logout clears cookies.\ndefault_handlers = [\n (r\"/login\", LoginHandler),\n (r\"/logout\", LogoutHandler),\n]\n", "path": "jupyterhub/handlers/login.py"}], "after_files": [{"content": "\"\"\"HTTP Handlers for the hub server\"\"\"\n\n# Copyright (c) Jupyter Development Team.\n# Distributed under the terms of the Modified BSD License.\n\nfrom urllib.parse import urlparse\n\nfrom tornado.escape import url_escape\nfrom tornado import gen\nfrom tornado.httputil import url_concat\n\nfrom .base import BaseHandler\n\n\nclass LogoutHandler(BaseHandler):\n \"\"\"Log a user out by clearing their login cookie.\"\"\"\n def get(self):\n user = self.get_current_user()\n if user:\n self.log.info(\"User logged out: %s\", user.name)\n self.clear_login_cookie()\n self.statsd.incr('logout')\n if self.authenticator.auto_login:\n self.render('logout.html')\n else:\n self.redirect(self.settings['login_url'], permanent=False)\n\n\nclass LoginHandler(BaseHandler):\n \"\"\"Render the login page.\"\"\"\n\n def _render(self, login_error=None, username=None):\n return self.render_template('login.html',\n next=url_escape(self.get_argument('next', default='')),\n username=username,\n login_error=login_error,\n custom_html=self.authenticator.custom_html,\n login_url=self.settings['login_url'],\n authenticator_login_url=self.authenticator.login_url(self.hub.server.base_url),\n )\n\n def get(self):\n self.statsd.incr('login.request')\n next_url = self.get_argument('next', '')\n if (next_url + '/').startswith('%s://%s/' % (self.request.protocol, self.request.host)):\n # treat absolute URLs for our host as absolute paths:\n next_url = urlparse(next_url).path\n elif not next_url.startswith('/'):\n # disallow non-absolute next URLs (e.g. full URLs to other hosts)\n next_url = ''\n user = self.get_current_user()\n if user:\n if not next_url:\n if user.running:\n next_url = user.url\n else:\n next_url = self.hub.server.base_url\n # set new login cookie\n # because single-user cookie may have been cleared or incorrect\n self.set_login_cookie(self.get_current_user())\n self.redirect(next_url, permanent=False)\n else:\n if self.authenticator.auto_login:\n auto_login_url = self.authenticator.login_url(self.hub.server.base_url)\n if auto_login_url == self.settings['login_url']:\n self.authenticator.auto_login = False\n self.log.warning(\"Authenticator.auto_login cannot be used without a custom login_url\")\n else:\n if next_url:\n auto_login_url = url_concat(auto_login_url, {'next': next_url})\n self.redirect(auto_login_url)\n return\n username = self.get_argument('username', default='')\n self.finish(self._render(username=username))\n\n @gen.coroutine\n def post(self):\n # parse the arguments dict\n data = {}\n for arg in self.request.arguments:\n data[arg] = self.get_argument(arg, strip=False)\n\n auth_timer = self.statsd.timer('login.authenticate').start()\n username = yield self.authenticate(data)\n auth_timer.stop(send=False)\n\n if username:\n self.statsd.incr('login.success')\n self.statsd.timing('login.authenticate.success', auth_timer.ms)\n user = self.user_from_username(username)\n already_running = False\n if user.spawner:\n status = yield user.spawner.poll()\n already_running = (status == None)\n if not already_running and not user.spawner.options_form:\n yield self.spawn_single_user(user)\n self.set_login_cookie(user)\n next_url = self.get_argument('next', default='')\n if not next_url.startswith('/'):\n next_url = ''\n next_url = next_url or self.hub.server.base_url\n self.redirect(next_url)\n self.log.info(\"User logged in: %s\", username)\n else:\n self.statsd.incr('login.failure')\n self.statsd.timing('login.authenticate.failure', auth_timer.ms)\n self.log.debug(\"Failed login for %s\", data.get('username', 'unknown user'))\n html = self._render(\n login_error='Invalid username or password',\n username=username,\n )\n self.finish(html)\n\n\n# /login renders the login page or the \"Login with...\" link,\n# so it should always be registered.\n# /logout clears cookies.\ndefault_handlers = [\n (r\"/login\", LoginHandler),\n (r\"/logout\", LogoutHandler),\n]\n", "path": "jupyterhub/handlers/login.py"}]}
| 1,622 | 123 |
gh_patches_debug_40750
|
rasdani/github-patches
|
git_diff
|
streamlit__streamlit-188
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Blacklist common virtualenv folders by default
We should blacklist the folders below from being watched by Streamlit. This would fix the issue where some people hit the inotify watch limit when running Streamlit from a weird working directory.
* */.virtualenv
* */.venv
* */anaconda3
* */anaconda2
* */miniconda3
* */miniconda2
* Actually let's blacklist every hidden folder: `.*`
See also the config option `server.folderWatchBlacklist`. For this fix, you can probably use the same mechanism this config option uses.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `lib/streamlit/watcher/LocalSourcesWatcher.py`
Content:
```
1 # -*- coding: utf-8 -*-
2 # Copyright 2018-2019 Streamlit Inc.
3 #
4 # Licensed under the Apache License, Version 2.0 (the "License");
5 # you may not use this file except in compliance with the License.
6 # You may obtain a copy of the License at
7 #
8 # http://www.apache.org/licenses/LICENSE-2.0
9 #
10 # Unless required by applicable law or agreed to in writing, software
11 # distributed under the License is distributed on an "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 # See the License for the specific language governing permissions and
14 # limitations under the License.
15
16 import os
17 import sys
18 import collections
19
20 try:
21 # Python 2
22 import imp as importlib
23 except ImportError:
24 # Python 3
25 import importlib
26
27 from streamlit import config
28 from streamlit import util
29
30 from streamlit.logger import get_logger
31 LOGGER = get_logger(__name__)
32
33 try:
34 # If the watchdog module is installed.
35 from streamlit.watcher.EventBasedFileWatcher import (
36 EventBasedFileWatcher as FileWatcher,
37 )
38 except ImportError:
39 # Fallback that doesn't use watchdog.
40 from streamlit.watcher.PollingFileWatcher import PollingFileWatcher as FileWatcher
41
42 if not config.get_option('global.disableWatchdogWarning'):
43 msg = '\n $ xcode-select --install' if util.is_darwin() else ''
44
45 LOGGER.warning("""
46 For better performance, install the Watchdog module:
47 %s
48 $ pip install watchdog
49
50 """ % msg)
51
52
53 WatchedModule = collections.namedtuple("WatchedModule", ["watcher", "module_name"])
54
55
56 class LocalSourcesWatcher(object):
57 def __init__(self, report, on_file_changed):
58 self._report = report
59 self._on_file_changed = on_file_changed
60 self._is_closed = False
61
62 self._folder_blacklist = config.get_option("server.folderWatchBlacklist")
63
64 # A dict of filepath -> WatchedModule.
65 self._watched_modules = {}
66
67 self._register_watcher(
68 self._report.script_path,
69 module_name=None, # Only the root script has None here.
70 )
71
72 def on_file_changed(self, filepath):
73 if filepath not in self._watched_modules:
74 LOGGER.error("Received event for non-watched file", filepath)
75 return
76
77 wm = self._watched_modules[filepath]
78
79 if wm.module_name is not None and wm.module_name in sys.modules:
80 del sys.modules[wm.module_name]
81
82 self._on_file_changed()
83
84 def close(self):
85 for wm in self._watched_modules.values():
86 wm.watcher.close()
87 self._watched_modules = {}
88 self._is_closed = True
89
90 def _register_watcher(self, filepath, module_name):
91 wm = WatchedModule(
92 watcher=FileWatcher(filepath, self.on_file_changed), module_name=module_name
93 )
94 self._watched_modules[filepath] = wm
95
96 def _deregister_watcher(self, filepath):
97 if filepath not in self._watched_modules:
98 return
99
100 if filepath == self._report.script_path:
101 return
102
103 wm = self._watched_modules[filepath]
104 wm.watcher.close()
105 del self._watched_modules[filepath]
106
107 def update_watched_modules(self):
108 if self._is_closed:
109 return
110
111 local_filepaths = []
112
113 # Clone modules dict here because we may alter the original dict inside
114 # the loop.
115 modules = dict(sys.modules)
116
117 for name, module in modules.items():
118 try:
119 spec = getattr(module, "__spec__", None)
120
121 if spec is None:
122 filepath = getattr(module, "__file__", None)
123 if filepath is None:
124 # Some modules have neither a spec nor a file. But we
125 # can ignore those since they're not the user-created
126 # modules we want to watch anyway.
127 continue
128 else:
129 filepath = spec.origin
130
131 if filepath is None:
132 # Built-in modules (and other stuff) don't have origins.
133 continue
134
135 filepath = os.path.abspath(filepath)
136
137 if not os.path.isfile(filepath):
138 # There are some modules that have a .origin, but don't
139 # point to real files. For example, there's a module where
140 # .origin is 'built-in'.
141 continue
142
143 folder_is_blacklisted = any(
144 _file_is_in_folder(filepath, blacklisted_folder)
145 for blacklisted_folder in self._folder_blacklist
146 )
147
148 if folder_is_blacklisted:
149 continue
150
151 file_is_new = filepath not in self._watched_modules
152 file_is_local = _file_is_in_folder(filepath, self._report.script_folder)
153
154 local_filepaths.append(filepath)
155
156 if file_is_local and file_is_new:
157 self._register_watcher(filepath, name)
158
159 except Exception:
160 # In case there's a problem introspecting some specific module,
161 # let's not stop the entire loop from running. For example,
162 # the __spec__ field in some modules (like IPython) is actually
163 # a dynamic property, which can crash if the underlying
164 # module's code has a bug (as discovered by one of our users).
165 continue
166
167 # Clone dict here because we may alter the original dict inside the
168 # loop.
169 watched_modules = dict(self._watched_modules)
170
171 # Remove no-longer-depended-on files from self._watched_modules
172 # Will this ever happen?
173 for filepath in watched_modules:
174 if filepath not in local_filepaths:
175 self._deregister_watcher(filepath)
176
177
178 def _file_is_in_folder(filepath, folderpath):
179 # Assumes filepath is an absolute path, as a teeny tiny optimization.
180 folderpath = os.path.abspath(folderpath) + "/"
181 return filepath.startswith(folderpath)
182
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/lib/streamlit/watcher/LocalSourcesWatcher.py b/lib/streamlit/watcher/LocalSourcesWatcher.py
--- a/lib/streamlit/watcher/LocalSourcesWatcher.py
+++ b/lib/streamlit/watcher/LocalSourcesWatcher.py
@@ -13,6 +13,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
+import fnmatch
import os
import sys
import collections
@@ -28,6 +29,7 @@
from streamlit import util
from streamlit.logger import get_logger
+
LOGGER = get_logger(__name__)
try:
@@ -39,15 +41,24 @@
# Fallback that doesn't use watchdog.
from streamlit.watcher.PollingFileWatcher import PollingFileWatcher as FileWatcher
- if not config.get_option('global.disableWatchdogWarning'):
- msg = '\n $ xcode-select --install' if util.is_darwin() else ''
+ if not config.get_option("global.disableWatchdogWarning"):
+ msg = "\n $ xcode-select --install" if util.is_darwin() else ""
- LOGGER.warning("""
+ LOGGER.warning(
+ """
For better performance, install the Watchdog module:
%s
$ pip install watchdog
- """ % msg)
+ """
+ % msg
+ )
+
+
+# Streamlit never watches files in the folders below.
+DEFAULT_FOLDER_BLACKLIST = [
+ "**/.*", "**/anaconda2", "**/anaconda3", "**/miniconda2", "**/miniconda3"
+]
WatchedModule = collections.namedtuple("WatchedModule", ["watcher", "module_name"])
@@ -61,6 +72,9 @@
self._folder_blacklist = config.get_option("server.folderWatchBlacklist")
+ # Blacklist some additional folders, using glob syntax.
+ self._folder_blacklist.extend(DEFAULT_FOLDER_BLACKLIST)
+
# A dict of filepath -> WatchedModule.
self._watched_modules = {}
@@ -140,12 +154,12 @@
# .origin is 'built-in'.
continue
- folder_is_blacklisted = any(
+ is_in_blacklisted_folder = any(
_file_is_in_folder(filepath, blacklisted_folder)
for blacklisted_folder in self._folder_blacklist
)
- if folder_is_blacklisted:
+ if is_in_blacklisted_folder:
continue
file_is_new = filepath not in self._watched_modules
@@ -175,7 +189,10 @@
self._deregister_watcher(filepath)
-def _file_is_in_folder(filepath, folderpath):
- # Assumes filepath is an absolute path, as a teeny tiny optimization.
- folderpath = os.path.abspath(folderpath) + "/"
- return filepath.startswith(folderpath)
+def _file_is_in_folder(filepath, folderpath_glob):
+ # Strip trailing slash if it exists
+ if folderpath_glob.endswith("/"):
+ folderpath_glob = folderpath_glob[:-1]
+
+ file_dir = os.path.dirname(filepath)
+ return fnmatch.fnmatch(file_dir, folderpath_glob)
|
{"golden_diff": "diff --git a/lib/streamlit/watcher/LocalSourcesWatcher.py b/lib/streamlit/watcher/LocalSourcesWatcher.py\n--- a/lib/streamlit/watcher/LocalSourcesWatcher.py\n+++ b/lib/streamlit/watcher/LocalSourcesWatcher.py\n@@ -13,6 +13,7 @@\n # See the License for the specific language governing permissions and\n # limitations under the License.\n \n+import fnmatch\n import os\n import sys\n import collections\n@@ -28,6 +29,7 @@\n from streamlit import util\n \n from streamlit.logger import get_logger\n+\n LOGGER = get_logger(__name__)\n \n try:\n@@ -39,15 +41,24 @@\n # Fallback that doesn't use watchdog.\n from streamlit.watcher.PollingFileWatcher import PollingFileWatcher as FileWatcher\n \n- if not config.get_option('global.disableWatchdogWarning'):\n- msg = '\\n $ xcode-select --install' if util.is_darwin() else ''\n+ if not config.get_option(\"global.disableWatchdogWarning\"):\n+ msg = \"\\n $ xcode-select --install\" if util.is_darwin() else \"\"\n \n- LOGGER.warning(\"\"\"\n+ LOGGER.warning(\n+ \"\"\"\n For better performance, install the Watchdog module:\n %s\n $ pip install watchdog\n \n- \"\"\" % msg)\n+ \"\"\"\n+ % msg\n+ )\n+\n+\n+# Streamlit never watches files in the folders below.\n+DEFAULT_FOLDER_BLACKLIST = [\n+ \"**/.*\", \"**/anaconda2\", \"**/anaconda3\", \"**/miniconda2\", \"**/miniconda3\"\n+]\n \n \n WatchedModule = collections.namedtuple(\"WatchedModule\", [\"watcher\", \"module_name\"])\n@@ -61,6 +72,9 @@\n \n self._folder_blacklist = config.get_option(\"server.folderWatchBlacklist\")\n \n+ # Blacklist some additional folders, using glob syntax.\n+ self._folder_blacklist.extend(DEFAULT_FOLDER_BLACKLIST)\n+\n # A dict of filepath -> WatchedModule.\n self._watched_modules = {}\n \n@@ -140,12 +154,12 @@\n # .origin is 'built-in'.\n continue\n \n- folder_is_blacklisted = any(\n+ is_in_blacklisted_folder = any(\n _file_is_in_folder(filepath, blacklisted_folder)\n for blacklisted_folder in self._folder_blacklist\n )\n \n- if folder_is_blacklisted:\n+ if is_in_blacklisted_folder:\n continue\n \n file_is_new = filepath not in self._watched_modules\n@@ -175,7 +189,10 @@\n self._deregister_watcher(filepath)\n \n \n-def _file_is_in_folder(filepath, folderpath):\n- # Assumes filepath is an absolute path, as a teeny tiny optimization.\n- folderpath = os.path.abspath(folderpath) + \"/\"\n- return filepath.startswith(folderpath)\n+def _file_is_in_folder(filepath, folderpath_glob):\n+ # Strip trailing slash if it exists\n+ if folderpath_glob.endswith(\"/\"):\n+ folderpath_glob = folderpath_glob[:-1]\n+\n+ file_dir = os.path.dirname(filepath)\n+ return fnmatch.fnmatch(file_dir, folderpath_glob)\n", "issue": "Blacklist common virtualenv folders by default\nWe should blacklist the folders below from being watched by Streamlit. This would fix the issue where some people hit the inotify watch limit when running Streamlit from a weird working directory.\r\n\r\n* */.virtualenv\r\n* */.venv\r\n* */anaconda3\r\n* */anaconda2\r\n* */miniconda3\r\n* */miniconda2\r\n* Actually let's blacklist every hidden folder: `.*`\r\n\r\n\r\nSee also the config option `server.folderWatchBlacklist`. For this fix, you can probably use the same mechanism this config option uses.\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n# Copyright 2018-2019 Streamlit Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport os\nimport sys\nimport collections\n\ntry:\n # Python 2\n import imp as importlib\nexcept ImportError:\n # Python 3\n import importlib\n\nfrom streamlit import config\nfrom streamlit import util\n\nfrom streamlit.logger import get_logger\nLOGGER = get_logger(__name__)\n\ntry:\n # If the watchdog module is installed.\n from streamlit.watcher.EventBasedFileWatcher import (\n EventBasedFileWatcher as FileWatcher,\n )\nexcept ImportError:\n # Fallback that doesn't use watchdog.\n from streamlit.watcher.PollingFileWatcher import PollingFileWatcher as FileWatcher\n\n if not config.get_option('global.disableWatchdogWarning'):\n msg = '\\n $ xcode-select --install' if util.is_darwin() else ''\n\n LOGGER.warning(\"\"\"\n For better performance, install the Watchdog module:\n %s\n $ pip install watchdog\n\n \"\"\" % msg)\n\n\nWatchedModule = collections.namedtuple(\"WatchedModule\", [\"watcher\", \"module_name\"])\n\n\nclass LocalSourcesWatcher(object):\n def __init__(self, report, on_file_changed):\n self._report = report\n self._on_file_changed = on_file_changed\n self._is_closed = False\n\n self._folder_blacklist = config.get_option(\"server.folderWatchBlacklist\")\n\n # A dict of filepath -> WatchedModule.\n self._watched_modules = {}\n\n self._register_watcher(\n self._report.script_path,\n module_name=None, # Only the root script has None here.\n )\n\n def on_file_changed(self, filepath):\n if filepath not in self._watched_modules:\n LOGGER.error(\"Received event for non-watched file\", filepath)\n return\n\n wm = self._watched_modules[filepath]\n\n if wm.module_name is not None and wm.module_name in sys.modules:\n del sys.modules[wm.module_name]\n\n self._on_file_changed()\n\n def close(self):\n for wm in self._watched_modules.values():\n wm.watcher.close()\n self._watched_modules = {}\n self._is_closed = True\n\n def _register_watcher(self, filepath, module_name):\n wm = WatchedModule(\n watcher=FileWatcher(filepath, self.on_file_changed), module_name=module_name\n )\n self._watched_modules[filepath] = wm\n\n def _deregister_watcher(self, filepath):\n if filepath not in self._watched_modules:\n return\n\n if filepath == self._report.script_path:\n return\n\n wm = self._watched_modules[filepath]\n wm.watcher.close()\n del self._watched_modules[filepath]\n\n def update_watched_modules(self):\n if self._is_closed:\n return\n\n local_filepaths = []\n\n # Clone modules dict here because we may alter the original dict inside\n # the loop.\n modules = dict(sys.modules)\n\n for name, module in modules.items():\n try:\n spec = getattr(module, \"__spec__\", None)\n\n if spec is None:\n filepath = getattr(module, \"__file__\", None)\n if filepath is None:\n # Some modules have neither a spec nor a file. But we\n # can ignore those since they're not the user-created\n # modules we want to watch anyway.\n continue\n else:\n filepath = spec.origin\n\n if filepath is None:\n # Built-in modules (and other stuff) don't have origins.\n continue\n\n filepath = os.path.abspath(filepath)\n\n if not os.path.isfile(filepath):\n # There are some modules that have a .origin, but don't\n # point to real files. For example, there's a module where\n # .origin is 'built-in'.\n continue\n\n folder_is_blacklisted = any(\n _file_is_in_folder(filepath, blacklisted_folder)\n for blacklisted_folder in self._folder_blacklist\n )\n\n if folder_is_blacklisted:\n continue\n\n file_is_new = filepath not in self._watched_modules\n file_is_local = _file_is_in_folder(filepath, self._report.script_folder)\n\n local_filepaths.append(filepath)\n\n if file_is_local and file_is_new:\n self._register_watcher(filepath, name)\n\n except Exception:\n # In case there's a problem introspecting some specific module,\n # let's not stop the entire loop from running. For example,\n # the __spec__ field in some modules (like IPython) is actually\n # a dynamic property, which can crash if the underlying\n # module's code has a bug (as discovered by one of our users).\n continue\n\n # Clone dict here because we may alter the original dict inside the\n # loop.\n watched_modules = dict(self._watched_modules)\n\n # Remove no-longer-depended-on files from self._watched_modules\n # Will this ever happen?\n for filepath in watched_modules:\n if filepath not in local_filepaths:\n self._deregister_watcher(filepath)\n\n\ndef _file_is_in_folder(filepath, folderpath):\n # Assumes filepath is an absolute path, as a teeny tiny optimization.\n folderpath = os.path.abspath(folderpath) + \"/\"\n return filepath.startswith(folderpath)\n", "path": "lib/streamlit/watcher/LocalSourcesWatcher.py"}], "after_files": [{"content": "# -*- coding: utf-8 -*-\n# Copyright 2018-2019 Streamlit Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport fnmatch\nimport os\nimport sys\nimport collections\n\ntry:\n # Python 2\n import imp as importlib\nexcept ImportError:\n # Python 3\n import importlib\n\nfrom streamlit import config\nfrom streamlit import util\n\nfrom streamlit.logger import get_logger\n\nLOGGER = get_logger(__name__)\n\ntry:\n # If the watchdog module is installed.\n from streamlit.watcher.EventBasedFileWatcher import (\n EventBasedFileWatcher as FileWatcher,\n )\nexcept ImportError:\n # Fallback that doesn't use watchdog.\n from streamlit.watcher.PollingFileWatcher import PollingFileWatcher as FileWatcher\n\n if not config.get_option(\"global.disableWatchdogWarning\"):\n msg = \"\\n $ xcode-select --install\" if util.is_darwin() else \"\"\n\n LOGGER.warning(\n \"\"\"\n For better performance, install the Watchdog module:\n %s\n $ pip install watchdog\n\n \"\"\"\n % msg\n )\n\n\n# Streamlit never watches files in the folders below.\nDEFAULT_FOLDER_BLACKLIST = [\n \"**/.*\", \"**/anaconda2\", \"**/anaconda3\", \"**/miniconda2\", \"**/miniconda3\"\n]\n\n\nWatchedModule = collections.namedtuple(\"WatchedModule\", [\"watcher\", \"module_name\"])\n\n\nclass LocalSourcesWatcher(object):\n def __init__(self, report, on_file_changed):\n self._report = report\n self._on_file_changed = on_file_changed\n self._is_closed = False\n\n self._folder_blacklist = config.get_option(\"server.folderWatchBlacklist\")\n\n # Blacklist some additional folders, using glob syntax.\n self._folder_blacklist.extend(DEFAULT_FOLDER_BLACKLIST)\n\n # A dict of filepath -> WatchedModule.\n self._watched_modules = {}\n\n self._register_watcher(\n self._report.script_path,\n module_name=None, # Only the root script has None here.\n )\n\n def on_file_changed(self, filepath):\n if filepath not in self._watched_modules:\n LOGGER.error(\"Received event for non-watched file\", filepath)\n return\n\n wm = self._watched_modules[filepath]\n\n if wm.module_name is not None and wm.module_name in sys.modules:\n del sys.modules[wm.module_name]\n\n self._on_file_changed()\n\n def close(self):\n for wm in self._watched_modules.values():\n wm.watcher.close()\n self._watched_modules = {}\n self._is_closed = True\n\n def _register_watcher(self, filepath, module_name):\n wm = WatchedModule(\n watcher=FileWatcher(filepath, self.on_file_changed), module_name=module_name\n )\n self._watched_modules[filepath] = wm\n\n def _deregister_watcher(self, filepath):\n if filepath not in self._watched_modules:\n return\n\n if filepath == self._report.script_path:\n return\n\n wm = self._watched_modules[filepath]\n wm.watcher.close()\n del self._watched_modules[filepath]\n\n def update_watched_modules(self):\n if self._is_closed:\n return\n\n local_filepaths = []\n\n # Clone modules dict here because we may alter the original dict inside\n # the loop.\n modules = dict(sys.modules)\n\n for name, module in modules.items():\n try:\n spec = getattr(module, \"__spec__\", None)\n\n if spec is None:\n filepath = getattr(module, \"__file__\", None)\n if filepath is None:\n # Some modules have neither a spec nor a file. But we\n # can ignore those since they're not the user-created\n # modules we want to watch anyway.\n continue\n else:\n filepath = spec.origin\n\n if filepath is None:\n # Built-in modules (and other stuff) don't have origins.\n continue\n\n filepath = os.path.abspath(filepath)\n\n if not os.path.isfile(filepath):\n # There are some modules that have a .origin, but don't\n # point to real files. For example, there's a module where\n # .origin is 'built-in'.\n continue\n\n is_in_blacklisted_folder = any(\n _file_is_in_folder(filepath, blacklisted_folder)\n for blacklisted_folder in self._folder_blacklist\n )\n\n if is_in_blacklisted_folder:\n continue\n\n file_is_new = filepath not in self._watched_modules\n file_is_local = _file_is_in_folder(filepath, self._report.script_folder)\n\n local_filepaths.append(filepath)\n\n if file_is_local and file_is_new:\n self._register_watcher(filepath, name)\n\n except Exception:\n # In case there's a problem introspecting some specific module,\n # let's not stop the entire loop from running. For example,\n # the __spec__ field in some modules (like IPython) is actually\n # a dynamic property, which can crash if the underlying\n # module's code has a bug (as discovered by one of our users).\n continue\n\n # Clone dict here because we may alter the original dict inside the\n # loop.\n watched_modules = dict(self._watched_modules)\n\n # Remove no-longer-depended-on files from self._watched_modules\n # Will this ever happen?\n for filepath in watched_modules:\n if filepath not in local_filepaths:\n self._deregister_watcher(filepath)\n\n\ndef _file_is_in_folder(filepath, folderpath_glob):\n # Strip trailing slash if it exists\n if folderpath_glob.endswith(\"/\"):\n folderpath_glob = folderpath_glob[:-1]\n\n file_dir = os.path.dirname(filepath)\n return fnmatch.fnmatch(file_dir, folderpath_glob)\n", "path": "lib/streamlit/watcher/LocalSourcesWatcher.py"}]}
| 2,125 | 709 |
gh_patches_debug_9961
|
rasdani/github-patches
|
git_diff
|
pyjanitor-devs__pyjanitor-436
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Copyright notice is hardcoded to 2018
# Brief Description of Fix
<!-- Please describe the fix in terms of a "before" and "after". In other words, what's not so good about the current docs
page, and what you would like to see it become.
copyright notice is hard-coded to 2018. eg:
**©2018, Eric J. Ma. | Powered by Sphinx 2.1.2 & Alabaster 0.7.12 | Page source**
I propose modifying /pyjanitor/docs/conf.py to calculate and display current year.
Example starter wording is provided. -->
Currently, the docs...
I would like to propose a change, such that now the docs...
# Relevant Context
<!-- Please put here, in bullet points, links to the relevant docs page. A few starting template points are available
to get you started. -->
- [Link to documentation page](http://pyjanitor.readthedocs.io)
- [Link to exact file to be edited](https://github.com/ericmjl/pyjanitor/AUTHORS.rst)
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `docs/conf.py`
Content:
```
1 """Sphinx configuration."""
2
3 # -*- coding: utf-8 -*-
4 #
5 # Configuration file for the Sphinx documentation builder.
6 #
7 # This file does only contain a selection of the most common options. For a
8 # full list see the documentation:
9 # http://www.sphinx-doc.org/en/stable/config
10
11 # -- Path setup --------------------------------------------------------------
12
13 # If extensions (or modules to document with autodoc) are in another directory,
14 # add these directories to sys.path here. If the directory is relative to the
15 # documentation root, use os.path.abspath to make it absolute, like shown here.
16 #
17 import os
18 import sys
19 from pathlib import Path
20
21 sys.path.insert(0, os.path.abspath("."))
22 sys.path.insert(0, os.path.abspath("../examples"))
23
24 # Make a symlink in our sphinx source directory to the top-level
25 # examples/notebooks directory so we can include notebooks in the doc
26 notebooks = Path("./notebooks")
27 if not notebooks.exists():
28 print("Making symlink to ../examples/notebooks")
29 notebooks.symlink_to("../examples/notebooks")
30
31
32 # -- Project information -----------------------------------------------------
33
34 project = "pyjanitor"
35 copyright = "2018, Eric J. Ma"
36 author = "Eric J. Ma"
37
38 # The short X.Y version
39 version = "0.1.0"
40 # The full version, including alpha/beta/rc tags
41 release = ""
42
43
44 # -- General configuration ---------------------------------------------------
45
46 # If your documentation needs a minimal Sphinx version, state it here.
47 #
48 # needs_sphinx = '1.0'
49
50 # Add any Sphinx extension module names here, as strings. They can be
51 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
52 # ones.
53 extensions = [
54 "sphinx.ext.autodoc",
55 "sphinx.ext.doctest",
56 "sphinx.ext.intersphinx",
57 "sphinx.ext.todo",
58 "sphinx.ext.coverage",
59 "sphinx.ext.viewcode",
60 "sphinx.ext.githubpages",
61 "sphinxcontrib.fulltoc",
62 "nbsphinx",
63 "sphinx.ext.autosummary",
64 ]
65
66 # Add any paths that contain templates here, relative to this directory.
67 templates_path = ["_templates"]
68
69 # The suffix(es) of source filenames.
70 # You can specify multiple suffix as a list of string:
71 #
72 # source_suffix = ['.rst', '.md']
73 source_suffix = [".md", ".rst", ".ipynb"]
74
75 # The master toctree document.
76 master_doc = "index"
77
78 # The language for content autogenerated by Sphinx. Refer to documentation
79 # for a list of supported languages.
80 #
81 # This is also used if you do content translation via gettext catalogs.
82 # Usually you set "language" from the command line for these cases.
83 language = None
84
85 # List of patterns, relative to source directory, that match files and
86 # directories to ignore when looking for source files.
87 # This pattern also affects html_static_path and html_extra_path .
88 exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", "**.ipynb_checkpoints"]
89
90 # The name of the Pygments (syntax highlighting) style to use.
91 pygments_style = "sphinx"
92
93
94 # -- Options for HTML output -------------------------------------------------
95
96 # The theme to use for HTML and HTML Help pages. See the documentation for
97 # a list of builtin themes.
98 #
99 html_theme = "alabaster"
100
101 # Theme options are theme-specific and customize the look and feel of a theme
102 # further. For a list of options available for each theme, see the
103 # documentation.
104 #
105 html_theme_options = {"logo": "logo_title.svg"}
106
107 # Add any paths that contain custom static files (such as style sheets) here,
108 # relative to this directory. They are copied after the builtin static files,
109 # so a file named "default.css" will overwrite the builtin "default.css".
110 html_static_path = ["_static"]
111
112 # Custom sidebar templates, must be a dictionary that maps document names
113 # to template names.
114 #
115 # The default sidebars (for documents that don't match any pattern) are
116 # defined by theme itself. Builtin themes are using these templates by
117 # default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
118 # 'searchbox.html']``.
119 #
120 html_sidebars = {
121 "**": ["about.html", "navigation.html", "relations.html", "searchbox.html"]
122 }
123
124
125 # -- Options for HTMLHelp output ---------------------------------------------
126
127 # Output file base name for HTML help builder.
128 htmlhelp_basename = "pyjanitordoc"
129
130
131 # -- Options for LaTeX output ------------------------------------------------
132
133 latex_elements = {
134 # The paper size ('letterpaper' or 'a4paper').
135 #
136 # 'papersize': 'letterpaper',
137 # The font size ('10pt', '11pt' or '12pt').
138 #
139 # 'pointsize': '10pt',
140 # Additional stuff for the LaTeX preamble.
141 #
142 # 'preamble': '',
143 # Latex figure (float) alignment
144 #
145 # 'figure_align': 'htbp',
146 }
147
148 # Grouping the document tree into LaTeX files. List of tuples
149 # (source start file, target name, title,
150 # author, documentclass [howto, manual, or own class]).
151 latex_documents = [
152 (
153 master_doc,
154 "pyjanitor.tex",
155 "pyjanitor Documentation",
156 "Eric J. Ma",
157 "manual",
158 )
159 ]
160
161
162 # -- Options for manual page output ------------------------------------------
163
164 # One entry per manual page. List of tuples
165 # (source start file, name, description, authors, manual section).
166 man_pages = [(master_doc, "pyjanitor", "pyjanitor Documentation", [author], 1)]
167
168
169 # -- Options for Texinfo output ----------------------------------------------
170
171 # Grouping the document tree into Texinfo files. List of tuples
172 # (source start file, target name, title, author,
173 # dir menu entry, description, category)
174 texinfo_documents = [
175 (
176 master_doc,
177 "pyjanitor",
178 "pyjanitor Documentation",
179 author,
180 "pyjanitor",
181 "One line description of project.",
182 "Miscellaneous",
183 )
184 ]
185
186
187 # -- Extension configuration -------------------------------------------------
188
189 # -- Options for intersphinx extension ---------------------------------------
190
191 # Example configuration for intersphinx: refer to the Python standard library.
192 intersphinx_mapping = {
193 "https://docs.python.org/": None,
194 "https://pandas.pydata.org/pandas-docs/stable": None,
195 }
196
197 # -- Options for todo extension ----------------------------------------------
198
199 # If true, `todo` and `todoList` produce output, else they produce nothing.
200 todo_include_todos = True
201
202
203 # -- Other options -----------------------------------------------------------
204
205 autosummary_generate = True # Make _autosummary files and include them
206
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/docs/conf.py b/docs/conf.py
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -16,6 +16,7 @@
#
import os
import sys
+import datetime
from pathlib import Path
sys.path.insert(0, os.path.abspath("."))
@@ -32,7 +33,11 @@
# -- Project information -----------------------------------------------------
project = "pyjanitor"
-copyright = "2018, Eric J. Ma"
+
+
+now = datetime.datetime.now()
+CurrentYear = str(now.year)
+copyright = CurrentYear+", PyJanitor devs"
author = "Eric J. Ma"
# The short X.Y version
|
{"golden_diff": "diff --git a/docs/conf.py b/docs/conf.py\n--- a/docs/conf.py\n+++ b/docs/conf.py\n@@ -16,6 +16,7 @@\n #\n import os\n import sys\n+import datetime\n from pathlib import Path\n \n sys.path.insert(0, os.path.abspath(\".\"))\n@@ -32,7 +33,11 @@\n # -- Project information -----------------------------------------------------\n \n project = \"pyjanitor\"\n-copyright = \"2018, Eric J. Ma\"\n+\n+\n+now = datetime.datetime.now()\n+CurrentYear = str(now.year)\n+copyright = CurrentYear+\", PyJanitor devs\"\n author = \"Eric J. Ma\"\n \n # The short X.Y version\n", "issue": "Copyright notice is hardcoded to 2018\n# Brief Description of Fix\r\n\r\n<!-- Please describe the fix in terms of a \"before\" and \"after\". In other words, what's not so good about the current docs\r\npage, and what you would like to see it become. \r\n\r\ncopyright notice is hard-coded to 2018. eg: \r\n **\u00a92018, Eric J. Ma. | Powered by Sphinx 2.1.2 & Alabaster 0.7.12 | Page source**\r\nI propose modifying /pyjanitor/docs/conf.py to calculate and display current year.\r\n\r\nExample starter wording is provided. -->\r\n\r\nCurrently, the docs...\r\n\r\nI would like to propose a change, such that now the docs...\r\n\r\n# Relevant Context\r\n\r\n<!-- Please put here, in bullet points, links to the relevant docs page. A few starting template points are available\r\nto get you started. -->\r\n\r\n- [Link to documentation page](http://pyjanitor.readthedocs.io)\r\n- [Link to exact file to be edited](https://github.com/ericmjl/pyjanitor/AUTHORS.rst)\r\n\n", "before_files": [{"content": "\"\"\"Sphinx configuration.\"\"\"\n\n# -*- coding: utf-8 -*-\n#\n# Configuration file for the Sphinx documentation builder.\n#\n# This file does only contain a selection of the most common options. For a\n# full list see the documentation:\n# http://www.sphinx-doc.org/en/stable/config\n\n# -- Path setup --------------------------------------------------------------\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\n#\nimport os\nimport sys\nfrom pathlib import Path\n\nsys.path.insert(0, os.path.abspath(\".\"))\nsys.path.insert(0, os.path.abspath(\"../examples\"))\n\n# Make a symlink in our sphinx source directory to the top-level\n# examples/notebooks directory so we can include notebooks in the doc\nnotebooks = Path(\"./notebooks\")\nif not notebooks.exists():\n print(\"Making symlink to ../examples/notebooks\")\n notebooks.symlink_to(\"../examples/notebooks\")\n\n\n# -- Project information -----------------------------------------------------\n\nproject = \"pyjanitor\"\ncopyright = \"2018, Eric J. Ma\"\nauthor = \"Eric J. Ma\"\n\n# The short X.Y version\nversion = \"0.1.0\"\n# The full version, including alpha/beta/rc tags\nrelease = \"\"\n\n\n# -- General configuration ---------------------------------------------------\n\n# If your documentation needs a minimal Sphinx version, state it here.\n#\n# needs_sphinx = '1.0'\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom\n# ones.\nextensions = [\n \"sphinx.ext.autodoc\",\n \"sphinx.ext.doctest\",\n \"sphinx.ext.intersphinx\",\n \"sphinx.ext.todo\",\n \"sphinx.ext.coverage\",\n \"sphinx.ext.viewcode\",\n \"sphinx.ext.githubpages\",\n \"sphinxcontrib.fulltoc\",\n \"nbsphinx\",\n \"sphinx.ext.autosummary\",\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = [\"_templates\"]\n\n# The suffix(es) of source filenames.\n# You can specify multiple suffix as a list of string:\n#\n# source_suffix = ['.rst', '.md']\nsource_suffix = [\".md\", \".rst\", \".ipynb\"]\n\n# The master toctree document.\nmaster_doc = \"index\"\n\n# The language for content autogenerated by Sphinx. Refer to documentation\n# for a list of supported languages.\n#\n# This is also used if you do content translation via gettext catalogs.\n# Usually you set \"language\" from the command line for these cases.\nlanguage = None\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This pattern also affects html_static_path and html_extra_path .\nexclude_patterns = [\"_build\", \"Thumbs.db\", \".DS_Store\", \"**.ipynb_checkpoints\"]\n\n# The name of the Pygments (syntax highlighting) style to use.\npygments_style = \"sphinx\"\n\n\n# -- Options for HTML output -------------------------------------------------\n\n# The theme to use for HTML and HTML Help pages. See the documentation for\n# a list of builtin themes.\n#\nhtml_theme = \"alabaster\"\n\n# Theme options are theme-specific and customize the look and feel of a theme\n# further. For a list of options available for each theme, see the\n# documentation.\n#\nhtml_theme_options = {\"logo\": \"logo_title.svg\"}\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = [\"_static\"]\n\n# Custom sidebar templates, must be a dictionary that maps document names\n# to template names.\n#\n# The default sidebars (for documents that don't match any pattern) are\n# defined by theme itself. Builtin themes are using these templates by\n# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',\n# 'searchbox.html']``.\n#\nhtml_sidebars = {\n \"**\": [\"about.html\", \"navigation.html\", \"relations.html\", \"searchbox.html\"]\n}\n\n\n# -- Options for HTMLHelp output ---------------------------------------------\n\n# Output file base name for HTML help builder.\nhtmlhelp_basename = \"pyjanitordoc\"\n\n\n# -- Options for LaTeX output ------------------------------------------------\n\nlatex_elements = {\n # The paper size ('letterpaper' or 'a4paper').\n #\n # 'papersize': 'letterpaper',\n # The font size ('10pt', '11pt' or '12pt').\n #\n # 'pointsize': '10pt',\n # Additional stuff for the LaTeX preamble.\n #\n # 'preamble': '',\n # Latex figure (float) alignment\n #\n # 'figure_align': 'htbp',\n}\n\n# Grouping the document tree into LaTeX files. List of tuples\n# (source start file, target name, title,\n# author, documentclass [howto, manual, or own class]).\nlatex_documents = [\n (\n master_doc,\n \"pyjanitor.tex\",\n \"pyjanitor Documentation\",\n \"Eric J. Ma\",\n \"manual\",\n )\n]\n\n\n# -- Options for manual page output ------------------------------------------\n\n# One entry per manual page. List of tuples\n# (source start file, name, description, authors, manual section).\nman_pages = [(master_doc, \"pyjanitor\", \"pyjanitor Documentation\", [author], 1)]\n\n\n# -- Options for Texinfo output ----------------------------------------------\n\n# Grouping the document tree into Texinfo files. List of tuples\n# (source start file, target name, title, author,\n# dir menu entry, description, category)\ntexinfo_documents = [\n (\n master_doc,\n \"pyjanitor\",\n \"pyjanitor Documentation\",\n author,\n \"pyjanitor\",\n \"One line description of project.\",\n \"Miscellaneous\",\n )\n]\n\n\n# -- Extension configuration -------------------------------------------------\n\n# -- Options for intersphinx extension ---------------------------------------\n\n# Example configuration for intersphinx: refer to the Python standard library.\nintersphinx_mapping = {\n \"https://docs.python.org/\": None,\n \"https://pandas.pydata.org/pandas-docs/stable\": None,\n}\n\n# -- Options for todo extension ----------------------------------------------\n\n# If true, `todo` and `todoList` produce output, else they produce nothing.\ntodo_include_todos = True\n\n\n# -- Other options -----------------------------------------------------------\n\nautosummary_generate = True # Make _autosummary files and include them\n", "path": "docs/conf.py"}], "after_files": [{"content": "\"\"\"Sphinx configuration.\"\"\"\n\n# -*- coding: utf-8 -*-\n#\n# Configuration file for the Sphinx documentation builder.\n#\n# This file does only contain a selection of the most common options. For a\n# full list see the documentation:\n# http://www.sphinx-doc.org/en/stable/config\n\n# -- Path setup --------------------------------------------------------------\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\n#\nimport os\nimport sys\nimport datetime\nfrom pathlib import Path\n\nsys.path.insert(0, os.path.abspath(\".\"))\nsys.path.insert(0, os.path.abspath(\"../examples\"))\n\n# Make a symlink in our sphinx source directory to the top-level\n# examples/notebooks directory so we can include notebooks in the doc\nnotebooks = Path(\"./notebooks\")\nif not notebooks.exists():\n print(\"Making symlink to ../examples/notebooks\")\n notebooks.symlink_to(\"../examples/notebooks\")\n\n\n# -- Project information -----------------------------------------------------\n\nproject = \"pyjanitor\"\n\n\nnow = datetime.datetime.now()\nCurrentYear = str(now.year)\ncopyright = CurrentYear+\", PyJanitor devs\"\nauthor = \"Eric J. Ma\"\n\n# The short X.Y version\nversion = \"0.1.0\"\n# The full version, including alpha/beta/rc tags\nrelease = \"\"\n\n\n# -- General configuration ---------------------------------------------------\n\n# If your documentation needs a minimal Sphinx version, state it here.\n#\n# needs_sphinx = '1.0'\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom\n# ones.\nextensions = [\n \"sphinx.ext.autodoc\",\n \"sphinx.ext.doctest\",\n \"sphinx.ext.intersphinx\",\n \"sphinx.ext.todo\",\n \"sphinx.ext.coverage\",\n \"sphinx.ext.viewcode\",\n \"sphinx.ext.githubpages\",\n \"sphinxcontrib.fulltoc\",\n \"nbsphinx\",\n \"sphinx.ext.autosummary\",\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = [\"_templates\"]\n\n# The suffix(es) of source filenames.\n# You can specify multiple suffix as a list of string:\n#\n# source_suffix = ['.rst', '.md']\nsource_suffix = [\".md\", \".rst\", \".ipynb\"]\n\n# The master toctree document.\nmaster_doc = \"index\"\n\n# The language for content autogenerated by Sphinx. Refer to documentation\n# for a list of supported languages.\n#\n# This is also used if you do content translation via gettext catalogs.\n# Usually you set \"language\" from the command line for these cases.\nlanguage = None\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This pattern also affects html_static_path and html_extra_path .\nexclude_patterns = [\"_build\", \"Thumbs.db\", \".DS_Store\", \"**.ipynb_checkpoints\"]\n\n# The name of the Pygments (syntax highlighting) style to use.\npygments_style = \"sphinx\"\n\n\n# -- Options for HTML output -------------------------------------------------\n\n# The theme to use for HTML and HTML Help pages. See the documentation for\n# a list of builtin themes.\n#\nhtml_theme = \"alabaster\"\n\n# Theme options are theme-specific and customize the look and feel of a theme\n# further. For a list of options available for each theme, see the\n# documentation.\n#\nhtml_theme_options = {\"logo\": \"logo_title.svg\"}\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = [\"_static\"]\n\n# Custom sidebar templates, must be a dictionary that maps document names\n# to template names.\n#\n# The default sidebars (for documents that don't match any pattern) are\n# defined by theme itself. Builtin themes are using these templates by\n# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',\n# 'searchbox.html']``.\n#\nhtml_sidebars = {\n \"**\": [\"about.html\", \"navigation.html\", \"relations.html\", \"searchbox.html\"]\n}\n\n\n# -- Options for HTMLHelp output ---------------------------------------------\n\n# Output file base name for HTML help builder.\nhtmlhelp_basename = \"pyjanitordoc\"\n\n\n# -- Options for LaTeX output ------------------------------------------------\n\nlatex_elements = {\n # The paper size ('letterpaper' or 'a4paper').\n #\n # 'papersize': 'letterpaper',\n # The font size ('10pt', '11pt' or '12pt').\n #\n # 'pointsize': '10pt',\n # Additional stuff for the LaTeX preamble.\n #\n # 'preamble': '',\n # Latex figure (float) alignment\n #\n # 'figure_align': 'htbp',\n}\n\n# Grouping the document tree into LaTeX files. List of tuples\n# (source start file, target name, title,\n# author, documentclass [howto, manual, or own class]).\nlatex_documents = [\n (\n master_doc,\n \"pyjanitor.tex\",\n \"pyjanitor Documentation\",\n \"Eric J. Ma\",\n \"manual\",\n )\n]\n\n\n# -- Options for manual page output ------------------------------------------\n\n# One entry per manual page. List of tuples\n# (source start file, name, description, authors, manual section).\nman_pages = [(master_doc, \"pyjanitor\", \"pyjanitor Documentation\", [author], 1)]\n\n\n# -- Options for Texinfo output ----------------------------------------------\n\n# Grouping the document tree into Texinfo files. List of tuples\n# (source start file, target name, title, author,\n# dir menu entry, description, category)\ntexinfo_documents = [\n (\n master_doc,\n \"pyjanitor\",\n \"pyjanitor Documentation\",\n author,\n \"pyjanitor\",\n \"One line description of project.\",\n \"Miscellaneous\",\n )\n]\n\n\n# -- Extension configuration -------------------------------------------------\n\n# -- Options for intersphinx extension ---------------------------------------\n\n# Example configuration for intersphinx: refer to the Python standard library.\nintersphinx_mapping = {\n \"https://docs.python.org/\": None,\n \"https://pandas.pydata.org/pandas-docs/stable\": None,\n}\n\n# -- Options for todo extension ----------------------------------------------\n\n# If true, `todo` and `todoList` produce output, else they produce nothing.\ntodo_include_todos = True\n\n\n# -- Other options -----------------------------------------------------------\n\nautosummary_generate = True # Make _autosummary files and include them\n", "path": "docs/conf.py"}]}
| 2,466 | 148 |
gh_patches_debug_66426
|
rasdani/github-patches
|
git_diff
|
Textualize__textual-3531
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Missing link styles in `Toast` notifcations
This follows on from discussion #3526 about adding a clickable link in a notification.
The `Toast` widget doesn't inherit the styling from the base class, so the "default" links styling defined in Widget is lost. You can obviously just add it back in like I've done here, but it might be nicer if you didn't have to do that.
```python
# toast_with_link.py
import webbrowser
from textual.app import App
class ToastLinkApp(App):
# Uncomment the CSS_PATH to see the link!
# CSS_PATH = "toast_with_link.css"
def on_mount(self) -> None:
self.notify(
"Don't forget to "
"[@click=link('https://github.com/Textualize/textual')]star[/] "
"the repository!",
timeout=10,
)
def action_link(self, href: str) -> None:
webbrowser.open(href)
if __name__ == "__main__":
app = ToastLinkApp()
app.run()
```
```css
/* toast_with_link.css */
Toast {
link-background: ;
link-color: $text;
link-style: underline;
link-hover-background: $accent;
link-hover-color: $text;
link-hover-style: bold not underline;
}
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/textual/widgets/_toast.py`
Content:
```
1 """Widgets for showing notification messages in toasts."""
2
3 from __future__ import annotations
4
5 from typing import ClassVar
6
7 from rich.console import RenderableType
8 from rich.text import Text
9
10 from .. import on
11 from ..containers import Container
12 from ..css.query import NoMatches
13 from ..events import Click, Mount
14 from ..notifications import Notification, Notifications
15 from ._static import Static
16
17
18 class ToastHolder(Container, inherit_css=False):
19 """Container that holds a single toast.
20
21 Used to control the alignment of each of the toasts in the main toast
22 container.
23 """
24
25 DEFAULT_CSS = """
26 ToastHolder {
27 align-horizontal: right;
28 width: 1fr;
29 height: auto;
30 visibility: hidden;
31 }
32 """
33
34
35 class Toast(Static, inherit_css=False):
36 """A widget for displaying short-lived notifications."""
37
38 DEFAULT_CSS = """
39 Toast {
40 width: 60;
41 max-width: 50%;
42 height: auto;
43 visibility: visible;
44 margin-top: 1;
45 padding: 1 1;
46 background: $panel;
47 tint: white 5%;
48 }
49
50 .toast--title {
51 text-style: bold;
52 }
53
54 Toast {
55 border-right: wide $background;
56 }
57
58 Toast.-information {
59 border-left: wide $success;
60 }
61
62 Toast.-information .toast--title {
63 color: $success-darken-1;
64 }
65
66 Toast.-warning {
67 border-left: wide $warning;
68 }
69
70 Toast.-warning .toast--title {
71 color: $warning-darken-1;
72 }
73
74 Toast.-error {
75 border-left: wide $error;
76 }
77
78 Toast.-error .toast--title {
79 color: $error-darken-1;
80 }
81 """
82
83 COMPONENT_CLASSES: ClassVar[set[str]] = {"toast--title"}
84 """
85 | Class | Description |
86 | :- | :- |
87 | `toast--title` | Targets the title of the toast. |
88 """
89
90 def __init__(self, notification: Notification) -> None:
91 """Initialise the toast.
92
93 Args:
94 notification: The notification to show in the toast.
95 """
96 super().__init__(classes=f"-{notification.severity}")
97 self._notification = notification
98 self._timeout = notification.time_left
99
100 def render(self) -> RenderableType:
101 """Render the toast's content.
102
103 Returns:
104 A Rich renderable for the title and content of the Toast.
105 """
106 notification = self._notification
107 if notification.title:
108 header_style = self.get_component_rich_style("toast--title")
109 notification_text = Text.assemble(
110 (notification.title, header_style),
111 "\n",
112 Text.from_markup(notification.message),
113 )
114 else:
115 notification_text = Text.assemble(
116 Text.from_markup(notification.message),
117 )
118 return notification_text
119
120 def _on_mount(self, _: Mount) -> None:
121 """Set the time running once the toast is mounted."""
122 self.set_timer(self._timeout, self._expire)
123
124 @on(Click)
125 def _expire(self) -> None:
126 """Remove the toast once the timer has expired."""
127 # Before we removed ourself, we also call on the app to forget about
128 # the notification that caused us to exist. Note that we tell the
129 # app to not bother refreshing the display on our account, we're
130 # about to handle that anyway.
131 self.app._unnotify(self._notification, refresh=False)
132 # Note that we attempt to remove our parent, because we're wrapped
133 # inside an alignment container. The testing that we are is as much
134 # to keep type checkers happy as anything else.
135 (self.parent if isinstance(self.parent, ToastHolder) else self).remove()
136
137
138 class ToastRack(Container, inherit_css=False):
139 """A container for holding toasts."""
140
141 DEFAULT_CSS = """
142 ToastRack {
143 layer: _toastrack;
144 width: 1fr;
145 height: auto;
146 dock: top;
147 align: right bottom;
148 visibility: hidden;
149 layout: vertical;
150 overflow-y: scroll;
151 margin-bottom: 1;
152 margin-right: 1;
153 }
154 """
155
156 @staticmethod
157 def _toast_id(notification: Notification) -> str:
158 """Create a Textual-DOM-internal ID for the given notification.
159
160 Args:
161 notification: The notification to create the ID for.
162
163 Returns:
164 An ID for the notification that can be used within the DOM.
165 """
166 return f"--textual-toast-{notification.identity}"
167
168 def show(self, notifications: Notifications) -> None:
169 """Show the notifications as toasts.
170
171 Args:
172 notifications: The notifications to show.
173 """
174
175 # Look for any stale toasts and remove them.
176 for toast in self.query(Toast):
177 if toast._notification not in notifications:
178 toast.remove()
179
180 # Gather up all the notifications that we don't have toasts for yet.
181 new_toasts: list[Notification] = []
182 for notification in notifications:
183 try:
184 # See if there's already a toast for that notification.
185 _ = self.get_child_by_id(self._toast_id(notification))
186 except NoMatches:
187 if not notification.has_expired:
188 new_toasts.append(notification)
189
190 # If we got any...
191 if new_toasts:
192 # ...mount them.
193 self.mount_all(
194 ToastHolder(Toast(toast), id=self._toast_id(toast))
195 for toast in new_toasts
196 )
197 self.call_later(self.scroll_end, animate=False, force=True)
198
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/textual/widgets/_toast.py b/src/textual/widgets/_toast.py
--- a/src/textual/widgets/_toast.py
+++ b/src/textual/widgets/_toast.py
@@ -45,6 +45,12 @@
padding: 1 1;
background: $panel;
tint: white 5%;
+ link-background:;
+ link-color: $text;
+ link-style: underline;
+ link-hover-background: $accent;
+ link-hover-color: $text;
+ link-hover-style: bold not underline;
}
.toast--title {
|
{"golden_diff": "diff --git a/src/textual/widgets/_toast.py b/src/textual/widgets/_toast.py\n--- a/src/textual/widgets/_toast.py\n+++ b/src/textual/widgets/_toast.py\n@@ -45,6 +45,12 @@\n padding: 1 1;\n background: $panel;\n tint: white 5%;\n+ link-background:;\n+ link-color: $text;\n+ link-style: underline;\n+ link-hover-background: $accent;\n+ link-hover-color: $text;\n+ link-hover-style: bold not underline;\n }\n \n .toast--title {\n", "issue": "Missing link styles in `Toast` notifcations\nThis follows on from discussion #3526 about adding a clickable link in a notification.\r\n\r\n The `Toast` widget doesn't inherit the styling from the base class, so the \"default\" links styling defined in Widget is lost. You can obviously just add it back in like I've done here, but it might be nicer if you didn't have to do that.\r\n\r\n```python\r\n# toast_with_link.py\r\n\r\nimport webbrowser\r\n\r\nfrom textual.app import App\r\n\r\n\r\nclass ToastLinkApp(App):\r\n # Uncomment the CSS_PATH to see the link!\r\n # CSS_PATH = \"toast_with_link.css\"\r\n\r\n def on_mount(self) -> None:\r\n self.notify(\r\n \"Don't forget to \"\r\n \"[@click=link('https://github.com/Textualize/textual')]star[/] \"\r\n \"the repository!\",\r\n timeout=10,\r\n )\r\n\r\n def action_link(self, href: str) -> None:\r\n webbrowser.open(href)\r\n\r\n\r\nif __name__ == \"__main__\":\r\n app = ToastLinkApp()\r\n app.run()\r\n```\r\n\r\n```css\r\n/* toast_with_link.css */\r\n\r\nToast {\r\n link-background: ;\r\n link-color: $text;\r\n link-style: underline;\r\n link-hover-background: $accent;\r\n link-hover-color: $text;\r\n link-hover-style: bold not underline;\r\n}\r\n```\r\n\r\n\n", "before_files": [{"content": "\"\"\"Widgets for showing notification messages in toasts.\"\"\"\n\nfrom __future__ import annotations\n\nfrom typing import ClassVar\n\nfrom rich.console import RenderableType\nfrom rich.text import Text\n\nfrom .. import on\nfrom ..containers import Container\nfrom ..css.query import NoMatches\nfrom ..events import Click, Mount\nfrom ..notifications import Notification, Notifications\nfrom ._static import Static\n\n\nclass ToastHolder(Container, inherit_css=False):\n \"\"\"Container that holds a single toast.\n\n Used to control the alignment of each of the toasts in the main toast\n container.\n \"\"\"\n\n DEFAULT_CSS = \"\"\"\n ToastHolder {\n align-horizontal: right;\n width: 1fr;\n height: auto;\n visibility: hidden;\n }\n \"\"\"\n\n\nclass Toast(Static, inherit_css=False):\n \"\"\"A widget for displaying short-lived notifications.\"\"\"\n\n DEFAULT_CSS = \"\"\"\n Toast {\n width: 60;\n max-width: 50%;\n height: auto;\n visibility: visible;\n margin-top: 1;\n padding: 1 1;\n background: $panel;\n tint: white 5%;\n }\n\n .toast--title {\n text-style: bold;\n }\n\n Toast {\n border-right: wide $background;\n }\n\n Toast.-information {\n border-left: wide $success;\n }\n\n Toast.-information .toast--title {\n color: $success-darken-1;\n }\n\n Toast.-warning {\n border-left: wide $warning;\n }\n\n Toast.-warning .toast--title {\n color: $warning-darken-1;\n }\n\n Toast.-error {\n border-left: wide $error;\n }\n\n Toast.-error .toast--title {\n color: $error-darken-1;\n }\n \"\"\"\n\n COMPONENT_CLASSES: ClassVar[set[str]] = {\"toast--title\"}\n \"\"\"\n | Class | Description |\n | :- | :- |\n | `toast--title` | Targets the title of the toast. |\n \"\"\"\n\n def __init__(self, notification: Notification) -> None:\n \"\"\"Initialise the toast.\n\n Args:\n notification: The notification to show in the toast.\n \"\"\"\n super().__init__(classes=f\"-{notification.severity}\")\n self._notification = notification\n self._timeout = notification.time_left\n\n def render(self) -> RenderableType:\n \"\"\"Render the toast's content.\n\n Returns:\n A Rich renderable for the title and content of the Toast.\n \"\"\"\n notification = self._notification\n if notification.title:\n header_style = self.get_component_rich_style(\"toast--title\")\n notification_text = Text.assemble(\n (notification.title, header_style),\n \"\\n\",\n Text.from_markup(notification.message),\n )\n else:\n notification_text = Text.assemble(\n Text.from_markup(notification.message),\n )\n return notification_text\n\n def _on_mount(self, _: Mount) -> None:\n \"\"\"Set the time running once the toast is mounted.\"\"\"\n self.set_timer(self._timeout, self._expire)\n\n @on(Click)\n def _expire(self) -> None:\n \"\"\"Remove the toast once the timer has expired.\"\"\"\n # Before we removed ourself, we also call on the app to forget about\n # the notification that caused us to exist. Note that we tell the\n # app to not bother refreshing the display on our account, we're\n # about to handle that anyway.\n self.app._unnotify(self._notification, refresh=False)\n # Note that we attempt to remove our parent, because we're wrapped\n # inside an alignment container. The testing that we are is as much\n # to keep type checkers happy as anything else.\n (self.parent if isinstance(self.parent, ToastHolder) else self).remove()\n\n\nclass ToastRack(Container, inherit_css=False):\n \"\"\"A container for holding toasts.\"\"\"\n\n DEFAULT_CSS = \"\"\"\n ToastRack {\n layer: _toastrack;\n width: 1fr;\n height: auto;\n dock: top;\n align: right bottom;\n visibility: hidden;\n layout: vertical;\n overflow-y: scroll;\n margin-bottom: 1;\n margin-right: 1;\n }\n \"\"\"\n\n @staticmethod\n def _toast_id(notification: Notification) -> str:\n \"\"\"Create a Textual-DOM-internal ID for the given notification.\n\n Args:\n notification: The notification to create the ID for.\n\n Returns:\n An ID for the notification that can be used within the DOM.\n \"\"\"\n return f\"--textual-toast-{notification.identity}\"\n\n def show(self, notifications: Notifications) -> None:\n \"\"\"Show the notifications as toasts.\n\n Args:\n notifications: The notifications to show.\n \"\"\"\n\n # Look for any stale toasts and remove them.\n for toast in self.query(Toast):\n if toast._notification not in notifications:\n toast.remove()\n\n # Gather up all the notifications that we don't have toasts for yet.\n new_toasts: list[Notification] = []\n for notification in notifications:\n try:\n # See if there's already a toast for that notification.\n _ = self.get_child_by_id(self._toast_id(notification))\n except NoMatches:\n if not notification.has_expired:\n new_toasts.append(notification)\n\n # If we got any...\n if new_toasts:\n # ...mount them.\n self.mount_all(\n ToastHolder(Toast(toast), id=self._toast_id(toast))\n for toast in new_toasts\n )\n self.call_later(self.scroll_end, animate=False, force=True)\n", "path": "src/textual/widgets/_toast.py"}], "after_files": [{"content": "\"\"\"Widgets for showing notification messages in toasts.\"\"\"\n\nfrom __future__ import annotations\n\nfrom typing import ClassVar\n\nfrom rich.console import RenderableType\nfrom rich.text import Text\n\nfrom .. import on\nfrom ..containers import Container\nfrom ..css.query import NoMatches\nfrom ..events import Click, Mount\nfrom ..notifications import Notification, Notifications\nfrom ._static import Static\n\n\nclass ToastHolder(Container, inherit_css=False):\n \"\"\"Container that holds a single toast.\n\n Used to control the alignment of each of the toasts in the main toast\n container.\n \"\"\"\n\n DEFAULT_CSS = \"\"\"\n ToastHolder {\n align-horizontal: right;\n width: 1fr;\n height: auto;\n visibility: hidden;\n }\n \"\"\"\n\n\nclass Toast(Static, inherit_css=False):\n \"\"\"A widget for displaying short-lived notifications.\"\"\"\n\n DEFAULT_CSS = \"\"\"\n Toast {\n width: 60;\n max-width: 50%;\n height: auto;\n visibility: visible;\n margin-top: 1;\n padding: 1 1;\n background: $panel;\n tint: white 5%;\n link-background:;\n link-color: $text;\n link-style: underline;\n link-hover-background: $accent;\n link-hover-color: $text;\n link-hover-style: bold not underline;\n }\n\n .toast--title {\n text-style: bold;\n }\n\n Toast {\n border-right: wide $background;\n }\n\n Toast.-information {\n border-left: wide $success;\n }\n\n Toast.-information .toast--title {\n color: $success-darken-1;\n }\n\n Toast.-warning {\n border-left: wide $warning;\n }\n\n Toast.-warning .toast--title {\n color: $warning-darken-1;\n }\n\n Toast.-error {\n border-left: wide $error;\n }\n\n Toast.-error .toast--title {\n color: $error-darken-1;\n }\n \"\"\"\n\n COMPONENT_CLASSES: ClassVar[set[str]] = {\"toast--title\"}\n \"\"\"\n | Class | Description |\n | :- | :- |\n | `toast--title` | Targets the title of the toast. |\n \"\"\"\n\n def __init__(self, notification: Notification) -> None:\n \"\"\"Initialise the toast.\n\n Args:\n notification: The notification to show in the toast.\n \"\"\"\n super().__init__(classes=f\"-{notification.severity}\")\n self._notification = notification\n self._timeout = notification.time_left\n\n def render(self) -> RenderableType:\n \"\"\"Render the toast's content.\n\n Returns:\n A Rich renderable for the title and content of the Toast.\n \"\"\"\n notification = self._notification\n if notification.title:\n header_style = self.get_component_rich_style(\"toast--title\")\n notification_text = Text.assemble(\n (notification.title, header_style),\n \"\\n\",\n Text.from_markup(notification.message),\n )\n else:\n notification_text = Text.assemble(\n Text.from_markup(notification.message),\n )\n return notification_text\n\n def _on_mount(self, _: Mount) -> None:\n \"\"\"Set the time running once the toast is mounted.\"\"\"\n self.set_timer(self._timeout, self._expire)\n\n @on(Click)\n def _expire(self) -> None:\n \"\"\"Remove the toast once the timer has expired.\"\"\"\n # Before we removed ourself, we also call on the app to forget about\n # the notification that caused us to exist. Note that we tell the\n # app to not bother refreshing the display on our account, we're\n # about to handle that anyway.\n self.app._unnotify(self._notification, refresh=False)\n # Note that we attempt to remove our parent, because we're wrapped\n # inside an alignment container. The testing that we are is as much\n # to keep type checkers happy as anything else.\n (self.parent if isinstance(self.parent, ToastHolder) else self).remove()\n\n\nclass ToastRack(Container, inherit_css=False):\n \"\"\"A container for holding toasts.\"\"\"\n\n DEFAULT_CSS = \"\"\"\n ToastRack {\n layer: _toastrack;\n width: 1fr;\n height: auto;\n dock: top;\n align: right bottom;\n visibility: hidden;\n layout: vertical;\n overflow-y: scroll;\n margin-bottom: 1;\n margin-right: 1;\n }\n \"\"\"\n\n @staticmethod\n def _toast_id(notification: Notification) -> str:\n \"\"\"Create a Textual-DOM-internal ID for the given notification.\n\n Args:\n notification: The notification to create the ID for.\n\n Returns:\n An ID for the notification that can be used within the DOM.\n \"\"\"\n return f\"--textual-toast-{notification.identity}\"\n\n def show(self, notifications: Notifications) -> None:\n \"\"\"Show the notifications as toasts.\n\n Args:\n notifications: The notifications to show.\n \"\"\"\n\n # Look for any stale toasts and remove them.\n for toast in self.query(Toast):\n if toast._notification not in notifications:\n toast.remove()\n\n # Gather up all the notifications that we don't have toasts for yet.\n new_toasts: list[Notification] = []\n for notification in notifications:\n try:\n # See if there's already a toast for that notification.\n _ = self.get_child_by_id(self._toast_id(notification))\n except NoMatches:\n if not notification.has_expired:\n new_toasts.append(notification)\n\n # If we got any...\n if new_toasts:\n # ...mount them.\n self.mount_all(\n ToastHolder(Toast(toast), id=self._toast_id(toast))\n for toast in new_toasts\n )\n self.call_later(self.scroll_end, animate=False, force=True)\n", "path": "src/textual/widgets/_toast.py"}]}
| 2,260 | 131 |
gh_patches_debug_29108
|
rasdani/github-patches
|
git_diff
|
rlworkgroup__garage-774
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Remove conda environment from CI/Dockerfiles
Now that we use setup.py for tracking dependencies, there's no need be creating conda environments inside the Dockerfile and CI. We can replace them with a vanilla virtualenv for greatest compatibility.
I suggest we add tests which ensure that the package can still be successfully solved and installed by conda and pipenv. If they don't take too long (<2min) then we can run them in the main CI, otherwise they will be cron_job tests (which are run only nightly).
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 from setuptools import find_packages
2 from setuptools import setup
3
4 # Required dependencies
5 required = [
6 # Please keep alphabetized
7 'akro==0.0.6',
8 'cached_property',
9 'click',
10 'cloudpickle',
11 'cma==1.1.06',
12 # dm_control throws an error during install about not being able to
13 # find a build dependency (absl-py). Later pip executes the `install`
14 # command again and the install succeeds because absl-py has been
15 # installed. This is stupid, but harmless.
16 'dm_control @ https://api.github.com/repos/deepmind/dm_control/tarball/7a36377879c57777e5d5b4da5aae2cd2a29b607a', # noqa: E501
17 'dowel==0.0.2',
18 'gym[all]==0.12.4',
19 'joblib<0.13,>=0.12',
20 'matplotlib',
21 'mujoco-py<2.1,>=2.0',
22 'numpy==1.14.5',
23 'psutil',
24 # Pyglet 1.4.0 introduces some api change which breaks some
25 # gym environments
26 # See: https://github.com/openai/gym/issues/1588
27 'pyglet<1.4.0,>=1.3.0',
28 'pyprind',
29 'python-dateutil',
30 'torch==1.1.0',
31 'scikit-image',
32 'scipy',
33 'tensorflow<1.13,>=1.12.0',
34 'tensorflow-probability<0.6.0,>=0.5.0', # for tensorflow 1.12
35 'torchvision==0.3.0'
36 ]
37
38 # Dependencies for optional features
39 extras = {}
40 extras['all'] = list(set(sum(extras.values(), [])))
41
42 # Intel dependencies not included in all
43 extras['intel'] = ['intel-tensorflow<1.13,>=1.12.0']
44
45 # Development dependencies (*not* included in "all")
46 extras['dev'] = [
47 # Please keep alphabetized
48 'baselines @ https://api.github.com/repos/openai/baselines/tarball/f2729693253c0ef4d4086231d36e0a4307ec1cb3', # noqa: E501
49 'flake8',
50 'flake8-docstrings==1.3.0',
51 'flake8-import-order',
52 'pandas',
53 'pep8-naming==0.7.0',
54 'pre-commit',
55 # pydocstyle 4.0.0 breaks flake8-docstrings 1.3.0
56 # See https://gitlab.com/pycqa/flake8-docstrings/issues/36
57 'pydocstyle<4.0.0',
58 'pylint==1.9.2',
59 'pytest>=3.6', # Required for pytest-cov on Python 3.6
60 'pytest-cov',
61 'sphinx',
62 'sphinx_rtd_theme',
63 'yapf',
64 ]
65
66 with open('README.md') as f:
67 readme = f.read()
68
69 # Get the package version dynamically
70 with open('VERSION') as v:
71 version = v.read().strip()
72
73 setup(
74 name='garage',
75 version=version,
76 author='Reinforcement Learning Working Group',
77 description='A framework for reproducible reinforcement learning research',
78 url='https://github.com/rlworkgroup/garage',
79 packages=find_packages(where='src'),
80 package_dir={'': 'src'},
81 scripts=['scripts/garage'],
82 install_requires=required,
83 extras_require=extras,
84 license='MIT',
85 long_description=readme,
86 long_description_content_type='text/markdown',
87 classifiers=[
88 'Development Status :: 4 - Beta',
89 'Intended Audience :: Developers',
90 'Intended Audience :: Education',
91 'Intended Audience :: Science/Research',
92 'License :: OSI Approved :: MIT License',
93 'Programming Language :: Python :: 3.5',
94 'Programming Language :: Python :: 3.6',
95 'Programming Language :: Python :: 3.7',
96 'Programming Language :: Python :: 3 :: Only',
97 'Topic :: Scientific/Engineering :: Artificial Intelligence',
98 'Topic :: Scientific/Engineering :: Mathematics',
99 'Topic :: Software Development :: Libraries',
100 ],
101 )
102
```
Path: `src/garage/np/algos/cem.py`
Content:
```
1 from dowel import logger, tabular
2 import numpy as np
3
4 from garage.np.algos import BatchPolopt
5
6
7 class CEM(BatchPolopt):
8 """Cross Entropy Method.
9
10 CEM works by iteratively optimizing a gaussian distribution of policy.
11
12 In each epoch, CEM does the following:
13 1. Sample n_samples policies from a gaussian distribution of
14 mean cur_mean and std cur_std.
15 2. Do rollouts for each policy.
16 3. Update cur_mean and cur_std by doing Maximum Likelihood Estimation
17 over the n_best top policies in terms of return.
18
19 Note:
20 When training CEM with LocalRunner, make sure that n_epoch_cycles for
21 runner equals to n_samples for CEM.
22
23 This implementation leverage n_epoch_cycles to do rollouts for a single
24 policy in an epoch cycle.
25
26 Args:
27 env_spec (garage.envs.EnvSpec): Environment specification.
28 policy (garage.np.policies.Policy): Action policy.
29 baseline(garage.np.baselines.Baseline): Baseline for GAE
30 (Generalized Advantage Estimation).
31 n_samples (int): Number of policies sampled in one epoch.
32 discount (float): Environment reward discount.
33 max_path_length (int): Maximum length of a single rollout.
34 best_frac (float): The best fraction.
35 init_std (float): Initial std for policy param distribution.
36 extra_std (float): Decaying std added to param distribution.
37 extra_decay_time (float): Epochs that it takes to decay extra std.
38
39 """
40
41 def __init__(self,
42 env_spec,
43 policy,
44 baseline,
45 n_samples,
46 discount=0.99,
47 max_path_length=500,
48 init_std=1,
49 best_frac=0.05,
50 extra_std=1.,
51 extra_decay_time=100):
52 super().__init__(policy, baseline, discount, max_path_length,
53 n_samples)
54 self.env_spec = env_spec
55
56 self.init_std = init_std
57 self.best_frac = best_frac
58 self.extra_std = extra_std
59 self.extra_decay_time = extra_decay_time
60
61 # epoch-wise
62 self.cur_std = self.init_std
63 self.cur_mean = self.policy.get_param_values()
64 # epoch-cycle-wise
65 self.cur_params = self.cur_mean
66 self.all_returns = []
67 self.all_params = [self.cur_mean.copy()]
68 # fixed
69 self.n_best = int(n_samples * best_frac)
70 assert self.n_best >= 1, (
71 f'n_samples is too low. Make sure that n_samples * best_frac >= 1')
72 self.n_params = len(self.cur_mean)
73
74 def sample_params(self, epoch):
75 extra_var_mult = max(1.0 - epoch / self.extra_decay_time, 0)
76 sample_std = np.sqrt(
77 np.square(self.cur_std) +
78 np.square(self.extra_std) * extra_var_mult)
79 return np.random.standard_normal(
80 self.n_params) * sample_std + self.cur_mean
81
82 def train_once(self, itr, paths):
83 paths = self.process_samples(itr, paths)
84
85 epoch = itr // self.n_samples
86 i_sample = itr - epoch * self.n_samples
87 tabular.record('Epoch', epoch)
88 tabular.record('# Sample', i_sample)
89 # -- Stage: Process path
90 rtn = paths['average_return']
91 self.all_returns.append(paths['average_return'])
92
93 # -- Stage: Update policy distribution.
94 if (itr + 1) % self.n_samples == 0:
95 avg_rtns = np.array(self.all_returns)
96 best_inds = np.argsort(-avg_rtns)[:self.n_best]
97 best_params = np.array(self.all_params)[best_inds]
98
99 # MLE of normal distribution
100 self.cur_mean = best_params.mean(axis=0)
101 self.cur_std = best_params.std(axis=0)
102 self.policy.set_param_values(self.cur_mean)
103
104 # Clear for next epoch
105 rtn = max(self.all_returns)
106 self.all_returns.clear()
107 self.all_params.clear()
108
109 # -- Stage: Generate a new policy for next path sampling
110 self.cur_params = self.sample_params(itr)
111 self.all_params.append(self.cur_params.copy())
112 self.policy.set_param_values(self.cur_params)
113
114 logger.log(tabular)
115 return rtn
116
117 def get_itr_snapshot(self, itr):
118 return dict(itr=itr, policy=self.policy, baseline=self.baseline)
119
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -1,6 +1,15 @@
from setuptools import find_packages
from setuptools import setup
+try:
+ # pylint: disable=unused-import
+ import numpy # noqa: F401
+except ImportError:
+ raise RuntimeError(
+ 'garage requires numpy in the environment to install. '
+ 'Please install numpy==1.14.5 and try again. See '
+ 'https://github.com/rlworkgroup/garage/issues/800 for more info.')
+
# Required dependencies
required = [
# Please keep alphabetized
@@ -58,6 +67,7 @@
'pylint==1.9.2',
'pytest>=3.6', # Required for pytest-cov on Python 3.6
'pytest-cov',
+ 'pytest-xdist',
'sphinx',
'sphinx_rtd_theme',
'yapf',
@@ -79,6 +89,7 @@
packages=find_packages(where='src'),
package_dir={'': 'src'},
scripts=['scripts/garage'],
+ python_requires='>=3.5',
install_requires=required,
extras_require=extras,
license='MIT',
diff --git a/src/garage/np/algos/cem.py b/src/garage/np/algos/cem.py
--- a/src/garage/np/algos/cem.py
+++ b/src/garage/np/algos/cem.py
@@ -68,7 +68,7 @@
# fixed
self.n_best = int(n_samples * best_frac)
assert self.n_best >= 1, (
- f'n_samples is too low. Make sure that n_samples * best_frac >= 1')
+ 'n_samples is too low. Make sure that n_samples * best_frac >= 1')
self.n_params = len(self.cur_mean)
def sample_params(self, epoch):
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -1,6 +1,15 @@\n from setuptools import find_packages\n from setuptools import setup\n \n+try:\n+ # pylint: disable=unused-import\n+ import numpy # noqa: F401\n+except ImportError:\n+ raise RuntimeError(\n+ 'garage requires numpy in the environment to install. '\n+ 'Please install numpy==1.14.5 and try again. See '\n+ 'https://github.com/rlworkgroup/garage/issues/800 for more info.')\n+\n # Required dependencies\n required = [\n # Please keep alphabetized\n@@ -58,6 +67,7 @@\n 'pylint==1.9.2',\n 'pytest>=3.6', # Required for pytest-cov on Python 3.6\n 'pytest-cov',\n+ 'pytest-xdist',\n 'sphinx',\n 'sphinx_rtd_theme',\n 'yapf',\n@@ -79,6 +89,7 @@\n packages=find_packages(where='src'),\n package_dir={'': 'src'},\n scripts=['scripts/garage'],\n+ python_requires='>=3.5',\n install_requires=required,\n extras_require=extras,\n license='MIT',\ndiff --git a/src/garage/np/algos/cem.py b/src/garage/np/algos/cem.py\n--- a/src/garage/np/algos/cem.py\n+++ b/src/garage/np/algos/cem.py\n@@ -68,7 +68,7 @@\n # fixed\n self.n_best = int(n_samples * best_frac)\n assert self.n_best >= 1, (\n- f'n_samples is too low. Make sure that n_samples * best_frac >= 1')\n+ 'n_samples is too low. Make sure that n_samples * best_frac >= 1')\n self.n_params = len(self.cur_mean)\n \n def sample_params(self, epoch):\n", "issue": "Remove conda environment from CI/Dockerfiles\nNow that we use setup.py for tracking dependencies, there's no need be creating conda environments inside the Dockerfile and CI. We can replace them with a vanilla virtualenv for greatest compatibility.\r\n\r\nI suggest we add tests which ensure that the package can still be successfully solved and installed by conda and pipenv. If they don't take too long (<2min) then we can run them in the main CI, otherwise they will be cron_job tests (which are run only nightly).\n", "before_files": [{"content": "from setuptools import find_packages\nfrom setuptools import setup\n\n# Required dependencies\nrequired = [\n # Please keep alphabetized\n 'akro==0.0.6',\n 'cached_property',\n 'click',\n 'cloudpickle',\n 'cma==1.1.06',\n # dm_control throws an error during install about not being able to\n # find a build dependency (absl-py). Later pip executes the `install`\n # command again and the install succeeds because absl-py has been\n # installed. This is stupid, but harmless.\n 'dm_control @ https://api.github.com/repos/deepmind/dm_control/tarball/7a36377879c57777e5d5b4da5aae2cd2a29b607a', # noqa: E501\n 'dowel==0.0.2',\n 'gym[all]==0.12.4',\n 'joblib<0.13,>=0.12',\n 'matplotlib',\n 'mujoco-py<2.1,>=2.0',\n 'numpy==1.14.5',\n 'psutil',\n # Pyglet 1.4.0 introduces some api change which breaks some\n # gym environments\n # See: https://github.com/openai/gym/issues/1588\n 'pyglet<1.4.0,>=1.3.0',\n 'pyprind',\n 'python-dateutil',\n 'torch==1.1.0',\n 'scikit-image',\n 'scipy',\n 'tensorflow<1.13,>=1.12.0',\n 'tensorflow-probability<0.6.0,>=0.5.0', # for tensorflow 1.12\n 'torchvision==0.3.0'\n]\n\n# Dependencies for optional features\nextras = {}\nextras['all'] = list(set(sum(extras.values(), [])))\n\n# Intel dependencies not included in all\nextras['intel'] = ['intel-tensorflow<1.13,>=1.12.0']\n\n# Development dependencies (*not* included in \"all\")\nextras['dev'] = [\n # Please keep alphabetized\n 'baselines @ https://api.github.com/repos/openai/baselines/tarball/f2729693253c0ef4d4086231d36e0a4307ec1cb3', # noqa: E501\n 'flake8',\n 'flake8-docstrings==1.3.0',\n 'flake8-import-order',\n 'pandas',\n 'pep8-naming==0.7.0',\n 'pre-commit',\n # pydocstyle 4.0.0 breaks flake8-docstrings 1.3.0\n # See https://gitlab.com/pycqa/flake8-docstrings/issues/36\n 'pydocstyle<4.0.0',\n 'pylint==1.9.2',\n 'pytest>=3.6', # Required for pytest-cov on Python 3.6\n 'pytest-cov',\n 'sphinx',\n 'sphinx_rtd_theme',\n 'yapf',\n]\n\nwith open('README.md') as f:\n readme = f.read()\n\n# Get the package version dynamically\nwith open('VERSION') as v:\n version = v.read().strip()\n\nsetup(\n name='garage',\n version=version,\n author='Reinforcement Learning Working Group',\n description='A framework for reproducible reinforcement learning research',\n url='https://github.com/rlworkgroup/garage',\n packages=find_packages(where='src'),\n package_dir={'': 'src'},\n scripts=['scripts/garage'],\n install_requires=required,\n extras_require=extras,\n license='MIT',\n long_description=readme,\n long_description_content_type='text/markdown',\n classifiers=[\n 'Development Status :: 4 - Beta',\n 'Intended Audience :: Developers',\n 'Intended Audience :: Education',\n 'Intended Audience :: Science/Research',\n 'License :: OSI Approved :: MIT License',\n 'Programming Language :: Python :: 3.5',\n 'Programming Language :: Python :: 3.6',\n 'Programming Language :: Python :: 3.7',\n 'Programming Language :: Python :: 3 :: Only',\n 'Topic :: Scientific/Engineering :: Artificial Intelligence',\n 'Topic :: Scientific/Engineering :: Mathematics',\n 'Topic :: Software Development :: Libraries',\n ],\n)\n", "path": "setup.py"}, {"content": "from dowel import logger, tabular\nimport numpy as np\n\nfrom garage.np.algos import BatchPolopt\n\n\nclass CEM(BatchPolopt):\n \"\"\"Cross Entropy Method.\n\n CEM works by iteratively optimizing a gaussian distribution of policy.\n\n In each epoch, CEM does the following:\n 1. Sample n_samples policies from a gaussian distribution of\n mean cur_mean and std cur_std.\n 2. Do rollouts for each policy.\n 3. Update cur_mean and cur_std by doing Maximum Likelihood Estimation\n over the n_best top policies in terms of return.\n\n Note:\n When training CEM with LocalRunner, make sure that n_epoch_cycles for\n runner equals to n_samples for CEM.\n\n This implementation leverage n_epoch_cycles to do rollouts for a single\n policy in an epoch cycle.\n\n Args:\n env_spec (garage.envs.EnvSpec): Environment specification.\n policy (garage.np.policies.Policy): Action policy.\n baseline(garage.np.baselines.Baseline): Baseline for GAE\n (Generalized Advantage Estimation).\n n_samples (int): Number of policies sampled in one epoch.\n discount (float): Environment reward discount.\n max_path_length (int): Maximum length of a single rollout.\n best_frac (float): The best fraction.\n init_std (float): Initial std for policy param distribution.\n extra_std (float): Decaying std added to param distribution.\n extra_decay_time (float): Epochs that it takes to decay extra std.\n\n \"\"\"\n\n def __init__(self,\n env_spec,\n policy,\n baseline,\n n_samples,\n discount=0.99,\n max_path_length=500,\n init_std=1,\n best_frac=0.05,\n extra_std=1.,\n extra_decay_time=100):\n super().__init__(policy, baseline, discount, max_path_length,\n n_samples)\n self.env_spec = env_spec\n\n self.init_std = init_std\n self.best_frac = best_frac\n self.extra_std = extra_std\n self.extra_decay_time = extra_decay_time\n\n # epoch-wise\n self.cur_std = self.init_std\n self.cur_mean = self.policy.get_param_values()\n # epoch-cycle-wise\n self.cur_params = self.cur_mean\n self.all_returns = []\n self.all_params = [self.cur_mean.copy()]\n # fixed\n self.n_best = int(n_samples * best_frac)\n assert self.n_best >= 1, (\n f'n_samples is too low. Make sure that n_samples * best_frac >= 1')\n self.n_params = len(self.cur_mean)\n\n def sample_params(self, epoch):\n extra_var_mult = max(1.0 - epoch / self.extra_decay_time, 0)\n sample_std = np.sqrt(\n np.square(self.cur_std) +\n np.square(self.extra_std) * extra_var_mult)\n return np.random.standard_normal(\n self.n_params) * sample_std + self.cur_mean\n\n def train_once(self, itr, paths):\n paths = self.process_samples(itr, paths)\n\n epoch = itr // self.n_samples\n i_sample = itr - epoch * self.n_samples\n tabular.record('Epoch', epoch)\n tabular.record('# Sample', i_sample)\n # -- Stage: Process path\n rtn = paths['average_return']\n self.all_returns.append(paths['average_return'])\n\n # -- Stage: Update policy distribution.\n if (itr + 1) % self.n_samples == 0:\n avg_rtns = np.array(self.all_returns)\n best_inds = np.argsort(-avg_rtns)[:self.n_best]\n best_params = np.array(self.all_params)[best_inds]\n\n # MLE of normal distribution\n self.cur_mean = best_params.mean(axis=0)\n self.cur_std = best_params.std(axis=0)\n self.policy.set_param_values(self.cur_mean)\n\n # Clear for next epoch\n rtn = max(self.all_returns)\n self.all_returns.clear()\n self.all_params.clear()\n\n # -- Stage: Generate a new policy for next path sampling\n self.cur_params = self.sample_params(itr)\n self.all_params.append(self.cur_params.copy())\n self.policy.set_param_values(self.cur_params)\n\n logger.log(tabular)\n return rtn\n\n def get_itr_snapshot(self, itr):\n return dict(itr=itr, policy=self.policy, baseline=self.baseline)\n", "path": "src/garage/np/algos/cem.py"}], "after_files": [{"content": "from setuptools import find_packages\nfrom setuptools import setup\n\ntry:\n # pylint: disable=unused-import\n import numpy # noqa: F401\nexcept ImportError:\n raise RuntimeError(\n 'garage requires numpy in the environment to install. '\n 'Please install numpy==1.14.5 and try again. See '\n 'https://github.com/rlworkgroup/garage/issues/800 for more info.')\n\n# Required dependencies\nrequired = [\n # Please keep alphabetized\n 'akro==0.0.6',\n 'cached_property',\n 'click',\n 'cloudpickle',\n 'cma==1.1.06',\n # dm_control throws an error during install about not being able to\n # find a build dependency (absl-py). Later pip executes the `install`\n # command again and the install succeeds because absl-py has been\n # installed. This is stupid, but harmless.\n 'dm_control @ https://api.github.com/repos/deepmind/dm_control/tarball/7a36377879c57777e5d5b4da5aae2cd2a29b607a', # noqa: E501\n 'dowel==0.0.2',\n 'gym[all]==0.12.4',\n 'joblib<0.13,>=0.12',\n 'matplotlib',\n 'mujoco-py<2.1,>=2.0',\n 'numpy==1.14.5',\n 'psutil',\n # Pyglet 1.4.0 introduces some api change which breaks some\n # gym environments\n # See: https://github.com/openai/gym/issues/1588\n 'pyglet<1.4.0,>=1.3.0',\n 'pyprind',\n 'python-dateutil',\n 'torch==1.1.0',\n 'scikit-image',\n 'scipy',\n 'tensorflow<1.13,>=1.12.0',\n 'tensorflow-probability<0.6.0,>=0.5.0', # for tensorflow 1.12\n 'torchvision==0.3.0'\n]\n\n# Dependencies for optional features\nextras = {}\nextras['all'] = list(set(sum(extras.values(), [])))\n\n# Intel dependencies not included in all\nextras['intel'] = ['intel-tensorflow<1.13,>=1.12.0']\n\n# Development dependencies (*not* included in \"all\")\nextras['dev'] = [\n # Please keep alphabetized\n 'baselines @ https://api.github.com/repos/openai/baselines/tarball/f2729693253c0ef4d4086231d36e0a4307ec1cb3', # noqa: E501\n 'flake8',\n 'flake8-docstrings==1.3.0',\n 'flake8-import-order',\n 'pandas',\n 'pep8-naming==0.7.0',\n 'pre-commit',\n # pydocstyle 4.0.0 breaks flake8-docstrings 1.3.0\n # See https://gitlab.com/pycqa/flake8-docstrings/issues/36\n 'pydocstyle<4.0.0',\n 'pylint==1.9.2',\n 'pytest>=3.6', # Required for pytest-cov on Python 3.6\n 'pytest-cov',\n 'pytest-xdist',\n 'sphinx',\n 'sphinx_rtd_theme',\n 'yapf',\n]\n\nwith open('README.md') as f:\n readme = f.read()\n\n# Get the package version dynamically\nwith open('VERSION') as v:\n version = v.read().strip()\n\nsetup(\n name='garage',\n version=version,\n author='Reinforcement Learning Working Group',\n description='A framework for reproducible reinforcement learning research',\n url='https://github.com/rlworkgroup/garage',\n packages=find_packages(where='src'),\n package_dir={'': 'src'},\n scripts=['scripts/garage'],\n python_requires='>=3.5',\n install_requires=required,\n extras_require=extras,\n license='MIT',\n long_description=readme,\n long_description_content_type='text/markdown',\n classifiers=[\n 'Development Status :: 4 - Beta',\n 'Intended Audience :: Developers',\n 'Intended Audience :: Education',\n 'Intended Audience :: Science/Research',\n 'License :: OSI Approved :: MIT License',\n 'Programming Language :: Python :: 3.5',\n 'Programming Language :: Python :: 3.6',\n 'Programming Language :: Python :: 3.7',\n 'Programming Language :: Python :: 3 :: Only',\n 'Topic :: Scientific/Engineering :: Artificial Intelligence',\n 'Topic :: Scientific/Engineering :: Mathematics',\n 'Topic :: Software Development :: Libraries',\n ],\n)\n", "path": "setup.py"}, {"content": "from dowel import logger, tabular\nimport numpy as np\n\nfrom garage.np.algos import BatchPolopt\n\n\nclass CEM(BatchPolopt):\n \"\"\"Cross Entropy Method.\n\n CEM works by iteratively optimizing a gaussian distribution of policy.\n\n In each epoch, CEM does the following:\n 1. Sample n_samples policies from a gaussian distribution of\n mean cur_mean and std cur_std.\n 2. Do rollouts for each policy.\n 3. Update cur_mean and cur_std by doing Maximum Likelihood Estimation\n over the n_best top policies in terms of return.\n\n Note:\n When training CEM with LocalRunner, make sure that n_epoch_cycles for\n runner equals to n_samples for CEM.\n\n This implementation leverage n_epoch_cycles to do rollouts for a single\n policy in an epoch cycle.\n\n Args:\n env_spec (garage.envs.EnvSpec): Environment specification.\n policy (garage.np.policies.Policy): Action policy.\n baseline(garage.np.baselines.Baseline): Baseline for GAE\n (Generalized Advantage Estimation).\n n_samples (int): Number of policies sampled in one epoch.\n discount (float): Environment reward discount.\n max_path_length (int): Maximum length of a single rollout.\n best_frac (float): The best fraction.\n init_std (float): Initial std for policy param distribution.\n extra_std (float): Decaying std added to param distribution.\n extra_decay_time (float): Epochs that it takes to decay extra std.\n\n \"\"\"\n\n def __init__(self,\n env_spec,\n policy,\n baseline,\n n_samples,\n discount=0.99,\n max_path_length=500,\n init_std=1,\n best_frac=0.05,\n extra_std=1.,\n extra_decay_time=100):\n super().__init__(policy, baseline, discount, max_path_length,\n n_samples)\n self.env_spec = env_spec\n\n self.init_std = init_std\n self.best_frac = best_frac\n self.extra_std = extra_std\n self.extra_decay_time = extra_decay_time\n\n # epoch-wise\n self.cur_std = self.init_std\n self.cur_mean = self.policy.get_param_values()\n # epoch-cycle-wise\n self.cur_params = self.cur_mean\n self.all_returns = []\n self.all_params = [self.cur_mean.copy()]\n # fixed\n self.n_best = int(n_samples * best_frac)\n assert self.n_best >= 1, (\n 'n_samples is too low. Make sure that n_samples * best_frac >= 1')\n self.n_params = len(self.cur_mean)\n\n def sample_params(self, epoch):\n extra_var_mult = max(1.0 - epoch / self.extra_decay_time, 0)\n sample_std = np.sqrt(\n np.square(self.cur_std) +\n np.square(self.extra_std) * extra_var_mult)\n return np.random.standard_normal(\n self.n_params) * sample_std + self.cur_mean\n\n def train_once(self, itr, paths):\n paths = self.process_samples(itr, paths)\n\n epoch = itr // self.n_samples\n i_sample = itr - epoch * self.n_samples\n tabular.record('Epoch', epoch)\n tabular.record('# Sample', i_sample)\n # -- Stage: Process path\n rtn = paths['average_return']\n self.all_returns.append(paths['average_return'])\n\n # -- Stage: Update policy distribution.\n if (itr + 1) % self.n_samples == 0:\n avg_rtns = np.array(self.all_returns)\n best_inds = np.argsort(-avg_rtns)[:self.n_best]\n best_params = np.array(self.all_params)[best_inds]\n\n # MLE of normal distribution\n self.cur_mean = best_params.mean(axis=0)\n self.cur_std = best_params.std(axis=0)\n self.policy.set_param_values(self.cur_mean)\n\n # Clear for next epoch\n rtn = max(self.all_returns)\n self.all_returns.clear()\n self.all_params.clear()\n\n # -- Stage: Generate a new policy for next path sampling\n self.cur_params = self.sample_params(itr)\n self.all_params.append(self.cur_params.copy())\n self.policy.set_param_values(self.cur_params)\n\n logger.log(tabular)\n return rtn\n\n def get_itr_snapshot(self, itr):\n return dict(itr=itr, policy=self.policy, baseline=self.baseline)\n", "path": "src/garage/np/algos/cem.py"}]}
| 2,820 | 447 |
gh_patches_debug_34606
|
rasdani/github-patches
|
git_diff
|
ansible__awx-8016
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Add insignts_credential paramter to tower_inventory
<!-- Issues are for **concrete, actionable bugs and feature requests** only - if you're just asking for debugging help or technical support, please use:
- http://webchat.freenode.net/?channels=ansible-awx
- https://groups.google.com/forum/#!forum/awx-project
We have to limit this because of limited volunteer time to respond to issues! -->
##### ISSUE TYPE
- Feature Idea
##### SUMMARY
<!-- Briefly describe the problem or desired enhancement. -->
Per PR #7963 tower_inventory is missing support for the insights_credential API parameter.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `awx_collection/plugins/modules/tower_inventory.py`
Content:
```
1 #!/usr/bin/python
2 # coding: utf-8 -*-
3
4 # (c) 2017, Wayne Witzel III <[email protected]>
5 # GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)
6
7 from __future__ import absolute_import, division, print_function
8 __metaclass__ = type
9
10
11 ANSIBLE_METADATA = {'metadata_version': '1.1',
12 'status': ['preview'],
13 'supported_by': 'community'}
14
15
16 DOCUMENTATION = '''
17 ---
18 module: tower_inventory
19 author: "Wayne Witzel III (@wwitzel3)"
20 short_description: create, update, or destroy Ansible Tower inventory.
21 description:
22 - Create, update, or destroy Ansible Tower inventories. See
23 U(https://www.ansible.com/tower) for an overview.
24 options:
25 name:
26 description:
27 - The name to use for the inventory.
28 required: True
29 type: str
30 description:
31 description:
32 - The description to use for the inventory.
33 type: str
34 organization:
35 description:
36 - Organization the inventory belongs to.
37 required: True
38 type: str
39 variables:
40 description:
41 - Inventory variables.
42 type: dict
43 kind:
44 description:
45 - The kind field. Cannot be modified after created.
46 default: ""
47 choices: ["", "smart"]
48 type: str
49 host_filter:
50 description:
51 - The host_filter field. Only useful when C(kind=smart).
52 type: str
53 state:
54 description:
55 - Desired state of the resource.
56 default: "present"
57 choices: ["present", "absent"]
58 type: str
59 extends_documentation_fragment: awx.awx.auth
60 '''
61
62
63 EXAMPLES = '''
64 - name: Add tower inventory
65 tower_inventory:
66 name: "Foo Inventory"
67 description: "Our Foo Cloud Servers"
68 organization: "Bar Org"
69 state: present
70 tower_config_file: "~/tower_cli.cfg"
71 '''
72
73
74 from ..module_utils.tower_api import TowerAPIModule
75 import json
76
77
78 def main():
79 # Any additional arguments that are not fields of the item can be added here
80 argument_spec = dict(
81 name=dict(required=True),
82 description=dict(),
83 organization=dict(required=True),
84 variables=dict(type='dict'),
85 kind=dict(choices=['', 'smart'], default=''),
86 host_filter=dict(),
87 state=dict(choices=['present', 'absent'], default='present'),
88 )
89
90 # Create a module for ourselves
91 module = TowerAPIModule(argument_spec=argument_spec)
92
93 # Extract our parameters
94 name = module.params.get('name')
95 description = module.params.get('description')
96 organization = module.params.get('organization')
97 variables = module.params.get('variables')
98 state = module.params.get('state')
99 kind = module.params.get('kind')
100 host_filter = module.params.get('host_filter')
101
102 # Attempt to look up the related items the user specified (these will fail the module if not found)
103 org_id = module.resolve_name_to_id('organizations', organization)
104
105 # Attempt to look up inventory based on the provided name and org ID
106 inventory = module.get_one('inventories', **{
107 'data': {
108 'name': name,
109 'organization': org_id
110 }
111 })
112
113 if state == 'absent':
114 # If the state was absent we can let the module delete it if needed, the module will handle exiting from this
115 module.delete_if_needed(inventory)
116
117 # Create the data that gets sent for create and update
118 inventory_fields = {
119 'name': name,
120 'organization': org_id,
121 'kind': kind,
122 'host_filter': host_filter,
123 }
124 if description is not None:
125 inventory_fields['description'] = description
126 if variables is not None:
127 inventory_fields['variables'] = json.dumps(variables)
128
129 # We need to perform a check to make sure you are not trying to convert a regular inventory into a smart one.
130 if inventory and inventory['kind'] == '' and inventory_fields['kind'] == 'smart':
131 module.fail_json(msg='You cannot turn a regular inventory into a "smart" inventory.')
132
133 # If the state was present and we can let the module build or update the existing inventory, this will return on its own
134 module.create_or_update_if_needed(inventory, inventory_fields, endpoint='inventories', item_type='inventory')
135
136
137 if __name__ == '__main__':
138 main()
139
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/awx_collection/plugins/modules/tower_inventory.py b/awx_collection/plugins/modules/tower_inventory.py
--- a/awx_collection/plugins/modules/tower_inventory.py
+++ b/awx_collection/plugins/modules/tower_inventory.py
@@ -48,7 +48,11 @@
type: str
host_filter:
description:
- - The host_filter field. Only useful when C(kind=smart).
+ - The host_filter field. Only useful when C(kind=smart).
+ type: str
+ insights_credential:
+ description:
+ - Credentials to be used by hosts belonging to this inventory when accessing Red Hat Insights API.
type: str
state:
description:
@@ -84,6 +88,7 @@
variables=dict(type='dict'),
kind=dict(choices=['', 'smart'], default=''),
host_filter=dict(),
+ insights_credential=dict(),
state=dict(choices=['present', 'absent'], default='present'),
)
@@ -98,6 +103,7 @@
state = module.params.get('state')
kind = module.params.get('kind')
host_filter = module.params.get('host_filter')
+ insights_credential = module.params.get('insights_credential')
# Attempt to look up the related items the user specified (these will fail the module if not found)
org_id = module.resolve_name_to_id('organizations', organization)
@@ -125,6 +131,8 @@
inventory_fields['description'] = description
if variables is not None:
inventory_fields['variables'] = json.dumps(variables)
+ if insights_credential is not None:
+ inventory_fields['insights_credential'] = module.resolve_name_to_id('credentials', insights_credential)
# We need to perform a check to make sure you are not trying to convert a regular inventory into a smart one.
if inventory and inventory['kind'] == '' and inventory_fields['kind'] == 'smart':
|
{"golden_diff": "diff --git a/awx_collection/plugins/modules/tower_inventory.py b/awx_collection/plugins/modules/tower_inventory.py\n--- a/awx_collection/plugins/modules/tower_inventory.py\n+++ b/awx_collection/plugins/modules/tower_inventory.py\n@@ -48,7 +48,11 @@\n type: str\n host_filter:\n description:\n- - The host_filter field. Only useful when C(kind=smart).\n+ - The host_filter field. Only useful when C(kind=smart).\n+ type: str\n+ insights_credential:\n+ description:\n+ - Credentials to be used by hosts belonging to this inventory when accessing Red Hat Insights API.\n type: str\n state:\n description:\n@@ -84,6 +88,7 @@\n variables=dict(type='dict'),\n kind=dict(choices=['', 'smart'], default=''),\n host_filter=dict(),\n+ insights_credential=dict(),\n state=dict(choices=['present', 'absent'], default='present'),\n )\n \n@@ -98,6 +103,7 @@\n state = module.params.get('state')\n kind = module.params.get('kind')\n host_filter = module.params.get('host_filter')\n+ insights_credential = module.params.get('insights_credential')\n \n # Attempt to look up the related items the user specified (these will fail the module if not found)\n org_id = module.resolve_name_to_id('organizations', organization)\n@@ -125,6 +131,8 @@\n inventory_fields['description'] = description\n if variables is not None:\n inventory_fields['variables'] = json.dumps(variables)\n+ if insights_credential is not None:\n+ inventory_fields['insights_credential'] = module.resolve_name_to_id('credentials', insights_credential)\n \n # We need to perform a check to make sure you are not trying to convert a regular inventory into a smart one.\n if inventory and inventory['kind'] == '' and inventory_fields['kind'] == 'smart':\n", "issue": "Add insignts_credential paramter to tower_inventory\n<!-- Issues are for **concrete, actionable bugs and feature requests** only - if you're just asking for debugging help or technical support, please use:\r\n\r\n- http://webchat.freenode.net/?channels=ansible-awx\r\n- https://groups.google.com/forum/#!forum/awx-project\r\n\r\nWe have to limit this because of limited volunteer time to respond to issues! -->\r\n\r\n##### ISSUE TYPE\r\n - Feature Idea\r\n\r\n##### SUMMARY\r\n<!-- Briefly describe the problem or desired enhancement. -->\r\nPer PR #7963 tower_inventory is missing support for the insights_credential API parameter.\n", "before_files": [{"content": "#!/usr/bin/python\n# coding: utf-8 -*-\n\n# (c) 2017, Wayne Witzel III <[email protected]>\n# GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)\n\nfrom __future__ import absolute_import, division, print_function\n__metaclass__ = type\n\n\nANSIBLE_METADATA = {'metadata_version': '1.1',\n 'status': ['preview'],\n 'supported_by': 'community'}\n\n\nDOCUMENTATION = '''\n---\nmodule: tower_inventory\nauthor: \"Wayne Witzel III (@wwitzel3)\"\nshort_description: create, update, or destroy Ansible Tower inventory.\ndescription:\n - Create, update, or destroy Ansible Tower inventories. See\n U(https://www.ansible.com/tower) for an overview.\noptions:\n name:\n description:\n - The name to use for the inventory.\n required: True\n type: str\n description:\n description:\n - The description to use for the inventory.\n type: str\n organization:\n description:\n - Organization the inventory belongs to.\n required: True\n type: str\n variables:\n description:\n - Inventory variables.\n type: dict\n kind:\n description:\n - The kind field. Cannot be modified after created.\n default: \"\"\n choices: [\"\", \"smart\"]\n type: str\n host_filter:\n description:\n - The host_filter field. Only useful when C(kind=smart).\n type: str\n state:\n description:\n - Desired state of the resource.\n default: \"present\"\n choices: [\"present\", \"absent\"]\n type: str\nextends_documentation_fragment: awx.awx.auth\n'''\n\n\nEXAMPLES = '''\n- name: Add tower inventory\n tower_inventory:\n name: \"Foo Inventory\"\n description: \"Our Foo Cloud Servers\"\n organization: \"Bar Org\"\n state: present\n tower_config_file: \"~/tower_cli.cfg\"\n'''\n\n\nfrom ..module_utils.tower_api import TowerAPIModule\nimport json\n\n\ndef main():\n # Any additional arguments that are not fields of the item can be added here\n argument_spec = dict(\n name=dict(required=True),\n description=dict(),\n organization=dict(required=True),\n variables=dict(type='dict'),\n kind=dict(choices=['', 'smart'], default=''),\n host_filter=dict(),\n state=dict(choices=['present', 'absent'], default='present'),\n )\n\n # Create a module for ourselves\n module = TowerAPIModule(argument_spec=argument_spec)\n\n # Extract our parameters\n name = module.params.get('name')\n description = module.params.get('description')\n organization = module.params.get('organization')\n variables = module.params.get('variables')\n state = module.params.get('state')\n kind = module.params.get('kind')\n host_filter = module.params.get('host_filter')\n\n # Attempt to look up the related items the user specified (these will fail the module if not found)\n org_id = module.resolve_name_to_id('organizations', organization)\n\n # Attempt to look up inventory based on the provided name and org ID\n inventory = module.get_one('inventories', **{\n 'data': {\n 'name': name,\n 'organization': org_id\n }\n })\n\n if state == 'absent':\n # If the state was absent we can let the module delete it if needed, the module will handle exiting from this\n module.delete_if_needed(inventory)\n\n # Create the data that gets sent for create and update\n inventory_fields = {\n 'name': name,\n 'organization': org_id,\n 'kind': kind,\n 'host_filter': host_filter,\n }\n if description is not None:\n inventory_fields['description'] = description\n if variables is not None:\n inventory_fields['variables'] = json.dumps(variables)\n\n # We need to perform a check to make sure you are not trying to convert a regular inventory into a smart one.\n if inventory and inventory['kind'] == '' and inventory_fields['kind'] == 'smart':\n module.fail_json(msg='You cannot turn a regular inventory into a \"smart\" inventory.')\n\n # If the state was present and we can let the module build or update the existing inventory, this will return on its own\n module.create_or_update_if_needed(inventory, inventory_fields, endpoint='inventories', item_type='inventory')\n\n\nif __name__ == '__main__':\n main()\n", "path": "awx_collection/plugins/modules/tower_inventory.py"}], "after_files": [{"content": "#!/usr/bin/python\n# coding: utf-8 -*-\n\n# (c) 2017, Wayne Witzel III <[email protected]>\n# GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)\n\nfrom __future__ import absolute_import, division, print_function\n__metaclass__ = type\n\n\nANSIBLE_METADATA = {'metadata_version': '1.1',\n 'status': ['preview'],\n 'supported_by': 'community'}\n\n\nDOCUMENTATION = '''\n---\nmodule: tower_inventory\nauthor: \"Wayne Witzel III (@wwitzel3)\"\nshort_description: create, update, or destroy Ansible Tower inventory.\ndescription:\n - Create, update, or destroy Ansible Tower inventories. See\n U(https://www.ansible.com/tower) for an overview.\noptions:\n name:\n description:\n - The name to use for the inventory.\n required: True\n type: str\n description:\n description:\n - The description to use for the inventory.\n type: str\n organization:\n description:\n - Organization the inventory belongs to.\n required: True\n type: str\n variables:\n description:\n - Inventory variables.\n type: dict\n kind:\n description:\n - The kind field. Cannot be modified after created.\n default: \"\"\n choices: [\"\", \"smart\"]\n type: str\n host_filter:\n description:\n - The host_filter field. Only useful when C(kind=smart).\n type: str\n insights_credential:\n description:\n - Credentials to be used by hosts belonging to this inventory when accessing Red Hat Insights API.\n type: str\n state:\n description:\n - Desired state of the resource.\n default: \"present\"\n choices: [\"present\", \"absent\"]\n type: str\nextends_documentation_fragment: awx.awx.auth\n'''\n\n\nEXAMPLES = '''\n- name: Add tower inventory\n tower_inventory:\n name: \"Foo Inventory\"\n description: \"Our Foo Cloud Servers\"\n organization: \"Bar Org\"\n state: present\n tower_config_file: \"~/tower_cli.cfg\"\n'''\n\n\nfrom ..module_utils.tower_api import TowerAPIModule\nimport json\n\n\ndef main():\n # Any additional arguments that are not fields of the item can be added here\n argument_spec = dict(\n name=dict(required=True),\n description=dict(),\n organization=dict(required=True),\n variables=dict(type='dict'),\n kind=dict(choices=['', 'smart'], default=''),\n host_filter=dict(),\n insights_credential=dict(),\n state=dict(choices=['present', 'absent'], default='present'),\n )\n\n # Create a module for ourselves\n module = TowerAPIModule(argument_spec=argument_spec)\n\n # Extract our parameters\n name = module.params.get('name')\n description = module.params.get('description')\n organization = module.params.get('organization')\n variables = module.params.get('variables')\n state = module.params.get('state')\n kind = module.params.get('kind')\n host_filter = module.params.get('host_filter')\n insights_credential = module.params.get('insights_credential')\n\n # Attempt to look up the related items the user specified (these will fail the module if not found)\n org_id = module.resolve_name_to_id('organizations', organization)\n\n # Attempt to look up inventory based on the provided name and org ID\n inventory = module.get_one('inventories', **{\n 'data': {\n 'name': name,\n 'organization': org_id\n }\n })\n\n if state == 'absent':\n # If the state was absent we can let the module delete it if needed, the module will handle exiting from this\n module.delete_if_needed(inventory)\n\n # Create the data that gets sent for create and update\n inventory_fields = {\n 'name': name,\n 'organization': org_id,\n 'kind': kind,\n 'host_filter': host_filter,\n }\n if description is not None:\n inventory_fields['description'] = description\n if variables is not None:\n inventory_fields['variables'] = json.dumps(variables)\n if insights_credential is not None:\n inventory_fields['insights_credential'] = module.resolve_name_to_id('credentials', insights_credential)\n\n # We need to perform a check to make sure you are not trying to convert a regular inventory into a smart one.\n if inventory and inventory['kind'] == '' and inventory_fields['kind'] == 'smart':\n module.fail_json(msg='You cannot turn a regular inventory into a \"smart\" inventory.')\n\n # If the state was present and we can let the module build or update the existing inventory, this will return on its own\n module.create_or_update_if_needed(inventory, inventory_fields, endpoint='inventories', item_type='inventory')\n\n\nif __name__ == '__main__':\n main()\n", "path": "awx_collection/plugins/modules/tower_inventory.py"}]}
| 1,692 | 433 |
gh_patches_debug_12719
|
rasdani/github-patches
|
git_diff
|
microsoft__playwright-python-593
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Async API - asyncio error
After updating to the 1.9.2 version, for **Async API** I get the following error:
Exception ignored in: <function BaseSubprocessTransport.__del__ at 0x0000000002E1E9D0>
Traceback (most recent call last):
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\base_subprocess.py", line 126, in __del__
self.close()
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\base_subprocess.py", line 104, in close
proto.pipe.close()
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\proactor_events.py", line 108, in close
self._loop.call_soon(self._call_connection_lost, None)
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\base_events.py", line 746, in call_soon
self._check_closed()
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\base_events.py", line 510, in _check_closed
raise RuntimeError('Event loop is closed')
RuntimeError: Event loop is closed
Exception ignored in: <function _ProactorBasePipeTransport.__del__ at 0x0000000002E4A280>
Traceback (most recent call last):
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\proactor_events.py", line 116, in __del__
self.close()
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\proactor_events.py", line 108, in close
self._loop.call_soon(self._call_connection_lost, None)
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\base_events.py", line 746, in call_soon
self._check_closed()
File "C:\Users\Matthew\AppData\Local\Programs\Python\Python39\lib\asyncio\base_events.py", line 510, in _check_closed
raise RuntimeError('Event loop is closed')
RuntimeError: Event loop is closed
Versions:
playwright=1.9.2
asyncio=3.4.3
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `playwright/_impl/_transport.py`
Content:
```
1 # Copyright (c) Microsoft Corporation.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 import asyncio
16 import io
17 import json
18 import os
19 import sys
20 from pathlib import Path
21 from typing import Dict, Optional
22
23
24 # Sourced from: https://github.com/pytest-dev/pytest/blob/da01ee0a4bb0af780167ecd228ab3ad249511302/src/_pytest/faulthandler.py#L69-L77
25 def _get_stderr_fileno() -> Optional[int]:
26 try:
27 return sys.stderr.fileno()
28 except (AttributeError, io.UnsupportedOperation):
29 # pytest-xdist monkeypatches sys.stderr with an object that is not an actual file.
30 # https://docs.python.org/3/library/faulthandler.html#issue-with-file-descriptors
31 # This is potentially dangerous, but the best we can do.
32 if not hasattr(sys, "__stderr__") or not sys.__stderr__:
33 return None
34 return sys.__stderr__.fileno()
35
36
37 class Transport:
38 def __init__(self, driver_executable: Path) -> None:
39 super().__init__()
40 self.on_message = lambda _: None
41 self._stopped = False
42 self._driver_executable = driver_executable
43 self._loop: asyncio.AbstractEventLoop
44
45 def stop(self) -> None:
46 self._stopped = True
47 self._output.close()
48
49 async def wait_until_stopped(self) -> None:
50 await self._stopped_future
51
52 async def run(self) -> None:
53 self._loop = asyncio.get_running_loop()
54 self._stopped_future: asyncio.Future = asyncio.Future()
55
56 proc = await asyncio.create_subprocess_exec(
57 str(self._driver_executable),
58 "run-driver",
59 stdin=asyncio.subprocess.PIPE,
60 stdout=asyncio.subprocess.PIPE,
61 stderr=_get_stderr_fileno(),
62 limit=32768,
63 )
64 assert proc.stdout
65 assert proc.stdin
66 self._output = proc.stdin
67
68 while not self._stopped:
69 try:
70 buffer = await proc.stdout.readexactly(4)
71 length = int.from_bytes(buffer, byteorder="little", signed=False)
72 buffer = bytes(0)
73 while length:
74 to_read = min(length, 32768)
75 data = await proc.stdout.readexactly(to_read)
76 length -= to_read
77 if len(buffer):
78 buffer = buffer + data
79 else:
80 buffer = data
81 obj = json.loads(buffer)
82
83 if "DEBUGP" in os.environ: # pragma: no cover
84 print("\x1b[33mRECV>\x1b[0m", json.dumps(obj, indent=2))
85 self.on_message(obj)
86 except asyncio.IncompleteReadError:
87 break
88 await asyncio.sleep(0)
89 self._stopped_future.set_result(None)
90
91 def send(self, message: Dict) -> None:
92 msg = json.dumps(message)
93 if "DEBUGP" in os.environ: # pragma: no cover
94 print("\x1b[32mSEND>\x1b[0m", json.dumps(message, indent=2))
95 data = msg.encode()
96 self._output.write(
97 len(data).to_bytes(4, byteorder="little", signed=False) + data
98 )
99
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/playwright/_impl/_transport.py b/playwright/_impl/_transport.py
--- a/playwright/_impl/_transport.py
+++ b/playwright/_impl/_transport.py
@@ -48,12 +48,13 @@
async def wait_until_stopped(self) -> None:
await self._stopped_future
+ await self._proc.wait()
async def run(self) -> None:
self._loop = asyncio.get_running_loop()
self._stopped_future: asyncio.Future = asyncio.Future()
- proc = await asyncio.create_subprocess_exec(
+ self._proc = proc = await asyncio.create_subprocess_exec(
str(self._driver_executable),
"run-driver",
stdin=asyncio.subprocess.PIPE,
|
{"golden_diff": "diff --git a/playwright/_impl/_transport.py b/playwright/_impl/_transport.py\n--- a/playwright/_impl/_transport.py\n+++ b/playwright/_impl/_transport.py\n@@ -48,12 +48,13 @@\n \n async def wait_until_stopped(self) -> None:\n await self._stopped_future\n+ await self._proc.wait()\n \n async def run(self) -> None:\n self._loop = asyncio.get_running_loop()\n self._stopped_future: asyncio.Future = asyncio.Future()\n \n- proc = await asyncio.create_subprocess_exec(\n+ self._proc = proc = await asyncio.create_subprocess_exec(\n str(self._driver_executable),\n \"run-driver\",\n stdin=asyncio.subprocess.PIPE,\n", "issue": "Async API - asyncio error\nAfter updating to the 1.9.2 version, for **Async API** I get the following error:\r\n\r\nException ignored in: <function BaseSubprocessTransport.__del__ at 0x0000000002E1E9D0>\r\nTraceback (most recent call last):\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\base_subprocess.py\", line 126, in __del__\r\n self.close()\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\base_subprocess.py\", line 104, in close \r\n proto.pipe.close()\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\proactor_events.py\", line 108, in close \r\n self._loop.call_soon(self._call_connection_lost, None)\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\base_events.py\", line 746, in call_soon\r\n self._check_closed()\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\base_events.py\", line 510, in _check_closed\r\n raise RuntimeError('Event loop is closed')\r\nRuntimeError: Event loop is closed\r\nException ignored in: <function _ProactorBasePipeTransport.__del__ at 0x0000000002E4A280>\r\nTraceback (most recent call last):\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\proactor_events.py\", line 116, in __del__\r\n self.close()\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\proactor_events.py\", line 108, in close\r\n self._loop.call_soon(self._call_connection_lost, None)\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\base_events.py\", line 746, in call_soon\r\n self._check_closed()\r\n File \"C:\\Users\\Matthew\\AppData\\Local\\Programs\\Python\\Python39\\lib\\asyncio\\base_events.py\", line 510, in _check_closed\r\n raise RuntimeError('Event loop is closed')\r\nRuntimeError: Event loop is closed\r\n\r\nVersions:\r\nplaywright=1.9.2\r\nasyncio=3.4.3\n", "before_files": [{"content": "# Copyright (c) Microsoft Corporation.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport asyncio\nimport io\nimport json\nimport os\nimport sys\nfrom pathlib import Path\nfrom typing import Dict, Optional\n\n\n# Sourced from: https://github.com/pytest-dev/pytest/blob/da01ee0a4bb0af780167ecd228ab3ad249511302/src/_pytest/faulthandler.py#L69-L77\ndef _get_stderr_fileno() -> Optional[int]:\n try:\n return sys.stderr.fileno()\n except (AttributeError, io.UnsupportedOperation):\n # pytest-xdist monkeypatches sys.stderr with an object that is not an actual file.\n # https://docs.python.org/3/library/faulthandler.html#issue-with-file-descriptors\n # This is potentially dangerous, but the best we can do.\n if not hasattr(sys, \"__stderr__\") or not sys.__stderr__:\n return None\n return sys.__stderr__.fileno()\n\n\nclass Transport:\n def __init__(self, driver_executable: Path) -> None:\n super().__init__()\n self.on_message = lambda _: None\n self._stopped = False\n self._driver_executable = driver_executable\n self._loop: asyncio.AbstractEventLoop\n\n def stop(self) -> None:\n self._stopped = True\n self._output.close()\n\n async def wait_until_stopped(self) -> None:\n await self._stopped_future\n\n async def run(self) -> None:\n self._loop = asyncio.get_running_loop()\n self._stopped_future: asyncio.Future = asyncio.Future()\n\n proc = await asyncio.create_subprocess_exec(\n str(self._driver_executable),\n \"run-driver\",\n stdin=asyncio.subprocess.PIPE,\n stdout=asyncio.subprocess.PIPE,\n stderr=_get_stderr_fileno(),\n limit=32768,\n )\n assert proc.stdout\n assert proc.stdin\n self._output = proc.stdin\n\n while not self._stopped:\n try:\n buffer = await proc.stdout.readexactly(4)\n length = int.from_bytes(buffer, byteorder=\"little\", signed=False)\n buffer = bytes(0)\n while length:\n to_read = min(length, 32768)\n data = await proc.stdout.readexactly(to_read)\n length -= to_read\n if len(buffer):\n buffer = buffer + data\n else:\n buffer = data\n obj = json.loads(buffer)\n\n if \"DEBUGP\" in os.environ: # pragma: no cover\n print(\"\\x1b[33mRECV>\\x1b[0m\", json.dumps(obj, indent=2))\n self.on_message(obj)\n except asyncio.IncompleteReadError:\n break\n await asyncio.sleep(0)\n self._stopped_future.set_result(None)\n\n def send(self, message: Dict) -> None:\n msg = json.dumps(message)\n if \"DEBUGP\" in os.environ: # pragma: no cover\n print(\"\\x1b[32mSEND>\\x1b[0m\", json.dumps(message, indent=2))\n data = msg.encode()\n self._output.write(\n len(data).to_bytes(4, byteorder=\"little\", signed=False) + data\n )\n", "path": "playwright/_impl/_transport.py"}], "after_files": [{"content": "# Copyright (c) Microsoft Corporation.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport asyncio\nimport io\nimport json\nimport os\nimport sys\nfrom pathlib import Path\nfrom typing import Dict, Optional\n\n\n# Sourced from: https://github.com/pytest-dev/pytest/blob/da01ee0a4bb0af780167ecd228ab3ad249511302/src/_pytest/faulthandler.py#L69-L77\ndef _get_stderr_fileno() -> Optional[int]:\n try:\n return sys.stderr.fileno()\n except (AttributeError, io.UnsupportedOperation):\n # pytest-xdist monkeypatches sys.stderr with an object that is not an actual file.\n # https://docs.python.org/3/library/faulthandler.html#issue-with-file-descriptors\n # This is potentially dangerous, but the best we can do.\n if not hasattr(sys, \"__stderr__\") or not sys.__stderr__:\n return None\n return sys.__stderr__.fileno()\n\n\nclass Transport:\n def __init__(self, driver_executable: Path) -> None:\n super().__init__()\n self.on_message = lambda _: None\n self._stopped = False\n self._driver_executable = driver_executable\n self._loop: asyncio.AbstractEventLoop\n\n def stop(self) -> None:\n self._stopped = True\n self._output.close()\n\n async def wait_until_stopped(self) -> None:\n await self._stopped_future\n await self._proc.wait()\n\n async def run(self) -> None:\n self._loop = asyncio.get_running_loop()\n self._stopped_future: asyncio.Future = asyncio.Future()\n\n self._proc = proc = await asyncio.create_subprocess_exec(\n str(self._driver_executable),\n \"run-driver\",\n stdin=asyncio.subprocess.PIPE,\n stdout=asyncio.subprocess.PIPE,\n stderr=_get_stderr_fileno(),\n limit=32768,\n )\n assert proc.stdout\n assert proc.stdin\n self._output = proc.stdin\n\n while not self._stopped:\n try:\n buffer = await proc.stdout.readexactly(4)\n length = int.from_bytes(buffer, byteorder=\"little\", signed=False)\n buffer = bytes(0)\n while length:\n to_read = min(length, 32768)\n data = await proc.stdout.readexactly(to_read)\n length -= to_read\n if len(buffer):\n buffer = buffer + data\n else:\n buffer = data\n obj = json.loads(buffer)\n\n if \"DEBUGP\" in os.environ: # pragma: no cover\n print(\"\\x1b[33mRECV>\\x1b[0m\", json.dumps(obj, indent=2))\n self.on_message(obj)\n except asyncio.IncompleteReadError:\n break\n await asyncio.sleep(0)\n self._stopped_future.set_result(None)\n\n def send(self, message: Dict) -> None:\n msg = json.dumps(message)\n if \"DEBUGP\" in os.environ: # pragma: no cover\n print(\"\\x1b[32mSEND>\\x1b[0m\", json.dumps(message, indent=2))\n data = msg.encode()\n self._output.write(\n len(data).to_bytes(4, byteorder=\"little\", signed=False) + data\n )\n", "path": "playwright/_impl/_transport.py"}]}
| 1,873 | 163 |
gh_patches_debug_47861
|
rasdani/github-patches
|
git_diff
|
saleor__saleor-4008
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Duplicate choices in shipping address
### What I'm trying to achieve
I'm trying to set shipping user for Russian user and there are duplicate values in "Oblast" selector.
### Steps to reproduce the problem
1. Create new shipping address
2. Country --> Russia
3. There are duplicated values in "Oblast" selector
### What I expected to happen
There are no duplicated values in "Oblast" selector
### Screenshots
What happens now
<img src="https://user-images.githubusercontent.com/13136992/53255369-8a239600-36d6-11e9-84a6-24a10b96a321.png" width="300">
What I expect to see
<img src="https://user-images.githubusercontent.com/13136992/53255400-99a2df00-36d6-11e9-8913-ecaec174487a.png" width="300">
**System information**
Operating system: Manjaro Linux
Browser: Google Chrome 72.0.3626.81
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `saleor/account/forms.py`
Content:
```
1 from captcha.fields import ReCaptchaField
2 from django import forms
3 from django.conf import settings
4 from django.contrib.auth import forms as django_forms, update_session_auth_hash
5 from django.utils.translation import pgettext, pgettext_lazy
6 from phonenumbers.phonenumberutil import country_code_for_region
7
8 from ..account.models import User
9 from . import emails
10 from .i18n import AddressMetaForm, get_address_form_class
11
12
13 class FormWithReCaptcha(forms.BaseForm):
14 def __new__(cls, *args, **kwargs):
15 if settings.RECAPTCHA_PUBLIC_KEY and settings.RECAPTCHA_PRIVATE_KEY:
16 # insert a Google reCaptcha field inside the form
17 # note: label is empty, the reCaptcha is self-explanatory making
18 # the form simpler for the user.
19 cls.base_fields['_captcha'] = ReCaptchaField(label='')
20 return super(FormWithReCaptcha, cls).__new__(cls)
21
22
23 def get_address_form(
24 data, country_code, initial=None, instance=None, **kwargs):
25 country_form = AddressMetaForm(data, initial=initial)
26 preview = False
27 if country_form.is_valid():
28 country_code = country_form.cleaned_data['country']
29 preview = country_form.cleaned_data['preview']
30
31 if initial is None and country_code:
32 initial = {}
33 if country_code:
34 initial['phone'] = '+{}'.format(country_code_for_region(country_code))
35
36 address_form_class = get_address_form_class(country_code)
37
38 if not preview and instance is not None:
39 address_form_class = get_address_form_class(instance.country.code)
40 address_form = address_form_class(data, instance=instance, **kwargs)
41 else:
42 initial_address = (
43 initial if not preview
44 else data.dict() if data is not None else data)
45 address_form = address_form_class(
46 not preview and data or None,
47 initial=initial_address,
48 **kwargs)
49 return address_form, preview
50
51
52 class ChangePasswordForm(django_forms.PasswordChangeForm):
53 def __init__(self, *args, **kwargs):
54 super().__init__(*args, **kwargs)
55 self.fields['new_password1'].user = self.user
56 self.fields['old_password'].widget.attrs['placeholder'] = ''
57 self.fields['new_password1'].widget.attrs['placeholder'] = ''
58 del self.fields['new_password2']
59
60
61 def logout_on_password_change(request, user):
62 if (update_session_auth_hash is not None and
63 not settings.LOGOUT_ON_PASSWORD_CHANGE):
64 update_session_auth_hash(request, user)
65
66
67 class LoginForm(django_forms.AuthenticationForm, FormWithReCaptcha):
68 username = forms.EmailField(
69 label=pgettext('Form field', 'Email'), max_length=75)
70
71 def __init__(self, request=None, *args, **kwargs):
72 super().__init__(request=request, *args, **kwargs)
73 if request:
74 email = request.GET.get('email')
75 if email:
76 self.fields['username'].initial = email
77
78
79 class SignupForm(forms.ModelForm, FormWithReCaptcha):
80 password = forms.CharField(
81 widget=forms.PasswordInput,
82 label=pgettext('Password', 'Password'))
83 email = forms.EmailField(
84 label=pgettext('Email', 'Email'),
85 error_messages={
86 'unique': pgettext_lazy(
87 'Registration error',
88 'This email has already been registered.')})
89
90 class Meta:
91 model = User
92 fields = ('email',)
93
94 def __init__(self, *args, **kwargs):
95 super().__init__(*args, **kwargs)
96 if self._meta.model.USERNAME_FIELD in self.fields:
97 self.fields[self._meta.model.USERNAME_FIELD].widget.attrs.update(
98 {'autofocus': ''})
99
100 def save(self, request=None, commit=True):
101 user = super().save(commit=False)
102 password = self.cleaned_data['password']
103 user.set_password(password)
104 if commit:
105 user.save()
106 return user
107
108
109 class PasswordResetForm(django_forms.PasswordResetForm, FormWithReCaptcha):
110 """Allow resetting passwords.
111
112 This subclass overrides sending emails to use templated email.
113 """
114
115 def get_users(self, email):
116 active_users = User.objects.filter(email__iexact=email, is_active=True)
117 return active_users
118
119 def send_mail(
120 self, subject_template_name, email_template_name, context,
121 from_email, to_email, html_email_template_name=None):
122 # Passing the user object to the Celery task throws an
123 # error "'User' is not JSON serializable". Since it's not used in our
124 # template, we remove it from the context.
125 del context['user']
126 emails.send_password_reset_email.delay(context, to_email)
127
128
129 class NameForm(forms.ModelForm):
130 class Meta:
131 model = User
132 fields = ['first_name', 'last_name']
133 labels = {
134 'first_name': pgettext_lazy(
135 'Customer form: Given name field', 'Given name'),
136 'last_name': pgettext_lazy(
137 'Customer form: Family name field', 'Family name')}
138
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/saleor/account/forms.py b/saleor/account/forms.py
--- a/saleor/account/forms.py
+++ b/saleor/account/forms.py
@@ -46,6 +46,11 @@
not preview and data or None,
initial=initial_address,
**kwargs)
+
+ if hasattr(address_form.fields['country_area'], 'choices'):
+ choices = address_form.fields['country_area'].choices
+ choices = [(choice[1], choice[1]) for choice in choices]
+ address_form.fields['country_area'].choices = choices
return address_form, preview
|
{"golden_diff": "diff --git a/saleor/account/forms.py b/saleor/account/forms.py\n--- a/saleor/account/forms.py\n+++ b/saleor/account/forms.py\n@@ -46,6 +46,11 @@\n not preview and data or None,\n initial=initial_address,\n **kwargs)\n+\n+ if hasattr(address_form.fields['country_area'], 'choices'):\n+ choices = address_form.fields['country_area'].choices\n+ choices = [(choice[1], choice[1]) for choice in choices]\n+ address_form.fields['country_area'].choices = choices\n return address_form, preview\n", "issue": "Duplicate choices in shipping address\n### What I'm trying to achieve\r\nI'm trying to set shipping user for Russian user and there are duplicate values in \"Oblast\" selector.\r\n\r\n### Steps to reproduce the problem\r\n1. Create new shipping address\r\n2. Country --> Russia\r\n3. There are duplicated values in \"Oblast\" selector\r\n\r\n### What I expected to happen\r\nThere are no duplicated values in \"Oblast\" selector\r\n\r\n### Screenshots\r\nWhat happens now\r\n<img src=\"https://user-images.githubusercontent.com/13136992/53255369-8a239600-36d6-11e9-84a6-24a10b96a321.png\" width=\"300\">\r\n\r\n\r\nWhat I expect to see\r\n<img src=\"https://user-images.githubusercontent.com/13136992/53255400-99a2df00-36d6-11e9-8913-ecaec174487a.png\" width=\"300\">\r\n\r\n\r\n**System information**\r\nOperating system: Manjaro Linux\r\nBrowser: Google Chrome 72.0.3626.81\r\n\n", "before_files": [{"content": "from captcha.fields import ReCaptchaField\nfrom django import forms\nfrom django.conf import settings\nfrom django.contrib.auth import forms as django_forms, update_session_auth_hash\nfrom django.utils.translation import pgettext, pgettext_lazy\nfrom phonenumbers.phonenumberutil import country_code_for_region\n\nfrom ..account.models import User\nfrom . import emails\nfrom .i18n import AddressMetaForm, get_address_form_class\n\n\nclass FormWithReCaptcha(forms.BaseForm):\n def __new__(cls, *args, **kwargs):\n if settings.RECAPTCHA_PUBLIC_KEY and settings.RECAPTCHA_PRIVATE_KEY:\n # insert a Google reCaptcha field inside the form\n # note: label is empty, the reCaptcha is self-explanatory making\n # the form simpler for the user.\n cls.base_fields['_captcha'] = ReCaptchaField(label='')\n return super(FormWithReCaptcha, cls).__new__(cls)\n\n\ndef get_address_form(\n data, country_code, initial=None, instance=None, **kwargs):\n country_form = AddressMetaForm(data, initial=initial)\n preview = False\n if country_form.is_valid():\n country_code = country_form.cleaned_data['country']\n preview = country_form.cleaned_data['preview']\n\n if initial is None and country_code:\n initial = {}\n if country_code:\n initial['phone'] = '+{}'.format(country_code_for_region(country_code))\n\n address_form_class = get_address_form_class(country_code)\n\n if not preview and instance is not None:\n address_form_class = get_address_form_class(instance.country.code)\n address_form = address_form_class(data, instance=instance, **kwargs)\n else:\n initial_address = (\n initial if not preview\n else data.dict() if data is not None else data)\n address_form = address_form_class(\n not preview and data or None,\n initial=initial_address,\n **kwargs)\n return address_form, preview\n\n\nclass ChangePasswordForm(django_forms.PasswordChangeForm):\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n self.fields['new_password1'].user = self.user\n self.fields['old_password'].widget.attrs['placeholder'] = ''\n self.fields['new_password1'].widget.attrs['placeholder'] = ''\n del self.fields['new_password2']\n\n\ndef logout_on_password_change(request, user):\n if (update_session_auth_hash is not None and\n not settings.LOGOUT_ON_PASSWORD_CHANGE):\n update_session_auth_hash(request, user)\n\n\nclass LoginForm(django_forms.AuthenticationForm, FormWithReCaptcha):\n username = forms.EmailField(\n label=pgettext('Form field', 'Email'), max_length=75)\n\n def __init__(self, request=None, *args, **kwargs):\n super().__init__(request=request, *args, **kwargs)\n if request:\n email = request.GET.get('email')\n if email:\n self.fields['username'].initial = email\n\n\nclass SignupForm(forms.ModelForm, FormWithReCaptcha):\n password = forms.CharField(\n widget=forms.PasswordInput,\n label=pgettext('Password', 'Password'))\n email = forms.EmailField(\n label=pgettext('Email', 'Email'),\n error_messages={\n 'unique': pgettext_lazy(\n 'Registration error',\n 'This email has already been registered.')})\n\n class Meta:\n model = User\n fields = ('email',)\n\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n if self._meta.model.USERNAME_FIELD in self.fields:\n self.fields[self._meta.model.USERNAME_FIELD].widget.attrs.update(\n {'autofocus': ''})\n\n def save(self, request=None, commit=True):\n user = super().save(commit=False)\n password = self.cleaned_data['password']\n user.set_password(password)\n if commit:\n user.save()\n return user\n\n\nclass PasswordResetForm(django_forms.PasswordResetForm, FormWithReCaptcha):\n \"\"\"Allow resetting passwords.\n\n This subclass overrides sending emails to use templated email.\n \"\"\"\n\n def get_users(self, email):\n active_users = User.objects.filter(email__iexact=email, is_active=True)\n return active_users\n\n def send_mail(\n self, subject_template_name, email_template_name, context,\n from_email, to_email, html_email_template_name=None):\n # Passing the user object to the Celery task throws an\n # error \"'User' is not JSON serializable\". Since it's not used in our\n # template, we remove it from the context.\n del context['user']\n emails.send_password_reset_email.delay(context, to_email)\n\n\nclass NameForm(forms.ModelForm):\n class Meta:\n model = User\n fields = ['first_name', 'last_name']\n labels = {\n 'first_name': pgettext_lazy(\n 'Customer form: Given name field', 'Given name'),\n 'last_name': pgettext_lazy(\n 'Customer form: Family name field', 'Family name')}\n", "path": "saleor/account/forms.py"}], "after_files": [{"content": "from captcha.fields import ReCaptchaField\nfrom django import forms\nfrom django.conf import settings\nfrom django.contrib.auth import forms as django_forms, update_session_auth_hash\nfrom django.utils.translation import pgettext, pgettext_lazy\nfrom phonenumbers.phonenumberutil import country_code_for_region\n\nfrom ..account.models import User\nfrom . import emails\nfrom .i18n import AddressMetaForm, get_address_form_class\n\n\nclass FormWithReCaptcha(forms.BaseForm):\n def __new__(cls, *args, **kwargs):\n if settings.RECAPTCHA_PUBLIC_KEY and settings.RECAPTCHA_PRIVATE_KEY:\n # insert a Google reCaptcha field inside the form\n # note: label is empty, the reCaptcha is self-explanatory making\n # the form simpler for the user.\n cls.base_fields['_captcha'] = ReCaptchaField(label='')\n return super(FormWithReCaptcha, cls).__new__(cls)\n\n\ndef get_address_form(\n data, country_code, initial=None, instance=None, **kwargs):\n country_form = AddressMetaForm(data, initial=initial)\n preview = False\n if country_form.is_valid():\n country_code = country_form.cleaned_data['country']\n preview = country_form.cleaned_data['preview']\n\n if initial is None and country_code:\n initial = {}\n if country_code:\n initial['phone'] = '+{}'.format(country_code_for_region(country_code))\n\n address_form_class = get_address_form_class(country_code)\n\n if not preview and instance is not None:\n address_form_class = get_address_form_class(instance.country.code)\n address_form = address_form_class(data, instance=instance, **kwargs)\n else:\n initial_address = (\n initial if not preview\n else data.dict() if data is not None else data)\n address_form = address_form_class(\n not preview and data or None,\n initial=initial_address,\n **kwargs)\n\n if hasattr(address_form.fields['country_area'], 'choices'):\n choices = address_form.fields['country_area'].choices\n choices = [(choice[1], choice[1]) for choice in choices]\n address_form.fields['country_area'].choices = choices\n return address_form, preview\n\n\nclass ChangePasswordForm(django_forms.PasswordChangeForm):\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n self.fields['new_password1'].user = self.user\n self.fields['old_password'].widget.attrs['placeholder'] = ''\n self.fields['new_password1'].widget.attrs['placeholder'] = ''\n del self.fields['new_password2']\n\n\ndef logout_on_password_change(request, user):\n if (update_session_auth_hash is not None and\n not settings.LOGOUT_ON_PASSWORD_CHANGE):\n update_session_auth_hash(request, user)\n\n\nclass LoginForm(django_forms.AuthenticationForm, FormWithReCaptcha):\n username = forms.EmailField(\n label=pgettext('Form field', 'Email'), max_length=75)\n\n def __init__(self, request=None, *args, **kwargs):\n super().__init__(request=request, *args, **kwargs)\n if request:\n email = request.GET.get('email')\n if email:\n self.fields['username'].initial = email\n\n\nclass SignupForm(forms.ModelForm, FormWithReCaptcha):\n password = forms.CharField(\n widget=forms.PasswordInput,\n label=pgettext('Password', 'Password'))\n email = forms.EmailField(\n label=pgettext('Email', 'Email'),\n error_messages={\n 'unique': pgettext_lazy(\n 'Registration error',\n 'This email has already been registered.')})\n\n class Meta:\n model = User\n fields = ('email',)\n\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n if self._meta.model.USERNAME_FIELD in self.fields:\n self.fields[self._meta.model.USERNAME_FIELD].widget.attrs.update(\n {'autofocus': ''})\n\n def save(self, request=None, commit=True):\n user = super().save(commit=False)\n password = self.cleaned_data['password']\n user.set_password(password)\n if commit:\n user.save()\n return user\n\n\nclass PasswordResetForm(django_forms.PasswordResetForm, FormWithReCaptcha):\n \"\"\"Allow resetting passwords.\n\n This subclass overrides sending emails to use templated email.\n \"\"\"\n\n def get_users(self, email):\n active_users = User.objects.filter(email__iexact=email, is_active=True)\n return active_users\n\n def send_mail(\n self, subject_template_name, email_template_name, context,\n from_email, to_email, html_email_template_name=None):\n # Passing the user object to the Celery task throws an\n # error \"'User' is not JSON serializable\". Since it's not used in our\n # template, we remove it from the context.\n del context['user']\n emails.send_password_reset_email.delay(context, to_email)\n\n\nclass NameForm(forms.ModelForm):\n class Meta:\n model = User\n fields = ['first_name', 'last_name']\n labels = {\n 'first_name': pgettext_lazy(\n 'Customer form: Given name field', 'Given name'),\n 'last_name': pgettext_lazy(\n 'Customer form: Family name field', 'Family name')}\n", "path": "saleor/account/forms.py"}]}
| 1,929 | 133 |
gh_patches_debug_25512
|
rasdani/github-patches
|
git_diff
|
openstates__openstates-scrapers-2059
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
RI failing since at least 2018-01-02
RI has been failing since 2018-01-02
Based on automated runs it appears that RI has not run successfully in 2 days (2018-01-02).
```
no pupa_settings on path, using defaults
ri (scrape, import)
bills: {}
people: {}
committees: {}
23:00:36 CRITICAL pupa: Session(s) 2018 were reported by RhodeIsland.get_session_list() but were not found in RhodeIsland.legislative_sessions or RhodeIsland.ignored_scraped_sessions.
```
Visit http://bobsled.openstates.org for more info.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `billy_metadata/ri.py`
Content:
```
1 import datetime
2
3 metadata = {
4 'name': 'Rhode Island',
5 'abbreviation': 'ri',
6 'legislature_name': 'Rhode Island General Assembly',
7 'legislature_url': 'http://www.rilin.state.ri.us/',
8 'capitol_timezone': 'America/New_York',
9 'chambers': {
10 'upper': {'name': 'Senate', 'title': 'Senator'},
11 'lower': {'name': 'House', 'title': 'Representative'},
12 },
13 'terms': [
14 {
15 'name': '2012',
16 'start_year': 2012,
17 'end_year': 2012,
18 'sessions': ['2012'],
19 },
20 {
21 'name': '2013',
22 'start_year': 2013,
23 'end_year': 2013,
24 'sessions': ['2013'],
25 },
26
27 {
28 'name': '2014',
29 'start_year': 2014,
30 'end_year': 2014,
31 'sessions': ['2014'],
32 },
33 {
34 'name': '2015',
35 'start_year': 2015,
36 'end_year': 2015,
37 'sessions': ['2015'],
38 },
39 {
40 'name': '2016',
41 'start_year': 2016,
42 'end_year': 2017,
43 'sessions': ['2016'],
44 },
45 {
46 'name': '2017',
47 'start_year': 2017,
48 'end_year': 2018,
49 'sessions': ['2017'],
50 },
51 ],
52 'session_details': {
53 '2012': {
54 'type': 'primary',
55 'start_date': datetime.date(2012, 1, 3),
56 'end_date': datetime.date(2012, 6, 13),
57 'display_name': '2012 Regular Session',
58 '_scraped_name': '2012',
59 },
60 '2013': {
61 'type': 'primary',
62 'start_date': datetime.date(2013, 1, 1),
63 'end_date': datetime.date(2013, 7, 3),
64 'display_name': '2013 Regular Session',
65 '_scraped_name': '2013',
66 },
67 '2014': {
68 'type': 'primary',
69 'start_date': datetime.date(2014, 1, 7),
70 'end_date': datetime.date(2014, 6, 21),
71 'display_name': '2014 Regular Session',
72 '_scraped_name': '2014',
73 },
74 '2015': {
75 'type': 'primary',
76 'start_date': datetime.date(2015, 1, 6),
77 'end_date': datetime.date(2015, 6, 25),
78 'display_name': '2015 Regular Session',
79 '_scraped_name': '2015',
80 },
81 '2016': {
82 'type': 'primary',
83 'start_date': datetime.date(2016, 1, 5),
84 'display_name': '2016 Regular Session',
85 '_scraped_name': '2016',
86 },
87 '2017': {
88 'type': 'primary',
89 'display_name': '2017 Regular Session',
90 '_scraped_name': '2017',
91 },
92 },
93 'feature_flags': ['subjects', 'events', 'influenceexplorer'],
94 '_ignored_scraped_sessions': [
95 '2015',
96 '2014',
97 '2013',
98 '2012',
99 '2011',
100 '2010',
101 '2009',
102 '2008',
103 '2007'
104 ],
105 }
106
```
Path: `openstates/ri/__init__.py`
Content:
```
1 from pupa.scrape import Jurisdiction, Organization
2
3 from openstates.utils import url_xpath
4
5 from .bills import RIBillScraper
6 from .events import RIEventScraper
7 from .people import RIPersonScraper
8 from .committees import RICommitteeScraper
9
10
11 class RhodeIsland(Jurisdiction):
12 division_id = "ocd-division/country:us/state:ri"
13 classification = "government"
14 name = "Rhode Island"
15 url = "http://www.ri.gov/"
16 scrapers = {
17 'bills': RIBillScraper,
18 'events': RIEventScraper,
19 'people': RIPersonScraper,
20 'committees': RICommitteeScraper,
21 }
22 parties = [
23 {'name': 'Republican'},
24 {'name': 'Democratic'}
25 ]
26 legislative_sessions = [
27 {
28 "_scraped_name": "2012",
29 "classification": "primary",
30 "end_date": "2012-06-13",
31 "identifier": "2012",
32 "name": "2012 Regular Session",
33 "start_date": "2012-01-03"
34 },
35 {
36 "_scraped_name": "2013",
37 "classification": "primary",
38 "end_date": "2013-07-03",
39 "identifier": "2013",
40 "name": "2013 Regular Session",
41 "start_date": "2013-01-01"
42 },
43 {
44 "_scraped_name": "2014",
45 "classification": "primary",
46 "end_date": "2014-06-21",
47 "identifier": "2014",
48 "name": "2014 Regular Session",
49 "start_date": "2014-01-07"
50 },
51 {
52 "_scraped_name": "2015",
53 "classification": "primary",
54 "end_date": "2015-06-25",
55 "identifier": "2015",
56 "name": "2015 Regular Session",
57 "start_date": "2015-01-06"
58 },
59 {
60 "_scraped_name": "2016",
61 "classification": "primary",
62 "identifier": "2016",
63 "name": "2016 Regular Session",
64 "start_date": "2016-01-05"
65 },
66 {
67 "_scraped_name": "2017",
68 "classification": "primary",
69 "identifier": "2017",
70 "name": "2017 Regular Session",
71 "start_date": "2017-01-03",
72 "end_date": "2017-06-30",
73 }
74 ]
75 ignored_scraped_sessions = [
76 "2015",
77 "2014",
78 "2013",
79 "2012",
80 "2011",
81 "2010",
82 "2009",
83 "2008",
84 "2007"
85 ]
86
87 def get_organizations(self):
88 legislature_name = "Rhode Island General Assembly"
89 lower_chamber_name = "House of Representatives"
90 lower_seats = 75
91 lower_title = "Representative"
92 upper_chamber_name = "Senate"
93 upper_seats = 38
94 upper_title = "Senator"
95
96 legislature = Organization(name=legislature_name,
97 classification="legislature")
98 executive = Organization(name='Office of the Governor',
99 classification="executive")
100 upper = Organization(upper_chamber_name, classification='upper',
101 parent_id=legislature._id)
102 lower = Organization(lower_chamber_name, classification='lower',
103 parent_id=legislature._id)
104
105 for n in range(1, upper_seats + 1):
106 upper.add_post(
107 label=str(n), role=upper_title,
108 division_id='{}/sldu:{}'.format(self.division_id, n))
109 for n in range(1, lower_seats + 1):
110 lower.add_post(
111 label=str(n), role=lower_title,
112 division_id='{}/sldl:{}'.format(self.division_id, n))
113
114 yield legislature
115 yield executive
116 yield upper
117 yield lower
118
119 def get_session_list(self):
120 return url_xpath(
121 'http://status.rilin.state.ri.us/bill_history.aspx?mode=previous',
122 '//select[@name="ctl00$rilinContent$cbYear"]/option/text()')
123
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/billy_metadata/ri.py b/billy_metadata/ri.py
--- a/billy_metadata/ri.py
+++ b/billy_metadata/ri.py
@@ -46,7 +46,7 @@
'name': '2017',
'start_year': 2017,
'end_year': 2018,
- 'sessions': ['2017'],
+ 'sessions': ['2017', '2018'],
},
],
'session_details': {
@@ -89,6 +89,11 @@
'display_name': '2017 Regular Session',
'_scraped_name': '2017',
},
+ '2018': {
+ 'type': 'primary',
+ 'display_name': '2018 Regular Session',
+ '_scraped_name': '2018',
+ },
},
'feature_flags': ['subjects', 'events', 'influenceexplorer'],
'_ignored_scraped_sessions': [
diff --git a/openstates/ri/__init__.py b/openstates/ri/__init__.py
--- a/openstates/ri/__init__.py
+++ b/openstates/ri/__init__.py
@@ -70,7 +70,14 @@
"name": "2017 Regular Session",
"start_date": "2017-01-03",
"end_date": "2017-06-30",
- }
+ },
+ {
+ "_scraped_name": "2018",
+ "classification": "primary",
+ "identifier": "2018",
+ "name": "2018 Regular Session",
+ "start_date": "2018-01-02",
+ },
]
ignored_scraped_sessions = [
"2015",
|
{"golden_diff": "diff --git a/billy_metadata/ri.py b/billy_metadata/ri.py\n--- a/billy_metadata/ri.py\n+++ b/billy_metadata/ri.py\n@@ -46,7 +46,7 @@\n 'name': '2017',\n 'start_year': 2017,\n 'end_year': 2018,\n- 'sessions': ['2017'],\n+ 'sessions': ['2017', '2018'],\n },\n ],\n 'session_details': {\n@@ -89,6 +89,11 @@\n 'display_name': '2017 Regular Session',\n '_scraped_name': '2017',\n },\n+ '2018': {\n+ 'type': 'primary',\n+ 'display_name': '2018 Regular Session',\n+ '_scraped_name': '2018',\n+ },\n },\n 'feature_flags': ['subjects', 'events', 'influenceexplorer'],\n '_ignored_scraped_sessions': [\ndiff --git a/openstates/ri/__init__.py b/openstates/ri/__init__.py\n--- a/openstates/ri/__init__.py\n+++ b/openstates/ri/__init__.py\n@@ -70,7 +70,14 @@\n \"name\": \"2017 Regular Session\",\n \"start_date\": \"2017-01-03\",\n \"end_date\": \"2017-06-30\",\n- }\n+ },\n+ {\n+ \"_scraped_name\": \"2018\",\n+ \"classification\": \"primary\",\n+ \"identifier\": \"2018\",\n+ \"name\": \"2018 Regular Session\",\n+ \"start_date\": \"2018-01-02\",\n+ },\n ]\n ignored_scraped_sessions = [\n \"2015\",\n", "issue": "RI failing since at least 2018-01-02\nRI has been failing since 2018-01-02\n\nBased on automated runs it appears that RI has not run successfully in 2 days (2018-01-02).\n\n\n```\n no pupa_settings on path, using defaults\nri (scrape, import)\n bills: {}\n people: {}\n committees: {}\n23:00:36 CRITICAL pupa: Session(s) 2018 were reported by RhodeIsland.get_session_list() but were not found in RhodeIsland.legislative_sessions or RhodeIsland.ignored_scraped_sessions.\n```\n\nVisit http://bobsled.openstates.org for more info.\n\n", "before_files": [{"content": "import datetime\n\nmetadata = {\n 'name': 'Rhode Island',\n 'abbreviation': 'ri',\n 'legislature_name': 'Rhode Island General Assembly',\n 'legislature_url': 'http://www.rilin.state.ri.us/',\n 'capitol_timezone': 'America/New_York',\n 'chambers': {\n 'upper': {'name': 'Senate', 'title': 'Senator'},\n 'lower': {'name': 'House', 'title': 'Representative'},\n },\n 'terms': [\n {\n 'name': '2012',\n 'start_year': 2012,\n 'end_year': 2012,\n 'sessions': ['2012'],\n },\n {\n 'name': '2013',\n 'start_year': 2013,\n 'end_year': 2013,\n 'sessions': ['2013'],\n },\n\n {\n 'name': '2014',\n 'start_year': 2014,\n 'end_year': 2014,\n 'sessions': ['2014'],\n },\n {\n 'name': '2015',\n 'start_year': 2015,\n 'end_year': 2015,\n 'sessions': ['2015'],\n },\n {\n 'name': '2016',\n 'start_year': 2016,\n 'end_year': 2017,\n 'sessions': ['2016'],\n },\n {\n 'name': '2017',\n 'start_year': 2017,\n 'end_year': 2018,\n 'sessions': ['2017'],\n },\n ],\n 'session_details': {\n '2012': {\n 'type': 'primary',\n 'start_date': datetime.date(2012, 1, 3),\n 'end_date': datetime.date(2012, 6, 13),\n 'display_name': '2012 Regular Session',\n '_scraped_name': '2012',\n },\n '2013': {\n 'type': 'primary',\n 'start_date': datetime.date(2013, 1, 1),\n 'end_date': datetime.date(2013, 7, 3),\n 'display_name': '2013 Regular Session',\n '_scraped_name': '2013',\n },\n '2014': {\n 'type': 'primary',\n 'start_date': datetime.date(2014, 1, 7),\n 'end_date': datetime.date(2014, 6, 21),\n 'display_name': '2014 Regular Session',\n '_scraped_name': '2014',\n },\n '2015': {\n 'type': 'primary',\n 'start_date': datetime.date(2015, 1, 6),\n 'end_date': datetime.date(2015, 6, 25),\n 'display_name': '2015 Regular Session',\n '_scraped_name': '2015',\n },\n '2016': {\n 'type': 'primary',\n 'start_date': datetime.date(2016, 1, 5),\n 'display_name': '2016 Regular Session',\n '_scraped_name': '2016',\n },\n '2017': {\n 'type': 'primary',\n 'display_name': '2017 Regular Session',\n '_scraped_name': '2017',\n },\n },\n 'feature_flags': ['subjects', 'events', 'influenceexplorer'],\n '_ignored_scraped_sessions': [\n '2015',\n '2014',\n '2013',\n '2012',\n '2011',\n '2010',\n '2009',\n '2008',\n '2007'\n ],\n}\n", "path": "billy_metadata/ri.py"}, {"content": "from pupa.scrape import Jurisdiction, Organization\n\nfrom openstates.utils import url_xpath\n\nfrom .bills import RIBillScraper\nfrom .events import RIEventScraper\nfrom .people import RIPersonScraper\nfrom .committees import RICommitteeScraper\n\n\nclass RhodeIsland(Jurisdiction):\n division_id = \"ocd-division/country:us/state:ri\"\n classification = \"government\"\n name = \"Rhode Island\"\n url = \"http://www.ri.gov/\"\n scrapers = {\n 'bills': RIBillScraper,\n 'events': RIEventScraper,\n 'people': RIPersonScraper,\n 'committees': RICommitteeScraper,\n }\n parties = [\n {'name': 'Republican'},\n {'name': 'Democratic'}\n ]\n legislative_sessions = [\n {\n \"_scraped_name\": \"2012\",\n \"classification\": \"primary\",\n \"end_date\": \"2012-06-13\",\n \"identifier\": \"2012\",\n \"name\": \"2012 Regular Session\",\n \"start_date\": \"2012-01-03\"\n },\n {\n \"_scraped_name\": \"2013\",\n \"classification\": \"primary\",\n \"end_date\": \"2013-07-03\",\n \"identifier\": \"2013\",\n \"name\": \"2013 Regular Session\",\n \"start_date\": \"2013-01-01\"\n },\n {\n \"_scraped_name\": \"2014\",\n \"classification\": \"primary\",\n \"end_date\": \"2014-06-21\",\n \"identifier\": \"2014\",\n \"name\": \"2014 Regular Session\",\n \"start_date\": \"2014-01-07\"\n },\n {\n \"_scraped_name\": \"2015\",\n \"classification\": \"primary\",\n \"end_date\": \"2015-06-25\",\n \"identifier\": \"2015\",\n \"name\": \"2015 Regular Session\",\n \"start_date\": \"2015-01-06\"\n },\n {\n \"_scraped_name\": \"2016\",\n \"classification\": \"primary\",\n \"identifier\": \"2016\",\n \"name\": \"2016 Regular Session\",\n \"start_date\": \"2016-01-05\"\n },\n {\n \"_scraped_name\": \"2017\",\n \"classification\": \"primary\",\n \"identifier\": \"2017\",\n \"name\": \"2017 Regular Session\",\n \"start_date\": \"2017-01-03\",\n \"end_date\": \"2017-06-30\",\n }\n ]\n ignored_scraped_sessions = [\n \"2015\",\n \"2014\",\n \"2013\",\n \"2012\",\n \"2011\",\n \"2010\",\n \"2009\",\n \"2008\",\n \"2007\"\n ]\n\n def get_organizations(self):\n legislature_name = \"Rhode Island General Assembly\"\n lower_chamber_name = \"House of Representatives\"\n lower_seats = 75\n lower_title = \"Representative\"\n upper_chamber_name = \"Senate\"\n upper_seats = 38\n upper_title = \"Senator\"\n\n legislature = Organization(name=legislature_name,\n classification=\"legislature\")\n executive = Organization(name='Office of the Governor',\n classification=\"executive\")\n upper = Organization(upper_chamber_name, classification='upper',\n parent_id=legislature._id)\n lower = Organization(lower_chamber_name, classification='lower',\n parent_id=legislature._id)\n\n for n in range(1, upper_seats + 1):\n upper.add_post(\n label=str(n), role=upper_title,\n division_id='{}/sldu:{}'.format(self.division_id, n))\n for n in range(1, lower_seats + 1):\n lower.add_post(\n label=str(n), role=lower_title,\n division_id='{}/sldl:{}'.format(self.division_id, n))\n\n yield legislature\n yield executive\n yield upper\n yield lower\n\n def get_session_list(self):\n return url_xpath(\n 'http://status.rilin.state.ri.us/bill_history.aspx?mode=previous',\n '//select[@name=\"ctl00$rilinContent$cbYear\"]/option/text()')\n", "path": "openstates/ri/__init__.py"}], "after_files": [{"content": "import datetime\n\nmetadata = {\n 'name': 'Rhode Island',\n 'abbreviation': 'ri',\n 'legislature_name': 'Rhode Island General Assembly',\n 'legislature_url': 'http://www.rilin.state.ri.us/',\n 'capitol_timezone': 'America/New_York',\n 'chambers': {\n 'upper': {'name': 'Senate', 'title': 'Senator'},\n 'lower': {'name': 'House', 'title': 'Representative'},\n },\n 'terms': [\n {\n 'name': '2012',\n 'start_year': 2012,\n 'end_year': 2012,\n 'sessions': ['2012'],\n },\n {\n 'name': '2013',\n 'start_year': 2013,\n 'end_year': 2013,\n 'sessions': ['2013'],\n },\n\n {\n 'name': '2014',\n 'start_year': 2014,\n 'end_year': 2014,\n 'sessions': ['2014'],\n },\n {\n 'name': '2015',\n 'start_year': 2015,\n 'end_year': 2015,\n 'sessions': ['2015'],\n },\n {\n 'name': '2016',\n 'start_year': 2016,\n 'end_year': 2017,\n 'sessions': ['2016'],\n },\n {\n 'name': '2017',\n 'start_year': 2017,\n 'end_year': 2018,\n 'sessions': ['2017', '2018'],\n },\n ],\n 'session_details': {\n '2012': {\n 'type': 'primary',\n 'start_date': datetime.date(2012, 1, 3),\n 'end_date': datetime.date(2012, 6, 13),\n 'display_name': '2012 Regular Session',\n '_scraped_name': '2012',\n },\n '2013': {\n 'type': 'primary',\n 'start_date': datetime.date(2013, 1, 1),\n 'end_date': datetime.date(2013, 7, 3),\n 'display_name': '2013 Regular Session',\n '_scraped_name': '2013',\n },\n '2014': {\n 'type': 'primary',\n 'start_date': datetime.date(2014, 1, 7),\n 'end_date': datetime.date(2014, 6, 21),\n 'display_name': '2014 Regular Session',\n '_scraped_name': '2014',\n },\n '2015': {\n 'type': 'primary',\n 'start_date': datetime.date(2015, 1, 6),\n 'end_date': datetime.date(2015, 6, 25),\n 'display_name': '2015 Regular Session',\n '_scraped_name': '2015',\n },\n '2016': {\n 'type': 'primary',\n 'start_date': datetime.date(2016, 1, 5),\n 'display_name': '2016 Regular Session',\n '_scraped_name': '2016',\n },\n '2017': {\n 'type': 'primary',\n 'display_name': '2017 Regular Session',\n '_scraped_name': '2017',\n },\n '2018': {\n 'type': 'primary',\n 'display_name': '2018 Regular Session',\n '_scraped_name': '2018',\n },\n },\n 'feature_flags': ['subjects', 'events', 'influenceexplorer'],\n '_ignored_scraped_sessions': [\n '2015',\n '2014',\n '2013',\n '2012',\n '2011',\n '2010',\n '2009',\n '2008',\n '2007'\n ],\n}\n", "path": "billy_metadata/ri.py"}, {"content": "from pupa.scrape import Jurisdiction, Organization\n\nfrom openstates.utils import url_xpath\n\nfrom .bills import RIBillScraper\nfrom .events import RIEventScraper\nfrom .people import RIPersonScraper\nfrom .committees import RICommitteeScraper\n\n\nclass RhodeIsland(Jurisdiction):\n division_id = \"ocd-division/country:us/state:ri\"\n classification = \"government\"\n name = \"Rhode Island\"\n url = \"http://www.ri.gov/\"\n scrapers = {\n 'bills': RIBillScraper,\n 'events': RIEventScraper,\n 'people': RIPersonScraper,\n 'committees': RICommitteeScraper,\n }\n parties = [\n {'name': 'Republican'},\n {'name': 'Democratic'}\n ]\n legislative_sessions = [\n {\n \"_scraped_name\": \"2012\",\n \"classification\": \"primary\",\n \"end_date\": \"2012-06-13\",\n \"identifier\": \"2012\",\n \"name\": \"2012 Regular Session\",\n \"start_date\": \"2012-01-03\"\n },\n {\n \"_scraped_name\": \"2013\",\n \"classification\": \"primary\",\n \"end_date\": \"2013-07-03\",\n \"identifier\": \"2013\",\n \"name\": \"2013 Regular Session\",\n \"start_date\": \"2013-01-01\"\n },\n {\n \"_scraped_name\": \"2014\",\n \"classification\": \"primary\",\n \"end_date\": \"2014-06-21\",\n \"identifier\": \"2014\",\n \"name\": \"2014 Regular Session\",\n \"start_date\": \"2014-01-07\"\n },\n {\n \"_scraped_name\": \"2015\",\n \"classification\": \"primary\",\n \"end_date\": \"2015-06-25\",\n \"identifier\": \"2015\",\n \"name\": \"2015 Regular Session\",\n \"start_date\": \"2015-01-06\"\n },\n {\n \"_scraped_name\": \"2016\",\n \"classification\": \"primary\",\n \"identifier\": \"2016\",\n \"name\": \"2016 Regular Session\",\n \"start_date\": \"2016-01-05\"\n },\n {\n \"_scraped_name\": \"2017\",\n \"classification\": \"primary\",\n \"identifier\": \"2017\",\n \"name\": \"2017 Regular Session\",\n \"start_date\": \"2017-01-03\",\n \"end_date\": \"2017-06-30\",\n },\n {\n \"_scraped_name\": \"2018\",\n \"classification\": \"primary\",\n \"identifier\": \"2018\",\n \"name\": \"2018 Regular Session\",\n \"start_date\": \"2018-01-02\",\n },\n ]\n ignored_scraped_sessions = [\n \"2015\",\n \"2014\",\n \"2013\",\n \"2012\",\n \"2011\",\n \"2010\",\n \"2009\",\n \"2008\",\n \"2007\"\n ]\n\n def get_organizations(self):\n legislature_name = \"Rhode Island General Assembly\"\n lower_chamber_name = \"House of Representatives\"\n lower_seats = 75\n lower_title = \"Representative\"\n upper_chamber_name = \"Senate\"\n upper_seats = 38\n upper_title = \"Senator\"\n\n legislature = Organization(name=legislature_name,\n classification=\"legislature\")\n executive = Organization(name='Office of the Governor',\n classification=\"executive\")\n upper = Organization(upper_chamber_name, classification='upper',\n parent_id=legislature._id)\n lower = Organization(lower_chamber_name, classification='lower',\n parent_id=legislature._id)\n\n for n in range(1, upper_seats + 1):\n upper.add_post(\n label=str(n), role=upper_title,\n division_id='{}/sldu:{}'.format(self.division_id, n))\n for n in range(1, lower_seats + 1):\n lower.add_post(\n label=str(n), role=lower_title,\n division_id='{}/sldl:{}'.format(self.division_id, n))\n\n yield legislature\n yield executive\n yield upper\n yield lower\n\n def get_session_list(self):\n return url_xpath(\n 'http://status.rilin.state.ri.us/bill_history.aspx?mode=previous',\n '//select[@name=\"ctl00$rilinContent$cbYear\"]/option/text()')\n", "path": "openstates/ri/__init__.py"}]}
| 2,887 | 431 |
gh_patches_debug_15196
|
rasdani/github-patches
|
git_diff
|
RedHatInsights__insights-core-3344
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Pinned jinja2 version is no longer supported and conflicts with the latest MarkupSafe
**Current behavior**
insights-core has pinned the jinja2 version to <=2.11.3 in #3057. This version is [no longer supported](https://github.com/pallets/jinja/issues/1585#issuecomment-1043892628).
**Expected behavior**
insights-core can be used with a maintained jinja2 version in applications that depend both on insights-core and jinja2.
**Impact**
jinja2-2.11.3 fails to import with the latest version of MarkupSafe, 2.1.0:
```
...
.tox/unit-py38/lib/python3.8/site-packages/jinja2/filters.py:13: in <module>
from markupsafe import soft_unicode
E ImportError: cannot import name 'soft_unicode' from 'markupsafe' (/builds/ccx/ccx-rules-ocp/.tox/unit-py38/lib64/python3.8/site-packages/markupsafe/__init__.py
```
All projects that depend on insights-core have to pin unsupported versions of MarkupSafe now. I would argue that it is important to keep up-to-date for a package that is used for secure handling of user input.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 import os
2 from setuptools import setup, find_packages
3
4 __here__ = os.path.dirname(os.path.abspath(__file__))
5
6 package_info = dict.fromkeys(["RELEASE", "COMMIT", "VERSION", "NAME"])
7
8 for name in package_info:
9 with open(os.path.join(__here__, "insights", name)) as f:
10 package_info[name] = f.read().strip()
11
12 entry_points = {
13 'console_scripts': [
14 'insights-collect = insights.collect:main',
15 'insights-run = insights:main',
16 'insights = insights.command_parser:main',
17 'insights-cat = insights.tools.cat:main',
18 'insights-dupkeycheck = insights.tools.dupkeycheck:main',
19 'insights-inspect = insights.tools.insights_inspect:main',
20 'insights-info = insights.tools.query:main',
21 'insights-ocpshell= insights.ocpshell:main',
22 'mangle = insights.util.mangle:main'
23 ]
24 }
25
26 runtime = set([
27 'six',
28 'requests',
29 'redis',
30 'cachecontrol',
31 'cachecontrol[redis]',
32 'cachecontrol[filecache]',
33 'defusedxml',
34 'lockfile',
35 'jinja2<=2.11.3',
36 'pyyaml>=3.10,<=3.13; python_version < "2.7"',
37 'pyyaml; python_version >= "2.7"',
38 ])
39
40
41 def maybe_require(pkg):
42 try:
43 __import__(pkg)
44 except ImportError:
45 runtime.add(pkg)
46
47
48 maybe_require("importlib")
49 maybe_require("argparse")
50
51
52 client = set([
53 'requests',
54 'python-gnupg==0.4.6',
55 'oyaml'
56 ])
57
58 develop = set([
59 'wheel',
60 ])
61
62 docs = set([
63 'docutils',
64 'Sphinx',
65 'nbsphinx',
66 'sphinx_rtd_theme',
67 'ipython',
68 'colorama',
69 'jinja2<=2.11.3',
70 'Pygments',
71 'jedi<0.18.0', # Open issue with jedi 0.18.0 and iPython <= 7.19
72 # https://github.com/davidhalter/jedi/issues/1714
73 ])
74
75 # python 2.6 requires setuptools~=36.8.0 to support this syntax
76 testing = set([
77 'coverage==4.3.4; python_version < "2.7"',
78 'coverage; python_version >= "2.7"',
79 'pytest==3.0.6; python_version < "2.7"',
80 'pytest~=4.6.0; python_version == "2.7"',
81 'pytest; python_version >= "3"',
82 'pytest-cov==2.4.0; python_version < "2.7"',
83 'pytest-cov; python_version >= "2.7"',
84 'mock==2.0.0',
85 ])
86
87 cluster = set([
88 'ansible',
89 'pandas',
90 'colorama',
91 ])
92
93 openshift = set([
94 'openshift'
95 ])
96
97 linting = set([
98 'flake8==2.6.2; python_version < "2.7"',
99 'flake8; python_version >= "2.7"'
100 ])
101
102 optional = set([
103 'python-cjson',
104 'python-logstash',
105 'python-statsd',
106 'watchdog',
107 ])
108
109 if __name__ == "__main__":
110 # allows for runtime modification of rpm name
111 name = os.environ.get("INSIGHTS_CORE_NAME", package_info["NAME"])
112
113 setup(
114 name=name,
115 version=package_info["VERSION"],
116 description="Insights Core is a data collection and analysis framework",
117 long_description=open("README.rst").read(),
118 url="https://github.com/redhatinsights/insights-core",
119 author="Red Hat, Inc.",
120 author_email="[email protected]",
121 packages=find_packages(),
122 install_requires=list(runtime),
123 package_data={'': ['LICENSE']},
124 license='Apache 2.0',
125 extras_require={
126 'develop': list(runtime | develop | client | docs | linting | testing | cluster),
127 'develop26': list(runtime | develop | client | linting | testing | cluster),
128 'client': list(runtime | client),
129 'client-develop': list(runtime | develop | client | linting | testing),
130 'cluster': list(runtime | cluster),
131 'openshift': list(runtime | openshift),
132 'optional': list(optional),
133 'docs': list(docs),
134 'linting': list(linting | client),
135 'testing': list(testing | client)
136 },
137 classifiers=[
138 'Development Status :: 5 - Production/Stable',
139 'Intended Audience :: Developers',
140 'Natural Language :: English',
141 'License :: OSI Approved :: Apache Software License',
142 'Programming Language :: Python',
143 'Programming Language :: Python :: 2.6',
144 'Programming Language :: Python :: 2.7',
145 'Programming Language :: Python :: 3.3',
146 'Programming Language :: Python :: 3.4',
147 'Programming Language :: Python :: 3.5',
148 'Programming Language :: Python :: 3.6'
149 ],
150 entry_points=entry_points,
151 include_package_data=True
152 )
153
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -32,7 +32,8 @@
'cachecontrol[filecache]',
'defusedxml',
'lockfile',
- 'jinja2<=2.11.3',
+ 'jinja2<=2.11.3; python_version <= "2.7"',
+ 'jinja2; python_version > "2.7"',
'pyyaml>=3.10,<=3.13; python_version < "2.7"',
'pyyaml; python_version >= "2.7"',
])
@@ -66,7 +67,6 @@
'sphinx_rtd_theme',
'ipython',
'colorama',
- 'jinja2<=2.11.3',
'Pygments',
'jedi<0.18.0', # Open issue with jedi 0.18.0 and iPython <= 7.19
# https://github.com/davidhalter/jedi/issues/1714
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -32,7 +32,8 @@\n 'cachecontrol[filecache]',\n 'defusedxml',\n 'lockfile',\n- 'jinja2<=2.11.3',\n+ 'jinja2<=2.11.3; python_version <= \"2.7\"',\n+ 'jinja2; python_version > \"2.7\"',\n 'pyyaml>=3.10,<=3.13; python_version < \"2.7\"',\n 'pyyaml; python_version >= \"2.7\"',\n ])\n@@ -66,7 +67,6 @@\n 'sphinx_rtd_theme',\n 'ipython',\n 'colorama',\n- 'jinja2<=2.11.3',\n 'Pygments',\n 'jedi<0.18.0', # Open issue with jedi 0.18.0 and iPython <= 7.19\n # https://github.com/davidhalter/jedi/issues/1714\n", "issue": "Pinned jinja2 version is no longer supported and conflicts with the latest MarkupSafe\n**Current behavior**\r\n\r\ninsights-core has pinned the jinja2 version to <=2.11.3 in #3057. This version is [no longer supported](https://github.com/pallets/jinja/issues/1585#issuecomment-1043892628).\r\n\r\n**Expected behavior**\r\n\r\ninsights-core can be used with a maintained jinja2 version in applications that depend both on insights-core and jinja2.\r\n\r\n**Impact**\r\n\r\njinja2-2.11.3 fails to import with the latest version of MarkupSafe, 2.1.0:\r\n\r\n```\r\n...\r\n.tox/unit-py38/lib/python3.8/site-packages/jinja2/filters.py:13: in <module>\r\n from markupsafe import soft_unicode\r\nE ImportError: cannot import name 'soft_unicode' from 'markupsafe' (/builds/ccx/ccx-rules-ocp/.tox/unit-py38/lib64/python3.8/site-packages/markupsafe/__init__.py\r\n```\r\n\r\nAll projects that depend on insights-core have to pin unsupported versions of MarkupSafe now. I would argue that it is important to keep up-to-date for a package that is used for secure handling of user input.\n", "before_files": [{"content": "import os\nfrom setuptools import setup, find_packages\n\n__here__ = os.path.dirname(os.path.abspath(__file__))\n\npackage_info = dict.fromkeys([\"RELEASE\", \"COMMIT\", \"VERSION\", \"NAME\"])\n\nfor name in package_info:\n with open(os.path.join(__here__, \"insights\", name)) as f:\n package_info[name] = f.read().strip()\n\nentry_points = {\n 'console_scripts': [\n 'insights-collect = insights.collect:main',\n 'insights-run = insights:main',\n 'insights = insights.command_parser:main',\n 'insights-cat = insights.tools.cat:main',\n 'insights-dupkeycheck = insights.tools.dupkeycheck:main',\n 'insights-inspect = insights.tools.insights_inspect:main',\n 'insights-info = insights.tools.query:main',\n 'insights-ocpshell= insights.ocpshell:main',\n 'mangle = insights.util.mangle:main'\n ]\n}\n\nruntime = set([\n 'six',\n 'requests',\n 'redis',\n 'cachecontrol',\n 'cachecontrol[redis]',\n 'cachecontrol[filecache]',\n 'defusedxml',\n 'lockfile',\n 'jinja2<=2.11.3',\n 'pyyaml>=3.10,<=3.13; python_version < \"2.7\"',\n 'pyyaml; python_version >= \"2.7\"',\n])\n\n\ndef maybe_require(pkg):\n try:\n __import__(pkg)\n except ImportError:\n runtime.add(pkg)\n\n\nmaybe_require(\"importlib\")\nmaybe_require(\"argparse\")\n\n\nclient = set([\n 'requests',\n 'python-gnupg==0.4.6',\n 'oyaml'\n])\n\ndevelop = set([\n 'wheel',\n])\n\ndocs = set([\n 'docutils',\n 'Sphinx',\n 'nbsphinx',\n 'sphinx_rtd_theme',\n 'ipython',\n 'colorama',\n 'jinja2<=2.11.3',\n 'Pygments',\n 'jedi<0.18.0', # Open issue with jedi 0.18.0 and iPython <= 7.19\n # https://github.com/davidhalter/jedi/issues/1714\n])\n\n# python 2.6 requires setuptools~=36.8.0 to support this syntax\ntesting = set([\n 'coverage==4.3.4; python_version < \"2.7\"',\n 'coverage; python_version >= \"2.7\"',\n 'pytest==3.0.6; python_version < \"2.7\"',\n 'pytest~=4.6.0; python_version == \"2.7\"',\n 'pytest; python_version >= \"3\"',\n 'pytest-cov==2.4.0; python_version < \"2.7\"',\n 'pytest-cov; python_version >= \"2.7\"',\n 'mock==2.0.0',\n])\n\ncluster = set([\n 'ansible',\n 'pandas',\n 'colorama',\n])\n\nopenshift = set([\n 'openshift'\n])\n\nlinting = set([\n 'flake8==2.6.2; python_version < \"2.7\"',\n 'flake8; python_version >= \"2.7\"'\n])\n\noptional = set([\n 'python-cjson',\n 'python-logstash',\n 'python-statsd',\n 'watchdog',\n])\n\nif __name__ == \"__main__\":\n # allows for runtime modification of rpm name\n name = os.environ.get(\"INSIGHTS_CORE_NAME\", package_info[\"NAME\"])\n\n setup(\n name=name,\n version=package_info[\"VERSION\"],\n description=\"Insights Core is a data collection and analysis framework\",\n long_description=open(\"README.rst\").read(),\n url=\"https://github.com/redhatinsights/insights-core\",\n author=\"Red Hat, Inc.\",\n author_email=\"[email protected]\",\n packages=find_packages(),\n install_requires=list(runtime),\n package_data={'': ['LICENSE']},\n license='Apache 2.0',\n extras_require={\n 'develop': list(runtime | develop | client | docs | linting | testing | cluster),\n 'develop26': list(runtime | develop | client | linting | testing | cluster),\n 'client': list(runtime | client),\n 'client-develop': list(runtime | develop | client | linting | testing),\n 'cluster': list(runtime | cluster),\n 'openshift': list(runtime | openshift),\n 'optional': list(optional),\n 'docs': list(docs),\n 'linting': list(linting | client),\n 'testing': list(testing | client)\n },\n classifiers=[\n 'Development Status :: 5 - Production/Stable',\n 'Intended Audience :: Developers',\n 'Natural Language :: English',\n 'License :: OSI Approved :: Apache Software License',\n 'Programming Language :: Python',\n 'Programming Language :: Python :: 2.6',\n 'Programming Language :: Python :: 2.7',\n 'Programming Language :: Python :: 3.3',\n 'Programming Language :: Python :: 3.4',\n 'Programming Language :: Python :: 3.5',\n 'Programming Language :: Python :: 3.6'\n ],\n entry_points=entry_points,\n include_package_data=True\n )\n", "path": "setup.py"}], "after_files": [{"content": "import os\nfrom setuptools import setup, find_packages\n\n__here__ = os.path.dirname(os.path.abspath(__file__))\n\npackage_info = dict.fromkeys([\"RELEASE\", \"COMMIT\", \"VERSION\", \"NAME\"])\n\nfor name in package_info:\n with open(os.path.join(__here__, \"insights\", name)) as f:\n package_info[name] = f.read().strip()\n\nentry_points = {\n 'console_scripts': [\n 'insights-collect = insights.collect:main',\n 'insights-run = insights:main',\n 'insights = insights.command_parser:main',\n 'insights-cat = insights.tools.cat:main',\n 'insights-dupkeycheck = insights.tools.dupkeycheck:main',\n 'insights-inspect = insights.tools.insights_inspect:main',\n 'insights-info = insights.tools.query:main',\n 'insights-ocpshell= insights.ocpshell:main',\n 'mangle = insights.util.mangle:main'\n ]\n}\n\nruntime = set([\n 'six',\n 'requests',\n 'redis',\n 'cachecontrol',\n 'cachecontrol[redis]',\n 'cachecontrol[filecache]',\n 'defusedxml',\n 'lockfile',\n 'jinja2<=2.11.3; python_version <= \"2.7\"',\n 'jinja2; python_version > \"2.7\"',\n 'pyyaml>=3.10,<=3.13; python_version < \"2.7\"',\n 'pyyaml; python_version >= \"2.7\"',\n])\n\n\ndef maybe_require(pkg):\n try:\n __import__(pkg)\n except ImportError:\n runtime.add(pkg)\n\n\nmaybe_require(\"importlib\")\nmaybe_require(\"argparse\")\n\n\nclient = set([\n 'requests',\n 'python-gnupg==0.4.6',\n 'oyaml'\n])\n\ndevelop = set([\n 'wheel',\n])\n\ndocs = set([\n 'docutils',\n 'Sphinx',\n 'nbsphinx',\n 'sphinx_rtd_theme',\n 'ipython',\n 'colorama',\n 'Pygments',\n 'jedi<0.18.0', # Open issue with jedi 0.18.0 and iPython <= 7.19\n # https://github.com/davidhalter/jedi/issues/1714\n])\n\n# python 2.6 requires setuptools~=36.8.0 to support this syntax\ntesting = set([\n 'coverage==4.3.4; python_version < \"2.7\"',\n 'coverage; python_version >= \"2.7\"',\n 'pytest==3.0.6; python_version < \"2.7\"',\n 'pytest~=4.6.0; python_version == \"2.7\"',\n 'pytest; python_version >= \"3\"',\n 'pytest-cov==2.4.0; python_version < \"2.7\"',\n 'pytest-cov; python_version >= \"2.7\"',\n 'mock==2.0.0',\n])\n\ncluster = set([\n 'ansible',\n 'pandas',\n 'colorama',\n])\n\nopenshift = set([\n 'openshift'\n])\n\nlinting = set([\n 'flake8==2.6.2; python_version < \"2.7\"',\n 'flake8; python_version >= \"2.7\"'\n])\n\noptional = set([\n 'python-cjson',\n 'python-logstash',\n 'python-statsd',\n 'watchdog',\n])\n\nif __name__ == \"__main__\":\n # allows for runtime modification of rpm name\n name = os.environ.get(\"INSIGHTS_CORE_NAME\", package_info[\"NAME\"])\n\n setup(\n name=name,\n version=package_info[\"VERSION\"],\n description=\"Insights Core is a data collection and analysis framework\",\n long_description=open(\"README.rst\").read(),\n url=\"https://github.com/redhatinsights/insights-core\",\n author=\"Red Hat, Inc.\",\n author_email=\"[email protected]\",\n packages=find_packages(),\n install_requires=list(runtime),\n package_data={'': ['LICENSE']},\n license='Apache 2.0',\n extras_require={\n 'develop': list(runtime | develop | client | docs | linting | testing | cluster),\n 'develop26': list(runtime | develop | client | linting | testing | cluster),\n 'client': list(runtime | client),\n 'client-develop': list(runtime | develop | client | linting | testing),\n 'cluster': list(runtime | cluster),\n 'openshift': list(runtime | openshift),\n 'optional': list(optional),\n 'docs': list(docs),\n 'linting': list(linting | client),\n 'testing': list(testing | client)\n },\n classifiers=[\n 'Development Status :: 5 - Production/Stable',\n 'Intended Audience :: Developers',\n 'Natural Language :: English',\n 'License :: OSI Approved :: Apache Software License',\n 'Programming Language :: Python',\n 'Programming Language :: Python :: 2.6',\n 'Programming Language :: Python :: 2.7',\n 'Programming Language :: Python :: 3.3',\n 'Programming Language :: Python :: 3.4',\n 'Programming Language :: Python :: 3.5',\n 'Programming Language :: Python :: 3.6'\n ],\n entry_points=entry_points,\n include_package_data=True\n )\n", "path": "setup.py"}]}
| 2,050 | 243 |
gh_patches_debug_32097
|
rasdani/github-patches
|
git_diff
|
dotkom__onlineweb4-1208
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Posters issues
- [ ] Does not send mail [src](https://github.com/dotKom/onlineweb4/blob/f4c45b9d07bd2c20533dec840a3bdcb3b8d50dd3/apps/posters/dashboard/views.py#L106)
- [x] Group is set to "Komiteer" [src](https://github.com/dotKom/onlineweb4/blob/f4c45b9d07bd2c20533dec840a3bdcb3b8d50dd3/apps/posters/dashboard/views.py#L93)
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `apps/posters/dashboard/views.py`
Content:
```
1 # -*- encoding: utf-8 -*-
2
3 import json
4
5 from django.conf import settings
6 from django.contrib import messages
7 from django.contrib.auth.decorators import login_required
8 from django.contrib.auth.models import Group
9 from django.core.mail import EmailMessage
10 from django.core.exceptions import PermissionDenied, ObjectDoesNotExist
11 from django.core.urlresolvers import reverse
12 from django.forms.models import model_to_dict
13 from django.shortcuts import render, redirect, get_object_or_404, HttpResponseRedirect, HttpResponse
14 from django.utils import timezone
15 from django.utils.translation import ugettext as _
16 from django.views.decorators.csrf import ensure_csrf_cookie
17
18 from guardian.decorators import permission_required
19 from guardian.models import UserObjectPermission, GroupObjectPermission
20 # from guardian.core import ObjectPermissionChecker
21 import guardian
22
23 from datetime import datetime, timedelta
24
25 from apps.authentication.models import OnlineUser as User
26 from apps.dashboard.tools import has_access, get_base_context
27 from apps.posters.models import Poster
28 from apps.posters.forms import AddForm, AddPosterForm, AddBongForm, AddOtherForm, EditPosterForm
29 # from apps.dashboard.posters.models import PosterForm
30 from apps.companyprofile.models import Company
31 from apps.posters.models import Poster, OrderMixin
32 from apps.posters.permissions import has_view_perms, has_view_all_perms
33
34
35 @ensure_csrf_cookie
36 @login_required
37 @permission_required('posters.overview_poster_order', return_403=True)
38 def index(request):
39 if request.is_ajax():
40 do_ajax_shit = True
41
42 # The group with members who should populate the dropdownlist
43 group = Group.objects.get(name='proKom')
44 users_to_populate = group.user_set.all()
45
46 context = get_base_context(request)
47
48 # View to show if user not in committee, but wanting to see own orders
49 if not has_view_all_perms(request.user):
50 context['your_orders'] = [x for x in Poster.objects.filter(ordered_by=request.user) if request.user.has_perm('view_poster_order', x)]
51 return render(request, 'posters/dashboard/index.html', context)
52
53 orders = Poster.objects.all()
54
55 context['new_orders'] = orders.filter(assigned_to=None)
56 context['active_orders'] = orders.filter(finished=False).exclude(assigned_to=None)
57 context['hanging_orders'] = orders.filter(finished=True,
58 display_to__lte=datetime.now()+timedelta(days=3))
59
60 context['workers'] = User.objects.filter(groups=Group.objects.get(name='proKom'))
61
62 return render(request, 'posters/dashboard/index.html', context)
63
64
65 @ensure_csrf_cookie
66 @login_required
67 @permission_required('posters.add_poster_order', return_403=True)
68 def add(request, order_type=0):
69 order_type = int(order_type)
70 context = get_base_context(request)
71 type_names = ("Plakat", "Bong", "Generell ")
72 type_name = type_names[order_type-1]
73
74 poster = Poster()
75 form = None
76
77 if request.method == 'POST':
78 if order_type == 1:
79 form = AddPosterForm(data=request.POST, instance=poster)
80 elif order_type == 2:
81 form = AddBongForm(data=request.POST, instance=poster)
82 elif order_type == 3:
83 # poster = GeneralOrder()
84 form = AddOtherForm(data=request.POST, instance=poster)
85
86 if form.is_valid():
87 poster = form.save(commit=False)
88 if request.POST.get('company'):
89 poster.company = Company.objects.get(pk=request.POST.get('company'))
90 poster.ordered_by = request.user
91 # Should look for a more kosher solution
92 poster.ordered_committee = request.user.groups.exclude(name='Komiteer').filter(name__contains="Kom")[0]
93 poster.order_type = order_type
94
95 poster.save()
96
97 # for b in poster.__class__.__bases__:
98 # poster_mixin = OrderMixin.objects.get(id=poster.id)
99 # Let this user have permissions to show this order
100 UserObjectPermission.objects.assign_perm('view_poster_order', obj=poster, user=request.user)
101 GroupObjectPermission.objects.assign_perm('view_poster_order', obj=poster, group=Group.objects.get(name='proKom'))
102
103 title = unicode(poster)
104
105 # The great sending of emails
106 subject = '[ProKom] Ny bestilling for %s' % title
107 email_message = '%(message)s%(signature)s' % {
108 'message': _('''
109 Det har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.
110 \n
111 Antall og type: %(num)s * %(order_type)s\n
112 Arrangement: %(event_name)s\n
113 Bestilt av: %(ordered_by)s i %(ordered_by_committee)s\n
114 Bestilt dato: %(ordered_date)s\n
115 \n
116 For mer informasjon, sjekk ut bestillingen her: %(absolute_url)s
117 '''
118 % {
119 'site': '',
120 'order_type': type_name.lower(),
121 'num': poster.amount,
122 'ordered_by': poster.ordered_by,
123 'ordered_by_committee': poster.ordered_committee,
124 'id': poster.id,
125 'event_name': title,
126 'ordered_date': poster.ordered_date,
127 'absolute_url': request.build_absolute_uri(poster.get_dashboard_url())
128 }
129 ),
130 'signature': _('\n\nVennlig hilsen Linjeforeningen Online')
131 }
132 from_email = settings.EMAIL_PROKOM
133 to_emails = [settings.EMAIL_PROKOM, request.user.get_email()]
134
135 try:
136 email_sent = EmailMessage(unicode(subject), unicode(message), from_email, to_emails, []).send()
137 except:
138 email_sent = False
139
140 if email_sent:
141 messages.success(request, 'Opprettet bestilling')
142 else:
143 messages.error(request, 'Klarte ikke å sende epost, men bestillingen din ble fortsatt opprettet')
144
145 return redirect(poster.get_absolute_url())
146 else:
147 context['form'] = form
148 return render(request, 'posters/dashboard/add.html', context)
149
150 context["order_type_name"] = type_name
151 context['order_type'] = order_type
152 context['can_edit'] = True # request.user.has_perm('posters.view_poster')
153
154 if order_type == 1:
155 form = AddPosterForm()
156 elif order_type == 2:
157 form = AddBongForm()
158 elif order_type == 3:
159 form = AddOtherForm()
160
161 forms = (AddPosterForm(), AddBongForm(), AddOtherForm())
162
163 context['form'] = forms[order_type-1]
164
165 return render(request, 'posters/dashboard/add.html', context)
166
167
168 @ensure_csrf_cookie
169 @login_required
170 def edit(request, order_id=None):
171 context = get_base_context(request)
172 context['add_poster_form'] = EditPosterForm()
173
174 if order_id:
175 poster = get_object_or_404(Poster, pk=order_id)
176
177 if request.user != poster.ordered_by and 'proKom' not in request.user.groups:
178 raise PermissionDenied
179
180 if request.POST:
181 form = AddForm(request.POST, instance=poster)
182 if form.is_valid():
183 form.save()
184 # redirect_url = redirect(poster.get_absolute_url())
185 return HttpResponseRedirect("../detail/"+str(poster.id))
186
187 else:
188 context["form"] = AddForm(instance=poster)
189
190 return render(request, 'posters/dashboard/add.html', context)
191
192
193 @ensure_csrf_cookie
194 @login_required
195 @permission_required('view_poster_order', (Poster, 'pk', 'order_id'), return_403=True)
196 def detail(request, order_id=None):
197 if request.is_ajax():
198 do_ajax_shit = True
199
200 if not order_id:
201 return HttpResponse(status=400)
202
203 context = get_base_context(request)
204 poster = get_object_or_404(Poster, pk=order_id)
205 context['poster'] = poster
206
207 if not has_view_perms(request.user, poster):
208 raise PermissionDenied
209
210 order_type = poster.order_type
211 type_names = ("Plakat", "Bong", "Generell ")
212 type_name = type_names[order_type-1]
213 context["order_type_name"] = type_name
214
215 if request.method == 'POST':
216 poster_status = request.POST.get('completed')
217 if poster_status == 'true' or poster_status == 'false':
218 poster.toggle_finished()
219
220 return render(request, 'posters/dashboard/details.html', context)
221
222
223 # Ajax
224
225
226 # @ensure_csrf_cookie
227 @login_required
228 def assign_person(request):
229 if request.is_ajax():
230 if request.method == 'POST':
231 order_id = request.POST.get('order_id')
232 orders = Poster.objects.filter(pk=order_id)
233 assign_to_id = request.POST.get('assign_to_id')
234 assign_to = User.objects.get(pk=assign_to_id)
235
236 if orders.count() == 0:
237 response_text = json.dumps({'message': _(
238 u"""Kan ikke finne en ordre med denne IDen (%s).
239 Om feilen vedvarer etter en refresh, kontakt [email protected].""") % order_id})
240 return HttpResponse(status=412, content=response_text)
241
242 order = orders[0]
243
244 if order.finished or order.assigned_to is not None:
245 response_text = json.dumps({'message': _(u"Denne ordren er allerede behandlet.")})
246 return HttpResponse(status=412, content=response_text)
247
248 order.assigned_to = assign_to
249 order.save()
250
251 return HttpResponse(status=200)
252
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/apps/posters/dashboard/views.py b/apps/posters/dashboard/views.py
--- a/apps/posters/dashboard/views.py
+++ b/apps/posters/dashboard/views.py
@@ -106,14 +106,14 @@
subject = '[ProKom] Ny bestilling for %s' % title
email_message = '%(message)s%(signature)s' % {
'message': _('''
- Det har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.
- \n
- Antall og type: %(num)s * %(order_type)s\n
- Arrangement: %(event_name)s\n
- Bestilt av: %(ordered_by)s i %(ordered_by_committee)s\n
- Bestilt dato: %(ordered_date)s\n
- \n
- For mer informasjon, sjekk ut bestillingen her: %(absolute_url)s
+Det har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.
+\n
+Antall og type: %(num)s * %(order_type)s\n
+Arrangement: %(event_name)s\n
+Bestilt av: %(ordered_by)s i %(ordered_by_committee)s\n
+Bestilt dato: %(ordered_date)s\n
+\n
+For mer informasjon, sjekk ut bestillingen her: %(absolute_url)s
'''
% {
'site': '',
@@ -130,13 +130,9 @@
'signature': _('\n\nVennlig hilsen Linjeforeningen Online')
}
from_email = settings.EMAIL_PROKOM
- to_emails = [settings.EMAIL_PROKOM, request.user.get_email()]
-
- try:
- email_sent = EmailMessage(unicode(subject), unicode(message), from_email, to_emails, []).send()
- except:
- email_sent = False
+ to_emails = [settings.EMAIL_PROKOM, request.user.get_email().email]
+ email_sent = EmailMessage(unicode(subject), unicode(email_message), from_email, to_emails, []).send()
if email_sent:
messages.success(request, 'Opprettet bestilling')
else:
|
{"golden_diff": "diff --git a/apps/posters/dashboard/views.py b/apps/posters/dashboard/views.py\n--- a/apps/posters/dashboard/views.py\n+++ b/apps/posters/dashboard/views.py\n@@ -106,14 +106,14 @@\n subject = '[ProKom] Ny bestilling for %s' % title\n email_message = '%(message)s%(signature)s' % {\n 'message': _('''\n- Det har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.\n- \\n\n- Antall og type: %(num)s * %(order_type)s\\n\n- Arrangement: %(event_name)s\\n\n- Bestilt av: %(ordered_by)s i %(ordered_by_committee)s\\n\n- Bestilt dato: %(ordered_date)s\\n\n- \\n\n- For mer informasjon, sjekk ut bestillingen her: %(absolute_url)s\n+Det har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.\n+\\n\n+Antall og type: %(num)s * %(order_type)s\\n\n+Arrangement: %(event_name)s\\n\n+Bestilt av: %(ordered_by)s i %(ordered_by_committee)s\\n\n+Bestilt dato: %(ordered_date)s\\n\n+\\n\n+For mer informasjon, sjekk ut bestillingen her: %(absolute_url)s\n '''\n % {\n 'site': '',\n@@ -130,13 +130,9 @@\n 'signature': _('\\n\\nVennlig hilsen Linjeforeningen Online')\n }\n from_email = settings.EMAIL_PROKOM\n- to_emails = [settings.EMAIL_PROKOM, request.user.get_email()]\n-\n- try:\n- email_sent = EmailMessage(unicode(subject), unicode(message), from_email, to_emails, []).send()\n- except:\n- email_sent = False\n+ to_emails = [settings.EMAIL_PROKOM, request.user.get_email().email]\n \n+ email_sent = EmailMessage(unicode(subject), unicode(email_message), from_email, to_emails, []).send()\n if email_sent:\n messages.success(request, 'Opprettet bestilling')\n else:\n", "issue": "Posters issues\n- [ ] Does not send mail [src](https://github.com/dotKom/onlineweb4/blob/f4c45b9d07bd2c20533dec840a3bdcb3b8d50dd3/apps/posters/dashboard/views.py#L106)\n- [x] Group is set to \"Komiteer\" [src](https://github.com/dotKom/onlineweb4/blob/f4c45b9d07bd2c20533dec840a3bdcb3b8d50dd3/apps/posters/dashboard/views.py#L93)\n\n", "before_files": [{"content": "# -*- encoding: utf-8 -*-\n\nimport json\n\nfrom django.conf import settings\nfrom django.contrib import messages\nfrom django.contrib.auth.decorators import login_required\nfrom django.contrib.auth.models import Group\nfrom django.core.mail import EmailMessage\nfrom django.core.exceptions import PermissionDenied, ObjectDoesNotExist\nfrom django.core.urlresolvers import reverse\nfrom django.forms.models import model_to_dict\nfrom django.shortcuts import render, redirect, get_object_or_404, HttpResponseRedirect, HttpResponse\nfrom django.utils import timezone\nfrom django.utils.translation import ugettext as _\nfrom django.views.decorators.csrf import ensure_csrf_cookie\n\nfrom guardian.decorators import permission_required\nfrom guardian.models import UserObjectPermission, GroupObjectPermission\n# from guardian.core import ObjectPermissionChecker\nimport guardian\n\nfrom datetime import datetime, timedelta\n\nfrom apps.authentication.models import OnlineUser as User\nfrom apps.dashboard.tools import has_access, get_base_context\nfrom apps.posters.models import Poster\nfrom apps.posters.forms import AddForm, AddPosterForm, AddBongForm, AddOtherForm, EditPosterForm\n# from apps.dashboard.posters.models import PosterForm\nfrom apps.companyprofile.models import Company\nfrom apps.posters.models import Poster, OrderMixin\nfrom apps.posters.permissions import has_view_perms, has_view_all_perms\n\n\n@ensure_csrf_cookie\n@login_required\n@permission_required('posters.overview_poster_order', return_403=True)\ndef index(request):\n if request.is_ajax():\n do_ajax_shit = True\n\n # The group with members who should populate the dropdownlist\n group = Group.objects.get(name='proKom')\n users_to_populate = group.user_set.all()\n\n context = get_base_context(request)\n\n # View to show if user not in committee, but wanting to see own orders\n if not has_view_all_perms(request.user):\n context['your_orders'] = [x for x in Poster.objects.filter(ordered_by=request.user) if request.user.has_perm('view_poster_order', x)]\n return render(request, 'posters/dashboard/index.html', context)\n\n orders = Poster.objects.all()\n\n context['new_orders'] = orders.filter(assigned_to=None)\n context['active_orders'] = orders.filter(finished=False).exclude(assigned_to=None)\n context['hanging_orders'] = orders.filter(finished=True,\n display_to__lte=datetime.now()+timedelta(days=3))\n\n context['workers'] = User.objects.filter(groups=Group.objects.get(name='proKom'))\n\n return render(request, 'posters/dashboard/index.html', context)\n\n\n@ensure_csrf_cookie\n@login_required\n@permission_required('posters.add_poster_order', return_403=True)\ndef add(request, order_type=0):\n order_type = int(order_type)\n context = get_base_context(request)\n type_names = (\"Plakat\", \"Bong\", \"Generell \")\n type_name = type_names[order_type-1]\n\n poster = Poster()\n form = None\n\n if request.method == 'POST':\n if order_type == 1:\n form = AddPosterForm(data=request.POST, instance=poster)\n elif order_type == 2:\n form = AddBongForm(data=request.POST, instance=poster)\n elif order_type == 3:\n # poster = GeneralOrder()\n form = AddOtherForm(data=request.POST, instance=poster)\n\n if form.is_valid():\n poster = form.save(commit=False)\n if request.POST.get('company'):\n poster.company = Company.objects.get(pk=request.POST.get('company'))\n poster.ordered_by = request.user\n # Should look for a more kosher solution\n poster.ordered_committee = request.user.groups.exclude(name='Komiteer').filter(name__contains=\"Kom\")[0]\n poster.order_type = order_type\n\n poster.save()\n\n # for b in poster.__class__.__bases__:\n # poster_mixin = OrderMixin.objects.get(id=poster.id)\n # Let this user have permissions to show this order\n UserObjectPermission.objects.assign_perm('view_poster_order', obj=poster, user=request.user)\n GroupObjectPermission.objects.assign_perm('view_poster_order', obj=poster, group=Group.objects.get(name='proKom'))\n\n title = unicode(poster)\n\n # The great sending of emails\n subject = '[ProKom] Ny bestilling for %s' % title\n email_message = '%(message)s%(signature)s' % {\n 'message': _('''\n Det har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.\n \\n\n Antall og type: %(num)s * %(order_type)s\\n\n Arrangement: %(event_name)s\\n\n Bestilt av: %(ordered_by)s i %(ordered_by_committee)s\\n\n Bestilt dato: %(ordered_date)s\\n\n \\n\n For mer informasjon, sjekk ut bestillingen her: %(absolute_url)s\n '''\n % {\n 'site': '',\n 'order_type': type_name.lower(),\n 'num': poster.amount,\n 'ordered_by': poster.ordered_by,\n 'ordered_by_committee': poster.ordered_committee,\n 'id': poster.id,\n 'event_name': title,\n 'ordered_date': poster.ordered_date,\n 'absolute_url': request.build_absolute_uri(poster.get_dashboard_url())\n }\n ),\n 'signature': _('\\n\\nVennlig hilsen Linjeforeningen Online')\n }\n from_email = settings.EMAIL_PROKOM\n to_emails = [settings.EMAIL_PROKOM, request.user.get_email()]\n\n try:\n email_sent = EmailMessage(unicode(subject), unicode(message), from_email, to_emails, []).send()\n except:\n email_sent = False\n\n if email_sent:\n messages.success(request, 'Opprettet bestilling')\n else:\n messages.error(request, 'Klarte ikke \u00e5 sende epost, men bestillingen din ble fortsatt opprettet')\n\n return redirect(poster.get_absolute_url())\n else:\n context['form'] = form\n return render(request, 'posters/dashboard/add.html', context)\n\n context[\"order_type_name\"] = type_name\n context['order_type'] = order_type\n context['can_edit'] = True # request.user.has_perm('posters.view_poster')\n\n if order_type == 1:\n form = AddPosterForm()\n elif order_type == 2:\n form = AddBongForm()\n elif order_type == 3:\n form = AddOtherForm()\n\n forms = (AddPosterForm(), AddBongForm(), AddOtherForm())\n\n context['form'] = forms[order_type-1]\n\n return render(request, 'posters/dashboard/add.html', context)\n\n\n@ensure_csrf_cookie\n@login_required\ndef edit(request, order_id=None):\n context = get_base_context(request)\n context['add_poster_form'] = EditPosterForm()\n\n if order_id:\n poster = get_object_or_404(Poster, pk=order_id)\n\n if request.user != poster.ordered_by and 'proKom' not in request.user.groups:\n raise PermissionDenied\n\n if request.POST:\n form = AddForm(request.POST, instance=poster)\n if form.is_valid():\n form.save()\n # redirect_url = redirect(poster.get_absolute_url())\n return HttpResponseRedirect(\"../detail/\"+str(poster.id))\n\n else:\n context[\"form\"] = AddForm(instance=poster)\n\n return render(request, 'posters/dashboard/add.html', context)\n\n\n@ensure_csrf_cookie\n@login_required\n@permission_required('view_poster_order', (Poster, 'pk', 'order_id'), return_403=True)\ndef detail(request, order_id=None):\n if request.is_ajax():\n do_ajax_shit = True\n\n if not order_id:\n return HttpResponse(status=400)\n\n context = get_base_context(request)\n poster = get_object_or_404(Poster, pk=order_id)\n context['poster'] = poster\n\n if not has_view_perms(request.user, poster):\n raise PermissionDenied\n\n order_type = poster.order_type\n type_names = (\"Plakat\", \"Bong\", \"Generell \")\n type_name = type_names[order_type-1]\n context[\"order_type_name\"] = type_name\n\n if request.method == 'POST':\n poster_status = request.POST.get('completed')\n if poster_status == 'true' or poster_status == 'false':\n poster.toggle_finished()\n\n return render(request, 'posters/dashboard/details.html', context)\n\n\n# Ajax\n\n\n# @ensure_csrf_cookie\n@login_required\ndef assign_person(request):\n if request.is_ajax():\n if request.method == 'POST':\n order_id = request.POST.get('order_id')\n orders = Poster.objects.filter(pk=order_id)\n assign_to_id = request.POST.get('assign_to_id')\n assign_to = User.objects.get(pk=assign_to_id)\n\n if orders.count() == 0:\n response_text = json.dumps({'message': _(\n u\"\"\"Kan ikke finne en ordre med denne IDen (%s).\nOm feilen vedvarer etter en refresh, kontakt [email protected].\"\"\") % order_id})\n return HttpResponse(status=412, content=response_text)\n\n order = orders[0]\n\n if order.finished or order.assigned_to is not None:\n response_text = json.dumps({'message': _(u\"Denne ordren er allerede behandlet.\")})\n return HttpResponse(status=412, content=response_text)\n\n order.assigned_to = assign_to\n order.save()\n\n return HttpResponse(status=200)\n", "path": "apps/posters/dashboard/views.py"}], "after_files": [{"content": "# -*- encoding: utf-8 -*-\n\nimport json\n\nfrom django.conf import settings\nfrom django.contrib import messages\nfrom django.contrib.auth.decorators import login_required\nfrom django.contrib.auth.models import Group\nfrom django.core.mail import EmailMessage\nfrom django.core.exceptions import PermissionDenied, ObjectDoesNotExist\nfrom django.core.urlresolvers import reverse\nfrom django.forms.models import model_to_dict\nfrom django.shortcuts import render, redirect, get_object_or_404, HttpResponseRedirect, HttpResponse\nfrom django.utils import timezone\nfrom django.utils.translation import ugettext as _\nfrom django.views.decorators.csrf import ensure_csrf_cookie\n\nfrom guardian.decorators import permission_required\nfrom guardian.models import UserObjectPermission, GroupObjectPermission\n# from guardian.core import ObjectPermissionChecker\nimport guardian\n\nfrom datetime import datetime, timedelta\n\nfrom apps.authentication.models import OnlineUser as User\nfrom apps.dashboard.tools import has_access, get_base_context\nfrom apps.posters.models import Poster\nfrom apps.posters.forms import AddForm, AddPosterForm, AddBongForm, AddOtherForm, EditPosterForm\n# from apps.dashboard.posters.models import PosterForm\nfrom apps.companyprofile.models import Company\nfrom apps.posters.models import Poster, OrderMixin\nfrom apps.posters.permissions import has_view_perms, has_view_all_perms\n\n\n@ensure_csrf_cookie\n@login_required\n@permission_required('posters.overview_poster_order', return_403=True)\ndef index(request):\n if request.is_ajax():\n do_ajax_shit = True\n\n # The group with members who should populate the dropdownlist\n group = Group.objects.get(name='proKom')\n users_to_populate = group.user_set.all()\n\n context = get_base_context(request)\n\n # View to show if user not in committee, but wanting to see own orders\n if not has_view_all_perms(request.user):\n context['your_orders'] = [x for x in Poster.objects.filter(ordered_by=request.user) if request.user.has_perm('view_poster_order', x)]\n return render(request, 'posters/dashboard/index.html', context)\n\n orders = Poster.objects.all()\n\n context['new_orders'] = orders.filter(assigned_to=None)\n context['active_orders'] = orders.filter(finished=False).exclude(assigned_to=None)\n context['hanging_orders'] = orders.filter(finished=True,\n display_to__lte=datetime.now()+timedelta(days=3))\n\n context['workers'] = User.objects.filter(groups=Group.objects.get(name='proKom'))\n\n return render(request, 'posters/dashboard/index.html', context)\n\n\n@ensure_csrf_cookie\n@login_required\n@permission_required('posters.add_poster_order', return_403=True)\ndef add(request, order_type=0):\n order_type = int(order_type)\n context = get_base_context(request)\n type_names = (\"Plakat\", \"Bong\", \"Generell \")\n type_name = type_names[order_type-1]\n\n poster = Poster()\n form = None\n\n if request.method == 'POST':\n if order_type == 1:\n form = AddPosterForm(data=request.POST, instance=poster)\n elif order_type == 2:\n form = AddBongForm(data=request.POST, instance=poster)\n elif order_type == 3:\n # poster = GeneralOrder()\n form = AddOtherForm(data=request.POST, instance=poster)\n\n if form.is_valid():\n poster = form.save(commit=False)\n if request.POST.get('company'):\n poster.company = Company.objects.get(pk=request.POST.get('company'))\n poster.ordered_by = request.user\n # Should look for a more kosher solution\n poster.ordered_committee = request.user.groups.exclude(name='Komiteer').filter(name__contains=\"Kom\")[0]\n poster.order_type = order_type\n\n poster.save()\n\n # for b in poster.__class__.__bases__:\n # poster_mixin = OrderMixin.objects.get(id=poster.id)\n # Let this user have permissions to show this order\n UserObjectPermission.objects.assign_perm('view_poster_order', obj=poster, user=request.user)\n GroupObjectPermission.objects.assign_perm('view_poster_order', obj=poster, group=Group.objects.get(name='proKom'))\n\n title = unicode(poster)\n\n # The great sending of emails\n subject = '[ProKom] Ny bestilling for %s' % title\n email_message = '%(message)s%(signature)s' % {\n 'message': _('''\nDet har blitt registrert en ny %(order_type)sbestilling pa Online sine nettsider. Dette er bestilling nummer %(id)s.\n\\n\nAntall og type: %(num)s * %(order_type)s\\n\nArrangement: %(event_name)s\\n\nBestilt av: %(ordered_by)s i %(ordered_by_committee)s\\n\nBestilt dato: %(ordered_date)s\\n\n\\n\nFor mer informasjon, sjekk ut bestillingen her: %(absolute_url)s\n '''\n % {\n 'site': '',\n 'order_type': type_name.lower(),\n 'num': poster.amount,\n 'ordered_by': poster.ordered_by,\n 'ordered_by_committee': poster.ordered_committee,\n 'id': poster.id,\n 'event_name': title,\n 'ordered_date': poster.ordered_date,\n 'absolute_url': request.build_absolute_uri(poster.get_dashboard_url())\n }\n ),\n 'signature': _('\\n\\nVennlig hilsen Linjeforeningen Online')\n }\n from_email = settings.EMAIL_PROKOM\n to_emails = [settings.EMAIL_PROKOM, request.user.get_email().email]\n\n email_sent = EmailMessage(unicode(subject), unicode(email_message), from_email, to_emails, []).send()\n if email_sent:\n messages.success(request, 'Opprettet bestilling')\n else:\n messages.error(request, 'Klarte ikke \u00e5 sende epost, men bestillingen din ble fortsatt opprettet')\n\n return redirect(poster.get_absolute_url())\n else:\n context['form'] = form\n return render(request, 'posters/dashboard/add.html', context)\n\n context[\"order_type_name\"] = type_name\n context['order_type'] = order_type\n context['can_edit'] = True # request.user.has_perm('posters.view_poster')\n\n if order_type == 1:\n form = AddPosterForm()\n elif order_type == 2:\n form = AddBongForm()\n elif order_type == 3:\n form = AddOtherForm()\n\n forms = (AddPosterForm(), AddBongForm(), AddOtherForm())\n\n context['form'] = forms[order_type-1]\n\n return render(request, 'posters/dashboard/add.html', context)\n\n\n@ensure_csrf_cookie\n@login_required\ndef edit(request, order_id=None):\n context = get_base_context(request)\n context['add_poster_form'] = EditPosterForm()\n\n if order_id:\n poster = get_object_or_404(Poster, pk=order_id)\n\n if request.user != poster.ordered_by and 'proKom' not in request.user.groups:\n raise PermissionDenied\n\n if request.POST:\n form = AddForm(request.POST, instance=poster)\n if form.is_valid():\n form.save()\n # redirect_url = redirect(poster.get_absolute_url())\n return HttpResponseRedirect(\"../detail/\"+str(poster.id))\n\n else:\n context[\"form\"] = AddForm(instance=poster)\n\n return render(request, 'posters/dashboard/add.html', context)\n\n\n@ensure_csrf_cookie\n@login_required\n@permission_required('view_poster_order', (Poster, 'pk', 'order_id'), return_403=True)\ndef detail(request, order_id=None):\n if request.is_ajax():\n do_ajax_shit = True\n\n if not order_id:\n return HttpResponse(status=400)\n\n context = get_base_context(request)\n poster = get_object_or_404(Poster, pk=order_id)\n context['poster'] = poster\n\n if not has_view_perms(request.user, poster):\n raise PermissionDenied\n\n order_type = poster.order_type\n type_names = (\"Plakat\", \"Bong\", \"Generell \")\n type_name = type_names[order_type-1]\n context[\"order_type_name\"] = type_name\n\n if request.method == 'POST':\n poster_status = request.POST.get('completed')\n if poster_status == 'true' or poster_status == 'false':\n poster.toggle_finished()\n\n return render(request, 'posters/dashboard/details.html', context)\n\n\n# Ajax\n\n\n# @ensure_csrf_cookie\n@login_required\ndef assign_person(request):\n if request.is_ajax():\n if request.method == 'POST':\n order_id = request.POST.get('order_id')\n orders = Poster.objects.filter(pk=order_id)\n assign_to_id = request.POST.get('assign_to_id')\n assign_to = User.objects.get(pk=assign_to_id)\n\n if orders.count() == 0:\n response_text = json.dumps({'message': _(\n u\"\"\"Kan ikke finne en ordre med denne IDen (%s).\nOm feilen vedvarer etter en refresh, kontakt [email protected].\"\"\") % order_id})\n return HttpResponse(status=412, content=response_text)\n\n order = orders[0]\n\n if order.finished or order.assigned_to is not None:\n response_text = json.dumps({'message': _(u\"Denne ordren er allerede behandlet.\")})\n return HttpResponse(status=412, content=response_text)\n\n order.assigned_to = assign_to\n order.save()\n\n return HttpResponse(status=200)\n", "path": "apps/posters/dashboard/views.py"}]}
| 3,174 | 504 |
gh_patches_debug_49032
|
rasdani/github-patches
|
git_diff
|
pulp__pulpcore-5465
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Replication assumes every plugin supports Publications
The ```Replicator``` class, which is being subclassed inside plugins to support the replication feature, assumes that every plugin supports publications as it tries to access ```upstream_distribution["publication"]``` inside one of its methods (for some plugins, the dictionary simply doesn't contain the "publication" key so an exception gets raised). This forces certain subclasses of ```Replicator``` to create workarounds or rewrite the given method.
I propose making the method more general, removing such assumptions.
Relevant code: https://github.com/pulp/pulpcore/blob/c31a39c186fd734e9e0409321735d7d6509a12ee/pulpcore/app/replica.py#L97C9-L97C96
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `pulpcore/app/replica.py`
Content:
```
1 from django.db.models import Model
2 import logging
3
4 from pulp_glue.common.context import PulpContext
5 from pulpcore.tasking.tasks import dispatch
6 from pulpcore.app.tasks.base import (
7 general_update,
8 general_create,
9 general_multi_delete,
10 )
11 from pulpcore.plugin.util import get_url, get_domain
12
13 _logger = logging.getLogger(__name__)
14
15
16 class ReplicaContext(PulpContext):
17 def __init__(self, **kwargs):
18 super().__init__(**kwargs)
19 self.out_buf = ""
20 self.err_buf = ""
21
22 def echo(self, message: str, nl: bool = True, err: bool = False) -> None:
23 if err:
24 self.err_buf += message
25 if nl:
26 _logger.warn("{}", self.err_buf)
27 self.err_buf = ""
28 else:
29 self.out_buf += message
30 if nl:
31 _logger.info("{}", self.out_buf)
32 self.out_buf = ""
33
34
35 class Replicator:
36 distribution_ctx_cls = None
37 repository_ctx_cls = None
38 publication_ctx_cls = None
39 remote_model_cls = None
40 repository_model_cls = None
41 distribution_model_cls = None
42 distribution_serializer_name = None
43 repository_serializer_name = None
44 remote_serializer_name = None
45 app_label = None
46 sync_task = None
47
48 def __init__(self, pulp_ctx, task_group, tls_settings):
49 """
50 :param pulp_ctx: PulpReplicaContext
51 :param task_group: TaskGroup
52 :param ca_cert: str
53 """
54 self.pulp_ctx = pulp_ctx
55 self.task_group = task_group
56 self.tls_settings = tls_settings
57 self.domain = get_domain()
58 self.distros_uris = [f"pdrn:{self.domain.pulp_id}:distributions"]
59
60 @staticmethod
61 def needs_update(fields_dict, model_instance):
62 """
63 Compares a Model instance's attributes against a dictionary where keys are attribute
64 names and values are expected values.
65 """
66 needs_update = False
67 for field_name, value in fields_dict.items():
68 if isinstance(getattr(model_instance, field_name), Model):
69 if get_url(getattr(model_instance, field_name)) != value:
70 needs_update = True
71 elif getattr(model_instance, field_name) != value:
72 needs_update = True
73 return needs_update
74
75 def upstream_distributions(self, labels=None):
76 if labels:
77 params = {"pulp_label_select": labels}
78 else:
79 params = {}
80 offset = 0
81 list_size = 100
82 while True:
83 distributions = self.distribution_ctx_cls(self.pulp_ctx).list(list_size, offset, params)
84 for distro in distributions:
85 yield distro
86 if len(distributions) < list_size:
87 break
88 offset += list_size
89
90 def url(self, upstream_distribution):
91 return upstream_distribution["base_url"]
92
93 def remote_extra_fields(self, upstream_distribution):
94 return {}
95
96 def create_or_update_remote(self, upstream_distribution):
97 if not upstream_distribution["repository"] and not upstream_distribution["publication"]:
98 return None
99 url = self.url(upstream_distribution)
100 remote_fields_dict = {"url": url}
101 remote_fields_dict.update(self.tls_settings)
102 remote_fields_dict.update(self.remote_extra_fields(upstream_distribution))
103
104 # Check if there is a remote pointing to this distribution
105 try:
106 remote = self.remote_model_cls.objects.get(
107 name=upstream_distribution["name"], pulp_domain=self.domain
108 )
109 needs_update = self.needs_update(remote_fields_dict, remote)
110 if needs_update:
111 dispatch(
112 general_update,
113 task_group=self.task_group,
114 exclusive_resources=[remote],
115 args=(remote.pk, self.app_label, self.remote_serializer_name),
116 kwargs={"data": remote_fields_dict, "partial": True},
117 )
118 except self.remote_model_cls.DoesNotExist:
119 # Create the remote
120 remote = self.remote_model_cls(name=upstream_distribution["name"], **remote_fields_dict)
121 remote.save()
122
123 return remote
124
125 def repository_extra_fields(self, remote):
126 return {}
127
128 def create_or_update_repository(self, remote):
129 try:
130 repository = self.repository_model_cls.objects.get(
131 name=remote.name, pulp_domain=self.domain
132 )
133 repo_fields_dict = self.repository_extra_fields(remote)
134 needs_update = self.needs_update(repo_fields_dict, repository)
135 if needs_update:
136 dispatch(
137 general_update,
138 task_group=self.task_group,
139 exclusive_resources=[repository],
140 args=(repository.pk, self.app_label, self.repository_serializer_name),
141 kwargs={"data": repo_fields_dict, "partial": True},
142 )
143 except self.repository_model_cls.DoesNotExist:
144 repository = self.repository_model_cls(
145 name=remote.name, **self.repository_extra_fields(remote)
146 )
147 repository.save()
148 return repository
149
150 def distribution_data(self, repository, upstream_distribution):
151 """
152 Return the fields that need to be updated/cleared on distributions for idempotence.
153 """
154 return {
155 "repository": get_url(repository),
156 "publication": None,
157 "base_path": upstream_distribution["base_path"],
158 }
159
160 def create_or_update_distribution(self, repository, upstream_distribution):
161 distribution_data = self.distribution_data(repository, upstream_distribution)
162 try:
163 distro = self.distribution_model_cls.objects.get(
164 name=upstream_distribution["name"], pulp_domain=self.domain
165 )
166 # Check that the distribution has the right repository associated
167 needs_update = self.needs_update(distribution_data, distro)
168 if needs_update:
169 # Update the distribution
170 dispatch(
171 general_update,
172 task_group=self.task_group,
173 shared_resources=[repository],
174 exclusive_resources=self.distros_uris,
175 args=(distro.pk, self.app_label, self.distribution_serializer_name),
176 kwargs={
177 "data": distribution_data,
178 "partial": True,
179 },
180 )
181 except self.distribution_model_cls.DoesNotExist:
182 # Dispatch a task to create the distribution
183 distribution_data["name"] = upstream_distribution["name"]
184 dispatch(
185 general_create,
186 task_group=self.task_group,
187 shared_resources=[repository],
188 exclusive_resources=self.distros_uris,
189 args=(self.app_label, self.distribution_serializer_name),
190 kwargs={"data": distribution_data},
191 )
192
193 def sync_params(self, repository, remote):
194 """This method returns a dict that will be passed as kwargs to the sync task."""
195 raise NotImplementedError("Each replicator must supply its own sync params.")
196
197 def sync(self, repository, remote):
198 dispatch(
199 self.sync_task,
200 task_group=self.task_group,
201 shared_resources=[remote],
202 exclusive_resources=[repository],
203 kwargs=self.sync_params(repository, remote),
204 )
205
206 def remove_missing(self, names):
207 # Remove all distributions with names not present in the list of names
208 # Perform this in an extra task, because we hold a big lock here.
209 distribution_ids = [
210 (distribution.pk, self.app_label, self.distribution_serializer_name)
211 for distribution in self.distribution_model_cls.objects.filter(
212 pulp_domain=self.domain
213 ).exclude(name__in=names)
214 ]
215 if distribution_ids:
216 dispatch(
217 general_multi_delete,
218 task_group=self.task_group,
219 exclusive_resources=self.distros_uris,
220 args=(distribution_ids,),
221 )
222
223 # Remove all the repositories and remotes of the missing distributions
224 repositories = list(
225 self.repository_model_cls.objects.filter(
226 pulp_domain=self.domain, user_hidden=False
227 ).exclude(name__in=names)
228 )
229 repository_ids = [
230 (repo.pk, self.app_label, self.repository_serializer_name) for repo in repositories
231 ]
232
233 remotes = list(
234 self.remote_model_cls.objects.filter(pulp_domain=self.domain).exclude(name__in=names)
235 )
236 remote_ids = [
237 (remote.pk, self.app_label, self.remote_serializer_name) for remote in remotes
238 ]
239
240 if repository_ids or remote_ids:
241 dispatch(
242 general_multi_delete,
243 task_group=self.task_group,
244 exclusive_resources=repositories + remotes,
245 args=(repository_ids + remote_ids,),
246 )
247
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/pulpcore/app/replica.py b/pulpcore/app/replica.py
--- a/pulpcore/app/replica.py
+++ b/pulpcore/app/replica.py
@@ -94,7 +94,9 @@
return {}
def create_or_update_remote(self, upstream_distribution):
- if not upstream_distribution["repository"] and not upstream_distribution["publication"]:
+ if not upstream_distribution.get("repository") and not upstream_distribution.get(
+ "publication"
+ ):
return None
url = self.url(upstream_distribution)
remote_fields_dict = {"url": url}
|
{"golden_diff": "diff --git a/pulpcore/app/replica.py b/pulpcore/app/replica.py\n--- a/pulpcore/app/replica.py\n+++ b/pulpcore/app/replica.py\n@@ -94,7 +94,9 @@\n return {}\n \n def create_or_update_remote(self, upstream_distribution):\n- if not upstream_distribution[\"repository\"] and not upstream_distribution[\"publication\"]:\n+ if not upstream_distribution.get(\"repository\") and not upstream_distribution.get(\n+ \"publication\"\n+ ):\n return None\n url = self.url(upstream_distribution)\n remote_fields_dict = {\"url\": url}\n", "issue": "Replication assumes every plugin supports Publications\nThe ```Replicator``` class, which is being subclassed inside plugins to support the replication feature, assumes that every plugin supports publications as it tries to access ```upstream_distribution[\"publication\"]``` inside one of its methods (for some plugins, the dictionary simply doesn't contain the \"publication\" key so an exception gets raised). This forces certain subclasses of ```Replicator``` to create workarounds or rewrite the given method.\r\n\r\nI propose making the method more general, removing such assumptions.\r\n\r\nRelevant code: https://github.com/pulp/pulpcore/blob/c31a39c186fd734e9e0409321735d7d6509a12ee/pulpcore/app/replica.py#L97C9-L97C96\r\n\n", "before_files": [{"content": "from django.db.models import Model\nimport logging\n\nfrom pulp_glue.common.context import PulpContext\nfrom pulpcore.tasking.tasks import dispatch\nfrom pulpcore.app.tasks.base import (\n general_update,\n general_create,\n general_multi_delete,\n)\nfrom pulpcore.plugin.util import get_url, get_domain\n\n_logger = logging.getLogger(__name__)\n\n\nclass ReplicaContext(PulpContext):\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n self.out_buf = \"\"\n self.err_buf = \"\"\n\n def echo(self, message: str, nl: bool = True, err: bool = False) -> None:\n if err:\n self.err_buf += message\n if nl:\n _logger.warn(\"{}\", self.err_buf)\n self.err_buf = \"\"\n else:\n self.out_buf += message\n if nl:\n _logger.info(\"{}\", self.out_buf)\n self.out_buf = \"\"\n\n\nclass Replicator:\n distribution_ctx_cls = None\n repository_ctx_cls = None\n publication_ctx_cls = None\n remote_model_cls = None\n repository_model_cls = None\n distribution_model_cls = None\n distribution_serializer_name = None\n repository_serializer_name = None\n remote_serializer_name = None\n app_label = None\n sync_task = None\n\n def __init__(self, pulp_ctx, task_group, tls_settings):\n \"\"\"\n :param pulp_ctx: PulpReplicaContext\n :param task_group: TaskGroup\n :param ca_cert: str\n \"\"\"\n self.pulp_ctx = pulp_ctx\n self.task_group = task_group\n self.tls_settings = tls_settings\n self.domain = get_domain()\n self.distros_uris = [f\"pdrn:{self.domain.pulp_id}:distributions\"]\n\n @staticmethod\n def needs_update(fields_dict, model_instance):\n \"\"\"\n Compares a Model instance's attributes against a dictionary where keys are attribute\n names and values are expected values.\n \"\"\"\n needs_update = False\n for field_name, value in fields_dict.items():\n if isinstance(getattr(model_instance, field_name), Model):\n if get_url(getattr(model_instance, field_name)) != value:\n needs_update = True\n elif getattr(model_instance, field_name) != value:\n needs_update = True\n return needs_update\n\n def upstream_distributions(self, labels=None):\n if labels:\n params = {\"pulp_label_select\": labels}\n else:\n params = {}\n offset = 0\n list_size = 100\n while True:\n distributions = self.distribution_ctx_cls(self.pulp_ctx).list(list_size, offset, params)\n for distro in distributions:\n yield distro\n if len(distributions) < list_size:\n break\n offset += list_size\n\n def url(self, upstream_distribution):\n return upstream_distribution[\"base_url\"]\n\n def remote_extra_fields(self, upstream_distribution):\n return {}\n\n def create_or_update_remote(self, upstream_distribution):\n if not upstream_distribution[\"repository\"] and not upstream_distribution[\"publication\"]:\n return None\n url = self.url(upstream_distribution)\n remote_fields_dict = {\"url\": url}\n remote_fields_dict.update(self.tls_settings)\n remote_fields_dict.update(self.remote_extra_fields(upstream_distribution))\n\n # Check if there is a remote pointing to this distribution\n try:\n remote = self.remote_model_cls.objects.get(\n name=upstream_distribution[\"name\"], pulp_domain=self.domain\n )\n needs_update = self.needs_update(remote_fields_dict, remote)\n if needs_update:\n dispatch(\n general_update,\n task_group=self.task_group,\n exclusive_resources=[remote],\n args=(remote.pk, self.app_label, self.remote_serializer_name),\n kwargs={\"data\": remote_fields_dict, \"partial\": True},\n )\n except self.remote_model_cls.DoesNotExist:\n # Create the remote\n remote = self.remote_model_cls(name=upstream_distribution[\"name\"], **remote_fields_dict)\n remote.save()\n\n return remote\n\n def repository_extra_fields(self, remote):\n return {}\n\n def create_or_update_repository(self, remote):\n try:\n repository = self.repository_model_cls.objects.get(\n name=remote.name, pulp_domain=self.domain\n )\n repo_fields_dict = self.repository_extra_fields(remote)\n needs_update = self.needs_update(repo_fields_dict, repository)\n if needs_update:\n dispatch(\n general_update,\n task_group=self.task_group,\n exclusive_resources=[repository],\n args=(repository.pk, self.app_label, self.repository_serializer_name),\n kwargs={\"data\": repo_fields_dict, \"partial\": True},\n )\n except self.repository_model_cls.DoesNotExist:\n repository = self.repository_model_cls(\n name=remote.name, **self.repository_extra_fields(remote)\n )\n repository.save()\n return repository\n\n def distribution_data(self, repository, upstream_distribution):\n \"\"\"\n Return the fields that need to be updated/cleared on distributions for idempotence.\n \"\"\"\n return {\n \"repository\": get_url(repository),\n \"publication\": None,\n \"base_path\": upstream_distribution[\"base_path\"],\n }\n\n def create_or_update_distribution(self, repository, upstream_distribution):\n distribution_data = self.distribution_data(repository, upstream_distribution)\n try:\n distro = self.distribution_model_cls.objects.get(\n name=upstream_distribution[\"name\"], pulp_domain=self.domain\n )\n # Check that the distribution has the right repository associated\n needs_update = self.needs_update(distribution_data, distro)\n if needs_update:\n # Update the distribution\n dispatch(\n general_update,\n task_group=self.task_group,\n shared_resources=[repository],\n exclusive_resources=self.distros_uris,\n args=(distro.pk, self.app_label, self.distribution_serializer_name),\n kwargs={\n \"data\": distribution_data,\n \"partial\": True,\n },\n )\n except self.distribution_model_cls.DoesNotExist:\n # Dispatch a task to create the distribution\n distribution_data[\"name\"] = upstream_distribution[\"name\"]\n dispatch(\n general_create,\n task_group=self.task_group,\n shared_resources=[repository],\n exclusive_resources=self.distros_uris,\n args=(self.app_label, self.distribution_serializer_name),\n kwargs={\"data\": distribution_data},\n )\n\n def sync_params(self, repository, remote):\n \"\"\"This method returns a dict that will be passed as kwargs to the sync task.\"\"\"\n raise NotImplementedError(\"Each replicator must supply its own sync params.\")\n\n def sync(self, repository, remote):\n dispatch(\n self.sync_task,\n task_group=self.task_group,\n shared_resources=[remote],\n exclusive_resources=[repository],\n kwargs=self.sync_params(repository, remote),\n )\n\n def remove_missing(self, names):\n # Remove all distributions with names not present in the list of names\n # Perform this in an extra task, because we hold a big lock here.\n distribution_ids = [\n (distribution.pk, self.app_label, self.distribution_serializer_name)\n for distribution in self.distribution_model_cls.objects.filter(\n pulp_domain=self.domain\n ).exclude(name__in=names)\n ]\n if distribution_ids:\n dispatch(\n general_multi_delete,\n task_group=self.task_group,\n exclusive_resources=self.distros_uris,\n args=(distribution_ids,),\n )\n\n # Remove all the repositories and remotes of the missing distributions\n repositories = list(\n self.repository_model_cls.objects.filter(\n pulp_domain=self.domain, user_hidden=False\n ).exclude(name__in=names)\n )\n repository_ids = [\n (repo.pk, self.app_label, self.repository_serializer_name) for repo in repositories\n ]\n\n remotes = list(\n self.remote_model_cls.objects.filter(pulp_domain=self.domain).exclude(name__in=names)\n )\n remote_ids = [\n (remote.pk, self.app_label, self.remote_serializer_name) for remote in remotes\n ]\n\n if repository_ids or remote_ids:\n dispatch(\n general_multi_delete,\n task_group=self.task_group,\n exclusive_resources=repositories + remotes,\n args=(repository_ids + remote_ids,),\n )\n", "path": "pulpcore/app/replica.py"}], "after_files": [{"content": "from django.db.models import Model\nimport logging\n\nfrom pulp_glue.common.context import PulpContext\nfrom pulpcore.tasking.tasks import dispatch\nfrom pulpcore.app.tasks.base import (\n general_update,\n general_create,\n general_multi_delete,\n)\nfrom pulpcore.plugin.util import get_url, get_domain\n\n_logger = logging.getLogger(__name__)\n\n\nclass ReplicaContext(PulpContext):\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n self.out_buf = \"\"\n self.err_buf = \"\"\n\n def echo(self, message: str, nl: bool = True, err: bool = False) -> None:\n if err:\n self.err_buf += message\n if nl:\n _logger.warn(\"{}\", self.err_buf)\n self.err_buf = \"\"\n else:\n self.out_buf += message\n if nl:\n _logger.info(\"{}\", self.out_buf)\n self.out_buf = \"\"\n\n\nclass Replicator:\n distribution_ctx_cls = None\n repository_ctx_cls = None\n publication_ctx_cls = None\n remote_model_cls = None\n repository_model_cls = None\n distribution_model_cls = None\n distribution_serializer_name = None\n repository_serializer_name = None\n remote_serializer_name = None\n app_label = None\n sync_task = None\n\n def __init__(self, pulp_ctx, task_group, tls_settings):\n \"\"\"\n :param pulp_ctx: PulpReplicaContext\n :param task_group: TaskGroup\n :param ca_cert: str\n \"\"\"\n self.pulp_ctx = pulp_ctx\n self.task_group = task_group\n self.tls_settings = tls_settings\n self.domain = get_domain()\n self.distros_uris = [f\"pdrn:{self.domain.pulp_id}:distributions\"]\n\n @staticmethod\n def needs_update(fields_dict, model_instance):\n \"\"\"\n Compares a Model instance's attributes against a dictionary where keys are attribute\n names and values are expected values.\n \"\"\"\n needs_update = False\n for field_name, value in fields_dict.items():\n if isinstance(getattr(model_instance, field_name), Model):\n if get_url(getattr(model_instance, field_name)) != value:\n needs_update = True\n elif getattr(model_instance, field_name) != value:\n needs_update = True\n return needs_update\n\n def upstream_distributions(self, labels=None):\n if labels:\n params = {\"pulp_label_select\": labels}\n else:\n params = {}\n offset = 0\n list_size = 100\n while True:\n distributions = self.distribution_ctx_cls(self.pulp_ctx).list(list_size, offset, params)\n for distro in distributions:\n yield distro\n if len(distributions) < list_size:\n break\n offset += list_size\n\n def url(self, upstream_distribution):\n return upstream_distribution[\"base_url\"]\n\n def remote_extra_fields(self, upstream_distribution):\n return {}\n\n def create_or_update_remote(self, upstream_distribution):\n if not upstream_distribution.get(\"repository\") and not upstream_distribution.get(\n \"publication\"\n ):\n return None\n url = self.url(upstream_distribution)\n remote_fields_dict = {\"url\": url}\n remote_fields_dict.update(self.tls_settings)\n remote_fields_dict.update(self.remote_extra_fields(upstream_distribution))\n\n # Check if there is a remote pointing to this distribution\n try:\n remote = self.remote_model_cls.objects.get(\n name=upstream_distribution[\"name\"], pulp_domain=self.domain\n )\n needs_update = self.needs_update(remote_fields_dict, remote)\n if needs_update:\n dispatch(\n general_update,\n task_group=self.task_group,\n exclusive_resources=[remote],\n args=(remote.pk, self.app_label, self.remote_serializer_name),\n kwargs={\"data\": remote_fields_dict, \"partial\": True},\n )\n except self.remote_model_cls.DoesNotExist:\n # Create the remote\n remote = self.remote_model_cls(name=upstream_distribution[\"name\"], **remote_fields_dict)\n remote.save()\n\n return remote\n\n def repository_extra_fields(self, remote):\n return {}\n\n def create_or_update_repository(self, remote):\n try:\n repository = self.repository_model_cls.objects.get(\n name=remote.name, pulp_domain=self.domain\n )\n repo_fields_dict = self.repository_extra_fields(remote)\n needs_update = self.needs_update(repo_fields_dict, repository)\n if needs_update:\n dispatch(\n general_update,\n task_group=self.task_group,\n exclusive_resources=[repository],\n args=(repository.pk, self.app_label, self.repository_serializer_name),\n kwargs={\"data\": repo_fields_dict, \"partial\": True},\n )\n except self.repository_model_cls.DoesNotExist:\n repository = self.repository_model_cls(\n name=remote.name, **self.repository_extra_fields(remote)\n )\n repository.save()\n return repository\n\n def distribution_data(self, repository, upstream_distribution):\n \"\"\"\n Return the fields that need to be updated/cleared on distributions for idempotence.\n \"\"\"\n return {\n \"repository\": get_url(repository),\n \"publication\": None,\n \"base_path\": upstream_distribution[\"base_path\"],\n }\n\n def create_or_update_distribution(self, repository, upstream_distribution):\n distribution_data = self.distribution_data(repository, upstream_distribution)\n try:\n distro = self.distribution_model_cls.objects.get(\n name=upstream_distribution[\"name\"], pulp_domain=self.domain\n )\n # Check that the distribution has the right repository associated\n needs_update = self.needs_update(distribution_data, distro)\n if needs_update:\n # Update the distribution\n dispatch(\n general_update,\n task_group=self.task_group,\n shared_resources=[repository],\n exclusive_resources=self.distros_uris,\n args=(distro.pk, self.app_label, self.distribution_serializer_name),\n kwargs={\n \"data\": distribution_data,\n \"partial\": True,\n },\n )\n except self.distribution_model_cls.DoesNotExist:\n # Dispatch a task to create the distribution\n distribution_data[\"name\"] = upstream_distribution[\"name\"]\n dispatch(\n general_create,\n task_group=self.task_group,\n shared_resources=[repository],\n exclusive_resources=self.distros_uris,\n args=(self.app_label, self.distribution_serializer_name),\n kwargs={\"data\": distribution_data},\n )\n\n def sync_params(self, repository, remote):\n \"\"\"This method returns a dict that will be passed as kwargs to the sync task.\"\"\"\n raise NotImplementedError(\"Each replicator must supply its own sync params.\")\n\n def sync(self, repository, remote):\n dispatch(\n self.sync_task,\n task_group=self.task_group,\n shared_resources=[remote],\n exclusive_resources=[repository],\n kwargs=self.sync_params(repository, remote),\n )\n\n def remove_missing(self, names):\n # Remove all distributions with names not present in the list of names\n # Perform this in an extra task, because we hold a big lock here.\n distribution_ids = [\n (distribution.pk, self.app_label, self.distribution_serializer_name)\n for distribution in self.distribution_model_cls.objects.filter(\n pulp_domain=self.domain\n ).exclude(name__in=names)\n ]\n if distribution_ids:\n dispatch(\n general_multi_delete,\n task_group=self.task_group,\n exclusive_resources=self.distros_uris,\n args=(distribution_ids,),\n )\n\n # Remove all the repositories and remotes of the missing distributions\n repositories = list(\n self.repository_model_cls.objects.filter(\n pulp_domain=self.domain, user_hidden=False\n ).exclude(name__in=names)\n )\n repository_ids = [\n (repo.pk, self.app_label, self.repository_serializer_name) for repo in repositories\n ]\n\n remotes = list(\n self.remote_model_cls.objects.filter(pulp_domain=self.domain).exclude(name__in=names)\n )\n remote_ids = [\n (remote.pk, self.app_label, self.remote_serializer_name) for remote in remotes\n ]\n\n if repository_ids or remote_ids:\n dispatch(\n general_multi_delete,\n task_group=self.task_group,\n exclusive_resources=repositories + remotes,\n args=(repository_ids + remote_ids,),\n )\n", "path": "pulpcore/app/replica.py"}]}
| 2,817 | 134 |
gh_patches_debug_20975
|
rasdani/github-patches
|
git_diff
|
holoviz__panel-1318
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
DataFrame widget raises exception if two columns have the same names
Panel: 0.7
#### Description of expected behavior and the observed behavior
Normally I don't have the same column names for my dataframes. But I was trying to reproduce this dashboard https://getbootstrap.com/docs/4.3/examples/dashboard/ and they have the same column names in multiple columns.
I can see that the panel.widgets.DataFrame does not support this. I would have expected it to support this situation.
#### Complete, minimal, self-contained example code that reproduces the issue
```python
import panel as pn
import pandas as pd
table_data = pd.DataFrame([(1001, "Lorem"),], columns=["Header", "Header"])
pn.widgets.DataFrame(table_data).servable()
```
#### Stack traceback and/or browser JavaScript console output
```bash
$ python -m panel serve 'scripts\issue2.py' --dev
2019-11-29 09:00:56,834 Starting Bokeh server version 1.4.0 (running on Tornado 6.0.3)
2019-11-29 09:00:56,836 User authentication hooks NOT provided (default user enabled)
2019-11-29 09:00:56,840 Bokeh app running at: http://localhost:5006/issue2
2019-11-29 09:00:56,840 Starting Bokeh server with process id: 10992
2019-11-29 09:00:58,603 Error running application handler <bokeh.application.handlers.script.ScriptHandler object at 0x00000028FF59DD48>: 'DataFrame' object has no attribute 'dtype'
File "generic.py", line 5179, in __getattr__:
return object.__getattribute__(self, name) Traceback (most recent call last):
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\bokeh\application\handlers\code_runner.py", line 179, in run
exec(self._code, module.__dict__)
File "C:\repos\private\awesome-panel\scripts\issue2.py", line 5, in <module>
pn.widgets.DataFrame(table_data).servable()
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\panel\viewable.py", line 525, in servable
self.server_doc(title=title)
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\panel\viewable.py", line 498, in server_doc
model = self.get_root(doc)
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\panel\viewable.py", line 434, in get_root
root = self._get_model(doc, comm=comm)
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\panel\widgets\tables.py", line 112, in _get_model
model = DataTable(**self._get_properties())
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\panel\widgets\tables.py", line 99, in _get_properties
props['columns'] = self._get_columns()
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\panel\widgets\tables.py", line 61, in _get_columns
kind = data.dtype.kind
File "C:\repos\private\awesome-panel\.venv\lib\site-packages\pandas\core\generic.py", line 5179, in __getattr__
return object.__getattribute__(self, name)
AttributeError: 'DataFrame' object has no attribute 'dtype'
2019-11-29 09:00:58,990 WebSocket connection opened
2019-11-29 09:00:58,991 ServerConnection created
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `panel/widgets/tables.py`
Content:
```
1 from __future__ import absolute_import, division, unicode_literals
2
3 import numpy as np
4 import param
5
6 from bokeh.models import ColumnDataSource
7 from bokeh.models.widgets import (
8 DataTable, TableColumn, NumberEditor, NumberFormatter,
9 DateFormatter, DateEditor, StringFormatter, StringEditor, IntEditor
10 )
11
12 from ..viewable import Layoutable
13 from ..util import isdatetime
14 from .base import Widget
15
16
17 class DataFrame(Widget):
18
19 editors = param.Dict(default={}, doc="""
20 Bokeh CellEditor to use for a particular column
21 (overrides the default chosen based on the type).""")
22
23 formatters = param.Dict(default={}, doc="""
24 Bokeh CellFormatter to use for a particular column
25 (overrides the default chosen based on the type).""")
26
27 fit_columns = param.Boolean(default=True, doc="""
28 Whether columns should expand to the available width. This
29 results in no horizontal scrollbar showing up, but data can
30 get unreadable if there is no enough space available.""")
31
32 selection = param.List(default=[], doc="""
33 The currently selected rows of the table.""")
34
35 row_height = param.Integer(default=25, doc="""
36 The height of each table row.""")
37
38 widths = param.Dict(default={}, doc="""
39 A mapping from column name to column width.""")
40
41 value = param.Parameter(default=None)
42
43 _rename = {'editors': None, 'formatters': None, 'widths': None,
44 'disabled': None}
45
46 _manual_params = ['value', 'editors', 'formatters', 'selection', 'widths']
47
48 def __init__(self, value=None, **params):
49 super(DataFrame, self).__init__(value=value, **params)
50 self._renamed_cols = {}
51
52 def _get_columns(self):
53 if self.value is None:
54 return []
55
56 index = [self.value.index.name or 'index']
57 col_names = index + list(self.value.columns)
58 columns = []
59 for col in col_names:
60 if col in self.value.columns:
61 data = self.value[col]
62 else:
63 data = self.value.index
64 kind = data.dtype.kind
65 if kind == 'i':
66 formatter = NumberFormatter()
67 editor = IntEditor()
68 elif kind == 'f':
69 formatter = NumberFormatter(format='0,0.0[00000]')
70 editor = NumberEditor()
71 elif isdatetime(data) or kind == 'M':
72 formatter = DateFormatter(format='%Y-%m-%d %H:%M:%S')
73 editor = DateEditor()
74 else:
75 formatter = StringFormatter()
76 editor = StringEditor()
77
78 if col in self.editors:
79 editor = self.editors[col]
80 if col in self.formatters:
81 formatter = self.formatters[col]
82 if str(col) != col:
83 self._renamed_cols[str(col)] = col
84 width = self.widths.get(str(col))
85 column = TableColumn(field=str(col), title=str(col),
86 editor=editor, formatter=formatter,
87 width=width)
88 columns.append(column)
89 return columns
90
91 def _get_properties(self):
92 props = {p : getattr(self, p) for p in list(Layoutable.param)
93 if getattr(self, p) is not None}
94 if self.value is None:
95 data = {}
96 else:
97 data = {k if isinstance(k, str) else str(k): v
98 for k, v in ColumnDataSource.from_df(self.value).items()}
99 if props.get('height', None) is None:
100 length = max([len(v) for v in data.values()]) if data else 0
101 props['height'] = length * self.row_height + 30
102 props['source'] = ColumnDataSource(data=data)
103 props['columns'] = self._get_columns()
104 props['index_position'] = None
105 props['fit_columns'] = self.fit_columns
106 props['row_height'] = self.row_height
107 props['editable'] = not self.disabled
108 return props
109
110 def _process_param_change(self, msg):
111 if 'disabled' in msg:
112 msg['editable'] = not msg.pop('disabled')
113 return super(DataFrame, self)._process_param_change(msg)
114
115 def _get_model(self, doc, root=None, parent=None, comm=None):
116 model = DataTable(**self._get_properties())
117 if root is None:
118 root = model
119 self._link_props(model.source, ['data', ('patching', 'data')], doc, root, comm)
120 self._link_props(model.source.selected, ['indices'], doc, root, comm)
121 self._models[root.ref['id']] = (model, parent)
122 return model
123
124 def _manual_update(self, events, model, doc, root, parent, comm):
125 for event in events:
126 if event.name == 'value':
127 cds = model.source
128 data = {k if isinstance(k, str) else str(k): v
129 for k, v in ColumnDataSource.from_df(self.value).items()}
130 cds.data = data
131 model.columns = self._get_columns()
132 elif event.name == 'selection':
133 model.source.selected.indices = self.selection
134 else:
135 for col in model.columns:
136 if col.name in self.editors:
137 col.editor = self.editors[col.name]
138 if col.name in self.formatters:
139 col.formatter = self.formatters[col.name]
140 if col.name in self.widths:
141 col.width = self.widths[col.name]
142
143 def _process_events(self, events):
144 if 'data' in events:
145 data = events.pop('data')
146 updated = False
147 for k, v in data.items():
148 if k == 'index':
149 continue
150 k = self._renamed_cols.get(k, k)
151 if isinstance(v, dict):
152 v = [v for _, v in sorted(v.items(), key=lambda it: int(it[0]))]
153 try:
154 isequal = (self.value[k].values == np.asarray(v)).all()
155 except Exception:
156 isequal = False
157 if not isequal:
158 self.value[k] = v
159 updated = True
160 if updated:
161 self.param.trigger('value')
162 if 'indices' in events:
163 self.selection = events.pop('indices')
164 super(DataFrame, self)._process_events(events)
165
166 @property
167 def selected_dataframe(self):
168 """
169 Returns a DataFrame of the currently selected rows.
170 """
171 if not self.selection:
172 return self.value
173 return self.value.iloc[self.selection]
174
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/panel/widgets/tables.py b/panel/widgets/tables.py
--- a/panel/widgets/tables.py
+++ b/panel/widgets/tables.py
@@ -47,8 +47,18 @@
def __init__(self, value=None, **params):
super(DataFrame, self).__init__(value=value, **params)
+ self.param.watch(self._validate, 'value')
+ self._validate(None)
self._renamed_cols = {}
+ def _validate(self, event):
+ if self.value is None:
+ return
+ cols = self.value.columns
+ if len(cols) != len(cols.drop_duplicates()):
+ raise ValueError('Cannot display a pandas.DataFrame with '
+ 'duplicate column names.')
+
def _get_columns(self):
if self.value is None:
return []
@@ -122,6 +132,7 @@
return model
def _manual_update(self, events, model, doc, root, parent, comm):
+ self._validate(None)
for event in events:
if event.name == 'value':
cds = model.source
|
{"golden_diff": "diff --git a/panel/widgets/tables.py b/panel/widgets/tables.py\n--- a/panel/widgets/tables.py\n+++ b/panel/widgets/tables.py\n@@ -47,8 +47,18 @@\n \n def __init__(self, value=None, **params):\n super(DataFrame, self).__init__(value=value, **params)\n+ self.param.watch(self._validate, 'value')\n+ self._validate(None)\n self._renamed_cols = {}\n \n+ def _validate(self, event):\n+ if self.value is None:\n+ return\n+ cols = self.value.columns\n+ if len(cols) != len(cols.drop_duplicates()):\n+ raise ValueError('Cannot display a pandas.DataFrame with '\n+ 'duplicate column names.')\n+\n def _get_columns(self):\n if self.value is None:\n return []\n@@ -122,6 +132,7 @@\n return model\n \n def _manual_update(self, events, model, doc, root, parent, comm):\n+ self._validate(None)\n for event in events:\n if event.name == 'value':\n cds = model.source\n", "issue": "DataFrame widget raises exception if two columns have the same names\nPanel: 0.7\r\n\r\n#### Description of expected behavior and the observed behavior\r\n\r\nNormally I don't have the same column names for my dataframes. But I was trying to reproduce this dashboard https://getbootstrap.com/docs/4.3/examples/dashboard/ and they have the same column names in multiple columns.\r\n\r\nI can see that the panel.widgets.DataFrame does not support this. I would have expected it to support this situation.\r\n\r\n#### Complete, minimal, self-contained example code that reproduces the issue\r\n\r\n```python\r\nimport panel as pn\r\nimport pandas as pd\r\n\r\ntable_data = pd.DataFrame([(1001, \"Lorem\"),], columns=[\"Header\", \"Header\"])\r\npn.widgets.DataFrame(table_data).servable()\r\n```\r\n#### Stack traceback and/or browser JavaScript console output\r\n\r\n```bash\r\n$ python -m panel serve 'scripts\\issue2.py' --dev\r\n2019-11-29 09:00:56,834 Starting Bokeh server version 1.4.0 (running on Tornado 6.0.3)\r\n2019-11-29 09:00:56,836 User authentication hooks NOT provided (default user enabled)\r\n2019-11-29 09:00:56,840 Bokeh app running at: http://localhost:5006/issue2\r\n2019-11-29 09:00:56,840 Starting Bokeh server with process id: 10992\r\n2019-11-29 09:00:58,603 Error running application handler <bokeh.application.handlers.script.ScriptHandler object at 0x00000028FF59DD48>: 'DataFrame' object has no attribute 'dtype'\r\nFile \"generic.py\", line 5179, in __getattr__:\r\nreturn object.__getattribute__(self, name) Traceback (most recent call last):\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\bokeh\\application\\handlers\\code_runner.py\", line 179, in run\r\n exec(self._code, module.__dict__)\r\n File \"C:\\repos\\private\\awesome-panel\\scripts\\issue2.py\", line 5, in <module>\r\n pn.widgets.DataFrame(table_data).servable()\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\panel\\viewable.py\", line 525, in servable\r\n self.server_doc(title=title)\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\panel\\viewable.py\", line 498, in server_doc\r\n model = self.get_root(doc)\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\panel\\viewable.py\", line 434, in get_root\r\n root = self._get_model(doc, comm=comm)\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\panel\\widgets\\tables.py\", line 112, in _get_model\r\n model = DataTable(**self._get_properties())\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\panel\\widgets\\tables.py\", line 99, in _get_properties\r\n props['columns'] = self._get_columns()\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\panel\\widgets\\tables.py\", line 61, in _get_columns\r\n kind = data.dtype.kind\r\n File \"C:\\repos\\private\\awesome-panel\\.venv\\lib\\site-packages\\pandas\\core\\generic.py\", line 5179, in __getattr__\r\n return object.__getattribute__(self, name)\r\nAttributeError: 'DataFrame' object has no attribute 'dtype'\r\n\r\n2019-11-29 09:00:58,990 WebSocket connection opened\r\n2019-11-29 09:00:58,991 ServerConnection created\r\n```\n", "before_files": [{"content": "from __future__ import absolute_import, division, unicode_literals\n\nimport numpy as np\nimport param\n\nfrom bokeh.models import ColumnDataSource\nfrom bokeh.models.widgets import (\n DataTable, TableColumn, NumberEditor, NumberFormatter,\n DateFormatter, DateEditor, StringFormatter, StringEditor, IntEditor\n)\n\nfrom ..viewable import Layoutable\nfrom ..util import isdatetime\nfrom .base import Widget\n\n\nclass DataFrame(Widget):\n\n editors = param.Dict(default={}, doc=\"\"\"\n Bokeh CellEditor to use for a particular column\n (overrides the default chosen based on the type).\"\"\")\n\n formatters = param.Dict(default={}, doc=\"\"\"\n Bokeh CellFormatter to use for a particular column\n (overrides the default chosen based on the type).\"\"\")\n\n fit_columns = param.Boolean(default=True, doc=\"\"\"\n Whether columns should expand to the available width. This\n results in no horizontal scrollbar showing up, but data can\n get unreadable if there is no enough space available.\"\"\")\n\n selection = param.List(default=[], doc=\"\"\"\n The currently selected rows of the table.\"\"\")\n\n row_height = param.Integer(default=25, doc=\"\"\"\n The height of each table row.\"\"\")\n\n widths = param.Dict(default={}, doc=\"\"\"\n A mapping from column name to column width.\"\"\")\n\n value = param.Parameter(default=None)\n\n _rename = {'editors': None, 'formatters': None, 'widths': None,\n 'disabled': None}\n\n _manual_params = ['value', 'editors', 'formatters', 'selection', 'widths']\n\n def __init__(self, value=None, **params):\n super(DataFrame, self).__init__(value=value, **params)\n self._renamed_cols = {}\n\n def _get_columns(self):\n if self.value is None:\n return []\n\n index = [self.value.index.name or 'index']\n col_names = index + list(self.value.columns)\n columns = []\n for col in col_names:\n if col in self.value.columns:\n data = self.value[col]\n else:\n data = self.value.index\n kind = data.dtype.kind\n if kind == 'i':\n formatter = NumberFormatter()\n editor = IntEditor()\n elif kind == 'f':\n formatter = NumberFormatter(format='0,0.0[00000]')\n editor = NumberEditor()\n elif isdatetime(data) or kind == 'M':\n formatter = DateFormatter(format='%Y-%m-%d %H:%M:%S')\n editor = DateEditor()\n else:\n formatter = StringFormatter()\n editor = StringEditor()\n\n if col in self.editors:\n editor = self.editors[col]\n if col in self.formatters:\n formatter = self.formatters[col]\n if str(col) != col:\n self._renamed_cols[str(col)] = col\n width = self.widths.get(str(col))\n column = TableColumn(field=str(col), title=str(col),\n editor=editor, formatter=formatter,\n width=width)\n columns.append(column)\n return columns\n\n def _get_properties(self):\n props = {p : getattr(self, p) for p in list(Layoutable.param)\n if getattr(self, p) is not None}\n if self.value is None:\n data = {}\n else:\n data = {k if isinstance(k, str) else str(k): v\n for k, v in ColumnDataSource.from_df(self.value).items()}\n if props.get('height', None) is None:\n length = max([len(v) for v in data.values()]) if data else 0\n props['height'] = length * self.row_height + 30\n props['source'] = ColumnDataSource(data=data)\n props['columns'] = self._get_columns()\n props['index_position'] = None\n props['fit_columns'] = self.fit_columns\n props['row_height'] = self.row_height\n props['editable'] = not self.disabled\n return props\n\n def _process_param_change(self, msg):\n if 'disabled' in msg:\n msg['editable'] = not msg.pop('disabled')\n return super(DataFrame, self)._process_param_change(msg)\n \n def _get_model(self, doc, root=None, parent=None, comm=None):\n model = DataTable(**self._get_properties())\n if root is None:\n root = model\n self._link_props(model.source, ['data', ('patching', 'data')], doc, root, comm)\n self._link_props(model.source.selected, ['indices'], doc, root, comm)\n self._models[root.ref['id']] = (model, parent)\n return model\n\n def _manual_update(self, events, model, doc, root, parent, comm):\n for event in events:\n if event.name == 'value':\n cds = model.source\n data = {k if isinstance(k, str) else str(k): v\n for k, v in ColumnDataSource.from_df(self.value).items()}\n cds.data = data\n model.columns = self._get_columns()\n elif event.name == 'selection':\n model.source.selected.indices = self.selection\n else:\n for col in model.columns:\n if col.name in self.editors:\n col.editor = self.editors[col.name]\n if col.name in self.formatters:\n col.formatter = self.formatters[col.name]\n if col.name in self.widths:\n col.width = self.widths[col.name]\n\n def _process_events(self, events):\n if 'data' in events:\n data = events.pop('data')\n updated = False\n for k, v in data.items():\n if k == 'index':\n continue\n k = self._renamed_cols.get(k, k)\n if isinstance(v, dict):\n v = [v for _, v in sorted(v.items(), key=lambda it: int(it[0]))]\n try:\n isequal = (self.value[k].values == np.asarray(v)).all()\n except Exception:\n isequal = False\n if not isequal:\n self.value[k] = v\n updated = True\n if updated:\n self.param.trigger('value')\n if 'indices' in events:\n self.selection = events.pop('indices')\n super(DataFrame, self)._process_events(events)\n\n @property\n def selected_dataframe(self):\n \"\"\"\n Returns a DataFrame of the currently selected rows.\n \"\"\"\n if not self.selection:\n return self.value\n return self.value.iloc[self.selection]\n", "path": "panel/widgets/tables.py"}], "after_files": [{"content": "from __future__ import absolute_import, division, unicode_literals\n\nimport numpy as np\nimport param\n\nfrom bokeh.models import ColumnDataSource\nfrom bokeh.models.widgets import (\n DataTable, TableColumn, NumberEditor, NumberFormatter,\n DateFormatter, DateEditor, StringFormatter, StringEditor, IntEditor\n)\n\nfrom ..viewable import Layoutable\nfrom ..util import isdatetime\nfrom .base import Widget\n\n\nclass DataFrame(Widget):\n\n editors = param.Dict(default={}, doc=\"\"\"\n Bokeh CellEditor to use for a particular column\n (overrides the default chosen based on the type).\"\"\")\n\n formatters = param.Dict(default={}, doc=\"\"\"\n Bokeh CellFormatter to use for a particular column\n (overrides the default chosen based on the type).\"\"\")\n\n fit_columns = param.Boolean(default=True, doc=\"\"\"\n Whether columns should expand to the available width. This\n results in no horizontal scrollbar showing up, but data can\n get unreadable if there is no enough space available.\"\"\")\n\n selection = param.List(default=[], doc=\"\"\"\n The currently selected rows of the table.\"\"\")\n\n row_height = param.Integer(default=25, doc=\"\"\"\n The height of each table row.\"\"\")\n\n widths = param.Dict(default={}, doc=\"\"\"\n A mapping from column name to column width.\"\"\")\n\n value = param.Parameter(default=None)\n\n _rename = {'editors': None, 'formatters': None, 'widths': None,\n 'disabled': None}\n\n _manual_params = ['value', 'editors', 'formatters', 'selection', 'widths']\n\n def __init__(self, value=None, **params):\n super(DataFrame, self).__init__(value=value, **params)\n self.param.watch(self._validate, 'value')\n self._validate(None)\n self._renamed_cols = {}\n\n def _validate(self, event):\n if self.value is None:\n return\n cols = self.value.columns\n if len(cols) != len(cols.drop_duplicates()):\n raise ValueError('Cannot display a pandas.DataFrame with '\n 'duplicate column names.')\n\n def _get_columns(self):\n if self.value is None:\n return []\n\n index = [self.value.index.name or 'index']\n col_names = index + list(self.value.columns)\n columns = []\n for col in col_names:\n if col in self.value.columns:\n data = self.value[col]\n else:\n data = self.value.index\n kind = data.dtype.kind\n if kind == 'i':\n formatter = NumberFormatter()\n editor = IntEditor()\n elif kind == 'f':\n formatter = NumberFormatter(format='0,0.0[00000]')\n editor = NumberEditor()\n elif isdatetime(data) or kind == 'M':\n formatter = DateFormatter(format='%Y-%m-%d %H:%M:%S')\n editor = DateEditor()\n else:\n formatter = StringFormatter()\n editor = StringEditor()\n\n if col in self.editors:\n editor = self.editors[col]\n if col in self.formatters:\n formatter = self.formatters[col]\n if str(col) != col:\n self._renamed_cols[str(col)] = col\n width = self.widths.get(str(col))\n column = TableColumn(field=str(col), title=str(col),\n editor=editor, formatter=formatter,\n width=width)\n columns.append(column)\n return columns\n\n def _get_properties(self):\n props = {p : getattr(self, p) for p in list(Layoutable.param)\n if getattr(self, p) is not None}\n if self.value is None:\n data = {}\n else:\n data = {k if isinstance(k, str) else str(k): v\n for k, v in ColumnDataSource.from_df(self.value).items()}\n if props.get('height', None) is None:\n length = max([len(v) for v in data.values()]) if data else 0\n props['height'] = length * self.row_height + 30\n props['source'] = ColumnDataSource(data=data)\n props['columns'] = self._get_columns()\n props['index_position'] = None\n props['fit_columns'] = self.fit_columns\n props['row_height'] = self.row_height\n props['editable'] = not self.disabled\n return props\n\n def _process_param_change(self, msg):\n if 'disabled' in msg:\n msg['editable'] = not msg.pop('disabled')\n return super(DataFrame, self)._process_param_change(msg)\n \n def _get_model(self, doc, root=None, parent=None, comm=None):\n model = DataTable(**self._get_properties())\n if root is None:\n root = model\n self._link_props(model.source, ['data', ('patching', 'data')], doc, root, comm)\n self._link_props(model.source.selected, ['indices'], doc, root, comm)\n self._models[root.ref['id']] = (model, parent)\n return model\n\n def _manual_update(self, events, model, doc, root, parent, comm):\n self._validate(None)\n for event in events:\n if event.name == 'value':\n cds = model.source\n data = {k if isinstance(k, str) else str(k): v\n for k, v in ColumnDataSource.from_df(self.value).items()}\n cds.data = data\n model.columns = self._get_columns()\n elif event.name == 'selection':\n model.source.selected.indices = self.selection\n else:\n for col in model.columns:\n if col.name in self.editors:\n col.editor = self.editors[col.name]\n if col.name in self.formatters:\n col.formatter = self.formatters[col.name]\n if col.name in self.widths:\n col.width = self.widths[col.name]\n\n def _process_events(self, events):\n if 'data' in events:\n data = events.pop('data')\n updated = False\n for k, v in data.items():\n if k == 'index':\n continue\n k = self._renamed_cols.get(k, k)\n if isinstance(v, dict):\n v = [v for _, v in sorted(v.items(), key=lambda it: int(it[0]))]\n try:\n isequal = (self.value[k].values == np.asarray(v)).all()\n except Exception:\n isequal = False\n if not isequal:\n self.value[k] = v\n updated = True\n if updated:\n self.param.trigger('value')\n if 'indices' in events:\n self.selection = events.pop('indices')\n super(DataFrame, self)._process_events(events)\n\n @property\n def selected_dataframe(self):\n \"\"\"\n Returns a DataFrame of the currently selected rows.\n \"\"\"\n if not self.selection:\n return self.value\n return self.value.iloc[self.selection]\n", "path": "panel/widgets/tables.py"}]}
| 3,006 | 248 |
gh_patches_debug_42532
|
rasdani/github-patches
|
git_diff
|
kserve__kserve-1343
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Support cloud events for KFServing custom framework
/kind feature
**Describe the solution you'd like**
As a user when doing feature transformation the payload can be protobuf/avro or some other binary format delivered via HTTP or KAFKA in cloudevent binary format(https://github.com/cloudevents/spec/blob/v1.0.1/kafka-protocol-binding.md#32-binary-content-mode) but currently KFServing custom framework [only supports JSON](https://github.com/kubeflow/kfserving/blob/master/python/kfserving/kfserving/handlers/http.py#L51).
- I'd like to send cloud event to KFServer via KAFKA in following format and KFServer pass the decoded cloud event to `preprocess` or `predict` handler
```
------------------ Message -------------------
Topic Name: mytopic
------------------- key ----------------------
Key: mykey
------------------ headers -------------------
ce_specversion: "1.0"
ce_type: "com.example.someevent"
ce_source: "/mycontext/subcontext"
ce_id: "1234-1234-1234"
ce_time: "2018-04-05T03:56:24Z"
content-type: application/protobuf
------------------- value --------------------
... application data encoded in protobuf ...
-----------------------------------------------
consume http(cloudevent)
KAFKA ----------> Kafka Event Source -----------------> InferenceService
```
```python
def has_ce_headers(headers: typing.Dict[str, str]) -> bool:
return (
"ce-specversion" in headers
and "ce-source" in headers
and "ce-type" in headers
and "ce-id" in headers
)
if has_ce_headers(self.request.headers):
event = from_http(self.request.headers, self.request.body)
body = event['data']
else:
try:
body = json.loads(self.request.body)
except json.decoder.JSONDecodeError as e:
raise tornado.web.HTTPError(
status_code=HTTPStatus.BAD_REQUEST,
reason="Unrecognized request format: %s" % e)
```
- Currently HTTP headers are not exposed to the `preprocess` or `predict` handler, if a cloud event is sent to KFServer it is not possible for user to check the http headers which can be useful for tracing and examining the original event source(kafka or http).
`async def predict(self, request: Dict, headers: Dict) -> Dict:`
`async def preprocess(self, request: Dict, headers: Dict) -> Dict:`
- Also it would be nice if KFServing can generate cloud event response so that it works with knative eventing channels seamlessly.
**Anything else you would like to add:**
[Miscellaneous information that will assist in solving the issue.]
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `python/kfserving/kfserving/handlers/http.py`
Content:
```
1 # Copyright 2020 kubeflow.org.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 import inspect
16 import tornado.web
17 import json
18 from http import HTTPStatus
19 from kfserving.kfmodel_repository import KFModelRepository
20
21
22 class HTTPHandler(tornado.web.RequestHandler):
23 def initialize(self, models: KFModelRepository):
24 self.models = models # pylint:disable=attribute-defined-outside-init
25
26 def get_model(self, name: str):
27 model = self.models.get_model(name)
28 if model is None:
29 raise tornado.web.HTTPError(
30 status_code=HTTPStatus.NOT_FOUND,
31 reason="Model with name %s does not exist." % name
32 )
33 if not model.ready:
34 model.load()
35 return model
36
37 def validate(self, request):
38 if ("instances" in request and not isinstance(request["instances"], list)) or \
39 ("inputs" in request and not isinstance(request["inputs"], list)):
40 raise tornado.web.HTTPError(
41 status_code=HTTPStatus.BAD_REQUEST,
42 reason="Expected \"instances\" or \"inputs\" to be a list"
43 )
44 return request
45
46
47 class PredictHandler(HTTPHandler):
48 async def post(self, name: str):
49 model = self.get_model(name)
50 try:
51 body = json.loads(self.request.body)
52 except json.decoder.JSONDecodeError as e:
53 raise tornado.web.HTTPError(
54 status_code=HTTPStatus.BAD_REQUEST,
55 reason="Unrecognized request format: %s" % e
56 )
57 request = model.preprocess(body)
58 request = self.validate(request)
59 response = (await model.predict(request)) if inspect.iscoroutinefunction(model.predict) else model.predict(request)
60 response = model.postprocess(response)
61 self.write(response)
62
63
64 class ExplainHandler(HTTPHandler):
65 async def post(self, name: str):
66 model = self.get_model(name)
67 try:
68 body = json.loads(self.request.body)
69 except json.decoder.JSONDecodeError as e:
70 raise tornado.web.HTTPError(
71 status_code=HTTPStatus.BAD_REQUEST,
72 reason="Unrecognized request format: %s" % e
73 )
74 request = model.preprocess(body)
75 request = self.validate(request)
76 response = (await model.explain(request)) if inspect.iscoroutinefunction(model.explain) else model.explain(request)
77 response = model.postprocess(response)
78 self.write(response)
79
```
Path: `python/kfserving/kfserving/kfmodel.py`
Content:
```
1 # Copyright 2020 kubeflow.org.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 from typing import Dict
16 import sys
17
18 import json
19 import tornado.web
20 from tornado.httpclient import AsyncHTTPClient
21
22 PREDICTOR_URL_FORMAT = "http://{0}/v1/models/{1}:predict"
23 EXPLAINER_URL_FORMAT = "http://{0}/v1/models/{1}:explain"
24 PREDICTOR_V2_URL_FORMAT = "http://{0}/v2/models/{1}/infer"
25 EXPLAINER_V2_URL_FORMAT = "http://{0}/v2/models/{1}/explain"
26
27
28 # KFModel is intended to be subclassed by various components within KFServing.
29 class KFModel:
30
31 def __init__(self, name: str):
32 self.name = name
33 self.ready = False
34 self.protocol = "v1"
35 self.predictor_host = None
36 self.explainer_host = None
37 # The timeout matches what is set in generated Istio resources.
38 # We generally don't want things to time out at the request level here,
39 # timeouts should be handled elsewhere in the system.
40 self.timeout = 600
41 self._http_client_instance = None
42
43 @property
44 def _http_client(self):
45 if self._http_client_instance is None:
46 self._http_client_instance = AsyncHTTPClient(max_clients=sys.maxsize)
47 return self._http_client_instance
48
49 def load(self) -> bool:
50 self.ready = True
51 return self.ready
52
53 def preprocess(self, request: Dict) -> Dict:
54 return request
55
56 def postprocess(self, request: Dict) -> Dict:
57 return request
58
59 async def predict(self, request: Dict) -> Dict:
60 if not self.predictor_host:
61 raise NotImplementedError
62 predict_url = PREDICTOR_URL_FORMAT.format(self.predictor_host, self.name)
63 if self.protocol == "v2":
64 predict_url = PREDICTOR_V2_URL_FORMAT.format(self.predictor_host, self.name)
65 response = await self._http_client.fetch(
66 predict_url,
67 method='POST',
68 request_timeout=self.timeout,
69 body=json.dumps(request)
70 )
71 if response.code != 200:
72 raise tornado.web.HTTPError(
73 status_code=response.code,
74 reason=response.body)
75 return json.loads(response.body)
76
77 async def explain(self, request: Dict) -> Dict:
78 if self.explainer_host is None:
79 raise NotImplementedError
80 explain_url = EXPLAINER_URL_FORMAT.format(self.predictor_host, self.name)
81 if self.protocol == "v2":
82 explain_url = EXPLAINER_V2_URL_FORMAT.format(self.predictor_host, self.name)
83 response = await self._http_client.fetch(
84 url=explain_url,
85 method='POST',
86 request_timeout=self.timeout,
87 body=json.dumps(request)
88 )
89 if response.code != 200:
90 raise tornado.web.HTTPError(
91 status_code=response.code,
92 reason=response.body)
93 return json.loads(response.body)
94
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/python/kfserving/kfserving/handlers/http.py b/python/kfserving/kfserving/handlers/http.py
--- a/python/kfserving/kfserving/handlers/http.py
+++ b/python/kfserving/kfserving/handlers/http.py
@@ -14,9 +14,15 @@
import inspect
import tornado.web
+import typing
import json
+import pytz
+import cloudevents.exceptions as ce
+from cloudevents.http import CloudEvent, from_http, is_binary, is_structured, to_binary, to_structured
+from cloudevents.sdk.converters.util import has_binary_headers
from http import HTTPStatus
from kfserving.kfmodel_repository import KFModelRepository
+from datetime import datetime
class HTTPHandler(tornado.web.RequestHandler):
@@ -43,21 +49,52 @@
)
return request
-
class PredictHandler(HTTPHandler):
async def post(self, name: str):
+ if has_binary_headers(self.request.headers):
+ try:
+ #Use default unmarshaller if contenttype is set in header
+ if "ce-contenttype" in self.request.headers:
+ body = from_http(self.request.headers, self.request.body)
+ else:
+ body = from_http(self.request.headers, self.request.body, lambda x: x)
+ except (ce.MissingRequiredFields, ce.InvalidRequiredFields, ce.InvalidStructuredJSON, ce.InvalidHeadersFormat, ce.DataMarshallerError, ce.DataUnmarshallerError) as e:
+ raise tornado.web.HTTPError(
+ status_code=HTTPStatus.BAD_REQUEST,
+ reason="Cloud Event Exceptions: %s" % e
+ )
+ else:
+ try:
+ body = json.loads(self.request.body)
+ except json.decoder.JSONDecodeError as e:
+ raise tornado.web.HTTPError(
+ status_code=HTTPStatus.BAD_REQUEST,
+ reason="Unrecognized request format: %s" % e
+ )
+
model = self.get_model(name)
- try:
- body = json.loads(self.request.body)
- except json.decoder.JSONDecodeError as e:
- raise tornado.web.HTTPError(
- status_code=HTTPStatus.BAD_REQUEST,
- reason="Unrecognized request format: %s" % e
- )
request = model.preprocess(body)
request = self.validate(request)
response = (await model.predict(request)) if inspect.iscoroutinefunction(model.predict) else model.predict(request)
response = model.postprocess(response)
+
+ if has_binary_headers(self.request.headers):
+ event = CloudEvent(body._attributes, response)
+ if is_binary(self.request.headers):
+ eventheader, eventbody = to_binary(event)
+ elif is_structured(self.request.headers):
+ eventheader, eventbody = to_structured(event)
+ for k, v in eventheader.items():
+ if k != "ce-time":
+ self.set_header(k, v)
+ else: #utc now() timestamp
+ self.set_header('ce-time', datetime.utcnow().replace(tzinfo=pytz.utc).strftime('%Y-%m-%dT%H:%M:%S.%f%z'))
+
+ if isinstance(eventbody, (bytes, bytearray)):
+ response = eventbody
+ else:
+ response = eventbody.data
+
self.write(response)
diff --git a/python/kfserving/kfserving/kfmodel.py b/python/kfserving/kfserving/kfmodel.py
--- a/python/kfserving/kfserving/kfmodel.py
+++ b/python/kfserving/kfserving/kfmodel.py
@@ -51,7 +51,16 @@
return self.ready
def preprocess(self, request: Dict) -> Dict:
- return request
+ # If cloudevent dict, then parse 'data' field. Otherwise, pass through.
+ if "data" in request \
+ and "time" in request \
+ and "type" in request \
+ and "source" in request \
+ and "id" in request \
+ and "specversion" in request:
+ return request["data"]
+ else:
+ return request
def postprocess(self, request: Dict) -> Dict:
return request
@@ -91,3 +100,4 @@
status_code=response.code,
reason=response.body)
return json.loads(response.body)
+
|
{"golden_diff": "diff --git a/python/kfserving/kfserving/handlers/http.py b/python/kfserving/kfserving/handlers/http.py\n--- a/python/kfserving/kfserving/handlers/http.py\n+++ b/python/kfserving/kfserving/handlers/http.py\n@@ -14,9 +14,15 @@\n \n import inspect\n import tornado.web\n+import typing\n import json\n+import pytz\n+import cloudevents.exceptions as ce\n+from cloudevents.http import CloudEvent, from_http, is_binary, is_structured, to_binary, to_structured\n+from cloudevents.sdk.converters.util import has_binary_headers\n from http import HTTPStatus\n from kfserving.kfmodel_repository import KFModelRepository\n+from datetime import datetime\n \n \n class HTTPHandler(tornado.web.RequestHandler):\n@@ -43,21 +49,52 @@\n )\n return request\n \n-\n class PredictHandler(HTTPHandler):\n async def post(self, name: str):\n+ if has_binary_headers(self.request.headers): \n+ try:\n+ #Use default unmarshaller if contenttype is set in header\n+ if \"ce-contenttype\" in self.request.headers:\n+ body = from_http(self.request.headers, self.request.body)\n+ else:\n+ body = from_http(self.request.headers, self.request.body, lambda x: x)\n+ except (ce.MissingRequiredFields, ce.InvalidRequiredFields, ce.InvalidStructuredJSON, ce.InvalidHeadersFormat, ce.DataMarshallerError, ce.DataUnmarshallerError) as e:\n+ raise tornado.web.HTTPError(\n+ status_code=HTTPStatus.BAD_REQUEST,\n+ reason=\"Cloud Event Exceptions: %s\" % e\n+ )\n+ else:\n+ try:\n+ body = json.loads(self.request.body)\n+ except json.decoder.JSONDecodeError as e:\n+ raise tornado.web.HTTPError(\n+ status_code=HTTPStatus.BAD_REQUEST,\n+ reason=\"Unrecognized request format: %s\" % e\n+ )\n+\n model = self.get_model(name)\n- try:\n- body = json.loads(self.request.body)\n- except json.decoder.JSONDecodeError as e:\n- raise tornado.web.HTTPError(\n- status_code=HTTPStatus.BAD_REQUEST,\n- reason=\"Unrecognized request format: %s\" % e\n- )\n request = model.preprocess(body)\n request = self.validate(request)\n response = (await model.predict(request)) if inspect.iscoroutinefunction(model.predict) else model.predict(request)\n response = model.postprocess(response)\n+\n+ if has_binary_headers(self.request.headers):\n+ event = CloudEvent(body._attributes, response)\n+ if is_binary(self.request.headers):\n+ eventheader, eventbody = to_binary(event)\n+ elif is_structured(self.request.headers):\n+ eventheader, eventbody = to_structured(event)\n+ for k, v in eventheader.items():\n+ if k != \"ce-time\":\n+ self.set_header(k, v)\n+ else: #utc now() timestamp\n+ self.set_header('ce-time', datetime.utcnow().replace(tzinfo=pytz.utc).strftime('%Y-%m-%dT%H:%M:%S.%f%z'))\n+\n+ if isinstance(eventbody, (bytes, bytearray)):\n+ response = eventbody\n+ else:\n+ response = eventbody.data\n+\n self.write(response)\n \n \ndiff --git a/python/kfserving/kfserving/kfmodel.py b/python/kfserving/kfserving/kfmodel.py\n--- a/python/kfserving/kfserving/kfmodel.py\n+++ b/python/kfserving/kfserving/kfmodel.py\n@@ -51,7 +51,16 @@\n return self.ready\n \n def preprocess(self, request: Dict) -> Dict:\n- return request\n+ # If cloudevent dict, then parse 'data' field. Otherwise, pass through.\n+ if \"data\" in request \\\n+ and \"time\" in request \\\n+ and \"type\" in request \\\n+ and \"source\" in request \\\n+ and \"id\" in request \\\n+ and \"specversion\" in request:\n+ return request[\"data\"]\n+ else:\n+ return request\n \n def postprocess(self, request: Dict) -> Dict:\n return request\n@@ -91,3 +100,4 @@\n status_code=response.code,\n reason=response.body)\n return json.loads(response.body)\n+\n", "issue": "Support cloud events for KFServing custom framework \n/kind feature\r\n\r\n**Describe the solution you'd like**\r\nAs a user when doing feature transformation the payload can be protobuf/avro or some other binary format delivered via HTTP or KAFKA in cloudevent binary format(https://github.com/cloudevents/spec/blob/v1.0.1/kafka-protocol-binding.md#32-binary-content-mode) but currently KFServing custom framework [only supports JSON](https://github.com/kubeflow/kfserving/blob/master/python/kfserving/kfserving/handlers/http.py#L51).\r\n\r\n- I'd like to send cloud event to KFServer via KAFKA in following format and KFServer pass the decoded cloud event to `preprocess` or `predict` handler\r\n \r\n```\r\n------------------ Message -------------------\r\nTopic Name: mytopic\r\n------------------- key ----------------------\r\nKey: mykey\r\n------------------ headers -------------------\r\nce_specversion: \"1.0\"\r\nce_type: \"com.example.someevent\"\r\nce_source: \"/mycontext/subcontext\"\r\nce_id: \"1234-1234-1234\"\r\nce_time: \"2018-04-05T03:56:24Z\"\r\ncontent-type: application/protobuf\r\n------------------- value --------------------\r\n ... application data encoded in protobuf ...\r\n-----------------------------------------------\r\n\r\n consume http(cloudevent)\r\nKAFKA ----------> Kafka Event Source -----------------> InferenceService\r\n\r\n```\r\n\r\n\r\n\r\n\r\n```python\r\ndef has_ce_headers(headers: typing.Dict[str, str]) -> bool:\r\n return (\r\n \"ce-specversion\" in headers\r\n and \"ce-source\" in headers\r\n and \"ce-type\" in headers\r\n and \"ce-id\" in headers\r\n )\r\n \r\n\r\n if has_ce_headers(self.request.headers):\r\n event = from_http(self.request.headers, self.request.body)\r\n body = event['data']\r\n else:\r\n try:\r\n body = json.loads(self.request.body)\r\n except json.decoder.JSONDecodeError as e:\r\n raise tornado.web.HTTPError(\r\n status_code=HTTPStatus.BAD_REQUEST,\r\n reason=\"Unrecognized request format: %s\" % e)\r\n ``` \r\n \r\n- Currently HTTP headers are not exposed to the `preprocess` or `predict` handler, if a cloud event is sent to KFServer it is not possible for user to check the http headers which can be useful for tracing and examining the original event source(kafka or http).\r\n`async def predict(self, request: Dict, headers: Dict) -> Dict:`\r\n`async def preprocess(self, request: Dict, headers: Dict) -> Dict:`\r\n\r\n- Also it would be nice if KFServing can generate cloud event response so that it works with knative eventing channels seamlessly.\r\n\r\n**Anything else you would like to add:**\r\n[Miscellaneous information that will assist in solving the issue.]\r\n\n", "before_files": [{"content": "# Copyright 2020 kubeflow.org.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport inspect\nimport tornado.web\nimport json\nfrom http import HTTPStatus\nfrom kfserving.kfmodel_repository import KFModelRepository\n\n\nclass HTTPHandler(tornado.web.RequestHandler):\n def initialize(self, models: KFModelRepository):\n self.models = models # pylint:disable=attribute-defined-outside-init\n\n def get_model(self, name: str):\n model = self.models.get_model(name)\n if model is None:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.NOT_FOUND,\n reason=\"Model with name %s does not exist.\" % name\n )\n if not model.ready:\n model.load()\n return model\n\n def validate(self, request):\n if (\"instances\" in request and not isinstance(request[\"instances\"], list)) or \\\n (\"inputs\" in request and not isinstance(request[\"inputs\"], list)):\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Expected \\\"instances\\\" or \\\"inputs\\\" to be a list\"\n )\n return request\n\n\nclass PredictHandler(HTTPHandler):\n async def post(self, name: str):\n model = self.get_model(name)\n try:\n body = json.loads(self.request.body)\n except json.decoder.JSONDecodeError as e:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Unrecognized request format: %s\" % e\n )\n request = model.preprocess(body)\n request = self.validate(request)\n response = (await model.predict(request)) if inspect.iscoroutinefunction(model.predict) else model.predict(request)\n response = model.postprocess(response)\n self.write(response)\n\n\nclass ExplainHandler(HTTPHandler):\n async def post(self, name: str):\n model = self.get_model(name)\n try:\n body = json.loads(self.request.body)\n except json.decoder.JSONDecodeError as e:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Unrecognized request format: %s\" % e\n )\n request = model.preprocess(body)\n request = self.validate(request)\n response = (await model.explain(request)) if inspect.iscoroutinefunction(model.explain) else model.explain(request)\n response = model.postprocess(response)\n self.write(response)\n", "path": "python/kfserving/kfserving/handlers/http.py"}, {"content": "# Copyright 2020 kubeflow.org.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom typing import Dict\nimport sys\n\nimport json\nimport tornado.web\nfrom tornado.httpclient import AsyncHTTPClient\n\nPREDICTOR_URL_FORMAT = \"http://{0}/v1/models/{1}:predict\"\nEXPLAINER_URL_FORMAT = \"http://{0}/v1/models/{1}:explain\"\nPREDICTOR_V2_URL_FORMAT = \"http://{0}/v2/models/{1}/infer\"\nEXPLAINER_V2_URL_FORMAT = \"http://{0}/v2/models/{1}/explain\"\n\n\n# KFModel is intended to be subclassed by various components within KFServing.\nclass KFModel:\n\n def __init__(self, name: str):\n self.name = name\n self.ready = False\n self.protocol = \"v1\"\n self.predictor_host = None\n self.explainer_host = None\n # The timeout matches what is set in generated Istio resources.\n # We generally don't want things to time out at the request level here,\n # timeouts should be handled elsewhere in the system.\n self.timeout = 600\n self._http_client_instance = None\n\n @property\n def _http_client(self):\n if self._http_client_instance is None:\n self._http_client_instance = AsyncHTTPClient(max_clients=sys.maxsize)\n return self._http_client_instance\n\n def load(self) -> bool:\n self.ready = True\n return self.ready\n\n def preprocess(self, request: Dict) -> Dict:\n return request\n\n def postprocess(self, request: Dict) -> Dict:\n return request\n\n async def predict(self, request: Dict) -> Dict:\n if not self.predictor_host:\n raise NotImplementedError\n predict_url = PREDICTOR_URL_FORMAT.format(self.predictor_host, self.name)\n if self.protocol == \"v2\":\n predict_url = PREDICTOR_V2_URL_FORMAT.format(self.predictor_host, self.name)\n response = await self._http_client.fetch(\n predict_url,\n method='POST',\n request_timeout=self.timeout,\n body=json.dumps(request)\n )\n if response.code != 200:\n raise tornado.web.HTTPError(\n status_code=response.code,\n reason=response.body)\n return json.loads(response.body)\n\n async def explain(self, request: Dict) -> Dict:\n if self.explainer_host is None:\n raise NotImplementedError\n explain_url = EXPLAINER_URL_FORMAT.format(self.predictor_host, self.name)\n if self.protocol == \"v2\":\n explain_url = EXPLAINER_V2_URL_FORMAT.format(self.predictor_host, self.name)\n response = await self._http_client.fetch(\n url=explain_url,\n method='POST',\n request_timeout=self.timeout,\n body=json.dumps(request)\n )\n if response.code != 200:\n raise tornado.web.HTTPError(\n status_code=response.code,\n reason=response.body)\n return json.loads(response.body)\n", "path": "python/kfserving/kfserving/kfmodel.py"}], "after_files": [{"content": "# Copyright 2020 kubeflow.org.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport inspect\nimport tornado.web\nimport typing\nimport json\nimport pytz\nimport cloudevents.exceptions as ce\nfrom cloudevents.http import CloudEvent, from_http, is_binary, is_structured, to_binary, to_structured\nfrom cloudevents.sdk.converters.util import has_binary_headers\nfrom http import HTTPStatus\nfrom kfserving.kfmodel_repository import KFModelRepository\nfrom datetime import datetime\n\n\nclass HTTPHandler(tornado.web.RequestHandler):\n def initialize(self, models: KFModelRepository):\n self.models = models # pylint:disable=attribute-defined-outside-init\n\n def get_model(self, name: str):\n model = self.models.get_model(name)\n if model is None:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.NOT_FOUND,\n reason=\"Model with name %s does not exist.\" % name\n )\n if not model.ready:\n model.load()\n return model\n\n def validate(self, request):\n if (\"instances\" in request and not isinstance(request[\"instances\"], list)) or \\\n (\"inputs\" in request and not isinstance(request[\"inputs\"], list)):\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Expected \\\"instances\\\" or \\\"inputs\\\" to be a list\"\n )\n return request\n\nclass PredictHandler(HTTPHandler):\n async def post(self, name: str):\n if has_binary_headers(self.request.headers): \n try:\n #Use default unmarshaller if contenttype is set in header\n if \"ce-contenttype\" in self.request.headers:\n body = from_http(self.request.headers, self.request.body)\n else:\n body = from_http(self.request.headers, self.request.body, lambda x: x)\n except (ce.MissingRequiredFields, ce.InvalidRequiredFields, ce.InvalidStructuredJSON, ce.InvalidHeadersFormat, ce.DataMarshallerError, ce.DataUnmarshallerError) as e:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Cloud Event Exceptions: %s\" % e\n )\n else:\n try:\n body = json.loads(self.request.body)\n except json.decoder.JSONDecodeError as e:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Unrecognized request format: %s\" % e\n )\n\n model = self.get_model(name)\n request = model.preprocess(body)\n request = self.validate(request)\n response = (await model.predict(request)) if inspect.iscoroutinefunction(model.predict) else model.predict(request)\n response = model.postprocess(response)\n\n if has_binary_headers(self.request.headers):\n event = CloudEvent(body._attributes, response)\n if is_binary(self.request.headers):\n eventheader, eventbody = to_binary(event)\n elif is_structured(self.request.headers):\n eventheader, eventbody = to_structured(event)\n for k, v in eventheader.items():\n if k != \"ce-time\":\n self.set_header(k, v)\n else: #utc now() timestamp\n self.set_header('ce-time', datetime.utcnow().replace(tzinfo=pytz.utc).strftime('%Y-%m-%dT%H:%M:%S.%f%z'))\n\n if isinstance(eventbody, (bytes, bytearray)):\n response = eventbody\n else:\n response = eventbody.data\n\n self.write(response)\n\n\nclass ExplainHandler(HTTPHandler):\n async def post(self, name: str):\n model = self.get_model(name)\n try:\n body = json.loads(self.request.body)\n except json.decoder.JSONDecodeError as e:\n raise tornado.web.HTTPError(\n status_code=HTTPStatus.BAD_REQUEST,\n reason=\"Unrecognized request format: %s\" % e\n )\n request = model.preprocess(body)\n request = self.validate(request)\n response = (await model.explain(request)) if inspect.iscoroutinefunction(model.explain) else model.explain(request)\n response = model.postprocess(response)\n self.write(response)\n", "path": "python/kfserving/kfserving/handlers/http.py"}, {"content": "# Copyright 2020 kubeflow.org.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom typing import Dict\nimport sys\n\nimport json\nimport tornado.web\nfrom tornado.httpclient import AsyncHTTPClient\n\nPREDICTOR_URL_FORMAT = \"http://{0}/v1/models/{1}:predict\"\nEXPLAINER_URL_FORMAT = \"http://{0}/v1/models/{1}:explain\"\nPREDICTOR_V2_URL_FORMAT = \"http://{0}/v2/models/{1}/infer\"\nEXPLAINER_V2_URL_FORMAT = \"http://{0}/v2/models/{1}/explain\"\n\n\n# KFModel is intended to be subclassed by various components within KFServing.\nclass KFModel:\n\n def __init__(self, name: str):\n self.name = name\n self.ready = False\n self.protocol = \"v1\"\n self.predictor_host = None\n self.explainer_host = None\n # The timeout matches what is set in generated Istio resources.\n # We generally don't want things to time out at the request level here,\n # timeouts should be handled elsewhere in the system.\n self.timeout = 600\n self._http_client_instance = None\n\n @property\n def _http_client(self):\n if self._http_client_instance is None:\n self._http_client_instance = AsyncHTTPClient(max_clients=sys.maxsize)\n return self._http_client_instance\n\n def load(self) -> bool:\n self.ready = True\n return self.ready\n\n def preprocess(self, request: Dict) -> Dict:\n # If cloudevent dict, then parse 'data' field. Otherwise, pass through.\n if \"data\" in request \\\n and \"time\" in request \\\n and \"type\" in request \\\n and \"source\" in request \\\n and \"id\" in request \\\n and \"specversion\" in request:\n return request[\"data\"]\n else:\n return request\n\n def postprocess(self, request: Dict) -> Dict:\n return request\n\n async def predict(self, request: Dict) -> Dict:\n if not self.predictor_host:\n raise NotImplementedError\n predict_url = PREDICTOR_URL_FORMAT.format(self.predictor_host, self.name)\n if self.protocol == \"v2\":\n predict_url = PREDICTOR_V2_URL_FORMAT.format(self.predictor_host, self.name)\n response = await self._http_client.fetch(\n predict_url,\n method='POST',\n request_timeout=self.timeout,\n body=json.dumps(request)\n )\n if response.code != 200:\n raise tornado.web.HTTPError(\n status_code=response.code,\n reason=response.body)\n return json.loads(response.body)\n\n async def explain(self, request: Dict) -> Dict:\n if self.explainer_host is None:\n raise NotImplementedError\n explain_url = EXPLAINER_URL_FORMAT.format(self.predictor_host, self.name)\n if self.protocol == \"v2\":\n explain_url = EXPLAINER_V2_URL_FORMAT.format(self.predictor_host, self.name)\n response = await self._http_client.fetch(\n url=explain_url,\n method='POST',\n request_timeout=self.timeout,\n body=json.dumps(request)\n )\n if response.code != 200:\n raise tornado.web.HTTPError(\n status_code=response.code,\n reason=response.body)\n return json.loads(response.body)\n\n", "path": "python/kfserving/kfserving/kfmodel.py"}]}
| 2,609 | 971 |
gh_patches_debug_8100
|
rasdani/github-patches
|
git_diff
|
WeblateOrg__weblate-11568
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Time to use `build` from `setuptools` instead of `distutils`?
### Describe the problem
The following feature in setuptools has been deprecated for almost 2 years and is about to be removed:
https://github.com/pypa/setuptools/blob/1ed759173983656734c3606e9c97a348895e5e0c/setuptools/command/build.py#L13-L27
It might be a good idea to import `build` directly from setuptools for the following code:
https://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L9
https://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L51-L58
(`build` is available directly from setuptools, starting on version v62.4.0)
### Describe the solution you would like
Whenever possible, it might be a good idea to import from setuptools (and minimise imports to `distutils` to the minimum viable).
### Describe alternatives you have considered
_No response_
### Screenshots
_No response_
### Additional context
_No response_
Time to use `build` from `setuptools` instead of `distutils`?
### Describe the problem
The following feature in setuptools has been deprecated for almost 2 years and is about to be removed:
https://github.com/pypa/setuptools/blob/1ed759173983656734c3606e9c97a348895e5e0c/setuptools/command/build.py#L13-L27
It might be a good idea to import `build` directly from setuptools for the following code:
https://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L9
https://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L51-L58
(`build` is available directly from setuptools, starting on version v62.4.0)
### Describe the solution you would like
Whenever possible, it might be a good idea to import from setuptools (and minimise imports to `distutils` to the minimum viable).
### Describe alternatives you have considered
_No response_
### Screenshots
_No response_
### Additional context
_No response_
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 #!/usr/bin/env python3
2
3 # Copyright © Michal Čihař <[email protected]>
4 #
5 # SPDX-License-Identifier: GPL-3.0-or-later
6
7 import os
8 from distutils import log
9 from distutils.command.build import build
10 from distutils.core import Command
11 from glob import glob
12 from itertools import chain
13
14 from setuptools import setup
15 from setuptools.command.build_py import build_py
16 from setuptools.modified import newer
17 from translate.tools.pocompile import convertmo
18
19 LOCALE_MASKS = [
20 "weblate/locale/*/LC_MESSAGES/*.po",
21 ]
22
23
24 class WeblateBuildPy(build_py):
25 def find_package_modules(self, package, package_dir):
26 """Filter settings.py from built module."""
27 result = super().find_package_modules(package, package_dir)
28 return [item for item in result if item[2] != "weblate/settings.py"]
29
30
31 class BuildMo(Command):
32 description = "update MO files to match PO"
33 user_options = []
34
35 def initialize_options(self) -> None:
36 self.build_base = None
37
38 def finalize_options(self) -> None:
39 self.set_undefined_options("build", ("build_base", "build_base"))
40
41 def run(self) -> None:
42 for name in chain.from_iterable(glob(mask) for mask in LOCALE_MASKS):
43 output = os.path.splitext(name)[0] + ".mo"
44 if not newer(name, output):
45 continue
46 self.announce(f"compiling {name} -> {output}", level=log.INFO)
47 with open(name, "rb") as pofile, open(output, "wb") as mofile:
48 convertmo(pofile, mofile, None)
49
50
51 class WeblateBuild(build):
52 """Override the default build with new subcommands."""
53
54 # The build_mo has to be before build_data
55 sub_commands = [
56 ("build_mo", lambda self: True), # noqa: ARG005
57 *build.sub_commands,
58 ]
59
60
61 setup(
62 cmdclass={"build_py": WeblateBuildPy, "build_mo": BuildMo, "build": WeblateBuild},
63 )
64
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -6,12 +6,12 @@
import os
from distutils import log
-from distutils.command.build import build
from distutils.core import Command
from glob import glob
from itertools import chain
from setuptools import setup
+from setuptools.command.build import build
from setuptools.command.build_py import build_py
from setuptools.modified import newer
from translate.tools.pocompile import convertmo
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -6,12 +6,12 @@\n \n import os\n from distutils import log\n-from distutils.command.build import build\n from distutils.core import Command\n from glob import glob\n from itertools import chain\n \n from setuptools import setup\n+from setuptools.command.build import build\n from setuptools.command.build_py import build_py\n from setuptools.modified import newer\n from translate.tools.pocompile import convertmo\n", "issue": "Time to use `build` from `setuptools` instead of `distutils`?\n### Describe the problem\n\nThe following feature in setuptools has been deprecated for almost 2 years and is about to be removed:\r\n\r\nhttps://github.com/pypa/setuptools/blob/1ed759173983656734c3606e9c97a348895e5e0c/setuptools/command/build.py#L13-L27\r\n\r\nIt might be a good idea to import `build` directly from setuptools for the following code:\r\n\r\nhttps://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L9\r\nhttps://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L51-L58\r\n\r\n(`build` is available directly from setuptools, starting on version v62.4.0)\n\n### Describe the solution you would like\n\nWhenever possible, it might be a good idea to import from setuptools (and minimise imports to `distutils` to the minimum viable).\n\n### Describe alternatives you have considered\n\n_No response_\n\n### Screenshots\n\n_No response_\n\n### Additional context\n\n_No response_\nTime to use `build` from `setuptools` instead of `distutils`?\n### Describe the problem\n\nThe following feature in setuptools has been deprecated for almost 2 years and is about to be removed:\r\n\r\nhttps://github.com/pypa/setuptools/blob/1ed759173983656734c3606e9c97a348895e5e0c/setuptools/command/build.py#L13-L27\r\n\r\nIt might be a good idea to import `build` directly from setuptools for the following code:\r\n\r\nhttps://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L9\r\nhttps://github.com/WeblateOrg/weblate/blob/47f9f2870c4ed9fd5429eebfacc61d2267a5bb31/setup.py#L51-L58\r\n\r\n(`build` is available directly from setuptools, starting on version v62.4.0)\n\n### Describe the solution you would like\n\nWhenever possible, it might be a good idea to import from setuptools (and minimise imports to `distutils` to the minimum viable).\n\n### Describe alternatives you have considered\n\n_No response_\n\n### Screenshots\n\n_No response_\n\n### Additional context\n\n_No response_\n", "before_files": [{"content": "#!/usr/bin/env python3\n\n# Copyright \u00a9 Michal \u010ciha\u0159 <[email protected]>\n#\n# SPDX-License-Identifier: GPL-3.0-or-later\n\nimport os\nfrom distutils import log\nfrom distutils.command.build import build\nfrom distutils.core import Command\nfrom glob import glob\nfrom itertools import chain\n\nfrom setuptools import setup\nfrom setuptools.command.build_py import build_py\nfrom setuptools.modified import newer\nfrom translate.tools.pocompile import convertmo\n\nLOCALE_MASKS = [\n \"weblate/locale/*/LC_MESSAGES/*.po\",\n]\n\n\nclass WeblateBuildPy(build_py):\n def find_package_modules(self, package, package_dir):\n \"\"\"Filter settings.py from built module.\"\"\"\n result = super().find_package_modules(package, package_dir)\n return [item for item in result if item[2] != \"weblate/settings.py\"]\n\n\nclass BuildMo(Command):\n description = \"update MO files to match PO\"\n user_options = []\n\n def initialize_options(self) -> None:\n self.build_base = None\n\n def finalize_options(self) -> None:\n self.set_undefined_options(\"build\", (\"build_base\", \"build_base\"))\n\n def run(self) -> None:\n for name in chain.from_iterable(glob(mask) for mask in LOCALE_MASKS):\n output = os.path.splitext(name)[0] + \".mo\"\n if not newer(name, output):\n continue\n self.announce(f\"compiling {name} -> {output}\", level=log.INFO)\n with open(name, \"rb\") as pofile, open(output, \"wb\") as mofile:\n convertmo(pofile, mofile, None)\n\n\nclass WeblateBuild(build):\n \"\"\"Override the default build with new subcommands.\"\"\"\n\n # The build_mo has to be before build_data\n sub_commands = [\n (\"build_mo\", lambda self: True), # noqa: ARG005\n *build.sub_commands,\n ]\n\n\nsetup(\n cmdclass={\"build_py\": WeblateBuildPy, \"build_mo\": BuildMo, \"build\": WeblateBuild},\n)\n", "path": "setup.py"}], "after_files": [{"content": "#!/usr/bin/env python3\n\n# Copyright \u00a9 Michal \u010ciha\u0159 <[email protected]>\n#\n# SPDX-License-Identifier: GPL-3.0-or-later\n\nimport os\nfrom distutils import log\nfrom distutils.core import Command\nfrom glob import glob\nfrom itertools import chain\n\nfrom setuptools import setup\nfrom setuptools.command.build import build\nfrom setuptools.command.build_py import build_py\nfrom setuptools.modified import newer\nfrom translate.tools.pocompile import convertmo\n\nLOCALE_MASKS = [\n \"weblate/locale/*/LC_MESSAGES/*.po\",\n]\n\n\nclass WeblateBuildPy(build_py):\n def find_package_modules(self, package, package_dir):\n \"\"\"Filter settings.py from built module.\"\"\"\n result = super().find_package_modules(package, package_dir)\n return [item for item in result if item[2] != \"weblate/settings.py\"]\n\n\nclass BuildMo(Command):\n description = \"update MO files to match PO\"\n user_options = []\n\n def initialize_options(self) -> None:\n self.build_base = None\n\n def finalize_options(self) -> None:\n self.set_undefined_options(\"build\", (\"build_base\", \"build_base\"))\n\n def run(self) -> None:\n for name in chain.from_iterable(glob(mask) for mask in LOCALE_MASKS):\n output = os.path.splitext(name)[0] + \".mo\"\n if not newer(name, output):\n continue\n self.announce(f\"compiling {name} -> {output}\", level=log.INFO)\n with open(name, \"rb\") as pofile, open(output, \"wb\") as mofile:\n convertmo(pofile, mofile, None)\n\n\nclass WeblateBuild(build):\n \"\"\"Override the default build with new subcommands.\"\"\"\n\n # The build_mo has to be before build_data\n sub_commands = [\n (\"build_mo\", lambda self: True), # noqa: ARG005\n *build.sub_commands,\n ]\n\n\nsetup(\n cmdclass={\"build_py\": WeblateBuildPy, \"build_mo\": BuildMo, \"build\": WeblateBuild},\n)\n", "path": "setup.py"}]}
| 1,470 | 105 |
gh_patches_debug_8391
|
rasdani/github-patches
|
git_diff
|
scrapy__scrapy-3377
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
scrapy check exit code on exception
When I run `scrapy check` and a contract raises unhandled exception, the command exits with successful code `0`.
```
$ scrapy check $SPIDER_NAME
... some stuff ...
Ran 0 contracts in 0.000s
OK
$ echo $?
0
```
Is this intended, or should I fix it?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `scrapy/contracts/__init__.py`
Content:
```
1 import sys
2 import re
3 from functools import wraps
4 from inspect import getmembers
5 from unittest import TestCase
6
7 from scrapy.http import Request
8 from scrapy.utils.spider import iterate_spider_output
9 from scrapy.utils.python import get_spec
10
11
12 class ContractsManager(object):
13 contracts = {}
14
15 def __init__(self, contracts):
16 for contract in contracts:
17 self.contracts[contract.name] = contract
18
19 def tested_methods_from_spidercls(self, spidercls):
20 methods = []
21 for key, value in getmembers(spidercls):
22 if (callable(value) and value.__doc__ and
23 re.search(r'^\s*@', value.__doc__, re.MULTILINE)):
24 methods.append(key)
25
26 return methods
27
28 def extract_contracts(self, method):
29 contracts = []
30 for line in method.__doc__.split('\n'):
31 line = line.strip()
32
33 if line.startswith('@'):
34 name, args = re.match(r'@(\w+)\s*(.*)', line).groups()
35 args = re.split(r'\s+', args)
36
37 contracts.append(self.contracts[name](method, *args))
38
39 return contracts
40
41 def from_spider(self, spider, results):
42 requests = []
43 for method in self.tested_methods_from_spidercls(type(spider)):
44 bound_method = spider.__getattribute__(method)
45 requests.append(self.from_method(bound_method, results))
46
47 return requests
48
49 def from_method(self, method, results):
50 contracts = self.extract_contracts(method)
51 if contracts:
52 request_cls = Request
53 for contract in contracts:
54 if contract.request_cls is not None:
55 request_cls = contract.request_cls
56
57 # calculate request args
58 args, kwargs = get_spec(request_cls.__init__)
59 kwargs['callback'] = method
60 for contract in contracts:
61 kwargs = contract.adjust_request_args(kwargs)
62
63 args.remove('self')
64
65 # check if all positional arguments are defined in kwargs
66 if set(args).issubset(set(kwargs)):
67 request = request_cls(**kwargs)
68
69 # execute pre and post hooks in order
70 for contract in reversed(contracts):
71 request = contract.add_pre_hook(request, results)
72 for contract in contracts:
73 request = contract.add_post_hook(request, results)
74
75 self._clean_req(request, method, results)
76 return request
77
78 def _clean_req(self, request, method, results):
79 """ stop the request from returning objects and records any errors """
80
81 cb = request.callback
82
83 @wraps(cb)
84 def cb_wrapper(response):
85 try:
86 output = cb(response)
87 output = list(iterate_spider_output(output))
88 except:
89 case = _create_testcase(method, 'callback')
90 results.addError(case, sys.exc_info())
91
92 def eb_wrapper(failure):
93 case = _create_testcase(method, 'errback')
94 exc_info = failure.type, failure.value, failure.getTracebackObject()
95 results.addError(case, exc_info)
96
97 request.callback = cb_wrapper
98 request.errback = eb_wrapper
99
100
101 class Contract(object):
102 """ Abstract class for contracts """
103 request_cls = None
104
105 def __init__(self, method, *args):
106 self.testcase_pre = _create_testcase(method, '@%s pre-hook' % self.name)
107 self.testcase_post = _create_testcase(method, '@%s post-hook' % self.name)
108 self.args = args
109
110 def add_pre_hook(self, request, results):
111 if hasattr(self, 'pre_process'):
112 cb = request.callback
113
114 @wraps(cb)
115 def wrapper(response):
116 try:
117 results.startTest(self.testcase_pre)
118 self.pre_process(response)
119 results.stopTest(self.testcase_pre)
120 except AssertionError:
121 results.addFailure(self.testcase_pre, sys.exc_info())
122 except Exception:
123 results.addError(self.testcase_pre, sys.exc_info())
124 else:
125 results.addSuccess(self.testcase_pre)
126 finally:
127 return list(iterate_spider_output(cb(response)))
128
129 request.callback = wrapper
130
131 return request
132
133 def add_post_hook(self, request, results):
134 if hasattr(self, 'post_process'):
135 cb = request.callback
136
137 @wraps(cb)
138 def wrapper(response):
139 output = list(iterate_spider_output(cb(response)))
140 try:
141 results.startTest(self.testcase_post)
142 self.post_process(output)
143 results.stopTest(self.testcase_post)
144 except AssertionError:
145 results.addFailure(self.testcase_post, sys.exc_info())
146 except Exception:
147 results.addError(self.testcase_post, sys.exc_info())
148 else:
149 results.addSuccess(self.testcase_post)
150 finally:
151 return output
152
153 request.callback = wrapper
154
155 return request
156
157 def adjust_request_args(self, args):
158 return args
159
160
161 def _create_testcase(method, desc):
162 spider = method.__self__.name
163
164 class ContractTestCase(TestCase):
165 def __str__(_self):
166 return "[%s] %s (%s)" % (spider, method.__name__, desc)
167
168 name = '%s_%s' % (spider, method.__name__)
169 setattr(ContractTestCase, name, lambda x: x)
170 return ContractTestCase(name)
171
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/scrapy/contracts/__init__.py b/scrapy/contracts/__init__.py
--- a/scrapy/contracts/__init__.py
+++ b/scrapy/contracts/__init__.py
@@ -42,7 +42,11 @@
requests = []
for method in self.tested_methods_from_spidercls(type(spider)):
bound_method = spider.__getattribute__(method)
- requests.append(self.from_method(bound_method, results))
+ try:
+ requests.append(self.from_method(bound_method, results))
+ except Exception:
+ case = _create_testcase(bound_method, 'contract')
+ results.addError(case, sys.exc_info())
return requests
|
{"golden_diff": "diff --git a/scrapy/contracts/__init__.py b/scrapy/contracts/__init__.py\n--- a/scrapy/contracts/__init__.py\n+++ b/scrapy/contracts/__init__.py\n@@ -42,7 +42,11 @@\n requests = []\n for method in self.tested_methods_from_spidercls(type(spider)):\n bound_method = spider.__getattribute__(method)\n- requests.append(self.from_method(bound_method, results))\n+ try:\n+ requests.append(self.from_method(bound_method, results))\n+ except Exception:\n+ case = _create_testcase(bound_method, 'contract')\n+ results.addError(case, sys.exc_info())\n \n return requests\n", "issue": "scrapy check exit code on exception\nWhen I run `scrapy check` and a contract raises unhandled exception, the command exits with successful code `0`.\r\n\r\n```\r\n$ scrapy check $SPIDER_NAME\r\n... some stuff ...\r\nRan 0 contracts in 0.000s\r\nOK\r\n$ echo $?\r\n0\r\n```\r\n\r\nIs this intended, or should I fix it?\n", "before_files": [{"content": "import sys\nimport re\nfrom functools import wraps\nfrom inspect import getmembers\nfrom unittest import TestCase\n\nfrom scrapy.http import Request\nfrom scrapy.utils.spider import iterate_spider_output\nfrom scrapy.utils.python import get_spec\n\n\nclass ContractsManager(object):\n contracts = {}\n\n def __init__(self, contracts):\n for contract in contracts:\n self.contracts[contract.name] = contract\n\n def tested_methods_from_spidercls(self, spidercls):\n methods = []\n for key, value in getmembers(spidercls):\n if (callable(value) and value.__doc__ and\n re.search(r'^\\s*@', value.__doc__, re.MULTILINE)):\n methods.append(key)\n\n return methods\n\n def extract_contracts(self, method):\n contracts = []\n for line in method.__doc__.split('\\n'):\n line = line.strip()\n\n if line.startswith('@'):\n name, args = re.match(r'@(\\w+)\\s*(.*)', line).groups()\n args = re.split(r'\\s+', args)\n\n contracts.append(self.contracts[name](method, *args))\n\n return contracts\n\n def from_spider(self, spider, results):\n requests = []\n for method in self.tested_methods_from_spidercls(type(spider)):\n bound_method = spider.__getattribute__(method)\n requests.append(self.from_method(bound_method, results))\n\n return requests\n\n def from_method(self, method, results):\n contracts = self.extract_contracts(method)\n if contracts:\n request_cls = Request\n for contract in contracts:\n if contract.request_cls is not None:\n request_cls = contract.request_cls\n\n # calculate request args\n args, kwargs = get_spec(request_cls.__init__)\n kwargs['callback'] = method\n for contract in contracts:\n kwargs = contract.adjust_request_args(kwargs)\n\n args.remove('self')\n\n # check if all positional arguments are defined in kwargs\n if set(args).issubset(set(kwargs)):\n request = request_cls(**kwargs)\n\n # execute pre and post hooks in order\n for contract in reversed(contracts):\n request = contract.add_pre_hook(request, results)\n for contract in contracts:\n request = contract.add_post_hook(request, results)\n\n self._clean_req(request, method, results)\n return request\n\n def _clean_req(self, request, method, results):\n \"\"\" stop the request from returning objects and records any errors \"\"\"\n\n cb = request.callback\n\n @wraps(cb)\n def cb_wrapper(response):\n try:\n output = cb(response)\n output = list(iterate_spider_output(output))\n except:\n case = _create_testcase(method, 'callback')\n results.addError(case, sys.exc_info())\n\n def eb_wrapper(failure):\n case = _create_testcase(method, 'errback')\n exc_info = failure.type, failure.value, failure.getTracebackObject()\n results.addError(case, exc_info)\n\n request.callback = cb_wrapper\n request.errback = eb_wrapper\n\n\nclass Contract(object):\n \"\"\" Abstract class for contracts \"\"\"\n request_cls = None\n\n def __init__(self, method, *args):\n self.testcase_pre = _create_testcase(method, '@%s pre-hook' % self.name)\n self.testcase_post = _create_testcase(method, '@%s post-hook' % self.name)\n self.args = args\n\n def add_pre_hook(self, request, results):\n if hasattr(self, 'pre_process'):\n cb = request.callback\n\n @wraps(cb)\n def wrapper(response):\n try:\n results.startTest(self.testcase_pre)\n self.pre_process(response)\n results.stopTest(self.testcase_pre)\n except AssertionError:\n results.addFailure(self.testcase_pre, sys.exc_info())\n except Exception:\n results.addError(self.testcase_pre, sys.exc_info())\n else:\n results.addSuccess(self.testcase_pre)\n finally:\n return list(iterate_spider_output(cb(response)))\n\n request.callback = wrapper\n\n return request\n\n def add_post_hook(self, request, results):\n if hasattr(self, 'post_process'):\n cb = request.callback\n\n @wraps(cb)\n def wrapper(response):\n output = list(iterate_spider_output(cb(response)))\n try:\n results.startTest(self.testcase_post)\n self.post_process(output)\n results.stopTest(self.testcase_post)\n except AssertionError:\n results.addFailure(self.testcase_post, sys.exc_info())\n except Exception:\n results.addError(self.testcase_post, sys.exc_info())\n else:\n results.addSuccess(self.testcase_post)\n finally:\n return output\n\n request.callback = wrapper\n\n return request\n\n def adjust_request_args(self, args):\n return args\n\n\ndef _create_testcase(method, desc):\n spider = method.__self__.name\n\n class ContractTestCase(TestCase):\n def __str__(_self):\n return \"[%s] %s (%s)\" % (spider, method.__name__, desc)\n\n name = '%s_%s' % (spider, method.__name__)\n setattr(ContractTestCase, name, lambda x: x)\n return ContractTestCase(name)\n", "path": "scrapy/contracts/__init__.py"}], "after_files": [{"content": "import sys\nimport re\nfrom functools import wraps\nfrom inspect import getmembers\nfrom unittest import TestCase\n\nfrom scrapy.http import Request\nfrom scrapy.utils.spider import iterate_spider_output\nfrom scrapy.utils.python import get_spec\n\n\nclass ContractsManager(object):\n contracts = {}\n\n def __init__(self, contracts):\n for contract in contracts:\n self.contracts[contract.name] = contract\n\n def tested_methods_from_spidercls(self, spidercls):\n methods = []\n for key, value in getmembers(spidercls):\n if (callable(value) and value.__doc__ and\n re.search(r'^\\s*@', value.__doc__, re.MULTILINE)):\n methods.append(key)\n\n return methods\n\n def extract_contracts(self, method):\n contracts = []\n for line in method.__doc__.split('\\n'):\n line = line.strip()\n\n if line.startswith('@'):\n name, args = re.match(r'@(\\w+)\\s*(.*)', line).groups()\n args = re.split(r'\\s+', args)\n\n contracts.append(self.contracts[name](method, *args))\n\n return contracts\n\n def from_spider(self, spider, results):\n requests = []\n for method in self.tested_methods_from_spidercls(type(spider)):\n bound_method = spider.__getattribute__(method)\n try:\n requests.append(self.from_method(bound_method, results))\n except Exception:\n case = _create_testcase(bound_method, 'contract')\n results.addError(case, sys.exc_info())\n\n return requests\n\n def from_method(self, method, results):\n contracts = self.extract_contracts(method)\n if contracts:\n request_cls = Request\n for contract in contracts:\n if contract.request_cls is not None:\n request_cls = contract.request_cls\n\n # calculate request args\n args, kwargs = get_spec(request_cls.__init__)\n kwargs['callback'] = method\n for contract in contracts:\n kwargs = contract.adjust_request_args(kwargs)\n\n args.remove('self')\n\n # check if all positional arguments are defined in kwargs\n if set(args).issubset(set(kwargs)):\n request = request_cls(**kwargs)\n\n # execute pre and post hooks in order\n for contract in reversed(contracts):\n request = contract.add_pre_hook(request, results)\n for contract in contracts:\n request = contract.add_post_hook(request, results)\n\n self._clean_req(request, method, results)\n return request\n\n def _clean_req(self, request, method, results):\n \"\"\" stop the request from returning objects and records any errors \"\"\"\n\n cb = request.callback\n\n @wraps(cb)\n def cb_wrapper(response):\n try:\n output = cb(response)\n output = list(iterate_spider_output(output))\n except:\n case = _create_testcase(method, 'callback')\n results.addError(case, sys.exc_info())\n\n def eb_wrapper(failure):\n case = _create_testcase(method, 'errback')\n exc_info = failure.type, failure.value, failure.getTracebackObject()\n results.addError(case, exc_info)\n\n request.callback = cb_wrapper\n request.errback = eb_wrapper\n\n\nclass Contract(object):\n \"\"\" Abstract class for contracts \"\"\"\n request_cls = None\n\n def __init__(self, method, *args):\n self.testcase_pre = _create_testcase(method, '@%s pre-hook' % self.name)\n self.testcase_post = _create_testcase(method, '@%s post-hook' % self.name)\n self.args = args\n\n def add_pre_hook(self, request, results):\n if hasattr(self, 'pre_process'):\n cb = request.callback\n\n @wraps(cb)\n def wrapper(response):\n try:\n results.startTest(self.testcase_pre)\n self.pre_process(response)\n results.stopTest(self.testcase_pre)\n except AssertionError:\n results.addFailure(self.testcase_pre, sys.exc_info())\n except Exception:\n results.addError(self.testcase_pre, sys.exc_info())\n else:\n results.addSuccess(self.testcase_pre)\n finally:\n return list(iterate_spider_output(cb(response)))\n\n request.callback = wrapper\n\n return request\n\n def add_post_hook(self, request, results):\n if hasattr(self, 'post_process'):\n cb = request.callback\n\n @wraps(cb)\n def wrapper(response):\n output = list(iterate_spider_output(cb(response)))\n try:\n results.startTest(self.testcase_post)\n self.post_process(output)\n results.stopTest(self.testcase_post)\n except AssertionError:\n results.addFailure(self.testcase_post, sys.exc_info())\n except Exception:\n results.addError(self.testcase_post, sys.exc_info())\n else:\n results.addSuccess(self.testcase_post)\n finally:\n return output\n\n request.callback = wrapper\n\n return request\n\n def adjust_request_args(self, args):\n return args\n\n\ndef _create_testcase(method, desc):\n spider = method.__self__.name\n\n class ContractTestCase(TestCase):\n def __str__(_self):\n return \"[%s] %s (%s)\" % (spider, method.__name__, desc)\n\n name = '%s_%s' % (spider, method.__name__)\n setattr(ContractTestCase, name, lambda x: x)\n return ContractTestCase(name)\n", "path": "scrapy/contracts/__init__.py"}]}
| 1,876 | 154 |
gh_patches_debug_7395
|
rasdani/github-patches
|
git_diff
|
svthalia__concrexit-1513
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
URL's from Events API are not always full URL's
### Describe the bug
The `google_maps_url` from the Events API is not always a full URL.
### How to reproduce
Steps to reproduce the behaviour:
1. On staging, go to `https://staging.thalia.nu/api/v1/events/147/` and see that the `google_maps_url` is not a full URL but a relative one.
### Expected behaviour
The `google_maps_url` should always be a full URL.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `website/utils/snippets.py`
Content:
```
1 """Provides various utilities that are useful across the project."""
2 import datetime
3 import hmac
4 from base64 import urlsafe_b64decode, urlsafe_b64encode
5 from collections import namedtuple
6 from _sha1 import sha1
7
8 from django.conf import settings
9 from django.template.defaultfilters import urlencode
10 from django.templatetags.static import static
11 from django.utils import timezone, dateparse
12 from rest_framework.exceptions import ParseError
13
14
15 def dict2obj(d, name="Object"):
16 return namedtuple(name, d.keys())(*d.values())
17
18
19 def datetime_to_lectureyear(date):
20 """Convert a :class:`~datetime.date` to the start of the lectureyear.
21
22 >>> from datetime import date, datetime, timezone
23 >>> nov_23 = date(1990, 11, 7)
24 >>> datetime_to_lectureyear(nov_23)
25 1990
26 >>> mar_2 = date(1993, 3, 2)
27 >>> datetime_to_lectureyear(mar_2)
28 1992
29
30 Also works on :class:`~datetime.datetime`, but they need to be tz-aware:
31
32 >>> new_year = datetime(2000, 1, 1, tzinfo=timezone.utc)
33 >>> datetime_to_lectureyear(new_year)
34 1999
35 """
36 if isinstance(date, timezone.datetime):
37 date = timezone.localtime(date).date()
38 sept_1 = timezone.make_aware(timezone.datetime(date.year, 9, 1))
39 if date < sept_1.date():
40 return date.year - 1
41 return date.year
42
43
44 def create_google_maps_url(location, zoom, size):
45 if location.lower().strip() == "online":
46 return static("img/locations/online.png")
47 if location.lower().strip() == "discord":
48 return static("img/locations/discord.png")
49
50 maps_url = (
51 f"/maps/api/staticmap?"
52 f"center={ urlencode(location) }&"
53 f"zoom={ zoom }&size={ size }&"
54 f"markers={ urlencode(location) }&"
55 f"key={ settings.GOOGLE_MAPS_API_KEY }"
56 )
57
58 decoded_key = urlsafe_b64decode(settings.GOOGLE_MAPS_API_SECRET)
59
60 signature = hmac.new(decoded_key, maps_url.encode(), sha1)
61
62 encoded_signature = urlsafe_b64encode(signature.digest())
63
64 maps_url += f"&signature={encoded_signature.decode('utf-8')}"
65
66 return "https://maps.googleapis.com" + maps_url
67
68
69 def _extract_date(param):
70 """Extract the date from an arbitrary string."""
71 if param is None:
72 return None
73 try:
74 return dateparse.parse_datetime(param)
75 except ValueError:
76 return dateparse.parse_date(param)
77
78
79 def extract_date_range(request, allow_empty=False):
80 """Extract a date range from an arbitrary string."""
81 default_value = None
82
83 start = request.query_params.get("start", default_value)
84 if start or not allow_empty:
85 try:
86 start = dateparse.parse_datetime(start)
87 if not timezone.is_aware(start):
88 start = timezone.make_aware(start)
89 except (ValueError, AttributeError, TypeError) as e:
90 raise ParseError(detail="start query parameter invalid") from e
91
92 end = request.query_params.get("end", default_value)
93 if end or not allow_empty:
94 try:
95 end = dateparse.parse_datetime(end)
96 if not timezone.is_aware(end):
97 end = timezone.make_aware(end)
98 except (ValueError, AttributeError, TypeError) as e:
99 raise ParseError(detail="end query parameter invalid") from e
100
101 return start, end
102
103
104 def overlaps(check, others, can_equal=True):
105 """Check for overlapping date ranges.
106
107 This works by checking the maximum of the two `since` times, and the minimum of
108 the two `until` times. Because there are no infinite dates, the value date_max
109 is created for when the `until` value is None; this signifies a timespan that
110 has not ended yet and is the maximum possible date in Python's datetime.
111
112 The ranges overlap when the maximum start time is smaller than the minimum
113 end time, as can be seen in this example of two integer ranges:
114
115 check: . . . .[4]. . . . 9
116 other: . . 2 . .[5]. . . .
117
118 check: . . . .[4]. . . . 9
119 other: . . 2 . . . . . . . [date_max]
120
121 And when non overlapping:
122 check: . . . . . .[6] . . 9
123 other: . . 2 . .[5]. . . .
124
125 4 < 5 == True so these intervals overlap, while 6 < 5 == False so these intervals
126 don't overlap
127
128 The can_equal argument is used for boards, where the end date can't be the same
129 as the start date.
130
131 >>> overlaps( \
132 dict2obj({ \
133 'pk': 1 \
134 , 'since': datetime.date(2018, 12, 1) \
135 , 'until': datetime.date(2019, 1, 1) \
136 }) \
137 , [dict2obj({ \
138 'pk': 2 \
139 , 'since': datetime.date(2019, 1, 1) \
140 , 'until': datetime.date(2019, 1, 31) \
141 })])
142 False
143
144 >>> overlaps( \
145 dict2obj({ \
146 'pk': 1 \
147 , 'since': datetime.date(2018, 12, 1) \
148 , 'until': datetime.date(2019, 1, 1) \
149 }) \
150 , [dict2obj({ \
151 'pk': 2 \
152 , 'since': datetime.date(2019, 1, 1) \
153 , 'until': datetime.date(2019, 1, 31) \
154 })], False)
155 True
156
157 >>> overlaps( \
158 dict2obj({ \
159 'pk': 1 \
160 , 'since': datetime.date(2018, 12, 1) \
161 , 'until': datetime.date(2019, 1, 2) \
162 }) \
163 , [dict2obj({ \
164 'pk': 2 \
165 , 'since': datetime.date(2019, 1, 1) \
166 , 'until': datetime.date(2019, 1, 31) \
167 })])
168 True
169 """
170 date_max = datetime.date(datetime.MAXYEAR, 12, 31)
171 for other in others:
172 if check.pk == other.pk:
173 # No checks for the object we're validating
174 continue
175
176 max_start = max(check.since, other.since)
177 min_end = min(check.until or date_max, other.until or date_max)
178
179 if max_start == min_end and not can_equal:
180 return True
181 if max_start < min_end:
182 return True
183
184 return False
185
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/website/utils/snippets.py b/website/utils/snippets.py
--- a/website/utils/snippets.py
+++ b/website/utils/snippets.py
@@ -43,9 +43,9 @@
def create_google_maps_url(location, zoom, size):
if location.lower().strip() == "online":
- return static("img/locations/online.png")
+ return settings.BASE_URL + static("img/locations/online.png")
if location.lower().strip() == "discord":
- return static("img/locations/discord.png")
+ return settings.BASE_URL + static("img/locations/discord.png")
maps_url = (
f"/maps/api/staticmap?"
|
{"golden_diff": "diff --git a/website/utils/snippets.py b/website/utils/snippets.py\n--- a/website/utils/snippets.py\n+++ b/website/utils/snippets.py\n@@ -43,9 +43,9 @@\n \n def create_google_maps_url(location, zoom, size):\n if location.lower().strip() == \"online\":\n- return static(\"img/locations/online.png\")\n+ return settings.BASE_URL + static(\"img/locations/online.png\")\n if location.lower().strip() == \"discord\":\n- return static(\"img/locations/discord.png\")\n+ return settings.BASE_URL + static(\"img/locations/discord.png\")\n \n maps_url = (\n f\"/maps/api/staticmap?\"\n", "issue": "URL's from Events API are not always full URL's\n### Describe the bug\r\nThe `google_maps_url` from the Events API is not always a full URL.\r\n\r\n### How to reproduce\r\nSteps to reproduce the behaviour:\r\n1. On staging, go to `https://staging.thalia.nu/api/v1/events/147/` and see that the `google_maps_url` is not a full URL but a relative one.\r\n\r\n### Expected behaviour\r\nThe `google_maps_url` should always be a full URL.\r\n\r\n\n", "before_files": [{"content": "\"\"\"Provides various utilities that are useful across the project.\"\"\"\nimport datetime\nimport hmac\nfrom base64 import urlsafe_b64decode, urlsafe_b64encode\nfrom collections import namedtuple\nfrom _sha1 import sha1\n\nfrom django.conf import settings\nfrom django.template.defaultfilters import urlencode\nfrom django.templatetags.static import static\nfrom django.utils import timezone, dateparse\nfrom rest_framework.exceptions import ParseError\n\n\ndef dict2obj(d, name=\"Object\"):\n return namedtuple(name, d.keys())(*d.values())\n\n\ndef datetime_to_lectureyear(date):\n \"\"\"Convert a :class:`~datetime.date` to the start of the lectureyear.\n\n >>> from datetime import date, datetime, timezone\n >>> nov_23 = date(1990, 11, 7)\n >>> datetime_to_lectureyear(nov_23)\n 1990\n >>> mar_2 = date(1993, 3, 2)\n >>> datetime_to_lectureyear(mar_2)\n 1992\n\n Also works on :class:`~datetime.datetime`, but they need to be tz-aware:\n\n >>> new_year = datetime(2000, 1, 1, tzinfo=timezone.utc)\n >>> datetime_to_lectureyear(new_year)\n 1999\n \"\"\"\n if isinstance(date, timezone.datetime):\n date = timezone.localtime(date).date()\n sept_1 = timezone.make_aware(timezone.datetime(date.year, 9, 1))\n if date < sept_1.date():\n return date.year - 1\n return date.year\n\n\ndef create_google_maps_url(location, zoom, size):\n if location.lower().strip() == \"online\":\n return static(\"img/locations/online.png\")\n if location.lower().strip() == \"discord\":\n return static(\"img/locations/discord.png\")\n\n maps_url = (\n f\"/maps/api/staticmap?\"\n f\"center={ urlencode(location) }&\"\n f\"zoom={ zoom }&size={ size }&\"\n f\"markers={ urlencode(location) }&\"\n f\"key={ settings.GOOGLE_MAPS_API_KEY }\"\n )\n\n decoded_key = urlsafe_b64decode(settings.GOOGLE_MAPS_API_SECRET)\n\n signature = hmac.new(decoded_key, maps_url.encode(), sha1)\n\n encoded_signature = urlsafe_b64encode(signature.digest())\n\n maps_url += f\"&signature={encoded_signature.decode('utf-8')}\"\n\n return \"https://maps.googleapis.com\" + maps_url\n\n\ndef _extract_date(param):\n \"\"\"Extract the date from an arbitrary string.\"\"\"\n if param is None:\n return None\n try:\n return dateparse.parse_datetime(param)\n except ValueError:\n return dateparse.parse_date(param)\n\n\ndef extract_date_range(request, allow_empty=False):\n \"\"\"Extract a date range from an arbitrary string.\"\"\"\n default_value = None\n\n start = request.query_params.get(\"start\", default_value)\n if start or not allow_empty:\n try:\n start = dateparse.parse_datetime(start)\n if not timezone.is_aware(start):\n start = timezone.make_aware(start)\n except (ValueError, AttributeError, TypeError) as e:\n raise ParseError(detail=\"start query parameter invalid\") from e\n\n end = request.query_params.get(\"end\", default_value)\n if end or not allow_empty:\n try:\n end = dateparse.parse_datetime(end)\n if not timezone.is_aware(end):\n end = timezone.make_aware(end)\n except (ValueError, AttributeError, TypeError) as e:\n raise ParseError(detail=\"end query parameter invalid\") from e\n\n return start, end\n\n\ndef overlaps(check, others, can_equal=True):\n \"\"\"Check for overlapping date ranges.\n\n This works by checking the maximum of the two `since` times, and the minimum of\n the two `until` times. Because there are no infinite dates, the value date_max\n is created for when the `until` value is None; this signifies a timespan that\n has not ended yet and is the maximum possible date in Python's datetime.\n\n The ranges overlap when the maximum start time is smaller than the minimum\n end time, as can be seen in this example of two integer ranges:\n\n check: . . . .[4]. . . . 9\n other: . . 2 . .[5]. . . .\n\n check: . . . .[4]. . . . 9\n other: . . 2 . . . . . . . [date_max]\n\n And when non overlapping:\n check: . . . . . .[6] . . 9\n other: . . 2 . .[5]. . . .\n\n 4 < 5 == True so these intervals overlap, while 6 < 5 == False so these intervals\n don't overlap\n\n The can_equal argument is used for boards, where the end date can't be the same\n as the start date.\n\n >>> overlaps( \\\n dict2obj({ \\\n 'pk': 1 \\\n , 'since': datetime.date(2018, 12, 1) \\\n , 'until': datetime.date(2019, 1, 1) \\\n }) \\\n , [dict2obj({ \\\n 'pk': 2 \\\n , 'since': datetime.date(2019, 1, 1) \\\n , 'until': datetime.date(2019, 1, 31) \\\n })])\n False\n\n >>> overlaps( \\\n dict2obj({ \\\n 'pk': 1 \\\n , 'since': datetime.date(2018, 12, 1) \\\n , 'until': datetime.date(2019, 1, 1) \\\n }) \\\n , [dict2obj({ \\\n 'pk': 2 \\\n , 'since': datetime.date(2019, 1, 1) \\\n , 'until': datetime.date(2019, 1, 31) \\\n })], False)\n True\n\n >>> overlaps( \\\n dict2obj({ \\\n 'pk': 1 \\\n , 'since': datetime.date(2018, 12, 1) \\\n , 'until': datetime.date(2019, 1, 2) \\\n }) \\\n , [dict2obj({ \\\n 'pk': 2 \\\n , 'since': datetime.date(2019, 1, 1) \\\n , 'until': datetime.date(2019, 1, 31) \\\n })])\n True\n \"\"\"\n date_max = datetime.date(datetime.MAXYEAR, 12, 31)\n for other in others:\n if check.pk == other.pk:\n # No checks for the object we're validating\n continue\n\n max_start = max(check.since, other.since)\n min_end = min(check.until or date_max, other.until or date_max)\n\n if max_start == min_end and not can_equal:\n return True\n if max_start < min_end:\n return True\n\n return False\n", "path": "website/utils/snippets.py"}], "after_files": [{"content": "\"\"\"Provides various utilities that are useful across the project.\"\"\"\nimport datetime\nimport hmac\nfrom base64 import urlsafe_b64decode, urlsafe_b64encode\nfrom collections import namedtuple\nfrom _sha1 import sha1\n\nfrom django.conf import settings\nfrom django.template.defaultfilters import urlencode\nfrom django.templatetags.static import static\nfrom django.utils import timezone, dateparse\nfrom rest_framework.exceptions import ParseError\n\n\ndef dict2obj(d, name=\"Object\"):\n return namedtuple(name, d.keys())(*d.values())\n\n\ndef datetime_to_lectureyear(date):\n \"\"\"Convert a :class:`~datetime.date` to the start of the lectureyear.\n\n >>> from datetime import date, datetime, timezone\n >>> nov_23 = date(1990, 11, 7)\n >>> datetime_to_lectureyear(nov_23)\n 1990\n >>> mar_2 = date(1993, 3, 2)\n >>> datetime_to_lectureyear(mar_2)\n 1992\n\n Also works on :class:`~datetime.datetime`, but they need to be tz-aware:\n\n >>> new_year = datetime(2000, 1, 1, tzinfo=timezone.utc)\n >>> datetime_to_lectureyear(new_year)\n 1999\n \"\"\"\n if isinstance(date, timezone.datetime):\n date = timezone.localtime(date).date()\n sept_1 = timezone.make_aware(timezone.datetime(date.year, 9, 1))\n if date < sept_1.date():\n return date.year - 1\n return date.year\n\n\ndef create_google_maps_url(location, zoom, size):\n if location.lower().strip() == \"online\":\n return settings.BASE_URL + static(\"img/locations/online.png\")\n if location.lower().strip() == \"discord\":\n return settings.BASE_URL + static(\"img/locations/discord.png\")\n\n maps_url = (\n f\"/maps/api/staticmap?\"\n f\"center={ urlencode(location) }&\"\n f\"zoom={ zoom }&size={ size }&\"\n f\"markers={ urlencode(location) }&\"\n f\"key={ settings.GOOGLE_MAPS_API_KEY }\"\n )\n\n decoded_key = urlsafe_b64decode(settings.GOOGLE_MAPS_API_SECRET)\n\n signature = hmac.new(decoded_key, maps_url.encode(), sha1)\n\n encoded_signature = urlsafe_b64encode(signature.digest())\n\n maps_url += f\"&signature={encoded_signature.decode('utf-8')}\"\n\n return \"https://maps.googleapis.com\" + maps_url\n\n\ndef _extract_date(param):\n \"\"\"Extract the date from an arbitrary string.\"\"\"\n if param is None:\n return None\n try:\n return dateparse.parse_datetime(param)\n except ValueError:\n return dateparse.parse_date(param)\n\n\ndef extract_date_range(request, allow_empty=False):\n \"\"\"Extract a date range from an arbitrary string.\"\"\"\n default_value = None\n\n start = request.query_params.get(\"start\", default_value)\n if start or not allow_empty:\n try:\n start = dateparse.parse_datetime(start)\n if not timezone.is_aware(start):\n start = timezone.make_aware(start)\n except (ValueError, AttributeError, TypeError) as e:\n raise ParseError(detail=\"start query parameter invalid\") from e\n\n end = request.query_params.get(\"end\", default_value)\n if end or not allow_empty:\n try:\n end = dateparse.parse_datetime(end)\n if not timezone.is_aware(end):\n end = timezone.make_aware(end)\n except (ValueError, AttributeError, TypeError) as e:\n raise ParseError(detail=\"end query parameter invalid\") from e\n\n return start, end\n\n\ndef overlaps(check, others, can_equal=True):\n \"\"\"Check for overlapping date ranges.\n\n This works by checking the maximum of the two `since` times, and the minimum of\n the two `until` times. Because there are no infinite dates, the value date_max\n is created for when the `until` value is None; this signifies a timespan that\n has not ended yet and is the maximum possible date in Python's datetime.\n\n The ranges overlap when the maximum start time is smaller than the minimum\n end time, as can be seen in this example of two integer ranges:\n\n check: . . . .[4]. . . . 9\n other: . . 2 . .[5]. . . .\n\n check: . . . .[4]. . . . 9\n other: . . 2 . . . . . . . [date_max]\n\n And when non overlapping:\n check: . . . . . .[6] . . 9\n other: . . 2 . .[5]. . . .\n\n 4 < 5 == True so these intervals overlap, while 6 < 5 == False so these intervals\n don't overlap\n\n The can_equal argument is used for boards, where the end date can't be the same\n as the start date.\n\n >>> overlaps( \\\n dict2obj({ \\\n 'pk': 1 \\\n , 'since': datetime.date(2018, 12, 1) \\\n , 'until': datetime.date(2019, 1, 1) \\\n }) \\\n , [dict2obj({ \\\n 'pk': 2 \\\n , 'since': datetime.date(2019, 1, 1) \\\n , 'until': datetime.date(2019, 1, 31) \\\n })])\n False\n\n >>> overlaps( \\\n dict2obj({ \\\n 'pk': 1 \\\n , 'since': datetime.date(2018, 12, 1) \\\n , 'until': datetime.date(2019, 1, 1) \\\n }) \\\n , [dict2obj({ \\\n 'pk': 2 \\\n , 'since': datetime.date(2019, 1, 1) \\\n , 'until': datetime.date(2019, 1, 31) \\\n })], False)\n True\n\n >>> overlaps( \\\n dict2obj({ \\\n 'pk': 1 \\\n , 'since': datetime.date(2018, 12, 1) \\\n , 'until': datetime.date(2019, 1, 2) \\\n }) \\\n , [dict2obj({ \\\n 'pk': 2 \\\n , 'since': datetime.date(2019, 1, 1) \\\n , 'until': datetime.date(2019, 1, 31) \\\n })])\n True\n \"\"\"\n date_max = datetime.date(datetime.MAXYEAR, 12, 31)\n for other in others:\n if check.pk == other.pk:\n # No checks for the object we're validating\n continue\n\n max_start = max(check.since, other.since)\n min_end = min(check.until or date_max, other.until or date_max)\n\n if max_start == min_end and not can_equal:\n return True\n if max_start < min_end:\n return True\n\n return False\n", "path": "website/utils/snippets.py"}]}
| 2,405 | 152 |
gh_patches_debug_16724
|
rasdani/github-patches
|
git_diff
|
jazzband__pip-tools-828
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
log which python version to use/was used
eg add this to the header:
```
# This file is autogenerated by pip-compile on:
# Python 2.7.15+ (default, Oct 2 2018, 22:12:08)
# [GCC 8.2.0] on linux2
# To update, run:
#
# pip-compile --generate-hashes --output-file=requirements.txt requirements.in
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `piptools/writer.py`
Content:
```
1 import os
2 import re
3 from itertools import chain
4 from typing import BinaryIO, Dict, Iterable, Iterator, List, Optional, Set, Tuple
5
6 from click import unstyle
7 from click.core import Context
8 from pip._internal.models.format_control import FormatControl
9 from pip._internal.req.req_install import InstallRequirement
10 from pip._vendor.packaging.markers import Marker
11
12 from .logging import log
13 from .utils import (
14 UNSAFE_PACKAGES,
15 comment,
16 dedup,
17 format_requirement,
18 get_compile_command,
19 key_from_ireq,
20 )
21
22 MESSAGE_UNHASHED_PACKAGE = comment(
23 "# WARNING: pip install will require the following package to be hashed."
24 "\n# Consider using a hashable URL like "
25 "https://github.com/jazzband/pip-tools/archive/SOMECOMMIT.zip"
26 )
27
28 MESSAGE_UNSAFE_PACKAGES_UNPINNED = comment(
29 "# WARNING: The following packages were not pinned, but pip requires them to be"
30 "\n# pinned when the requirements file includes hashes. "
31 "Consider using the --allow-unsafe flag."
32 )
33
34 MESSAGE_UNSAFE_PACKAGES = comment(
35 "# The following packages are considered to be unsafe in a requirements file:"
36 )
37
38 MESSAGE_UNINSTALLABLE = (
39 "The generated requirements file may be rejected by pip install. "
40 "See # WARNING lines for details."
41 )
42
43
44 strip_comes_from_line_re = re.compile(r" \(line \d+\)$")
45
46
47 def _comes_from_as_string(ireq: InstallRequirement) -> str:
48 if isinstance(ireq.comes_from, str):
49 return strip_comes_from_line_re.sub("", ireq.comes_from)
50 return key_from_ireq(ireq.comes_from)
51
52
53 class OutputWriter:
54 def __init__(
55 self,
56 dst_file: BinaryIO,
57 click_ctx: Context,
58 dry_run: bool,
59 emit_header: bool,
60 emit_index_url: bool,
61 emit_trusted_host: bool,
62 annotate: bool,
63 generate_hashes: bool,
64 default_index_url: str,
65 index_urls: Iterable[str],
66 trusted_hosts: Iterable[str],
67 format_control: FormatControl,
68 allow_unsafe: bool,
69 find_links: List[str],
70 emit_find_links: bool,
71 ) -> None:
72 self.dst_file = dst_file
73 self.click_ctx = click_ctx
74 self.dry_run = dry_run
75 self.emit_header = emit_header
76 self.emit_index_url = emit_index_url
77 self.emit_trusted_host = emit_trusted_host
78 self.annotate = annotate
79 self.generate_hashes = generate_hashes
80 self.default_index_url = default_index_url
81 self.index_urls = index_urls
82 self.trusted_hosts = trusted_hosts
83 self.format_control = format_control
84 self.allow_unsafe = allow_unsafe
85 self.find_links = find_links
86 self.emit_find_links = emit_find_links
87
88 def _sort_key(self, ireq: InstallRequirement) -> Tuple[bool, str]:
89 return (not ireq.editable, str(ireq.req).lower())
90
91 def write_header(self) -> Iterator[str]:
92 if self.emit_header:
93 yield comment("#")
94 yield comment("# This file is autogenerated by pip-compile")
95 yield comment("# To update, run:")
96 yield comment("#")
97 compile_command = os.environ.get(
98 "CUSTOM_COMPILE_COMMAND"
99 ) or get_compile_command(self.click_ctx)
100 yield comment(f"# {compile_command}")
101 yield comment("#")
102
103 def write_index_options(self) -> Iterator[str]:
104 if self.emit_index_url:
105 for index, index_url in enumerate(dedup(self.index_urls)):
106 if index == 0 and index_url.rstrip("/") == self.default_index_url:
107 continue
108 flag = "--index-url" if index == 0 else "--extra-index-url"
109 yield f"{flag} {index_url}"
110
111 def write_trusted_hosts(self) -> Iterator[str]:
112 if self.emit_trusted_host:
113 for trusted_host in dedup(self.trusted_hosts):
114 yield f"--trusted-host {trusted_host}"
115
116 def write_format_controls(self) -> Iterator[str]:
117 for nb in dedup(sorted(self.format_control.no_binary)):
118 yield f"--no-binary {nb}"
119 for ob in dedup(sorted(self.format_control.only_binary)):
120 yield f"--only-binary {ob}"
121
122 def write_find_links(self) -> Iterator[str]:
123 if self.emit_find_links:
124 for find_link in dedup(self.find_links):
125 yield f"--find-links {find_link}"
126
127 def write_flags(self) -> Iterator[str]:
128 emitted = False
129 for line in chain(
130 self.write_index_options(),
131 self.write_find_links(),
132 self.write_trusted_hosts(),
133 self.write_format_controls(),
134 ):
135 emitted = True
136 yield line
137 if emitted:
138 yield ""
139
140 def _iter_lines(
141 self,
142 results: Set[InstallRequirement],
143 unsafe_requirements: Optional[Set[InstallRequirement]] = None,
144 markers: Optional[Dict[str, Marker]] = None,
145 hashes: Optional[Dict[InstallRequirement, Set[str]]] = None,
146 ) -> Iterator[str]:
147 # default values
148 unsafe_requirements = unsafe_requirements or set()
149 markers = markers or {}
150 hashes = hashes or {}
151
152 # Check for unhashed or unpinned packages if at least one package does have
153 # hashes, which will trigger pip install's --require-hashes mode.
154 warn_uninstallable = False
155 has_hashes = hashes and any(hash for hash in hashes.values())
156
157 yielded = False
158
159 for line in self.write_header():
160 yield line
161 yielded = True
162 for line in self.write_flags():
163 yield line
164 yielded = True
165
166 unsafe_requirements = (
167 {r for r in results if r.name in UNSAFE_PACKAGES}
168 if not unsafe_requirements
169 else unsafe_requirements
170 )
171 packages = {r for r in results if r.name not in UNSAFE_PACKAGES}
172
173 if packages:
174 for ireq in sorted(packages, key=self._sort_key):
175 if has_hashes and not hashes.get(ireq):
176 yield MESSAGE_UNHASHED_PACKAGE
177 warn_uninstallable = True
178 line = self._format_requirement(
179 ireq, markers.get(key_from_ireq(ireq)), hashes=hashes
180 )
181 yield line
182 yielded = True
183
184 if unsafe_requirements:
185 yield ""
186 yielded = True
187 if has_hashes and not self.allow_unsafe:
188 yield MESSAGE_UNSAFE_PACKAGES_UNPINNED
189 warn_uninstallable = True
190 else:
191 yield MESSAGE_UNSAFE_PACKAGES
192
193 for ireq in sorted(unsafe_requirements, key=self._sort_key):
194 ireq_key = key_from_ireq(ireq)
195 if not self.allow_unsafe:
196 yield comment(f"# {ireq_key}")
197 else:
198 line = self._format_requirement(
199 ireq, marker=markers.get(ireq_key), hashes=hashes
200 )
201 yield line
202
203 # Yield even when there's no real content, so that blank files are written
204 if not yielded:
205 yield ""
206
207 if warn_uninstallable:
208 log.warning(MESSAGE_UNINSTALLABLE)
209
210 def write(
211 self,
212 results: Set[InstallRequirement],
213 unsafe_requirements: Set[InstallRequirement],
214 markers: Dict[str, Marker],
215 hashes: Optional[Dict[InstallRequirement, Set[str]]],
216 ) -> None:
217
218 for line in self._iter_lines(results, unsafe_requirements, markers, hashes):
219 log.info(line)
220 if not self.dry_run:
221 self.dst_file.write(unstyle(line).encode())
222 self.dst_file.write(os.linesep.encode())
223
224 def _format_requirement(
225 self,
226 ireq: InstallRequirement,
227 marker: Optional[Marker] = None,
228 hashes: Optional[Dict[InstallRequirement, Set[str]]] = None,
229 ) -> str:
230 ireq_hashes = (hashes if hashes is not None else {}).get(ireq)
231
232 line = format_requirement(ireq, marker=marker, hashes=ireq_hashes)
233
234 if not self.annotate:
235 return line
236
237 # Annotate what packages or reqs-ins this package is required by
238 required_by = set()
239 if hasattr(ireq, "_source_ireqs"):
240 required_by |= {
241 _comes_from_as_string(src_ireq)
242 for src_ireq in ireq._source_ireqs
243 if src_ireq.comes_from
244 }
245 elif ireq.comes_from:
246 required_by.add(_comes_from_as_string(ireq))
247
248 if required_by:
249 sorted_required_by = sorted(required_by)
250 if len(sorted_required_by) == 1:
251 source = sorted_required_by[0]
252 annotation = " # via " + source
253 else:
254 annotation_lines = [" # via"]
255 for source in sorted_required_by:
256 annotation_lines.append(" # " + source)
257 annotation = "\n".join(annotation_lines)
258 line = f"{line}\n{comment(annotation)}"
259
260 return line
261
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/piptools/writer.py b/piptools/writer.py
--- a/piptools/writer.py
+++ b/piptools/writer.py
@@ -1,5 +1,6 @@
import os
import re
+import sys
from itertools import chain
from typing import BinaryIO, Dict, Iterable, Iterator, List, Optional, Set, Tuple
@@ -91,7 +92,10 @@
def write_header(self) -> Iterator[str]:
if self.emit_header:
yield comment("#")
- yield comment("# This file is autogenerated by pip-compile")
+ yield comment(
+ "# This file is autogenerated by pip-compile with python "
+ f"{sys.version_info.major}.{sys.version_info.minor}"
+ )
yield comment("# To update, run:")
yield comment("#")
compile_command = os.environ.get(
|
{"golden_diff": "diff --git a/piptools/writer.py b/piptools/writer.py\n--- a/piptools/writer.py\n+++ b/piptools/writer.py\n@@ -1,5 +1,6 @@\n import os\n import re\n+import sys\n from itertools import chain\n from typing import BinaryIO, Dict, Iterable, Iterator, List, Optional, Set, Tuple\n \n@@ -91,7 +92,10 @@\n def write_header(self) -> Iterator[str]:\n if self.emit_header:\n yield comment(\"#\")\n- yield comment(\"# This file is autogenerated by pip-compile\")\n+ yield comment(\n+ \"# This file is autogenerated by pip-compile with python \"\n+ f\"{sys.version_info.major}.{sys.version_info.minor}\"\n+ )\n yield comment(\"# To update, run:\")\n yield comment(\"#\")\n compile_command = os.environ.get(\n", "issue": "log which python version to use/was used\neg add this to the header:\r\n\r\n```\r\n # This file is autogenerated by pip-compile on:\r\n # Python 2.7.15+ (default, Oct 2 2018, 22:12:08) \r\n # [GCC 8.2.0] on linux2\r\n # To update, run:\r\n #\r\n # pip-compile --generate-hashes --output-file=requirements.txt requirements.in\r\n```\n", "before_files": [{"content": "import os\nimport re\nfrom itertools import chain\nfrom typing import BinaryIO, Dict, Iterable, Iterator, List, Optional, Set, Tuple\n\nfrom click import unstyle\nfrom click.core import Context\nfrom pip._internal.models.format_control import FormatControl\nfrom pip._internal.req.req_install import InstallRequirement\nfrom pip._vendor.packaging.markers import Marker\n\nfrom .logging import log\nfrom .utils import (\n UNSAFE_PACKAGES,\n comment,\n dedup,\n format_requirement,\n get_compile_command,\n key_from_ireq,\n)\n\nMESSAGE_UNHASHED_PACKAGE = comment(\n \"# WARNING: pip install will require the following package to be hashed.\"\n \"\\n# Consider using a hashable URL like \"\n \"https://github.com/jazzband/pip-tools/archive/SOMECOMMIT.zip\"\n)\n\nMESSAGE_UNSAFE_PACKAGES_UNPINNED = comment(\n \"# WARNING: The following packages were not pinned, but pip requires them to be\"\n \"\\n# pinned when the requirements file includes hashes. \"\n \"Consider using the --allow-unsafe flag.\"\n)\n\nMESSAGE_UNSAFE_PACKAGES = comment(\n \"# The following packages are considered to be unsafe in a requirements file:\"\n)\n\nMESSAGE_UNINSTALLABLE = (\n \"The generated requirements file may be rejected by pip install. \"\n \"See # WARNING lines for details.\"\n)\n\n\nstrip_comes_from_line_re = re.compile(r\" \\(line \\d+\\)$\")\n\n\ndef _comes_from_as_string(ireq: InstallRequirement) -> str:\n if isinstance(ireq.comes_from, str):\n return strip_comes_from_line_re.sub(\"\", ireq.comes_from)\n return key_from_ireq(ireq.comes_from)\n\n\nclass OutputWriter:\n def __init__(\n self,\n dst_file: BinaryIO,\n click_ctx: Context,\n dry_run: bool,\n emit_header: bool,\n emit_index_url: bool,\n emit_trusted_host: bool,\n annotate: bool,\n generate_hashes: bool,\n default_index_url: str,\n index_urls: Iterable[str],\n trusted_hosts: Iterable[str],\n format_control: FormatControl,\n allow_unsafe: bool,\n find_links: List[str],\n emit_find_links: bool,\n ) -> None:\n self.dst_file = dst_file\n self.click_ctx = click_ctx\n self.dry_run = dry_run\n self.emit_header = emit_header\n self.emit_index_url = emit_index_url\n self.emit_trusted_host = emit_trusted_host\n self.annotate = annotate\n self.generate_hashes = generate_hashes\n self.default_index_url = default_index_url\n self.index_urls = index_urls\n self.trusted_hosts = trusted_hosts\n self.format_control = format_control\n self.allow_unsafe = allow_unsafe\n self.find_links = find_links\n self.emit_find_links = emit_find_links\n\n def _sort_key(self, ireq: InstallRequirement) -> Tuple[bool, str]:\n return (not ireq.editable, str(ireq.req).lower())\n\n def write_header(self) -> Iterator[str]:\n if self.emit_header:\n yield comment(\"#\")\n yield comment(\"# This file is autogenerated by pip-compile\")\n yield comment(\"# To update, run:\")\n yield comment(\"#\")\n compile_command = os.environ.get(\n \"CUSTOM_COMPILE_COMMAND\"\n ) or get_compile_command(self.click_ctx)\n yield comment(f\"# {compile_command}\")\n yield comment(\"#\")\n\n def write_index_options(self) -> Iterator[str]:\n if self.emit_index_url:\n for index, index_url in enumerate(dedup(self.index_urls)):\n if index == 0 and index_url.rstrip(\"/\") == self.default_index_url:\n continue\n flag = \"--index-url\" if index == 0 else \"--extra-index-url\"\n yield f\"{flag} {index_url}\"\n\n def write_trusted_hosts(self) -> Iterator[str]:\n if self.emit_trusted_host:\n for trusted_host in dedup(self.trusted_hosts):\n yield f\"--trusted-host {trusted_host}\"\n\n def write_format_controls(self) -> Iterator[str]:\n for nb in dedup(sorted(self.format_control.no_binary)):\n yield f\"--no-binary {nb}\"\n for ob in dedup(sorted(self.format_control.only_binary)):\n yield f\"--only-binary {ob}\"\n\n def write_find_links(self) -> Iterator[str]:\n if self.emit_find_links:\n for find_link in dedup(self.find_links):\n yield f\"--find-links {find_link}\"\n\n def write_flags(self) -> Iterator[str]:\n emitted = False\n for line in chain(\n self.write_index_options(),\n self.write_find_links(),\n self.write_trusted_hosts(),\n self.write_format_controls(),\n ):\n emitted = True\n yield line\n if emitted:\n yield \"\"\n\n def _iter_lines(\n self,\n results: Set[InstallRequirement],\n unsafe_requirements: Optional[Set[InstallRequirement]] = None,\n markers: Optional[Dict[str, Marker]] = None,\n hashes: Optional[Dict[InstallRequirement, Set[str]]] = None,\n ) -> Iterator[str]:\n # default values\n unsafe_requirements = unsafe_requirements or set()\n markers = markers or {}\n hashes = hashes or {}\n\n # Check for unhashed or unpinned packages if at least one package does have\n # hashes, which will trigger pip install's --require-hashes mode.\n warn_uninstallable = False\n has_hashes = hashes and any(hash for hash in hashes.values())\n\n yielded = False\n\n for line in self.write_header():\n yield line\n yielded = True\n for line in self.write_flags():\n yield line\n yielded = True\n\n unsafe_requirements = (\n {r for r in results if r.name in UNSAFE_PACKAGES}\n if not unsafe_requirements\n else unsafe_requirements\n )\n packages = {r for r in results if r.name not in UNSAFE_PACKAGES}\n\n if packages:\n for ireq in sorted(packages, key=self._sort_key):\n if has_hashes and not hashes.get(ireq):\n yield MESSAGE_UNHASHED_PACKAGE\n warn_uninstallable = True\n line = self._format_requirement(\n ireq, markers.get(key_from_ireq(ireq)), hashes=hashes\n )\n yield line\n yielded = True\n\n if unsafe_requirements:\n yield \"\"\n yielded = True\n if has_hashes and not self.allow_unsafe:\n yield MESSAGE_UNSAFE_PACKAGES_UNPINNED\n warn_uninstallable = True\n else:\n yield MESSAGE_UNSAFE_PACKAGES\n\n for ireq in sorted(unsafe_requirements, key=self._sort_key):\n ireq_key = key_from_ireq(ireq)\n if not self.allow_unsafe:\n yield comment(f\"# {ireq_key}\")\n else:\n line = self._format_requirement(\n ireq, marker=markers.get(ireq_key), hashes=hashes\n )\n yield line\n\n # Yield even when there's no real content, so that blank files are written\n if not yielded:\n yield \"\"\n\n if warn_uninstallable:\n log.warning(MESSAGE_UNINSTALLABLE)\n\n def write(\n self,\n results: Set[InstallRequirement],\n unsafe_requirements: Set[InstallRequirement],\n markers: Dict[str, Marker],\n hashes: Optional[Dict[InstallRequirement, Set[str]]],\n ) -> None:\n\n for line in self._iter_lines(results, unsafe_requirements, markers, hashes):\n log.info(line)\n if not self.dry_run:\n self.dst_file.write(unstyle(line).encode())\n self.dst_file.write(os.linesep.encode())\n\n def _format_requirement(\n self,\n ireq: InstallRequirement,\n marker: Optional[Marker] = None,\n hashes: Optional[Dict[InstallRequirement, Set[str]]] = None,\n ) -> str:\n ireq_hashes = (hashes if hashes is not None else {}).get(ireq)\n\n line = format_requirement(ireq, marker=marker, hashes=ireq_hashes)\n\n if not self.annotate:\n return line\n\n # Annotate what packages or reqs-ins this package is required by\n required_by = set()\n if hasattr(ireq, \"_source_ireqs\"):\n required_by |= {\n _comes_from_as_string(src_ireq)\n for src_ireq in ireq._source_ireqs\n if src_ireq.comes_from\n }\n elif ireq.comes_from:\n required_by.add(_comes_from_as_string(ireq))\n\n if required_by:\n sorted_required_by = sorted(required_by)\n if len(sorted_required_by) == 1:\n source = sorted_required_by[0]\n annotation = \" # via \" + source\n else:\n annotation_lines = [\" # via\"]\n for source in sorted_required_by:\n annotation_lines.append(\" # \" + source)\n annotation = \"\\n\".join(annotation_lines)\n line = f\"{line}\\n{comment(annotation)}\"\n\n return line\n", "path": "piptools/writer.py"}], "after_files": [{"content": "import os\nimport re\nimport sys\nfrom itertools import chain\nfrom typing import BinaryIO, Dict, Iterable, Iterator, List, Optional, Set, Tuple\n\nfrom click import unstyle\nfrom click.core import Context\nfrom pip._internal.models.format_control import FormatControl\nfrom pip._internal.req.req_install import InstallRequirement\nfrom pip._vendor.packaging.markers import Marker\n\nfrom .logging import log\nfrom .utils import (\n UNSAFE_PACKAGES,\n comment,\n dedup,\n format_requirement,\n get_compile_command,\n key_from_ireq,\n)\n\nMESSAGE_UNHASHED_PACKAGE = comment(\n \"# WARNING: pip install will require the following package to be hashed.\"\n \"\\n# Consider using a hashable URL like \"\n \"https://github.com/jazzband/pip-tools/archive/SOMECOMMIT.zip\"\n)\n\nMESSAGE_UNSAFE_PACKAGES_UNPINNED = comment(\n \"# WARNING: The following packages were not pinned, but pip requires them to be\"\n \"\\n# pinned when the requirements file includes hashes. \"\n \"Consider using the --allow-unsafe flag.\"\n)\n\nMESSAGE_UNSAFE_PACKAGES = comment(\n \"# The following packages are considered to be unsafe in a requirements file:\"\n)\n\nMESSAGE_UNINSTALLABLE = (\n \"The generated requirements file may be rejected by pip install. \"\n \"See # WARNING lines for details.\"\n)\n\n\nstrip_comes_from_line_re = re.compile(r\" \\(line \\d+\\)$\")\n\n\ndef _comes_from_as_string(ireq: InstallRequirement) -> str:\n if isinstance(ireq.comes_from, str):\n return strip_comes_from_line_re.sub(\"\", ireq.comes_from)\n return key_from_ireq(ireq.comes_from)\n\n\nclass OutputWriter:\n def __init__(\n self,\n dst_file: BinaryIO,\n click_ctx: Context,\n dry_run: bool,\n emit_header: bool,\n emit_index_url: bool,\n emit_trusted_host: bool,\n annotate: bool,\n generate_hashes: bool,\n default_index_url: str,\n index_urls: Iterable[str],\n trusted_hosts: Iterable[str],\n format_control: FormatControl,\n allow_unsafe: bool,\n find_links: List[str],\n emit_find_links: bool,\n ) -> None:\n self.dst_file = dst_file\n self.click_ctx = click_ctx\n self.dry_run = dry_run\n self.emit_header = emit_header\n self.emit_index_url = emit_index_url\n self.emit_trusted_host = emit_trusted_host\n self.annotate = annotate\n self.generate_hashes = generate_hashes\n self.default_index_url = default_index_url\n self.index_urls = index_urls\n self.trusted_hosts = trusted_hosts\n self.format_control = format_control\n self.allow_unsafe = allow_unsafe\n self.find_links = find_links\n self.emit_find_links = emit_find_links\n\n def _sort_key(self, ireq: InstallRequirement) -> Tuple[bool, str]:\n return (not ireq.editable, str(ireq.req).lower())\n\n def write_header(self) -> Iterator[str]:\n if self.emit_header:\n yield comment(\"#\")\n yield comment(\n \"# This file is autogenerated by pip-compile with python \"\n f\"{sys.version_info.major}.{sys.version_info.minor}\"\n )\n yield comment(\"# To update, run:\")\n yield comment(\"#\")\n compile_command = os.environ.get(\n \"CUSTOM_COMPILE_COMMAND\"\n ) or get_compile_command(self.click_ctx)\n yield comment(f\"# {compile_command}\")\n yield comment(\"#\")\n\n def write_index_options(self) -> Iterator[str]:\n if self.emit_index_url:\n for index, index_url in enumerate(dedup(self.index_urls)):\n if index == 0 and index_url.rstrip(\"/\") == self.default_index_url:\n continue\n flag = \"--index-url\" if index == 0 else \"--extra-index-url\"\n yield f\"{flag} {index_url}\"\n\n def write_trusted_hosts(self) -> Iterator[str]:\n if self.emit_trusted_host:\n for trusted_host in dedup(self.trusted_hosts):\n yield f\"--trusted-host {trusted_host}\"\n\n def write_format_controls(self) -> Iterator[str]:\n for nb in dedup(sorted(self.format_control.no_binary)):\n yield f\"--no-binary {nb}\"\n for ob in dedup(sorted(self.format_control.only_binary)):\n yield f\"--only-binary {ob}\"\n\n def write_find_links(self) -> Iterator[str]:\n if self.emit_find_links:\n for find_link in dedup(self.find_links):\n yield f\"--find-links {find_link}\"\n\n def write_flags(self) -> Iterator[str]:\n emitted = False\n for line in chain(\n self.write_index_options(),\n self.write_find_links(),\n self.write_trusted_hosts(),\n self.write_format_controls(),\n ):\n emitted = True\n yield line\n if emitted:\n yield \"\"\n\n def _iter_lines(\n self,\n results: Set[InstallRequirement],\n unsafe_requirements: Optional[Set[InstallRequirement]] = None,\n markers: Optional[Dict[str, Marker]] = None,\n hashes: Optional[Dict[InstallRequirement, Set[str]]] = None,\n ) -> Iterator[str]:\n # default values\n unsafe_requirements = unsafe_requirements or set()\n markers = markers or {}\n hashes = hashes or {}\n\n # Check for unhashed or unpinned packages if at least one package does have\n # hashes, which will trigger pip install's --require-hashes mode.\n warn_uninstallable = False\n has_hashes = hashes and any(hash for hash in hashes.values())\n\n yielded = False\n\n for line in self.write_header():\n yield line\n yielded = True\n for line in self.write_flags():\n yield line\n yielded = True\n\n unsafe_requirements = (\n {r for r in results if r.name in UNSAFE_PACKAGES}\n if not unsafe_requirements\n else unsafe_requirements\n )\n packages = {r for r in results if r.name not in UNSAFE_PACKAGES}\n\n if packages:\n for ireq in sorted(packages, key=self._sort_key):\n if has_hashes and not hashes.get(ireq):\n yield MESSAGE_UNHASHED_PACKAGE\n warn_uninstallable = True\n line = self._format_requirement(\n ireq, markers.get(key_from_ireq(ireq)), hashes=hashes\n )\n yield line\n yielded = True\n\n if unsafe_requirements:\n yield \"\"\n yielded = True\n if has_hashes and not self.allow_unsafe:\n yield MESSAGE_UNSAFE_PACKAGES_UNPINNED\n warn_uninstallable = True\n else:\n yield MESSAGE_UNSAFE_PACKAGES\n\n for ireq in sorted(unsafe_requirements, key=self._sort_key):\n ireq_key = key_from_ireq(ireq)\n if not self.allow_unsafe:\n yield comment(f\"# {ireq_key}\")\n else:\n line = self._format_requirement(\n ireq, marker=markers.get(ireq_key), hashes=hashes\n )\n yield line\n\n # Yield even when there's no real content, so that blank files are written\n if not yielded:\n yield \"\"\n\n if warn_uninstallable:\n log.warning(MESSAGE_UNINSTALLABLE)\n\n def write(\n self,\n results: Set[InstallRequirement],\n unsafe_requirements: Set[InstallRequirement],\n markers: Dict[str, Marker],\n hashes: Optional[Dict[InstallRequirement, Set[str]]],\n ) -> None:\n\n for line in self._iter_lines(results, unsafe_requirements, markers, hashes):\n log.info(line)\n if not self.dry_run:\n self.dst_file.write(unstyle(line).encode())\n self.dst_file.write(os.linesep.encode())\n\n def _format_requirement(\n self,\n ireq: InstallRequirement,\n marker: Optional[Marker] = None,\n hashes: Optional[Dict[InstallRequirement, Set[str]]] = None,\n ) -> str:\n ireq_hashes = (hashes if hashes is not None else {}).get(ireq)\n\n line = format_requirement(ireq, marker=marker, hashes=ireq_hashes)\n\n if not self.annotate:\n return line\n\n # Annotate what packages or reqs-ins this package is required by\n required_by = set()\n if hasattr(ireq, \"_source_ireqs\"):\n required_by |= {\n _comes_from_as_string(src_ireq)\n for src_ireq in ireq._source_ireqs\n if src_ireq.comes_from\n }\n elif ireq.comes_from:\n required_by.add(_comes_from_as_string(ireq))\n\n if required_by:\n sorted_required_by = sorted(required_by)\n if len(sorted_required_by) == 1:\n source = sorted_required_by[0]\n annotation = \" # via \" + source\n else:\n annotation_lines = [\" # via\"]\n for source in sorted_required_by:\n annotation_lines.append(\" # \" + source)\n annotation = \"\\n\".join(annotation_lines)\n line = f\"{line}\\n{comment(annotation)}\"\n\n return line\n", "path": "piptools/writer.py"}]}
| 3,003 | 188 |
gh_patches_debug_5037
|
rasdani/github-patches
|
git_diff
|
facebookresearch__hydra-793
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[Bug] MISSING for Object Conf cls argument
# 🐛 Bug
OmegaConf cls argument should not be a mandatory value if target is defined. Can we change this to be an optional value with None being the default?
** Stack trace/error message **
```
omegaconf.errors.MissingMandatoryValue: Missing mandatory value: scheduler.cls
full_key: scheduler.cls
reference_type=ObjectConf
object_type=ObjectConf
```
## System information
- **Hydra Version** : 1.0.0rc2
- **Python version** : 3.7.7
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `hydra/types.py`
Content:
```
1 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
2 from dataclasses import dataclass, field
3 from enum import Enum
4 from typing import Any, Callable, Dict
5
6 from omegaconf import MISSING
7
8 TaskFunction = Callable[[Any], Any]
9
10
11 @dataclass
12 # This extends Dict[str, Any] to allow for the deprecated "class" field.
13 # Once support for class field removed this can stop extending Dict.
14 class ObjectConf(Dict[str, Any]):
15 # class, class method or function name
16 target: str = MISSING
17
18 # parameters to pass to cls when calling it
19 params: Any = field(default_factory=dict)
20
21 # cls is deprecated, use target, cls will be removed in Hydra 1.1
22 cls: str = MISSING
23
24 # class is deprecated, use target, class will be removed in Hydra 1.1
25 # (class is Python keyword and is only supported through DictConfig)
26 # class: str = MISSING
27
28
29 class RunMode(Enum):
30 RUN = 1
31 MULTIRUN = 2
32
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/hydra/types.py b/hydra/types.py
--- a/hydra/types.py
+++ b/hydra/types.py
@@ -18,13 +18,6 @@
# parameters to pass to cls when calling it
params: Any = field(default_factory=dict)
- # cls is deprecated, use target, cls will be removed in Hydra 1.1
- cls: str = MISSING
-
- # class is deprecated, use target, class will be removed in Hydra 1.1
- # (class is Python keyword and is only supported through DictConfig)
- # class: str = MISSING
-
class RunMode(Enum):
RUN = 1
|
{"golden_diff": "diff --git a/hydra/types.py b/hydra/types.py\n--- a/hydra/types.py\n+++ b/hydra/types.py\n@@ -18,13 +18,6 @@\n # parameters to pass to cls when calling it\n params: Any = field(default_factory=dict)\n \n- # cls is deprecated, use target, cls will be removed in Hydra 1.1\n- cls: str = MISSING\n-\n- # class is deprecated, use target, class will be removed in Hydra 1.1\n- # (class is Python keyword and is only supported through DictConfig)\n- # class: str = MISSING\n-\n \n class RunMode(Enum):\n RUN = 1\n", "issue": "[Bug] MISSING for Object Conf cls argument\n# \ud83d\udc1b Bug\r\n\r\nOmegaConf cls argument should not be a mandatory value if target is defined. Can we change this to be an optional value with None being the default?\r\n \r\n** Stack trace/error message **\r\n```\r\nomegaconf.errors.MissingMandatoryValue: Missing mandatory value: scheduler.cls\r\n full_key: scheduler.cls\r\n reference_type=ObjectConf\r\n object_type=ObjectConf\r\n```\r\n\r\n\r\n## System information\r\n- **Hydra Version** : 1.0.0rc2\r\n- **Python version** : 3.7.7\r\n\n", "before_files": [{"content": "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved\nfrom dataclasses import dataclass, field\nfrom enum import Enum\nfrom typing import Any, Callable, Dict\n\nfrom omegaconf import MISSING\n\nTaskFunction = Callable[[Any], Any]\n\n\n@dataclass\n# This extends Dict[str, Any] to allow for the deprecated \"class\" field.\n# Once support for class field removed this can stop extending Dict.\nclass ObjectConf(Dict[str, Any]):\n # class, class method or function name\n target: str = MISSING\n\n # parameters to pass to cls when calling it\n params: Any = field(default_factory=dict)\n\n # cls is deprecated, use target, cls will be removed in Hydra 1.1\n cls: str = MISSING\n\n # class is deprecated, use target, class will be removed in Hydra 1.1\n # (class is Python keyword and is only supported through DictConfig)\n # class: str = MISSING\n\n\nclass RunMode(Enum):\n RUN = 1\n MULTIRUN = 2\n", "path": "hydra/types.py"}], "after_files": [{"content": "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved\nfrom dataclasses import dataclass, field\nfrom enum import Enum\nfrom typing import Any, Callable, Dict\n\nfrom omegaconf import MISSING\n\nTaskFunction = Callable[[Any], Any]\n\n\n@dataclass\n# This extends Dict[str, Any] to allow for the deprecated \"class\" field.\n# Once support for class field removed this can stop extending Dict.\nclass ObjectConf(Dict[str, Any]):\n # class, class method or function name\n target: str = MISSING\n\n # parameters to pass to cls when calling it\n params: Any = field(default_factory=dict)\n\n\nclass RunMode(Enum):\n RUN = 1\n MULTIRUN = 2\n", "path": "hydra/types.py"}]}
| 678 | 156 |
gh_patches_debug_245
|
rasdani/github-patches
|
git_diff
|
mlcommons__GaNDLF-809
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
`gdown` does not seem to be working
**Describe the bug**
Current CI seems to be broken.
**To Reproduce**
Steps to reproduce the behavior:
1. Run any CI test
2. See error:
```python-traceback
[SNIP!]
if gdrive_file_id and is_gdrive_download_link:
content_disposition = six.moves.urllib_parse.unquote(
res.headers["Content-Disposition"]
)
m = re.search(r"filename\*=UTF-8''(.*)", content_disposition)
> filename_from_url = m.groups()[0]
E AttributeError: 'NoneType' object has no attribute 'groups'
```
Example: https://github.com/mlcommons/GaNDLF/actions/runs/7489779631/job/20387346791?pr=764#step:9:219
**Expected behavior**
The sample data file download should work.
**Screenshots**
N.A.
**GaNDLF Version**
Current master
**Desktop (please complete the following information):**
N.A.
**Additional context**
Basically, it is this error: https://github.com/wkentaro/gdown/issues/291
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 #!/usr/bin/env python
2
3 """The setup script."""
4
5
6 import sys, re, os
7 from setuptools import setup, find_packages
8 from setuptools.command.install import install
9 from setuptools.command.develop import develop
10 from setuptools.command.egg_info import egg_info
11
12 try:
13 with open("README.md") as readme_file:
14 readme = readme_file.read()
15 except Exception as error:
16 readme = "No README information found."
17 sys.stderr.write(
18 "Warning: Could not open '%s' due %s\n" % ("README.md", error)
19 )
20
21
22 class CustomInstallCommand(install):
23 def run(self):
24 install.run(self)
25
26
27 class CustomDevelopCommand(develop):
28 def run(self):
29 develop.run(self)
30
31
32 class CustomEggInfoCommand(egg_info):
33 def run(self):
34 egg_info.run(self)
35
36
37 try:
38 filepath = "GANDLF/version.py"
39 version_file = open(filepath)
40 (__version__,) = re.findall('__version__ = "(.*)"', version_file.read())
41
42 except Exception as error:
43 __version__ = "0.0.1"
44 sys.stderr.write(
45 "Warning: Could not open '%s' due %s\n" % (filepath, error)
46 )
47
48 # Handle cases where specific files need to be bundled into the final package as installed via PyPI
49 dockerfiles = [
50 item
51 for item in os.listdir(os.path.dirname(os.path.abspath(__file__)))
52 if (os.path.isfile(item) and item.startswith("Dockerfile-"))
53 ]
54 entrypoint_files = [
55 item
56 for item in os.listdir(os.path.dirname(os.path.abspath(__file__)))
57 if (os.path.isfile(item) and item.startswith("gandlf_"))
58 ]
59 setup_files = ["setup.py", ".dockerignore", "pyproject.toml", "MANIFEST.in"]
60 all_extra_files = dockerfiles + entrypoint_files + setup_files
61 all_extra_files_pathcorrected = [
62 os.path.join("../", item) for item in all_extra_files
63 ]
64 # find_packages should only ever find these as subpackages of gandlf, not as top-level packages
65 # generate this dynamically?
66 # GANDLF.GANDLF is needed to prevent recursion madness in deployments
67 toplevel_package_excludes = [
68 "GANDLF.GANDLF",
69 "anonymize",
70 "cli",
71 "compute",
72 "data",
73 "grad_clipping",
74 "losses",
75 "metrics",
76 "models",
77 "optimizers",
78 "schedulers",
79 "utils",
80 ]
81
82
83 requirements = [
84 "torch==2.1.2",
85 "black==23.11.0",
86 "numpy==1.25.0",
87 "scipy",
88 "SimpleITK!=2.0.*",
89 "SimpleITK!=2.2.1", # https://github.com/mlcommons/GaNDLF/issues/536
90 "torchvision",
91 "tqdm",
92 "torchio==0.19.5",
93 "pandas>=2.0.0",
94 "scikit-learn>=0.23.2",
95 "scikit-image>=0.19.1",
96 "setuptools",
97 "seaborn",
98 "pyyaml",
99 "tiffslide",
100 "matplotlib",
101 "gdown==4.6.3",
102 "pytest",
103 "coverage",
104 "pytest-cov",
105 "psutil",
106 "medcam",
107 "opencv-python",
108 "torchmetrics==1.1.2",
109 "zarr==2.10.3",
110 "pydicom",
111 "onnx",
112 "torchinfo==1.7.0",
113 "segmentation-models-pytorch==0.3.3",
114 "ACSConv==0.1.1",
115 "docker",
116 "dicom-anonymizer",
117 "twine",
118 "zarr",
119 "keyring",
120 "monai==1.3.0",
121 ]
122
123 if __name__ == "__main__":
124 setup(
125 name="GANDLF",
126 version=__version__,
127 author="MLCommons",
128 author_email="[email protected]",
129 python_requires=">3.8, <3.12",
130 packages=find_packages(
131 where=os.path.dirname(os.path.abspath(__file__)),
132 exclude=toplevel_package_excludes,
133 ),
134 cmdclass={
135 "install": CustomInstallCommand,
136 "develop": CustomDevelopCommand,
137 "egg_info": CustomEggInfoCommand,
138 },
139 scripts=[
140 "gandlf_run",
141 "gandlf_constructCSV",
142 "gandlf_collectStats",
143 "gandlf_patchMiner",
144 "gandlf_preprocess",
145 "gandlf_anonymizer",
146 "gandlf_verifyInstall",
147 "gandlf_configGenerator",
148 "gandlf_recoverConfig",
149 "gandlf_deploy",
150 "gandlf_optimizeModel",
151 "gandlf_generateMetrics",
152 ],
153 classifiers=[
154 "Development Status :: 3 - Alpha",
155 "Intended Audience :: Science/Research",
156 "License :: OSI Approved :: Apache Software License",
157 "Natural Language :: English",
158 "Operating System :: OS Independent",
159 "Programming Language :: Python :: 3.9",
160 "Programming Language :: Python :: 3.10",
161 "Programming Language :: Python :: 3.11",
162 "Topic :: Scientific/Engineering :: Medical Science Apps.",
163 ],
164 description=(
165 "PyTorch-based framework that handles segmentation/regression/classification using various DL architectures for medical imaging."
166 ),
167 install_requires=requirements,
168 license="Apache-2.0",
169 long_description=readme,
170 long_description_content_type="text/markdown",
171 include_package_data=True,
172 package_data={"GANDLF": all_extra_files_pathcorrected},
173 keywords="semantic, segmentation, regression, classification, data-augmentation, medical-imaging, clinical-workflows, deep-learning, pytorch",
174 zip_safe=False,
175 )
176
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -98,7 +98,7 @@
"pyyaml",
"tiffslide",
"matplotlib",
- "gdown==4.6.3",
+ "gdown==5.1.0",
"pytest",
"coverage",
"pytest-cov",
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -98,7 +98,7 @@\n \"pyyaml\",\n \"tiffslide\",\n \"matplotlib\",\n- \"gdown==4.6.3\",\n+ \"gdown==5.1.0\",\n \"pytest\",\n \"coverage\",\n \"pytest-cov\",\n", "issue": "`gdown` does not seem to be working\n**Describe the bug**\r\nCurrent CI seems to be broken.\r\n\r\n**To Reproduce**\r\nSteps to reproduce the behavior:\r\n1. Run any CI test\r\n2. See error:\r\n```python-traceback\r\n[SNIP!]\r\n if gdrive_file_id and is_gdrive_download_link:\r\n content_disposition = six.moves.urllib_parse.unquote(\r\n res.headers[\"Content-Disposition\"]\r\n )\r\n m = re.search(r\"filename\\*=UTF-8''(.*)\", content_disposition)\r\n> filename_from_url = m.groups()[0]\r\nE AttributeError: 'NoneType' object has no attribute 'groups'\r\n```\r\nExample: https://github.com/mlcommons/GaNDLF/actions/runs/7489779631/job/20387346791?pr=764#step:9:219\r\n\r\n**Expected behavior**\r\nThe sample data file download should work.\r\n\r\n**Screenshots**\r\nN.A.\r\n\r\n**GaNDLF Version**\r\nCurrent master\r\n\r\n**Desktop (please complete the following information):**\r\nN.A.\r\n\r\n**Additional context**\r\nBasically, it is this error: https://github.com/wkentaro/gdown/issues/291\r\n\n", "before_files": [{"content": "#!/usr/bin/env python\n\n\"\"\"The setup script.\"\"\"\n\n\nimport sys, re, os\nfrom setuptools import setup, find_packages\nfrom setuptools.command.install import install\nfrom setuptools.command.develop import develop\nfrom setuptools.command.egg_info import egg_info\n\ntry:\n with open(\"README.md\") as readme_file:\n readme = readme_file.read()\nexcept Exception as error:\n readme = \"No README information found.\"\n sys.stderr.write(\n \"Warning: Could not open '%s' due %s\\n\" % (\"README.md\", error)\n )\n\n\nclass CustomInstallCommand(install):\n def run(self):\n install.run(self)\n\n\nclass CustomDevelopCommand(develop):\n def run(self):\n develop.run(self)\n\n\nclass CustomEggInfoCommand(egg_info):\n def run(self):\n egg_info.run(self)\n\n\ntry:\n filepath = \"GANDLF/version.py\"\n version_file = open(filepath)\n (__version__,) = re.findall('__version__ = \"(.*)\"', version_file.read())\n\nexcept Exception as error:\n __version__ = \"0.0.1\"\n sys.stderr.write(\n \"Warning: Could not open '%s' due %s\\n\" % (filepath, error)\n )\n\n# Handle cases where specific files need to be bundled into the final package as installed via PyPI\ndockerfiles = [\n item\n for item in os.listdir(os.path.dirname(os.path.abspath(__file__)))\n if (os.path.isfile(item) and item.startswith(\"Dockerfile-\"))\n]\nentrypoint_files = [\n item\n for item in os.listdir(os.path.dirname(os.path.abspath(__file__)))\n if (os.path.isfile(item) and item.startswith(\"gandlf_\"))\n]\nsetup_files = [\"setup.py\", \".dockerignore\", \"pyproject.toml\", \"MANIFEST.in\"]\nall_extra_files = dockerfiles + entrypoint_files + setup_files\nall_extra_files_pathcorrected = [\n os.path.join(\"../\", item) for item in all_extra_files\n]\n# find_packages should only ever find these as subpackages of gandlf, not as top-level packages\n# generate this dynamically?\n# GANDLF.GANDLF is needed to prevent recursion madness in deployments\ntoplevel_package_excludes = [\n \"GANDLF.GANDLF\",\n \"anonymize\",\n \"cli\",\n \"compute\",\n \"data\",\n \"grad_clipping\",\n \"losses\",\n \"metrics\",\n \"models\",\n \"optimizers\",\n \"schedulers\",\n \"utils\",\n]\n\n\nrequirements = [\n \"torch==2.1.2\",\n \"black==23.11.0\",\n \"numpy==1.25.0\",\n \"scipy\",\n \"SimpleITK!=2.0.*\",\n \"SimpleITK!=2.2.1\", # https://github.com/mlcommons/GaNDLF/issues/536\n \"torchvision\",\n \"tqdm\",\n \"torchio==0.19.5\",\n \"pandas>=2.0.0\",\n \"scikit-learn>=0.23.2\",\n \"scikit-image>=0.19.1\",\n \"setuptools\",\n \"seaborn\",\n \"pyyaml\",\n \"tiffslide\",\n \"matplotlib\",\n \"gdown==4.6.3\",\n \"pytest\",\n \"coverage\",\n \"pytest-cov\",\n \"psutil\",\n \"medcam\",\n \"opencv-python\",\n \"torchmetrics==1.1.2\",\n \"zarr==2.10.3\",\n \"pydicom\",\n \"onnx\",\n \"torchinfo==1.7.0\",\n \"segmentation-models-pytorch==0.3.3\",\n \"ACSConv==0.1.1\",\n \"docker\",\n \"dicom-anonymizer\",\n \"twine\",\n \"zarr\",\n \"keyring\",\n \"monai==1.3.0\",\n]\n\nif __name__ == \"__main__\":\n setup(\n name=\"GANDLF\",\n version=__version__,\n author=\"MLCommons\",\n author_email=\"[email protected]\",\n python_requires=\">3.8, <3.12\",\n packages=find_packages(\n where=os.path.dirname(os.path.abspath(__file__)),\n exclude=toplevel_package_excludes,\n ),\n cmdclass={\n \"install\": CustomInstallCommand,\n \"develop\": CustomDevelopCommand,\n \"egg_info\": CustomEggInfoCommand,\n },\n scripts=[\n \"gandlf_run\",\n \"gandlf_constructCSV\",\n \"gandlf_collectStats\",\n \"gandlf_patchMiner\",\n \"gandlf_preprocess\",\n \"gandlf_anonymizer\",\n \"gandlf_verifyInstall\",\n \"gandlf_configGenerator\",\n \"gandlf_recoverConfig\",\n \"gandlf_deploy\",\n \"gandlf_optimizeModel\",\n \"gandlf_generateMetrics\",\n ],\n classifiers=[\n \"Development Status :: 3 - Alpha\",\n \"Intended Audience :: Science/Research\",\n \"License :: OSI Approved :: Apache Software License\",\n \"Natural Language :: English\",\n \"Operating System :: OS Independent\",\n \"Programming Language :: Python :: 3.9\",\n \"Programming Language :: Python :: 3.10\",\n \"Programming Language :: Python :: 3.11\",\n \"Topic :: Scientific/Engineering :: Medical Science Apps.\",\n ],\n description=(\n \"PyTorch-based framework that handles segmentation/regression/classification using various DL architectures for medical imaging.\"\n ),\n install_requires=requirements,\n license=\"Apache-2.0\",\n long_description=readme,\n long_description_content_type=\"text/markdown\",\n include_package_data=True,\n package_data={\"GANDLF\": all_extra_files_pathcorrected},\n keywords=\"semantic, segmentation, regression, classification, data-augmentation, medical-imaging, clinical-workflows, deep-learning, pytorch\",\n zip_safe=False,\n )\n", "path": "setup.py"}], "after_files": [{"content": "#!/usr/bin/env python\n\n\"\"\"The setup script.\"\"\"\n\n\nimport sys, re, os\nfrom setuptools import setup, find_packages\nfrom setuptools.command.install import install\nfrom setuptools.command.develop import develop\nfrom setuptools.command.egg_info import egg_info\n\ntry:\n with open(\"README.md\") as readme_file:\n readme = readme_file.read()\nexcept Exception as error:\n readme = \"No README information found.\"\n sys.stderr.write(\n \"Warning: Could not open '%s' due %s\\n\" % (\"README.md\", error)\n )\n\n\nclass CustomInstallCommand(install):\n def run(self):\n install.run(self)\n\n\nclass CustomDevelopCommand(develop):\n def run(self):\n develop.run(self)\n\n\nclass CustomEggInfoCommand(egg_info):\n def run(self):\n egg_info.run(self)\n\n\ntry:\n filepath = \"GANDLF/version.py\"\n version_file = open(filepath)\n (__version__,) = re.findall('__version__ = \"(.*)\"', version_file.read())\n\nexcept Exception as error:\n __version__ = \"0.0.1\"\n sys.stderr.write(\n \"Warning: Could not open '%s' due %s\\n\" % (filepath, error)\n )\n\n# Handle cases where specific files need to be bundled into the final package as installed via PyPI\ndockerfiles = [\n item\n for item in os.listdir(os.path.dirname(os.path.abspath(__file__)))\n if (os.path.isfile(item) and item.startswith(\"Dockerfile-\"))\n]\nentrypoint_files = [\n item\n for item in os.listdir(os.path.dirname(os.path.abspath(__file__)))\n if (os.path.isfile(item) and item.startswith(\"gandlf_\"))\n]\nsetup_files = [\"setup.py\", \".dockerignore\", \"pyproject.toml\", \"MANIFEST.in\"]\nall_extra_files = dockerfiles + entrypoint_files + setup_files\nall_extra_files_pathcorrected = [\n os.path.join(\"../\", item) for item in all_extra_files\n]\n# find_packages should only ever find these as subpackages of gandlf, not as top-level packages\n# generate this dynamically?\n# GANDLF.GANDLF is needed to prevent recursion madness in deployments\ntoplevel_package_excludes = [\n \"GANDLF.GANDLF\",\n \"anonymize\",\n \"cli\",\n \"compute\",\n \"data\",\n \"grad_clipping\",\n \"losses\",\n \"metrics\",\n \"models\",\n \"optimizers\",\n \"schedulers\",\n \"utils\",\n]\n\n\nrequirements = [\n \"torch==2.1.2\",\n \"black==23.11.0\",\n \"numpy==1.25.0\",\n \"scipy\",\n \"SimpleITK!=2.0.*\",\n \"SimpleITK!=2.2.1\", # https://github.com/mlcommons/GaNDLF/issues/536\n \"torchvision\",\n \"tqdm\",\n \"torchio==0.19.5\",\n \"pandas>=2.0.0\",\n \"scikit-learn>=0.23.2\",\n \"scikit-image>=0.19.1\",\n \"setuptools\",\n \"seaborn\",\n \"pyyaml\",\n \"tiffslide\",\n \"matplotlib\",\n \"gdown==5.1.0\",\n \"pytest\",\n \"coverage\",\n \"pytest-cov\",\n \"psutil\",\n \"medcam\",\n \"opencv-python\",\n \"torchmetrics==1.1.2\",\n \"zarr==2.10.3\",\n \"pydicom\",\n \"onnx\",\n \"torchinfo==1.7.0\",\n \"segmentation-models-pytorch==0.3.3\",\n \"ACSConv==0.1.1\",\n \"docker\",\n \"dicom-anonymizer\",\n \"twine\",\n \"zarr\",\n \"keyring\",\n \"monai==1.3.0\",\n]\n\nif __name__ == \"__main__\":\n setup(\n name=\"GANDLF\",\n version=__version__,\n author=\"MLCommons\",\n author_email=\"[email protected]\",\n python_requires=\">3.8, <3.12\",\n packages=find_packages(\n where=os.path.dirname(os.path.abspath(__file__)),\n exclude=toplevel_package_excludes,\n ),\n cmdclass={\n \"install\": CustomInstallCommand,\n \"develop\": CustomDevelopCommand,\n \"egg_info\": CustomEggInfoCommand,\n },\n scripts=[\n \"gandlf_run\",\n \"gandlf_constructCSV\",\n \"gandlf_collectStats\",\n \"gandlf_patchMiner\",\n \"gandlf_preprocess\",\n \"gandlf_anonymizer\",\n \"gandlf_verifyInstall\",\n \"gandlf_configGenerator\",\n \"gandlf_recoverConfig\",\n \"gandlf_deploy\",\n \"gandlf_optimizeModel\",\n \"gandlf_generateMetrics\",\n ],\n classifiers=[\n \"Development Status :: 3 - Alpha\",\n \"Intended Audience :: Science/Research\",\n \"License :: OSI Approved :: Apache Software License\",\n \"Natural Language :: English\",\n \"Operating System :: OS Independent\",\n \"Programming Language :: Python :: 3.9\",\n \"Programming Language :: Python :: 3.10\",\n \"Programming Language :: Python :: 3.11\",\n \"Topic :: Scientific/Engineering :: Medical Science Apps.\",\n ],\n description=(\n \"PyTorch-based framework that handles segmentation/regression/classification using various DL architectures for medical imaging.\"\n ),\n install_requires=requirements,\n license=\"Apache-2.0\",\n long_description=readme,\n long_description_content_type=\"text/markdown\",\n include_package_data=True,\n package_data={\"GANDLF\": all_extra_files_pathcorrected},\n keywords=\"semantic, segmentation, regression, classification, data-augmentation, medical-imaging, clinical-workflows, deep-learning, pytorch\",\n zip_safe=False,\n )\n", "path": "setup.py"}]}
| 2,241 | 85 |
gh_patches_debug_9165
|
rasdani/github-patches
|
git_diff
|
microsoft__DeepSpeed-1921
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[BUG] No module named 'fcntl' while importing the package
Hey,
Working on windows 11, Python 3.7 and tried importing the package.
Got the error in the title, is there a way around it since it's exclusive to Linux?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `deepspeed/utils/debug.py`
Content:
```
1 """ debug utils """
2
3 import fcntl
4
5 # for debug purposes map module and param objects to their fully qualified names
6 module_names = {}
7 param_names = {}
8
9
10 def debug_extract_module_and_param_names(model):
11 # extract the fully qualified names as soon as the model is acquired
12 global module_names
13 global param_names
14 # XXX: can probably make a map of param2module and vice-versa
15 module_names = {module: name for name, module in model.named_modules()}
16 param_names = {param: name for name, param in model.named_parameters()}
17
18
19 def debug_module2name(module):
20 if module in module_names:
21 return module_names[module]
22 else:
23 return "unknown"
24
25
26 def debug_module2name_id(module):
27 return f"name={debug_module2name(module)} id={module.id}"
28
29
30 def debug_module2name_class(module):
31 return f"name={debug_module2name(module)} {module.__class__.__name__}"
32
33
34 def debug_param2name(param):
35 if param in param_names:
36 return param_names[param]
37 else:
38 return "unknown"
39
40
41 def debug_param2name_id(param):
42 return f"name={debug_param2name(param)} id={param.ds_id}"
43
44
45 def debug_param2name_id_shape(param):
46 return f"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape}"
47
48
49 def debug_param2name_id_shape_device(param):
50 return f"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape} device={param.device}"
51
52
53 def debug_param2name_id_numel(param):
54 return f"name={debug_param2name(param)} id={param.ds_id} numel={param.numel()}"
55
56
57 def debug_param2name_id_shape_status(param):
58 return f"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape} status={param.ds_status}"
59
60
61 def printflock(*msgs):
62 """
63
64 For printing messages for all concurrent gpus w/o getting interleaved text.
65
66 This is useful when debugging issues where multi-gpus don't sync.
67
68 1. Enable the force debug in say partitioning and zero3 files
69 2. Override the usual versions with ::
70
71 def print_rank_0(message, debug=False, force=False):
72 rank = torch.distributed.get_rank()
73 printflock(f"[{rank}] {message}")
74 3. run the program and you get both logs non-interleaved
75
76 But this makes it very difficult to make sense of the output, so the ``log_rank_file`` helper
77 function might be more useful, as it's easier to send each log stream into a separate file and
78 then compare those.
79
80 """
81
82 with open(__file__, "r") as fh:
83 fcntl.flock(fh, fcntl.LOCK_EX)
84 try:
85 print(*msgs)
86 finally:
87 fcntl.flock(fh, fcntl.LOCK_UN)
88
89
90 fh = None
91
92
93 def log_rank_file(rank, *msgs):
94 """
95 Print to a log file of the given rank
96
97 This is useful for debugging hanging in sync processes. Here is a possible workflow:
98
99 1. Enable the force debug in say partitioning and zero3 files
100 2. Override the usual versions of print_rank_0 in those files with ::
101
102 def print_rank_0(message, debug=False, force=False):
103 rank = torch.distributed.get_rank()
104 log_rank_file(rank, message)
105
106 3. run the program
107 4. fix up the expected differences, e.g. different cuda numbers ::
108
109 perl -pi -e 's|cuda:1|cuda:0|' log_rank_*
110
111 5. now diff and see where names and ids diverge - you will find where the gpus don't do the same
112 work (e.g. when some layers get conditionally skipped on one gpu but not all)
113
114 diff -u log_rank_0.txt log_rank_1.txt | less
115
116 """
117 global fh
118 if fh is None:
119 fh = open(f"log_rank_{rank}.txt", "w")
120 for m in msgs:
121 fh.write(f"{m}\n")
122 fh.flush()
123
124
125 def print_backward_tensors(tensor):
126 def _print_bwd_tensors(grad_fn):
127 print(f"Backward tensors in {grad_fn}")
128 for funcs in grad_fn.next_functions:
129 if funcs[0]:
130 try:
131 tensor = getattr(funcs[0], 'variable')
132 print(funcs[0])
133 print(
134 f"Tensor - id: {id(tensor)}, shape: {tensor.shape}, data: {tensor}, grad: {tensor.grad}"
135 )
136 except AttributeError as e:
137 _print_bwd_tensors(funcs[0])
138
139 if hasattr(tensor, 'grad_fn'):
140 _print_bwd_tensors(tensor.grad_fn)
141
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/deepspeed/utils/debug.py b/deepspeed/utils/debug.py
--- a/deepspeed/utils/debug.py
+++ b/deepspeed/utils/debug.py
@@ -1,6 +1,7 @@
""" debug utils """
-import fcntl
+# For lazy import with printflock()
+fcntl = None
# for debug purposes map module and param objects to their fully qualified names
module_names = {}
@@ -78,6 +79,9 @@
then compare those.
"""
+ global fcntl
+ if fcntl == None:
+ import fcntl
with open(__file__, "r") as fh:
fcntl.flock(fh, fcntl.LOCK_EX)
|
{"golden_diff": "diff --git a/deepspeed/utils/debug.py b/deepspeed/utils/debug.py\n--- a/deepspeed/utils/debug.py\n+++ b/deepspeed/utils/debug.py\n@@ -1,6 +1,7 @@\n \"\"\" debug utils \"\"\"\n \n-import fcntl\n+# For lazy import with printflock()\n+fcntl = None\n \n # for debug purposes map module and param objects to their fully qualified names\n module_names = {}\n@@ -78,6 +79,9 @@\n then compare those.\n \n \"\"\"\n+ global fcntl\n+ if fcntl == None:\n+ import fcntl\n \n with open(__file__, \"r\") as fh:\n fcntl.flock(fh, fcntl.LOCK_EX)\n", "issue": "[BUG] No module named 'fcntl' while importing the package\nHey,\r\nWorking on windows 11, Python 3.7 and tried importing the package.\r\nGot the error in the title, is there a way around it since it's exclusive to Linux?\r\n\r\n\r\n \n", "before_files": [{"content": "\"\"\" debug utils \"\"\"\n\nimport fcntl\n\n# for debug purposes map module and param objects to their fully qualified names\nmodule_names = {}\nparam_names = {}\n\n\ndef debug_extract_module_and_param_names(model):\n # extract the fully qualified names as soon as the model is acquired\n global module_names\n global param_names\n # XXX: can probably make a map of param2module and vice-versa\n module_names = {module: name for name, module in model.named_modules()}\n param_names = {param: name for name, param in model.named_parameters()}\n\n\ndef debug_module2name(module):\n if module in module_names:\n return module_names[module]\n else:\n return \"unknown\"\n\n\ndef debug_module2name_id(module):\n return f\"name={debug_module2name(module)} id={module.id}\"\n\n\ndef debug_module2name_class(module):\n return f\"name={debug_module2name(module)} {module.__class__.__name__}\"\n\n\ndef debug_param2name(param):\n if param in param_names:\n return param_names[param]\n else:\n return \"unknown\"\n\n\ndef debug_param2name_id(param):\n return f\"name={debug_param2name(param)} id={param.ds_id}\"\n\n\ndef debug_param2name_id_shape(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape}\"\n\n\ndef debug_param2name_id_shape_device(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape} device={param.device}\"\n\n\ndef debug_param2name_id_numel(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} numel={param.numel()}\"\n\n\ndef debug_param2name_id_shape_status(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape} status={param.ds_status}\"\n\n\ndef printflock(*msgs):\n \"\"\"\n\n For printing messages for all concurrent gpus w/o getting interleaved text.\n\n This is useful when debugging issues where multi-gpus don't sync.\n\n 1. Enable the force debug in say partitioning and zero3 files\n 2. Override the usual versions with ::\n\n def print_rank_0(message, debug=False, force=False):\n rank = torch.distributed.get_rank()\n printflock(f\"[{rank}] {message}\")\n 3. run the program and you get both logs non-interleaved\n\n But this makes it very difficult to make sense of the output, so the ``log_rank_file`` helper\n function might be more useful, as it's easier to send each log stream into a separate file and\n then compare those.\n\n \"\"\"\n\n with open(__file__, \"r\") as fh:\n fcntl.flock(fh, fcntl.LOCK_EX)\n try:\n print(*msgs)\n finally:\n fcntl.flock(fh, fcntl.LOCK_UN)\n\n\nfh = None\n\n\ndef log_rank_file(rank, *msgs):\n \"\"\"\n Print to a log file of the given rank\n\n This is useful for debugging hanging in sync processes. Here is a possible workflow:\n\n 1. Enable the force debug in say partitioning and zero3 files\n 2. Override the usual versions of print_rank_0 in those files with ::\n\n def print_rank_0(message, debug=False, force=False):\n rank = torch.distributed.get_rank()\n log_rank_file(rank, message)\n\n 3. run the program\n 4. fix up the expected differences, e.g. different cuda numbers ::\n\n perl -pi -e 's|cuda:1|cuda:0|' log_rank_*\n\n 5. now diff and see where names and ids diverge - you will find where the gpus don't do the same\n work (e.g. when some layers get conditionally skipped on one gpu but not all)\n\n diff -u log_rank_0.txt log_rank_1.txt | less\n\n \"\"\"\n global fh\n if fh is None:\n fh = open(f\"log_rank_{rank}.txt\", \"w\")\n for m in msgs:\n fh.write(f\"{m}\\n\")\n fh.flush()\n\n\ndef print_backward_tensors(tensor):\n def _print_bwd_tensors(grad_fn):\n print(f\"Backward tensors in {grad_fn}\")\n for funcs in grad_fn.next_functions:\n if funcs[0]:\n try:\n tensor = getattr(funcs[0], 'variable')\n print(funcs[0])\n print(\n f\"Tensor - id: {id(tensor)}, shape: {tensor.shape}, data: {tensor}, grad: {tensor.grad}\"\n )\n except AttributeError as e:\n _print_bwd_tensors(funcs[0])\n\n if hasattr(tensor, 'grad_fn'):\n _print_bwd_tensors(tensor.grad_fn)\n", "path": "deepspeed/utils/debug.py"}], "after_files": [{"content": "\"\"\" debug utils \"\"\"\n\n# For lazy import with printflock()\nfcntl = None\n\n# for debug purposes map module and param objects to their fully qualified names\nmodule_names = {}\nparam_names = {}\n\n\ndef debug_extract_module_and_param_names(model):\n # extract the fully qualified names as soon as the model is acquired\n global module_names\n global param_names\n # XXX: can probably make a map of param2module and vice-versa\n module_names = {module: name for name, module in model.named_modules()}\n param_names = {param: name for name, param in model.named_parameters()}\n\n\ndef debug_module2name(module):\n if module in module_names:\n return module_names[module]\n else:\n return \"unknown\"\n\n\ndef debug_module2name_id(module):\n return f\"name={debug_module2name(module)} id={module.id}\"\n\n\ndef debug_module2name_class(module):\n return f\"name={debug_module2name(module)} {module.__class__.__name__}\"\n\n\ndef debug_param2name(param):\n if param in param_names:\n return param_names[param]\n else:\n return \"unknown\"\n\n\ndef debug_param2name_id(param):\n return f\"name={debug_param2name(param)} id={param.ds_id}\"\n\n\ndef debug_param2name_id_shape(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape}\"\n\n\ndef debug_param2name_id_shape_device(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape} device={param.device}\"\n\n\ndef debug_param2name_id_numel(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} numel={param.numel()}\"\n\n\ndef debug_param2name_id_shape_status(param):\n return f\"name={debug_param2name(param)} id={param.ds_id} shape={param.data.shape} status={param.ds_status}\"\n\n\ndef printflock(*msgs):\n \"\"\"\n\n For printing messages for all concurrent gpus w/o getting interleaved text.\n\n This is useful when debugging issues where multi-gpus don't sync.\n\n 1. Enable the force debug in say partitioning and zero3 files\n 2. Override the usual versions with ::\n\n def print_rank_0(message, debug=False, force=False):\n rank = torch.distributed.get_rank()\n printflock(f\"[{rank}] {message}\")\n 3. run the program and you get both logs non-interleaved\n\n But this makes it very difficult to make sense of the output, so the ``log_rank_file`` helper\n function might be more useful, as it's easier to send each log stream into a separate file and\n then compare those.\n\n \"\"\"\n global fcntl\n if fcntl == None:\n import fcntl\n\n with open(__file__, \"r\") as fh:\n fcntl.flock(fh, fcntl.LOCK_EX)\n try:\n print(*msgs)\n finally:\n fcntl.flock(fh, fcntl.LOCK_UN)\n\n\nfh = None\n\n\ndef log_rank_file(rank, *msgs):\n \"\"\"\n Print to a log file of the given rank\n\n This is useful for debugging hanging in sync processes. Here is a possible workflow:\n\n 1. Enable the force debug in say partitioning and zero3 files\n 2. Override the usual versions of print_rank_0 in those files with ::\n\n def print_rank_0(message, debug=False, force=False):\n rank = torch.distributed.get_rank()\n log_rank_file(rank, message)\n\n 3. run the program\n 4. fix up the expected differences, e.g. different cuda numbers ::\n\n perl -pi -e 's|cuda:1|cuda:0|' log_rank_*\n\n 5. now diff and see where names and ids diverge - you will find where the gpus don't do the same\n work (e.g. when some layers get conditionally skipped on one gpu but not all)\n\n diff -u log_rank_0.txt log_rank_1.txt | less\n\n \"\"\"\n global fh\n if fh is None:\n fh = open(f\"log_rank_{rank}.txt\", \"w\")\n for m in msgs:\n fh.write(f\"{m}\\n\")\n fh.flush()\n\n\ndef print_backward_tensors(tensor):\n def _print_bwd_tensors(grad_fn):\n print(f\"Backward tensors in {grad_fn}\")\n for funcs in grad_fn.next_functions:\n if funcs[0]:\n try:\n tensor = getattr(funcs[0], 'variable')\n print(funcs[0])\n print(\n f\"Tensor - id: {id(tensor)}, shape: {tensor.shape}, data: {tensor}, grad: {tensor.grad}\"\n )\n except AttributeError as e:\n _print_bwd_tensors(funcs[0])\n\n if hasattr(tensor, 'grad_fn'):\n _print_bwd_tensors(tensor.grad_fn)\n", "path": "deepspeed/utils/debug.py"}]}
| 1,753 | 152 |
gh_patches_debug_31923
|
rasdani/github-patches
|
git_diff
|
alpa-projects__alpa-511
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Adding the `pjit` in the comparison
Some people are more familiar with using model parallel via [`pjit`](https://github.com/google/jax/blob/main/jax/experimental/pjit.py). What about adding one more rows [here](https://github.com/alpa-projects/alpa/blob/main/docs/gallery/tutorials/alpa_vs_pmap.py#L46-L52)?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `docs/gallery/tutorials/alpa_vs_pmap.py`
Content:
```
1 """
2 Differences between alpa.parallelize and jax.pmap
3 =================================================
4
5 The most common tool for parallelization or distributed computing in jax is
6 `pmap <https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap>`_.
7 With several lines of code change, we can use ``pmap`` for data parallel
8 training. However, we cannot use ``pmap`` for model parallel training,
9 which is required for training large models with billions of parameters.
10
11 On the contrary, ``alpa.parallelize`` supports both data parallelism and
12 model parallelism in an automatic way. ``alpa.parallelize`` analyzes the
13 jax computational graph and picks the best strategy.
14 If data parallelism is more suitable, ``alpa.parallelize`` achieves the same
15 performance as ``pmap`` but with less code change.
16 If model parallelism is more suitable, ``alpa.parallelize`` achieves better performance
17 and uses less memory than ``pmap``.
18
19 In this tutorial, we are going to compare ``alpa.parallelize`` and ``pmap`` on two
20 workloads. A more detailed comparison among ``alpa.parallelize``, ``pmap``, and ``xmap``
21 is also attached at the end of the article.
22 """
23
24 ################################################################################
25 # When data parallelism is prefered
26 # ---------------------------------
27
28 # TODO
29
30 ################################################################################
31 # When model parallelism is prefered
32 # ----------------------------------
33
34 # TODO
35
36 ################################################################################
37 # Comparing ``alpa.parallelize``, ``pmap``, and ``xmap``
38 # ------------------------------------------------------
39 # Besides ``pmap``, jax also provides
40 # `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_
41 # for more advanced parallelization.
42 # The table below compares the features of ``alpa.parallelize``, ``pmap``, and ``xmap``.
43 # In summary, ``alpa.parallelize`` supports more parallelism techniques in a
44 # more automatic way.
45 #
46 # ================ ================ ==================== ==================== =========
47 # Transformation Data Parallelism Operator Parallelism Pipeline Parallelism Automated
48 # ================ ================ ==================== ==================== =========
49 # alpa.parallelize yes yes yes yes
50 # pmap yes no no no
51 # xmap yes yes no no
52 # ================ ================ ==================== ==================== =========
53 #
54 # .. note::
55 # Operator parallelism and pipeline parallelism are two forms of model parallelism.
56 # Operator parallelism partitions the work in a single operator and assigns them
57 # to different devices. Pipeline parallelism partitions the computational
58 # graphs and assigns different operators to different devices.
59
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/docs/gallery/tutorials/alpa_vs_pmap.py b/docs/gallery/tutorials/alpa_vs_pmap.py
--- a/docs/gallery/tutorials/alpa_vs_pmap.py
+++ b/docs/gallery/tutorials/alpa_vs_pmap.py
@@ -34,14 +34,15 @@
# TODO
################################################################################
-# Comparing ``alpa.parallelize``, ``pmap``, and ``xmap``
-# ------------------------------------------------------
+# Comparing ``alpa.parallelize``, ``pmap``, ``xmap``, and ``pjit``
+# -----------------------------------------------------------------
# Besides ``pmap``, jax also provides
-# `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_
+# `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_ and
+# `pjit <https://jax.readthedocs.io/en/latest/jax-101/08-pjit.html>`_
# for more advanced parallelization.
-# The table below compares the features of ``alpa.parallelize``, ``pmap``, and ``xmap``.
-# In summary, ``alpa.parallelize`` supports more parallelism techniques in a
-# more automatic way.
+# The table below compares the features of ``alpa.parallelize``, ``pmap``, ``xmap``
+# and ``pjit``. In summary, ``alpa.parallelize`` supports more parallelism
+# techniques in a more automatic way.
#
# ================ ================ ==================== ==================== =========
# Transformation Data Parallelism Operator Parallelism Pipeline Parallelism Automated
@@ -49,6 +50,7 @@
# alpa.parallelize yes yes yes yes
# pmap yes no no no
# xmap yes yes no no
+# pjit yes yes no no
# ================ ================ ==================== ==================== =========
#
# .. note::
|
{"golden_diff": "diff --git a/docs/gallery/tutorials/alpa_vs_pmap.py b/docs/gallery/tutorials/alpa_vs_pmap.py\n--- a/docs/gallery/tutorials/alpa_vs_pmap.py\n+++ b/docs/gallery/tutorials/alpa_vs_pmap.py\n@@ -34,14 +34,15 @@\n # TODO\n \n ################################################################################\n-# Comparing ``alpa.parallelize``, ``pmap``, and ``xmap``\n-# ------------------------------------------------------\n+# Comparing ``alpa.parallelize``, ``pmap``, ``xmap``, and ``pjit``\n+# -----------------------------------------------------------------\n # Besides ``pmap``, jax also provides\n-# `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_\n+# `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_ and \n+# `pjit <https://jax.readthedocs.io/en/latest/jax-101/08-pjit.html>`_\n # for more advanced parallelization.\n-# The table below compares the features of ``alpa.parallelize``, ``pmap``, and ``xmap``.\n-# In summary, ``alpa.parallelize`` supports more parallelism techniques in a\n-# more automatic way.\n+# The table below compares the features of ``alpa.parallelize``, ``pmap``, ``xmap`` \n+# and ``pjit``. In summary, ``alpa.parallelize`` supports more parallelism \n+# techniques in a more automatic way.\n #\n # ================ ================ ==================== ==================== =========\n # Transformation Data Parallelism Operator Parallelism Pipeline Parallelism Automated\n@@ -49,6 +50,7 @@\n # alpa.parallelize yes yes yes yes\n # pmap yes no no no\n # xmap yes yes no no\n+# pjit yes yes no no\n # ================ ================ ==================== ==================== =========\n #\n # .. note::\n", "issue": "Adding the `pjit` in the comparison\nSome people are more familiar with using model parallel via [`pjit`](https://github.com/google/jax/blob/main/jax/experimental/pjit.py). What about adding one more rows [here](https://github.com/alpa-projects/alpa/blob/main/docs/gallery/tutorials/alpa_vs_pmap.py#L46-L52)?\n", "before_files": [{"content": "\"\"\"\nDifferences between alpa.parallelize and jax.pmap\n=================================================\n\nThe most common tool for parallelization or distributed computing in jax is\n`pmap <https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap>`_.\nWith several lines of code change, we can use ``pmap`` for data parallel\ntraining. However, we cannot use ``pmap`` for model parallel training,\nwhich is required for training large models with billions of parameters.\n\nOn the contrary, ``alpa.parallelize`` supports both data parallelism and\nmodel parallelism in an automatic way. ``alpa.parallelize`` analyzes the\njax computational graph and picks the best strategy.\nIf data parallelism is more suitable, ``alpa.parallelize`` achieves the same\nperformance as ``pmap`` but with less code change.\nIf model parallelism is more suitable, ``alpa.parallelize`` achieves better performance\nand uses less memory than ``pmap``.\n\nIn this tutorial, we are going to compare ``alpa.parallelize`` and ``pmap`` on two\nworkloads. A more detailed comparison among ``alpa.parallelize``, ``pmap``, and ``xmap``\nis also attached at the end of the article.\n\"\"\"\n\n################################################################################\n# When data parallelism is prefered\n# ---------------------------------\n\n# TODO\n\n################################################################################\n# When model parallelism is prefered\n# ----------------------------------\n\n# TODO\n\n################################################################################\n# Comparing ``alpa.parallelize``, ``pmap``, and ``xmap``\n# ------------------------------------------------------\n# Besides ``pmap``, jax also provides\n# `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_\n# for more advanced parallelization.\n# The table below compares the features of ``alpa.parallelize``, ``pmap``, and ``xmap``.\n# In summary, ``alpa.parallelize`` supports more parallelism techniques in a\n# more automatic way.\n#\n# ================ ================ ==================== ==================== =========\n# Transformation Data Parallelism Operator Parallelism Pipeline Parallelism Automated\n# ================ ================ ==================== ==================== =========\n# alpa.parallelize yes yes yes yes\n# pmap yes no no no\n# xmap yes yes no no\n# ================ ================ ==================== ==================== =========\n#\n# .. note::\n# Operator parallelism and pipeline parallelism are two forms of model parallelism.\n# Operator parallelism partitions the work in a single operator and assigns them\n# to different devices. Pipeline parallelism partitions the computational\n# graphs and assigns different operators to different devices.\n", "path": "docs/gallery/tutorials/alpa_vs_pmap.py"}], "after_files": [{"content": "\"\"\"\nDifferences between alpa.parallelize and jax.pmap\n=================================================\n\nThe most common tool for parallelization or distributed computing in jax is\n`pmap <https://jax.readthedocs.io/en/latest/jax.html#parallelization-pmap>`_.\nWith several lines of code change, we can use ``pmap`` for data parallel\ntraining. However, we cannot use ``pmap`` for model parallel training,\nwhich is required for training large models with billions of parameters.\n\nOn the contrary, ``alpa.parallelize`` supports both data parallelism and\nmodel parallelism in an automatic way. ``alpa.parallelize`` analyzes the\njax computational graph and picks the best strategy.\nIf data parallelism is more suitable, ``alpa.parallelize`` achieves the same\nperformance as ``pmap`` but with less code change.\nIf model parallelism is more suitable, ``alpa.parallelize`` achieves better performance\nand uses less memory than ``pmap``.\n\nIn this tutorial, we are going to compare ``alpa.parallelize`` and ``pmap`` on two\nworkloads. A more detailed comparison among ``alpa.parallelize``, ``pmap``, and ``xmap``\nis also attached at the end of the article.\n\"\"\"\n\n################################################################################\n# When data parallelism is prefered\n# ---------------------------------\n\n# TODO\n\n################################################################################\n# When model parallelism is prefered\n# ----------------------------------\n\n# TODO\n\n################################################################################\n# Comparing ``alpa.parallelize``, ``pmap``, ``xmap``, and ``pjit``\n# -----------------------------------------------------------------\n# Besides ``pmap``, jax also provides\n# `xmap <https://jax.readthedocs.io/en/latest/notebooks/xmap_tutorial.html>`_ and \n# `pjit <https://jax.readthedocs.io/en/latest/jax-101/08-pjit.html>`_\n# for more advanced parallelization.\n# The table below compares the features of ``alpa.parallelize``, ``pmap``, ``xmap`` \n# and ``pjit``. In summary, ``alpa.parallelize`` supports more parallelism \n# techniques in a more automatic way.\n#\n# ================ ================ ==================== ==================== =========\n# Transformation Data Parallelism Operator Parallelism Pipeline Parallelism Automated\n# ================ ================ ==================== ==================== =========\n# alpa.parallelize yes yes yes yes\n# pmap yes no no no\n# xmap yes yes no no\n# pjit yes yes no no\n# ================ ================ ==================== ==================== =========\n#\n# .. note::\n# Operator parallelism and pipeline parallelism are two forms of model parallelism.\n# Operator parallelism partitions the work in a single operator and assigns them\n# to different devices. Pipeline parallelism partitions the computational\n# graphs and assigns different operators to different devices.\n", "path": "docs/gallery/tutorials/alpa_vs_pmap.py"}]}
| 1,017 | 424 |
gh_patches_debug_19670
|
rasdani/github-patches
|
git_diff
|
google__flax-2842
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
lm1b sampler update is out of bound?
Hi,
_Disclaimer: I'm not confident if this is some intended behavior._
I think in the lm1b example, the prediction sampler could write to indices out of bound of the result.
The particular offending line is: https://github.com/google/flax/blob/master/examples/lm1b/temperature_sampler.py#L109.
Since `i <= max_decode_len` according to https://github.com/google/flax/blob/master/examples/lm1b/temperature_sampler.py#L75, and since `prompt_inputs.shape[1] == max_decode_len`, the last iteration (or two iterations?) of while loop would overwrite to `prompt_inputs[..., max_decode_len - 1]` (due to XLA semantics).
It's either a subtle bug (it won't raise cause error), or there's something I'm not understanding about the sampling procedure.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `examples/lm1b/temperature_sampler.py`
Content:
```
1 # Copyright 2022 The Flax Authors.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Fast decoding routines for inference from a trained language model."""
16
17 from jax import lax
18 from jax import random
19 import jax.numpy as jnp
20
21
22 # Constants
23 # The default End-of-Sentence token id is 2 (SentencePiece).
24 EOS_ID = 2
25
26
27 def temperature_sample(prompt_inputs,
28 init_cache,
29 tokens_to_logits,
30 prng_key,
31 temperature=1.0,
32 topk=20,
33 eos_token=EOS_ID):
34 """Temperature sampling for language model generation.
35
36 Args:
37 prompt_inputs: array: [batch_size, max_decode_len] int32 sequence of tokens.
38 init_cache: flax attention cache.
39 tokens_to_logits: fast autoregressive decoder function taking single token
40 slices and cache and returning next-token logits and updated cache.
41 prng_key: JAX PRNGKey.
42 temperature: float: sampling temperature factor. As it approaches
43 zero this becomes equivalent to greedy sampling.
44 topk: integer: if nonzero only use the top-k logits to sample next token,
45 if zero don't use any cutoff and sample from full logits over vocabulary.
46 eos_token: int: end-of-sentence token for target vocabulary.
47
48 Returns:
49 Array of sampled sequences: [batch_size, max_decode_len]
50 """
51 batch_size = prompt_inputs.shape[0]
52 max_decode_len = prompt_inputs.shape[1]
53 end_marker = jnp.array(eos_token)
54 temperature = jnp.array(temperature)
55
56 # Initialize sampling loop state.
57 # initial loop PRNGKey
58 rng0 = prng_key
59 # loop position counter.
60 i0 = jnp.array(0)
61 # per batch-item holding current token in loop.
62 token0 = jnp.zeros((batch_size, 1), dtype=jnp.int32)
63 # per batch-item state bit indicating if sentence has finished.
64 ended0 = jnp.zeros((batch_size, 1), dtype=jnp.bool_)
65 # (batch, length) array containing prefix prompt tokens for sampling loop
66 # as well as the generated output of newly sampled tokens.
67 sequences0 = prompt_inputs
68 # Sampling loop state is stored in a simple tuple.
69 sampling_loop_init_state = (i0, sequences0, init_cache, token0, ended0, rng0)
70
71 def sampling_loop_cond_fn(state):
72 """Sampling loop termination condition."""
73 (i, _, _, _, ended, _) = state
74 # Have we reached max decoding length?
75 not_at_end = (i < max_decode_len)
76 # Have all sampled sequences reached an end marker?
77 all_sequences_ended = jnp.all(ended)
78 return not_at_end & (~all_sequences_ended)
79
80 def sampling_loop_body_fn(state):
81 """Sampling loop state update."""
82 i, sequences, cache, cur_token, ended, rng = state
83 # Split RNG for sampling.
84 rng1, rng2 = random.split(rng)
85 # Call fast-decoder model on current tokens to get next-position logits.
86 logits, new_cache = tokens_to_logits(cur_token, cache)
87 # Sample next token from logits.
88 # TODO(levskaya): add top-p "nucleus" sampling option.
89 if topk:
90 # Get top-k logits and their indices, sample within these top-k tokens.
91 topk_logits, topk_idxs = lax.top_k(logits, topk)
92 topk_token = jnp.expand_dims(random.categorical(
93 rng1, topk_logits / temperature).astype(jnp.int32), axis=-1)
94 # Return the original indices corresponding to the sampled top-k tokens.
95 next_token = jnp.squeeze(
96 jnp.take_along_axis(topk_idxs, topk_token, axis=-1), axis=-1)
97 else:
98 next_token = random.categorical(
99 rng1, logits / temperature).astype(jnp.int32)
100 # Only use sampled tokens if we're past provided prefix tokens.
101 out_of_prompt = (sequences[:, i+1] == 0)
102 next_token = (next_token * out_of_prompt +
103 sequences[:, i+1] * ~out_of_prompt)
104 # If end-marker reached for batch item, only emit padding tokens.
105 next_token_or_endpad = (next_token[None] * ~ended)
106 ended |= (next_token_or_endpad == end_marker)
107 # Add current sampled tokens to recorded sequences.
108 new_sequences = lax.dynamic_update_slice(
109 sequences, next_token_or_endpad, (0, i+1))
110 return (i+1, new_sequences, new_cache, next_token_or_endpad, ended, rng2)
111
112 # Run sampling loop and collect final state.
113 final_state = lax.while_loop(sampling_loop_cond_fn,
114 sampling_loop_body_fn,
115 sampling_loop_init_state)
116
117 # Pick part of the state corresponding to the sampled sequences.
118 final_sequences = final_state[1]
119 return final_sequences
120
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/examples/lm1b/temperature_sampler.py b/examples/lm1b/temperature_sampler.py
--- a/examples/lm1b/temperature_sampler.py
+++ b/examples/lm1b/temperature_sampler.py
@@ -57,7 +57,7 @@
# initial loop PRNGKey
rng0 = prng_key
# loop position counter.
- i0 = jnp.array(0)
+ i0 = jnp.array(-1)
# per batch-item holding current token in loop.
token0 = jnp.zeros((batch_size, 1), dtype=jnp.int32)
# per batch-item state bit indicating if sentence has finished.
@@ -72,7 +72,7 @@
"""Sampling loop termination condition."""
(i, _, _, _, ended, _) = state
# Have we reached max decoding length?
- not_at_end = (i < max_decode_len)
+ not_at_end = (i < max_decode_len - 1)
# Have all sampled sequences reached an end marker?
all_sequences_ended = jnp.all(ended)
return not_at_end & (~all_sequences_ended)
|
{"golden_diff": "diff --git a/examples/lm1b/temperature_sampler.py b/examples/lm1b/temperature_sampler.py\n--- a/examples/lm1b/temperature_sampler.py\n+++ b/examples/lm1b/temperature_sampler.py\n@@ -57,7 +57,7 @@\n # initial loop PRNGKey\n rng0 = prng_key\n # loop position counter.\n- i0 = jnp.array(0)\n+ i0 = jnp.array(-1)\n # per batch-item holding current token in loop.\n token0 = jnp.zeros((batch_size, 1), dtype=jnp.int32)\n # per batch-item state bit indicating if sentence has finished.\n@@ -72,7 +72,7 @@\n \"\"\"Sampling loop termination condition.\"\"\"\n (i, _, _, _, ended, _) = state\n # Have we reached max decoding length?\n- not_at_end = (i < max_decode_len)\n+ not_at_end = (i < max_decode_len - 1)\n # Have all sampled sequences reached an end marker?\n all_sequences_ended = jnp.all(ended)\n return not_at_end & (~all_sequences_ended)\n", "issue": "lm1b sampler update is out of bound?\nHi,\r\n\r\n_Disclaimer: I'm not confident if this is some intended behavior._\r\n\r\nI think in the lm1b example, the prediction sampler could write to indices out of bound of the result.\r\nThe particular offending line is: https://github.com/google/flax/blob/master/examples/lm1b/temperature_sampler.py#L109.\r\n\r\nSince `i <= max_decode_len` according to https://github.com/google/flax/blob/master/examples/lm1b/temperature_sampler.py#L75, and since `prompt_inputs.shape[1] == max_decode_len`, the last iteration (or two iterations?) of while loop would overwrite to `prompt_inputs[..., max_decode_len - 1]` (due to XLA semantics). \r\n\r\nIt's either a subtle bug (it won't raise cause error), or there's something I'm not understanding about the sampling procedure.\n", "before_files": [{"content": "# Copyright 2022 The Flax Authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Fast decoding routines for inference from a trained language model.\"\"\"\n\nfrom jax import lax\nfrom jax import random\nimport jax.numpy as jnp\n\n\n# Constants\n# The default End-of-Sentence token id is 2 (SentencePiece).\nEOS_ID = 2\n\n\ndef temperature_sample(prompt_inputs,\n init_cache,\n tokens_to_logits,\n prng_key,\n temperature=1.0,\n topk=20,\n eos_token=EOS_ID):\n \"\"\"Temperature sampling for language model generation.\n\n Args:\n prompt_inputs: array: [batch_size, max_decode_len] int32 sequence of tokens.\n init_cache: flax attention cache.\n tokens_to_logits: fast autoregressive decoder function taking single token\n slices and cache and returning next-token logits and updated cache.\n prng_key: JAX PRNGKey.\n temperature: float: sampling temperature factor. As it approaches\n zero this becomes equivalent to greedy sampling.\n topk: integer: if nonzero only use the top-k logits to sample next token,\n if zero don't use any cutoff and sample from full logits over vocabulary.\n eos_token: int: end-of-sentence token for target vocabulary.\n\n Returns:\n Array of sampled sequences: [batch_size, max_decode_len]\n \"\"\"\n batch_size = prompt_inputs.shape[0]\n max_decode_len = prompt_inputs.shape[1]\n end_marker = jnp.array(eos_token)\n temperature = jnp.array(temperature)\n\n # Initialize sampling loop state.\n # initial loop PRNGKey\n rng0 = prng_key\n # loop position counter.\n i0 = jnp.array(0)\n # per batch-item holding current token in loop.\n token0 = jnp.zeros((batch_size, 1), dtype=jnp.int32)\n # per batch-item state bit indicating if sentence has finished.\n ended0 = jnp.zeros((batch_size, 1), dtype=jnp.bool_)\n # (batch, length) array containing prefix prompt tokens for sampling loop\n # as well as the generated output of newly sampled tokens.\n sequences0 = prompt_inputs\n # Sampling loop state is stored in a simple tuple.\n sampling_loop_init_state = (i0, sequences0, init_cache, token0, ended0, rng0)\n\n def sampling_loop_cond_fn(state):\n \"\"\"Sampling loop termination condition.\"\"\"\n (i, _, _, _, ended, _) = state\n # Have we reached max decoding length?\n not_at_end = (i < max_decode_len)\n # Have all sampled sequences reached an end marker?\n all_sequences_ended = jnp.all(ended)\n return not_at_end & (~all_sequences_ended)\n\n def sampling_loop_body_fn(state):\n \"\"\"Sampling loop state update.\"\"\"\n i, sequences, cache, cur_token, ended, rng = state\n # Split RNG for sampling.\n rng1, rng2 = random.split(rng)\n # Call fast-decoder model on current tokens to get next-position logits.\n logits, new_cache = tokens_to_logits(cur_token, cache)\n # Sample next token from logits.\n # TODO(levskaya): add top-p \"nucleus\" sampling option.\n if topk:\n # Get top-k logits and their indices, sample within these top-k tokens.\n topk_logits, topk_idxs = lax.top_k(logits, topk)\n topk_token = jnp.expand_dims(random.categorical(\n rng1, topk_logits / temperature).astype(jnp.int32), axis=-1)\n # Return the original indices corresponding to the sampled top-k tokens.\n next_token = jnp.squeeze(\n jnp.take_along_axis(topk_idxs, topk_token, axis=-1), axis=-1)\n else:\n next_token = random.categorical(\n rng1, logits / temperature).astype(jnp.int32)\n # Only use sampled tokens if we're past provided prefix tokens.\n out_of_prompt = (sequences[:, i+1] == 0)\n next_token = (next_token * out_of_prompt +\n sequences[:, i+1] * ~out_of_prompt)\n # If end-marker reached for batch item, only emit padding tokens.\n next_token_or_endpad = (next_token[None] * ~ended)\n ended |= (next_token_or_endpad == end_marker)\n # Add current sampled tokens to recorded sequences.\n new_sequences = lax.dynamic_update_slice(\n sequences, next_token_or_endpad, (0, i+1))\n return (i+1, new_sequences, new_cache, next_token_or_endpad, ended, rng2)\n\n # Run sampling loop and collect final state.\n final_state = lax.while_loop(sampling_loop_cond_fn,\n sampling_loop_body_fn,\n sampling_loop_init_state)\n\n # Pick part of the state corresponding to the sampled sequences.\n final_sequences = final_state[1]\n return final_sequences\n", "path": "examples/lm1b/temperature_sampler.py"}], "after_files": [{"content": "# Copyright 2022 The Flax Authors.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Fast decoding routines for inference from a trained language model.\"\"\"\n\nfrom jax import lax\nfrom jax import random\nimport jax.numpy as jnp\n\n\n# Constants\n# The default End-of-Sentence token id is 2 (SentencePiece).\nEOS_ID = 2\n\n\ndef temperature_sample(prompt_inputs,\n init_cache,\n tokens_to_logits,\n prng_key,\n temperature=1.0,\n topk=20,\n eos_token=EOS_ID):\n \"\"\"Temperature sampling for language model generation.\n\n Args:\n prompt_inputs: array: [batch_size, max_decode_len] int32 sequence of tokens.\n init_cache: flax attention cache.\n tokens_to_logits: fast autoregressive decoder function taking single token\n slices and cache and returning next-token logits and updated cache.\n prng_key: JAX PRNGKey.\n temperature: float: sampling temperature factor. As it approaches\n zero this becomes equivalent to greedy sampling.\n topk: integer: if nonzero only use the top-k logits to sample next token,\n if zero don't use any cutoff and sample from full logits over vocabulary.\n eos_token: int: end-of-sentence token for target vocabulary.\n\n Returns:\n Array of sampled sequences: [batch_size, max_decode_len]\n \"\"\"\n batch_size = prompt_inputs.shape[0]\n max_decode_len = prompt_inputs.shape[1]\n end_marker = jnp.array(eos_token)\n temperature = jnp.array(temperature)\n\n # Initialize sampling loop state.\n # initial loop PRNGKey\n rng0 = prng_key\n # loop position counter.\n i0 = jnp.array(-1)\n # per batch-item holding current token in loop.\n token0 = jnp.zeros((batch_size, 1), dtype=jnp.int32)\n # per batch-item state bit indicating if sentence has finished.\n ended0 = jnp.zeros((batch_size, 1), dtype=jnp.bool_)\n # (batch, length) array containing prefix prompt tokens for sampling loop\n # as well as the generated output of newly sampled tokens.\n sequences0 = prompt_inputs\n # Sampling loop state is stored in a simple tuple.\n sampling_loop_init_state = (i0, sequences0, init_cache, token0, ended0, rng0)\n\n def sampling_loop_cond_fn(state):\n \"\"\"Sampling loop termination condition.\"\"\"\n (i, _, _, _, ended, _) = state\n # Have we reached max decoding length?\n not_at_end = (i < max_decode_len - 1)\n # Have all sampled sequences reached an end marker?\n all_sequences_ended = jnp.all(ended)\n return not_at_end & (~all_sequences_ended)\n\n def sampling_loop_body_fn(state):\n \"\"\"Sampling loop state update.\"\"\"\n i, sequences, cache, cur_token, ended, rng = state\n # Split RNG for sampling.\n rng1, rng2 = random.split(rng)\n # Call fast-decoder model on current tokens to get next-position logits.\n logits, new_cache = tokens_to_logits(cur_token, cache)\n # Sample next token from logits.\n # TODO(levskaya): add top-p \"nucleus\" sampling option.\n if topk:\n # Get top-k logits and their indices, sample within these top-k tokens.\n topk_logits, topk_idxs = lax.top_k(logits, topk)\n topk_token = jnp.expand_dims(random.categorical(\n rng1, topk_logits / temperature).astype(jnp.int32), axis=-1)\n # Return the original indices corresponding to the sampled top-k tokens.\n next_token = jnp.squeeze(\n jnp.take_along_axis(topk_idxs, topk_token, axis=-1), axis=-1)\n else:\n next_token = random.categorical(\n rng1, logits / temperature).astype(jnp.int32)\n # Only use sampled tokens if we're past provided prefix tokens.\n out_of_prompt = (sequences[:, i+1] == 0)\n next_token = (next_token * out_of_prompt +\n sequences[:, i+1] * ~out_of_prompt)\n # If end-marker reached for batch item, only emit padding tokens.\n next_token_or_endpad = (next_token[None] * ~ended)\n ended |= (next_token_or_endpad == end_marker)\n # Add current sampled tokens to recorded sequences.\n new_sequences = lax.dynamic_update_slice(\n sequences, next_token_or_endpad, (0, i+1))\n return (i+1, new_sequences, new_cache, next_token_or_endpad, ended, rng2)\n\n # Run sampling loop and collect final state.\n final_state = lax.while_loop(sampling_loop_cond_fn,\n sampling_loop_body_fn,\n sampling_loop_init_state)\n\n # Pick part of the state corresponding to the sampled sequences.\n final_sequences = final_state[1]\n return final_sequences\n", "path": "examples/lm1b/temperature_sampler.py"}]}
| 1,892 | 254 |
gh_patches_debug_12520
|
rasdani/github-patches
|
git_diff
|
rucio__rucio-1573
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Problems with accessing the REST API and the WebUI in the development docker container
Motivation
----------
It is not possible to access the REST API under 'https://localhost/proxy' and to access the Web UI under 'https://localhost/ui/' within the docker container build with the Dockerfile under /etc/docker/dev.
Modification
------------
A few modifications can be copied from the demo environment.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `lib/rucio/core/lifetime_exception.py`
Content:
```
1 # Copyright European Organization for Nuclear Research (CERN)
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # You may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 # http://www.apache.org/licenses/LICENSE-2.0
7 #
8 # Authors:
9 # - Cedric Serfon, <[email protected]>, 2016-2018
10
11 from re import match
12 from datetime import datetime, timedelta
13
14 from sqlalchemy import or_
15 from sqlalchemy.exc import IntegrityError
16 from sqlalchemy.orm.exc import NoResultFound
17
18 from rucio.common.exception import ConfigNotFound, RucioException, LifetimeExceptionDuplicate, LifetimeExceptionNotFound, UnsupportedOperation
19 from rucio.common.utils import generate_uuid, str_to_date
20 import rucio.common.policy
21 from rucio.core.config import get
22 from rucio.core.message import add_message
23 from rucio.core.rse import list_rse_attributes
24
25 from rucio.db.sqla import models
26 from rucio.db.sqla.constants import DIDType, LifetimeExceptionsState
27 from rucio.db.sqla.session import transactional_session, stream_session, read_session
28
29
30 @stream_session
31 def list_exceptions(exception_id, states, session=None):
32 """
33 List exceptions to Lifetime Model.
34
35 :param exception_id: The id of the exception
36 :param states: The states to filter
37 :param session: The database session in use.
38 """
39
40 state_clause = []
41 if states:
42 state_clause = [models.LifetimeExceptions.state == state for state in states]
43
44 query = session.query(models.LifetimeExceptions.id,
45 models.LifetimeExceptions.scope, models.LifetimeExceptions.name,
46 models.LifetimeExceptions.did_type,
47 models.LifetimeExceptions.account,
48 models.LifetimeExceptions.pattern,
49 models.LifetimeExceptions.comments,
50 models.LifetimeExceptions.state,
51 models.LifetimeExceptions.expires_at,
52 models.LifetimeExceptions.created_at)
53 if state_clause != []:
54 query = query.filter(or_(*state_clause))
55 if exception_id:
56 query = query.filter(id=exception_id)
57
58 for exception in query.yield_per(5):
59 yield {'id': exception.id, 'scope': exception.scope, 'name': exception.name,
60 'did_type': exception.did_type, 'account': exception.account,
61 'pattern': exception.pattern, 'comments': exception.comments,
62 'state': exception.state, 'created_at': exception.created_at,
63 'expires_at': exception.expires_at}
64
65
66 @transactional_session
67 def add_exception(dids, account, pattern, comments, expires_at, session=None):
68 """
69 Add exceptions to Lifetime Model.
70
71 :param dids: The list of dids
72 :param account: The account of the requester.
73 :param pattern: The account.
74 :param comments: The comments associated to the exception.
75 :param expires_at: The expiration date of the exception.
76 :param session: The database session in use.
77
78 returns: The id of the exception.
79 """
80 exception_id = generate_uuid()
81 text = 'Account %s requested a lifetime extension for a list of DIDs that can be found below\n' % account
82 reason = comments
83 volume = None
84 lifetime = None
85 if comments.find('||||') > -1:
86 reason, volume = comments.split('||||')
87 text += 'The reason for the extension is "%s"\n' % reason
88 text += 'It represents %s datasets\n' % len(dids)
89 if volume:
90 text += 'The estimated physical volume is %s\n' % volume
91 if expires_at and (isinstance(expires_at, str) or isinstance(expires_at, unicode)):
92 lifetime = str_to_date(expires_at)
93 text += 'The lifetime exception should expires on %s\n' % str(expires_at)
94 elif isinstance(expires_at, datetime):
95 lifetime = expires_at
96 text += 'The lifetime exception should expires on %s\n' % str(expires_at)
97 text += 'Link to approve or reject this request can be found at the end of the mail\n'
98 text += '\n'
99 text += 'DIDTYPE SCOPE NAME\n'
100 text += '\n'
101 truncated_message = False
102 for did in dids:
103 did_type = None
104 if 'did_type' in did:
105 if isinstance(did['did_type'], str) or isinstance(did['did_type'], unicode):
106 did_type = DIDType.from_sym(did['did_type'])
107 else:
108 did_type = did['did_type']
109 new_exception = models.LifetimeExceptions(id=exception_id, scope=did['scope'], name=did['name'], did_type=did_type,
110 account=account, pattern=pattern, comments=reason, state=LifetimeExceptionsState.WAITING, expires_at=lifetime)
111 if len(text) < 3000:
112 text += '%s %s %s\n' % (str(did_type), did['scope'], did['name'])
113 else:
114 truncated_message = True
115 try:
116 new_exception.save(session=session, flush=False)
117 except IntegrityError as error:
118 if match('.*ORA-00001.*', str(error.args[0]))\
119 or match('.*IntegrityError.*UNIQUE constraint failed.*', str(error.args[0]))\
120 or match('.*1062.*Duplicate entry.*for key.*', str(error.args[0]))\
121 or match('.*sqlite3.IntegrityError.*are not unique.*', error.args[0]):
122 raise LifetimeExceptionDuplicate()
123 raise RucioException(error.args[0])
124 if truncated_message:
125 text += '...\n'
126 text += 'List too long. Truncated\n'
127 text += '\n'
128 text += 'Approve: https://rucio-ui.cern.ch/lifetime_exception?id=%s&action=approve\n' % str(exception_id)
129 text += 'Deny: https://rucio-ui.cern.ch/lifetime_exception?id=%s&action=deny\n' % str(exception_id)
130 approvers_email = []
131 try:
132 approvers_email = get('lifetime_model', 'approvers_email', session=session)
133 approvers_email = approvers_email.split(',') # pylint: disable=no-member
134 except ConfigNotFound:
135 approvers_email = []
136
137 add_message(event_type='email',
138 payload={'body': text, 'to': approvers_email,
139 'subject': '[RUCIO] Request to approve lifetime exception %s' % str(exception_id)},
140 session=session)
141 return exception_id
142
143
144 @transactional_session
145 def update_exception(exception_id, state, session=None):
146 """
147 Update exceptions state to Lifetime Model.
148
149 :param exception_id: The id of the exception
150 :param state: The states to filter
151 :param session: The database session in use.
152 """
153 query = session.query(models.LifetimeExceptions).filter_by(id=exception_id)
154 try:
155 query.one()
156 except NoResultFound:
157 raise LifetimeExceptionNotFound
158
159 if state in [LifetimeExceptionsState.APPROVED, LifetimeExceptionsState.REJECTED]:
160 query.update({'state': state, 'updated_at': datetime.utcnow()}, synchronize_session=False)
161 else:
162 raise UnsupportedOperation
163
164
165 @read_session
166 def define_eol(scope, name, rses, session=None):
167 """
168 ATLAS policy for rules on SCRATCHDISK
169
170 :param scope: Scope of the DID.
171 :param name: Name of the DID.
172 :param rses: List of RSEs.
173 :param session: The database session in use.
174 """
175 policy = rucio.common.policy.get_policy()
176 if policy != 'atlas':
177 return None
178
179 # Check if on ATLAS managed space
180 if [rse for rse in rses if list_rse_attributes(rse=None, rse_id=rse['id'], session=session).get('type') in ['LOCALGROUPDISK', 'LOCALGROUPTAPE', 'GROUPDISK', 'GROUPTAPE']]:
181 return None
182 # Now check the lifetime policy
183 try:
184 did = session.query(models.DataIdentifier).filter(models.DataIdentifier.scope == scope,
185 models.DataIdentifier.name == name).one()
186 except NoResultFound:
187 return None
188 policy_dict = rucio.common.policy.get_lifetime_policy()
189 did_type = 'other'
190 if scope.startswith('mc'):
191 did_type = 'mc'
192 elif scope.startswith('data'):
193 did_type = 'data'
194 elif scope.startswith('valid'):
195 did_type = 'valid'
196 else:
197 did_type = 'other'
198 for policy in policy_dict[did_type]:
199 if 'exclude' in policy:
200 to_exclude = False
201 for key in policy['exclude']:
202 meta_key = None
203 if key not in ['datatype', 'project', ]:
204 if key == 'stream':
205 meta_key = 'stream_name'
206 elif key == 'tags':
207 meta_key = 'version'
208 else:
209 meta_key = key
210 values = policy['exclude'][key]
211 for value in values:
212 value = value.replace('%', '.*')
213 if meta_key and did[meta_key] and value and match(value, did[meta_key]):
214 to_exclude = True
215 break
216 if to_exclude:
217 break
218 if to_exclude:
219 continue
220 if 'include' in policy:
221 match_policy = True
222 for key in policy['include']:
223 meta_key = None
224 if key not in ['datatype', 'project', ]:
225 if key == 'stream':
226 meta_key = 'stream_name'
227 elif key == 'tags':
228 meta_key = 'version'
229 else:
230 continue
231 else:
232 meta_key = key
233 values = policy['include'][key]
234 to_keep = False
235 for value in values:
236 value = value.replace('%', '.*')
237 if meta_key and did[meta_key] and value and match(value, did[meta_key]):
238 to_keep = True
239 break
240 match_policy = match_policy and to_keep
241 if not to_keep:
242 match_policy = False
243 break
244 if match_policy:
245 if int(policy['age']) >= 12:
246 years = int(int(policy['age']) / 12)
247 months = int(policy['age']) - years * 12
248 lifetime_value = 365 * years + 30 * months
249 else:
250 lifetime_value = int(policy['age']) * 30
251 if int(policy['extension']) >= 12:
252 years = int(int(policy['extension']) / 12)
253 months = int(policy['extension']) - years * 12
254 extension = 365 * years + 30 * months
255 else:
256 extension = int(policy['extension']) * 30
257
258 default_eol_at = did.created_at + timedelta(days=lifetime_value)
259 eol_at = default_eol_at
260 if did.accessed_at:
261 eol_at = did.accessed_at + timedelta(days=extension)
262 if eol_at < default_eol_at:
263 eol_at = default_eol_at
264 return eol_at
265 return None
266
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/lib/rucio/core/lifetime_exception.py b/lib/rucio/core/lifetime_exception.py
--- a/lib/rucio/core/lifetime_exception.py
+++ b/lib/rucio/core/lifetime_exception.py
@@ -7,6 +7,7 @@
#
# Authors:
# - Cedric Serfon, <[email protected]>, 2016-2018
+# - Dimitrios Christidis, <[email protected]> 2018
from re import match
from datetime import datetime, timedelta
@@ -152,7 +153,7 @@
"""
query = session.query(models.LifetimeExceptions).filter_by(id=exception_id)
try:
- query.one()
+ query.first()
except NoResultFound:
raise LifetimeExceptionNotFound
|
{"golden_diff": "diff --git a/lib/rucio/core/lifetime_exception.py b/lib/rucio/core/lifetime_exception.py\n--- a/lib/rucio/core/lifetime_exception.py\n+++ b/lib/rucio/core/lifetime_exception.py\n@@ -7,6 +7,7 @@\n #\n # Authors:\n # - Cedric Serfon, <[email protected]>, 2016-2018\n+# - Dimitrios Christidis, <[email protected]> 2018\n \n from re import match\n from datetime import datetime, timedelta\n@@ -152,7 +153,7 @@\n \"\"\"\n query = session.query(models.LifetimeExceptions).filter_by(id=exception_id)\n try:\n- query.one()\n+ query.first()\n except NoResultFound:\n raise LifetimeExceptionNotFound\n", "issue": "Problems with accessing the REST API and the WebUI in the development docker container\nMotivation\r\n----------\r\nIt is not possible to access the REST API under 'https://localhost/proxy' and to access the Web UI under 'https://localhost/ui/' within the docker container build with the Dockerfile under /etc/docker/dev.\r\n\r\nModification\r\n------------\r\nA few modifications can be copied from the demo environment.\n", "before_files": [{"content": "# Copyright European Organization for Nuclear Research (CERN)\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# You may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Authors:\n# - Cedric Serfon, <[email protected]>, 2016-2018\n\nfrom re import match\nfrom datetime import datetime, timedelta\n\nfrom sqlalchemy import or_\nfrom sqlalchemy.exc import IntegrityError\nfrom sqlalchemy.orm.exc import NoResultFound\n\nfrom rucio.common.exception import ConfigNotFound, RucioException, LifetimeExceptionDuplicate, LifetimeExceptionNotFound, UnsupportedOperation\nfrom rucio.common.utils import generate_uuid, str_to_date\nimport rucio.common.policy\nfrom rucio.core.config import get\nfrom rucio.core.message import add_message\nfrom rucio.core.rse import list_rse_attributes\n\nfrom rucio.db.sqla import models\nfrom rucio.db.sqla.constants import DIDType, LifetimeExceptionsState\nfrom rucio.db.sqla.session import transactional_session, stream_session, read_session\n\n\n@stream_session\ndef list_exceptions(exception_id, states, session=None):\n \"\"\"\n List exceptions to Lifetime Model.\n\n :param exception_id: The id of the exception\n :param states: The states to filter\n :param session: The database session in use.\n \"\"\"\n\n state_clause = []\n if states:\n state_clause = [models.LifetimeExceptions.state == state for state in states]\n\n query = session.query(models.LifetimeExceptions.id,\n models.LifetimeExceptions.scope, models.LifetimeExceptions.name,\n models.LifetimeExceptions.did_type,\n models.LifetimeExceptions.account,\n models.LifetimeExceptions.pattern,\n models.LifetimeExceptions.comments,\n models.LifetimeExceptions.state,\n models.LifetimeExceptions.expires_at,\n models.LifetimeExceptions.created_at)\n if state_clause != []:\n query = query.filter(or_(*state_clause))\n if exception_id:\n query = query.filter(id=exception_id)\n\n for exception in query.yield_per(5):\n yield {'id': exception.id, 'scope': exception.scope, 'name': exception.name,\n 'did_type': exception.did_type, 'account': exception.account,\n 'pattern': exception.pattern, 'comments': exception.comments,\n 'state': exception.state, 'created_at': exception.created_at,\n 'expires_at': exception.expires_at}\n\n\n@transactional_session\ndef add_exception(dids, account, pattern, comments, expires_at, session=None):\n \"\"\"\n Add exceptions to Lifetime Model.\n\n :param dids: The list of dids\n :param account: The account of the requester.\n :param pattern: The account.\n :param comments: The comments associated to the exception.\n :param expires_at: The expiration date of the exception.\n :param session: The database session in use.\n\n returns: The id of the exception.\n \"\"\"\n exception_id = generate_uuid()\n text = 'Account %s requested a lifetime extension for a list of DIDs that can be found below\\n' % account\n reason = comments\n volume = None\n lifetime = None\n if comments.find('||||') > -1:\n reason, volume = comments.split('||||')\n text += 'The reason for the extension is \"%s\"\\n' % reason\n text += 'It represents %s datasets\\n' % len(dids)\n if volume:\n text += 'The estimated physical volume is %s\\n' % volume\n if expires_at and (isinstance(expires_at, str) or isinstance(expires_at, unicode)):\n lifetime = str_to_date(expires_at)\n text += 'The lifetime exception should expires on %s\\n' % str(expires_at)\n elif isinstance(expires_at, datetime):\n lifetime = expires_at\n text += 'The lifetime exception should expires on %s\\n' % str(expires_at)\n text += 'Link to approve or reject this request can be found at the end of the mail\\n'\n text += '\\n'\n text += 'DIDTYPE SCOPE NAME\\n'\n text += '\\n'\n truncated_message = False\n for did in dids:\n did_type = None\n if 'did_type' in did:\n if isinstance(did['did_type'], str) or isinstance(did['did_type'], unicode):\n did_type = DIDType.from_sym(did['did_type'])\n else:\n did_type = did['did_type']\n new_exception = models.LifetimeExceptions(id=exception_id, scope=did['scope'], name=did['name'], did_type=did_type,\n account=account, pattern=pattern, comments=reason, state=LifetimeExceptionsState.WAITING, expires_at=lifetime)\n if len(text) < 3000:\n text += '%s %s %s\\n' % (str(did_type), did['scope'], did['name'])\n else:\n truncated_message = True\n try:\n new_exception.save(session=session, flush=False)\n except IntegrityError as error:\n if match('.*ORA-00001.*', str(error.args[0]))\\\n or match('.*IntegrityError.*UNIQUE constraint failed.*', str(error.args[0]))\\\n or match('.*1062.*Duplicate entry.*for key.*', str(error.args[0]))\\\n or match('.*sqlite3.IntegrityError.*are not unique.*', error.args[0]):\n raise LifetimeExceptionDuplicate()\n raise RucioException(error.args[0])\n if truncated_message:\n text += '...\\n'\n text += 'List too long. Truncated\\n'\n text += '\\n'\n text += 'Approve: https://rucio-ui.cern.ch/lifetime_exception?id=%s&action=approve\\n' % str(exception_id)\n text += 'Deny: https://rucio-ui.cern.ch/lifetime_exception?id=%s&action=deny\\n' % str(exception_id)\n approvers_email = []\n try:\n approvers_email = get('lifetime_model', 'approvers_email', session=session)\n approvers_email = approvers_email.split(',') # pylint: disable=no-member\n except ConfigNotFound:\n approvers_email = []\n\n add_message(event_type='email',\n payload={'body': text, 'to': approvers_email,\n 'subject': '[RUCIO] Request to approve lifetime exception %s' % str(exception_id)},\n session=session)\n return exception_id\n\n\n@transactional_session\ndef update_exception(exception_id, state, session=None):\n \"\"\"\n Update exceptions state to Lifetime Model.\n\n :param exception_id: The id of the exception\n :param state: The states to filter\n :param session: The database session in use.\n \"\"\"\n query = session.query(models.LifetimeExceptions).filter_by(id=exception_id)\n try:\n query.one()\n except NoResultFound:\n raise LifetimeExceptionNotFound\n\n if state in [LifetimeExceptionsState.APPROVED, LifetimeExceptionsState.REJECTED]:\n query.update({'state': state, 'updated_at': datetime.utcnow()}, synchronize_session=False)\n else:\n raise UnsupportedOperation\n\n\n@read_session\ndef define_eol(scope, name, rses, session=None):\n \"\"\"\n ATLAS policy for rules on SCRATCHDISK\n\n :param scope: Scope of the DID.\n :param name: Name of the DID.\n :param rses: List of RSEs.\n :param session: The database session in use.\n \"\"\"\n policy = rucio.common.policy.get_policy()\n if policy != 'atlas':\n return None\n\n # Check if on ATLAS managed space\n if [rse for rse in rses if list_rse_attributes(rse=None, rse_id=rse['id'], session=session).get('type') in ['LOCALGROUPDISK', 'LOCALGROUPTAPE', 'GROUPDISK', 'GROUPTAPE']]:\n return None\n # Now check the lifetime policy\n try:\n did = session.query(models.DataIdentifier).filter(models.DataIdentifier.scope == scope,\n models.DataIdentifier.name == name).one()\n except NoResultFound:\n return None\n policy_dict = rucio.common.policy.get_lifetime_policy()\n did_type = 'other'\n if scope.startswith('mc'):\n did_type = 'mc'\n elif scope.startswith('data'):\n did_type = 'data'\n elif scope.startswith('valid'):\n did_type = 'valid'\n else:\n did_type = 'other'\n for policy in policy_dict[did_type]:\n if 'exclude' in policy:\n to_exclude = False\n for key in policy['exclude']:\n meta_key = None\n if key not in ['datatype', 'project', ]:\n if key == 'stream':\n meta_key = 'stream_name'\n elif key == 'tags':\n meta_key = 'version'\n else:\n meta_key = key\n values = policy['exclude'][key]\n for value in values:\n value = value.replace('%', '.*')\n if meta_key and did[meta_key] and value and match(value, did[meta_key]):\n to_exclude = True\n break\n if to_exclude:\n break\n if to_exclude:\n continue\n if 'include' in policy:\n match_policy = True\n for key in policy['include']:\n meta_key = None\n if key not in ['datatype', 'project', ]:\n if key == 'stream':\n meta_key = 'stream_name'\n elif key == 'tags':\n meta_key = 'version'\n else:\n continue\n else:\n meta_key = key\n values = policy['include'][key]\n to_keep = False\n for value in values:\n value = value.replace('%', '.*')\n if meta_key and did[meta_key] and value and match(value, did[meta_key]):\n to_keep = True\n break\n match_policy = match_policy and to_keep\n if not to_keep:\n match_policy = False\n break\n if match_policy:\n if int(policy['age']) >= 12:\n years = int(int(policy['age']) / 12)\n months = int(policy['age']) - years * 12\n lifetime_value = 365 * years + 30 * months\n else:\n lifetime_value = int(policy['age']) * 30\n if int(policy['extension']) >= 12:\n years = int(int(policy['extension']) / 12)\n months = int(policy['extension']) - years * 12\n extension = 365 * years + 30 * months\n else:\n extension = int(policy['extension']) * 30\n\n default_eol_at = did.created_at + timedelta(days=lifetime_value)\n eol_at = default_eol_at\n if did.accessed_at:\n eol_at = did.accessed_at + timedelta(days=extension)\n if eol_at < default_eol_at:\n eol_at = default_eol_at\n return eol_at\n return None\n", "path": "lib/rucio/core/lifetime_exception.py"}], "after_files": [{"content": "# Copyright European Organization for Nuclear Research (CERN)\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# You may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Authors:\n# - Cedric Serfon, <[email protected]>, 2016-2018\n# - Dimitrios Christidis, <[email protected]> 2018\n\nfrom re import match\nfrom datetime import datetime, timedelta\n\nfrom sqlalchemy import or_\nfrom sqlalchemy.exc import IntegrityError\nfrom sqlalchemy.orm.exc import NoResultFound\n\nfrom rucio.common.exception import ConfigNotFound, RucioException, LifetimeExceptionDuplicate, LifetimeExceptionNotFound, UnsupportedOperation\nfrom rucio.common.utils import generate_uuid, str_to_date\nimport rucio.common.policy\nfrom rucio.core.config import get\nfrom rucio.core.message import add_message\nfrom rucio.core.rse import list_rse_attributes\n\nfrom rucio.db.sqla import models\nfrom rucio.db.sqla.constants import DIDType, LifetimeExceptionsState\nfrom rucio.db.sqla.session import transactional_session, stream_session, read_session\n\n\n@stream_session\ndef list_exceptions(exception_id, states, session=None):\n \"\"\"\n List exceptions to Lifetime Model.\n\n :param exception_id: The id of the exception\n :param states: The states to filter\n :param session: The database session in use.\n \"\"\"\n\n state_clause = []\n if states:\n state_clause = [models.LifetimeExceptions.state == state for state in states]\n\n query = session.query(models.LifetimeExceptions.id,\n models.LifetimeExceptions.scope, models.LifetimeExceptions.name,\n models.LifetimeExceptions.did_type,\n models.LifetimeExceptions.account,\n models.LifetimeExceptions.pattern,\n models.LifetimeExceptions.comments,\n models.LifetimeExceptions.state,\n models.LifetimeExceptions.expires_at,\n models.LifetimeExceptions.created_at)\n if state_clause != []:\n query = query.filter(or_(*state_clause))\n if exception_id:\n query = query.filter(id=exception_id)\n\n for exception in query.yield_per(5):\n yield {'id': exception.id, 'scope': exception.scope, 'name': exception.name,\n 'did_type': exception.did_type, 'account': exception.account,\n 'pattern': exception.pattern, 'comments': exception.comments,\n 'state': exception.state, 'created_at': exception.created_at,\n 'expires_at': exception.expires_at}\n\n\n@transactional_session\ndef add_exception(dids, account, pattern, comments, expires_at, session=None):\n \"\"\"\n Add exceptions to Lifetime Model.\n\n :param dids: The list of dids\n :param account: The account of the requester.\n :param pattern: The account.\n :param comments: The comments associated to the exception.\n :param expires_at: The expiration date of the exception.\n :param session: The database session in use.\n\n returns: The id of the exception.\n \"\"\"\n exception_id = generate_uuid()\n text = 'Account %s requested a lifetime extension for a list of DIDs that can be found below\\n' % account\n reason = comments\n volume = None\n lifetime = None\n if comments.find('||||') > -1:\n reason, volume = comments.split('||||')\n text += 'The reason for the extension is \"%s\"\\n' % reason\n text += 'It represents %s datasets\\n' % len(dids)\n if volume:\n text += 'The estimated physical volume is %s\\n' % volume\n if expires_at and (isinstance(expires_at, str) or isinstance(expires_at, unicode)):\n lifetime = str_to_date(expires_at)\n text += 'The lifetime exception should expires on %s\\n' % str(expires_at)\n elif isinstance(expires_at, datetime):\n lifetime = expires_at\n text += 'The lifetime exception should expires on %s\\n' % str(expires_at)\n text += 'Link to approve or reject this request can be found at the end of the mail\\n'\n text += '\\n'\n text += 'DIDTYPE SCOPE NAME\\n'\n text += '\\n'\n truncated_message = False\n for did in dids:\n did_type = None\n if 'did_type' in did:\n if isinstance(did['did_type'], str) or isinstance(did['did_type'], unicode):\n did_type = DIDType.from_sym(did['did_type'])\n else:\n did_type = did['did_type']\n new_exception = models.LifetimeExceptions(id=exception_id, scope=did['scope'], name=did['name'], did_type=did_type,\n account=account, pattern=pattern, comments=reason, state=LifetimeExceptionsState.WAITING, expires_at=lifetime)\n if len(text) < 3000:\n text += '%s %s %s\\n' % (str(did_type), did['scope'], did['name'])\n else:\n truncated_message = True\n try:\n new_exception.save(session=session, flush=False)\n except IntegrityError as error:\n if match('.*ORA-00001.*', str(error.args[0]))\\\n or match('.*IntegrityError.*UNIQUE constraint failed.*', str(error.args[0]))\\\n or match('.*1062.*Duplicate entry.*for key.*', str(error.args[0]))\\\n or match('.*sqlite3.IntegrityError.*are not unique.*', error.args[0]):\n raise LifetimeExceptionDuplicate()\n raise RucioException(error.args[0])\n if truncated_message:\n text += '...\\n'\n text += 'List too long. Truncated\\n'\n text += '\\n'\n text += 'Approve: https://rucio-ui.cern.ch/lifetime_exception?id=%s&action=approve\\n' % str(exception_id)\n text += 'Deny: https://rucio-ui.cern.ch/lifetime_exception?id=%s&action=deny\\n' % str(exception_id)\n approvers_email = []\n try:\n approvers_email = get('lifetime_model', 'approvers_email', session=session)\n approvers_email = approvers_email.split(',') # pylint: disable=no-member\n except ConfigNotFound:\n approvers_email = []\n\n add_message(event_type='email',\n payload={'body': text, 'to': approvers_email,\n 'subject': '[RUCIO] Request to approve lifetime exception %s' % str(exception_id)},\n session=session)\n return exception_id\n\n\n@transactional_session\ndef update_exception(exception_id, state, session=None):\n \"\"\"\n Update exceptions state to Lifetime Model.\n\n :param exception_id: The id of the exception\n :param state: The states to filter\n :param session: The database session in use.\n \"\"\"\n query = session.query(models.LifetimeExceptions).filter_by(id=exception_id)\n try:\n query.first()\n except NoResultFound:\n raise LifetimeExceptionNotFound\n\n if state in [LifetimeExceptionsState.APPROVED, LifetimeExceptionsState.REJECTED]:\n query.update({'state': state, 'updated_at': datetime.utcnow()}, synchronize_session=False)\n else:\n raise UnsupportedOperation\n\n\n@read_session\ndef define_eol(scope, name, rses, session=None):\n \"\"\"\n ATLAS policy for rules on SCRATCHDISK\n\n :param scope: Scope of the DID.\n :param name: Name of the DID.\n :param rses: List of RSEs.\n :param session: The database session in use.\n \"\"\"\n policy = rucio.common.policy.get_policy()\n if policy != 'atlas':\n return None\n\n # Check if on ATLAS managed space\n if [rse for rse in rses if list_rse_attributes(rse=None, rse_id=rse['id'], session=session).get('type') in ['LOCALGROUPDISK', 'LOCALGROUPTAPE', 'GROUPDISK', 'GROUPTAPE']]:\n return None\n # Now check the lifetime policy\n try:\n did = session.query(models.DataIdentifier).filter(models.DataIdentifier.scope == scope,\n models.DataIdentifier.name == name).one()\n except NoResultFound:\n return None\n policy_dict = rucio.common.policy.get_lifetime_policy()\n did_type = 'other'\n if scope.startswith('mc'):\n did_type = 'mc'\n elif scope.startswith('data'):\n did_type = 'data'\n elif scope.startswith('valid'):\n did_type = 'valid'\n else:\n did_type = 'other'\n for policy in policy_dict[did_type]:\n if 'exclude' in policy:\n to_exclude = False\n for key in policy['exclude']:\n meta_key = None\n if key not in ['datatype', 'project', ]:\n if key == 'stream':\n meta_key = 'stream_name'\n elif key == 'tags':\n meta_key = 'version'\n else:\n meta_key = key\n values = policy['exclude'][key]\n for value in values:\n value = value.replace('%', '.*')\n if meta_key and did[meta_key] and value and match(value, did[meta_key]):\n to_exclude = True\n break\n if to_exclude:\n break\n if to_exclude:\n continue\n if 'include' in policy:\n match_policy = True\n for key in policy['include']:\n meta_key = None\n if key not in ['datatype', 'project', ]:\n if key == 'stream':\n meta_key = 'stream_name'\n elif key == 'tags':\n meta_key = 'version'\n else:\n continue\n else:\n meta_key = key\n values = policy['include'][key]\n to_keep = False\n for value in values:\n value = value.replace('%', '.*')\n if meta_key and did[meta_key] and value and match(value, did[meta_key]):\n to_keep = True\n break\n match_policy = match_policy and to_keep\n if not to_keep:\n match_policy = False\n break\n if match_policy:\n if int(policy['age']) >= 12:\n years = int(int(policy['age']) / 12)\n months = int(policy['age']) - years * 12\n lifetime_value = 365 * years + 30 * months\n else:\n lifetime_value = int(policy['age']) * 30\n if int(policy['extension']) >= 12:\n years = int(int(policy['extension']) / 12)\n months = int(policy['extension']) - years * 12\n extension = 365 * years + 30 * months\n else:\n extension = int(policy['extension']) * 30\n\n default_eol_at = did.created_at + timedelta(days=lifetime_value)\n eol_at = default_eol_at\n if did.accessed_at:\n eol_at = did.accessed_at + timedelta(days=extension)\n if eol_at < default_eol_at:\n eol_at = default_eol_at\n return eol_at\n return None\n", "path": "lib/rucio/core/lifetime_exception.py"}]}
| 3,489 | 186 |
gh_patches_debug_4479
|
rasdani/github-patches
|
git_diff
|
freedomofpress__securedrop-3709
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[functional testing] Fix staging CI job on tbb-0.9.0
We removed the application/functional test run from the staging environment in #3697. We should also update the testinfra test references and remove the application test run from CI, otherwise we get a few testinfra test failures due to pip deps, and an error when we attempt to run the application tests in CI:
```
TASK [Run application tests] ***************************************************
Friday 10 August 2018 19:28:17 +0000 (0:00:00.037) 0:01:08.223 *********
fatal: [app-staging]: FAILED! => {"changed": true, "msg": "non-zero return code", "rc": 127, "stderr": "Shared connection to 52.36.194.59 closed.\r\n", "stdout": "/home/sdrop/.ansible/tmp/ansible-tmp-1533929297.62-93522333058246/app-tests.sh: line 13: pytest: command not found\r\n", "stdout_lines": ["/home/sdrop/.ansible/tmp/ansible-tmp-1533929297.62-93522333058246/app-tests.sh: line 13: pytest: command not found"]}
...ignoring
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `securedrop/create-dev-data.py`
Content:
```
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 import datetime
5 import os
6 import sys
7 import argparse
8 from sqlalchemy.exc import IntegrityError
9
10 os.environ["SECUREDROP_ENV"] = "dev" # noqa
11 import journalist_app
12 from sdconfig import config
13 from db import db
14 from models import Journalist, Source, Submission
15
16
17 def add_test_user(username, password, otp_secret, is_admin=False):
18 context = journalist_app.create_app(config).app_context()
19 context.push()
20
21 try:
22 user = Journalist(username=username,
23 password=password,
24 is_admin=is_admin)
25 user.otp_secret = otp_secret
26 db.session.add(user)
27 db.session.commit()
28 print('Test user successfully added: '
29 'username={}, password={}, otp_secret={}, is_admin={}'
30 ''.format(username, password, otp_secret, is_admin))
31 except IntegrityError:
32 print("Test user already added")
33 db.session.rollback()
34
35 context.pop()
36
37
38 def create_source_and_submissions(num_submissions=2):
39 app = journalist_app.create_app(config)
40
41 with app.app_context():
42 # Store source in database
43 codename = app.crypto_util.genrandomid()
44 filesystem_id = app.crypto_util.hash_codename(codename)
45 journalist_designation = app.crypto_util.display_id()
46 source = Source(filesystem_id, journalist_designation)
47 source.pending = False
48 db.session.add(source)
49 db.session.commit()
50
51 # Generate submissions directory and generate source key
52 os.mkdir(app.storage.path(source.filesystem_id))
53 app.crypto_util.genkeypair(source.filesystem_id, codename)
54
55 # Generate some test submissions
56 for _ in range(num_submissions):
57 source.interaction_count += 1
58 fpath = app.storage.save_message_submission(
59 source.filesystem_id,
60 source.interaction_count,
61 source.journalist_filename,
62 'test submission!'
63 )
64 source.last_updated = datetime.datetime.utcnow()
65 submission = Submission(source, fpath)
66 db.session.add(submission)
67
68 db.session.commit()
69 print("Test source '{}' added with {} submissions".format(
70 journalist_designation, num_submissions)
71 )
72
73
74 if __name__ == "__main__": # pragma: no cover
75 # Add two test users
76 test_password = "correct horse battery staple profanity oil chewy"
77 test_otp_secret = "JHCOGO7VCER3EJ4L"
78
79 parser = argparse.ArgumentParser()
80 parser.add_argument("--staging", help="Adding user for staging tests.",
81 action="store_true")
82 args = parser.parse_args()
83 add_test_user("journalist",
84 test_password,
85 test_otp_secret,
86 is_admin=True)
87
88 # If staging, we only need the journalist user (admin)
89 if args.staging:
90 sys.exit(0)
91
92 add_test_user("dellsberg",
93 test_password,
94 test_otp_secret,
95 is_admin=False)
96
97 # Add test sources and submissions
98 num_sources = 2
99 for _ in range(num_sources):
100 create_source_and_submissions()
101
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/securedrop/create-dev-data.py b/securedrop/create-dev-data.py
--- a/securedrop/create-dev-data.py
+++ b/securedrop/create-dev-data.py
@@ -78,7 +78,7 @@
parser = argparse.ArgumentParser()
parser.add_argument("--staging", help="Adding user for staging tests.",
- action="store_true")
+ action="store_true")
args = parser.parse_args()
add_test_user("journalist",
test_password,
|
{"golden_diff": "diff --git a/securedrop/create-dev-data.py b/securedrop/create-dev-data.py\n--- a/securedrop/create-dev-data.py\n+++ b/securedrop/create-dev-data.py\n@@ -78,7 +78,7 @@\n \n parser = argparse.ArgumentParser()\n parser.add_argument(\"--staging\", help=\"Adding user for staging tests.\",\n- action=\"store_true\")\n+ action=\"store_true\")\n args = parser.parse_args()\n add_test_user(\"journalist\",\n test_password,\n", "issue": "[functional testing] Fix staging CI job on tbb-0.9.0\nWe removed the application/functional test run from the staging environment in #3697. We should also update the testinfra test references and remove the application test run from CI, otherwise we get a few testinfra test failures due to pip deps, and an error when we attempt to run the application tests in CI: \r\n\r\n```\r\nTASK [Run application tests] ***************************************************\r\n Friday 10 August 2018 19:28:17 +0000 (0:00:00.037) 0:01:08.223 *********\r\n fatal: [app-staging]: FAILED! => {\"changed\": true, \"msg\": \"non-zero return code\", \"rc\": 127, \"stderr\": \"Shared connection to 52.36.194.59 closed.\\r\\n\", \"stdout\": \"/home/sdrop/.ansible/tmp/ansible-tmp-1533929297.62-93522333058246/app-tests.sh: line 13: pytest: command not found\\r\\n\", \"stdout_lines\": [\"/home/sdrop/.ansible/tmp/ansible-tmp-1533929297.62-93522333058246/app-tests.sh: line 13: pytest: command not found\"]}\r\n ...ignoring\r\n```\n", "before_files": [{"content": "#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\nimport datetime\nimport os\nimport sys\nimport argparse\nfrom sqlalchemy.exc import IntegrityError\n\nos.environ[\"SECUREDROP_ENV\"] = \"dev\" # noqa\nimport journalist_app\nfrom sdconfig import config\nfrom db import db\nfrom models import Journalist, Source, Submission\n\n\ndef add_test_user(username, password, otp_secret, is_admin=False):\n context = journalist_app.create_app(config).app_context()\n context.push()\n\n try:\n user = Journalist(username=username,\n password=password,\n is_admin=is_admin)\n user.otp_secret = otp_secret\n db.session.add(user)\n db.session.commit()\n print('Test user successfully added: '\n 'username={}, password={}, otp_secret={}, is_admin={}'\n ''.format(username, password, otp_secret, is_admin))\n except IntegrityError:\n print(\"Test user already added\")\n db.session.rollback()\n\n context.pop()\n\n\ndef create_source_and_submissions(num_submissions=2):\n app = journalist_app.create_app(config)\n\n with app.app_context():\n # Store source in database\n codename = app.crypto_util.genrandomid()\n filesystem_id = app.crypto_util.hash_codename(codename)\n journalist_designation = app.crypto_util.display_id()\n source = Source(filesystem_id, journalist_designation)\n source.pending = False\n db.session.add(source)\n db.session.commit()\n\n # Generate submissions directory and generate source key\n os.mkdir(app.storage.path(source.filesystem_id))\n app.crypto_util.genkeypair(source.filesystem_id, codename)\n\n # Generate some test submissions\n for _ in range(num_submissions):\n source.interaction_count += 1\n fpath = app.storage.save_message_submission(\n source.filesystem_id,\n source.interaction_count,\n source.journalist_filename,\n 'test submission!'\n )\n source.last_updated = datetime.datetime.utcnow()\n submission = Submission(source, fpath)\n db.session.add(submission)\n\n db.session.commit()\n print(\"Test source '{}' added with {} submissions\".format(\n journalist_designation, num_submissions)\n )\n\n\nif __name__ == \"__main__\": # pragma: no cover\n # Add two test users\n test_password = \"correct horse battery staple profanity oil chewy\"\n test_otp_secret = \"JHCOGO7VCER3EJ4L\"\n\n parser = argparse.ArgumentParser()\n parser.add_argument(\"--staging\", help=\"Adding user for staging tests.\",\n action=\"store_true\")\n args = parser.parse_args()\n add_test_user(\"journalist\",\n test_password,\n test_otp_secret,\n is_admin=True)\n\n # If staging, we only need the journalist user (admin)\n if args.staging:\n sys.exit(0)\n\n add_test_user(\"dellsberg\",\n test_password,\n test_otp_secret,\n is_admin=False)\n\n # Add test sources and submissions\n num_sources = 2\n for _ in range(num_sources):\n create_source_and_submissions()\n", "path": "securedrop/create-dev-data.py"}], "after_files": [{"content": "#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\nimport datetime\nimport os\nimport sys\nimport argparse\nfrom sqlalchemy.exc import IntegrityError\n\nos.environ[\"SECUREDROP_ENV\"] = \"dev\" # noqa\nimport journalist_app\nfrom sdconfig import config\nfrom db import db\nfrom models import Journalist, Source, Submission\n\n\ndef add_test_user(username, password, otp_secret, is_admin=False):\n context = journalist_app.create_app(config).app_context()\n context.push()\n\n try:\n user = Journalist(username=username,\n password=password,\n is_admin=is_admin)\n user.otp_secret = otp_secret\n db.session.add(user)\n db.session.commit()\n print('Test user successfully added: '\n 'username={}, password={}, otp_secret={}, is_admin={}'\n ''.format(username, password, otp_secret, is_admin))\n except IntegrityError:\n print(\"Test user already added\")\n db.session.rollback()\n\n context.pop()\n\n\ndef create_source_and_submissions(num_submissions=2):\n app = journalist_app.create_app(config)\n\n with app.app_context():\n # Store source in database\n codename = app.crypto_util.genrandomid()\n filesystem_id = app.crypto_util.hash_codename(codename)\n journalist_designation = app.crypto_util.display_id()\n source = Source(filesystem_id, journalist_designation)\n source.pending = False\n db.session.add(source)\n db.session.commit()\n\n # Generate submissions directory and generate source key\n os.mkdir(app.storage.path(source.filesystem_id))\n app.crypto_util.genkeypair(source.filesystem_id, codename)\n\n # Generate some test submissions\n for _ in range(num_submissions):\n source.interaction_count += 1\n fpath = app.storage.save_message_submission(\n source.filesystem_id,\n source.interaction_count,\n source.journalist_filename,\n 'test submission!'\n )\n source.last_updated = datetime.datetime.utcnow()\n submission = Submission(source, fpath)\n db.session.add(submission)\n\n db.session.commit()\n print(\"Test source '{}' added with {} submissions\".format(\n journalist_designation, num_submissions)\n )\n\n\nif __name__ == \"__main__\": # pragma: no cover\n # Add two test users\n test_password = \"correct horse battery staple profanity oil chewy\"\n test_otp_secret = \"JHCOGO7VCER3EJ4L\"\n\n parser = argparse.ArgumentParser()\n parser.add_argument(\"--staging\", help=\"Adding user for staging tests.\",\n action=\"store_true\")\n args = parser.parse_args()\n add_test_user(\"journalist\",\n test_password,\n test_otp_secret,\n is_admin=True)\n\n # If staging, we only need the journalist user (admin)\n if args.staging:\n sys.exit(0)\n\n add_test_user(\"dellsberg\",\n test_password,\n test_otp_secret,\n is_admin=False)\n\n # Add test sources and submissions\n num_sources = 2\n for _ in range(num_sources):\n create_source_and_submissions()\n", "path": "securedrop/create-dev-data.py"}]}
| 1,458 | 108 |
gh_patches_debug_3856
|
rasdani/github-patches
|
git_diff
|
googleapis__google-auth-library-python-385
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Docs: compute_engine.credentials doesn't render note for service_account_email
On this doc item: https://google-auth.readthedocs.io/en/latest/reference/google.auth.compute_engine.credentials.html#google.auth.compute_engine.credentials.Credentials.service_account_email
The rendered docs say simply `The service account email.`
However, the [docstring](https://google-auth.readthedocs.io/en/latest/_modules/google/auth/compute_engine/credentials.html#Credentials.refresh) has more information:
```
"""The service account email.
.. note: This is not guaranteed to be set until :meth`refresh` has been
called.
"""
```
Why is this important note not rendered?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `google/auth/compute_engine/credentials.py`
Content:
```
1 # Copyright 2016 Google Inc.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Google Compute Engine credentials.
16
17 This module provides authentication for application running on Google Compute
18 Engine using the Compute Engine metadata server.
19
20 """
21
22 import datetime
23
24 import six
25
26 from google.auth import _helpers
27 from google.auth import credentials
28 from google.auth import exceptions
29 from google.auth import iam
30 from google.auth import jwt
31 from google.auth.compute_engine import _metadata
32 from google.oauth2 import _client
33
34
35 class Credentials(credentials.ReadOnlyScoped, credentials.Credentials):
36 """Compute Engine Credentials.
37
38 These credentials use the Google Compute Engine metadata server to obtain
39 OAuth 2.0 access tokens associated with the instance's service account.
40
41 For more information about Compute Engine authentication, including how
42 to configure scopes, see the `Compute Engine authentication
43 documentation`_.
44
45 .. note:: Compute Engine instances can be created with scopes and therefore
46 these credentials are considered to be 'scoped'. However, you can
47 not use :meth:`~google.auth.credentials.ScopedCredentials.with_scopes`
48 because it is not possible to change the scopes that the instance
49 has. Also note that
50 :meth:`~google.auth.credentials.ScopedCredentials.has_scopes` will not
51 work until the credentials have been refreshed.
52
53 .. _Compute Engine authentication documentation:
54 https://cloud.google.com/compute/docs/authentication#using
55 """
56
57 def __init__(self, service_account_email="default"):
58 """
59 Args:
60 service_account_email (str): The service account email to use, or
61 'default'. A Compute Engine instance may have multiple service
62 accounts.
63 """
64 super(Credentials, self).__init__()
65 self._service_account_email = service_account_email
66
67 def _retrieve_info(self, request):
68 """Retrieve information about the service account.
69
70 Updates the scopes and retrieves the full service account email.
71
72 Args:
73 request (google.auth.transport.Request): The object used to make
74 HTTP requests.
75 """
76 info = _metadata.get_service_account_info(
77 request, service_account=self._service_account_email
78 )
79
80 self._service_account_email = info["email"]
81 self._scopes = info["scopes"]
82
83 def refresh(self, request):
84 """Refresh the access token and scopes.
85
86 Args:
87 request (google.auth.transport.Request): The object used to make
88 HTTP requests.
89
90 Raises:
91 google.auth.exceptions.RefreshError: If the Compute Engine metadata
92 service can't be reached if if the instance has not
93 credentials.
94 """
95 try:
96 self._retrieve_info(request)
97 self.token, self.expiry = _metadata.get_service_account_token(
98 request, service_account=self._service_account_email
99 )
100 except exceptions.TransportError as caught_exc:
101 new_exc = exceptions.RefreshError(caught_exc)
102 six.raise_from(new_exc, caught_exc)
103
104 @property
105 def service_account_email(self):
106 """The service account email.
107
108 .. note: This is not guaranteed to be set until :meth`refresh` has been
109 called.
110 """
111 return self._service_account_email
112
113 @property
114 def requires_scopes(self):
115 """False: Compute Engine credentials can not be scoped."""
116 return False
117
118
119 _DEFAULT_TOKEN_LIFETIME_SECS = 3600 # 1 hour in seconds
120 _DEFAULT_TOKEN_URI = "https://www.googleapis.com/oauth2/v4/token"
121
122
123 class IDTokenCredentials(credentials.Credentials, credentials.Signing):
124 """Open ID Connect ID Token-based service account credentials.
125
126 These credentials relies on the default service account of a GCE instance.
127
128 In order for this to work, the GCE instance must have been started with
129 a service account that has access to the IAM Cloud API.
130 """
131
132 def __init__(
133 self,
134 request,
135 target_audience,
136 token_uri=_DEFAULT_TOKEN_URI,
137 additional_claims=None,
138 service_account_email=None,
139 ):
140 """
141 Args:
142 request (google.auth.transport.Request): The object used to make
143 HTTP requests.
144 target_audience (str): The intended audience for these credentials,
145 used when requesting the ID Token. The ID Token's ``aud`` claim
146 will be set to this string.
147 token_uri (str): The OAuth 2.0 Token URI.
148 additional_claims (Mapping[str, str]): Any additional claims for
149 the JWT assertion used in the authorization grant.
150 service_account_email (str): Optional explicit service account to
151 use to sign JWT tokens.
152 By default, this is the default GCE service account.
153 """
154 super(IDTokenCredentials, self).__init__()
155
156 if service_account_email is None:
157 sa_info = _metadata.get_service_account_info(request)
158 service_account_email = sa_info["email"]
159 self._service_account_email = service_account_email
160
161 self._signer = iam.Signer(
162 request=request,
163 credentials=Credentials(),
164 service_account_email=service_account_email,
165 )
166
167 self._token_uri = token_uri
168 self._target_audience = target_audience
169
170 if additional_claims is not None:
171 self._additional_claims = additional_claims
172 else:
173 self._additional_claims = {}
174
175 def with_target_audience(self, target_audience):
176 """Create a copy of these credentials with the specified target
177 audience.
178 Args:
179 target_audience (str): The intended audience for these credentials,
180 used when requesting the ID Token.
181 Returns:
182 google.auth.service_account.IDTokenCredentials: A new credentials
183 instance.
184 """
185 return self.__class__(
186 self._signer,
187 service_account_email=self._service_account_email,
188 token_uri=self._token_uri,
189 target_audience=target_audience,
190 additional_claims=self._additional_claims.copy(),
191 )
192
193 def _make_authorization_grant_assertion(self):
194 """Create the OAuth 2.0 assertion.
195 This assertion is used during the OAuth 2.0 grant to acquire an
196 ID token.
197 Returns:
198 bytes: The authorization grant assertion.
199 """
200 now = _helpers.utcnow()
201 lifetime = datetime.timedelta(seconds=_DEFAULT_TOKEN_LIFETIME_SECS)
202 expiry = now + lifetime
203
204 payload = {
205 "iat": _helpers.datetime_to_secs(now),
206 "exp": _helpers.datetime_to_secs(expiry),
207 # The issuer must be the service account email.
208 "iss": self.service_account_email,
209 # The audience must be the auth token endpoint's URI
210 "aud": self._token_uri,
211 # The target audience specifies which service the ID token is
212 # intended for.
213 "target_audience": self._target_audience,
214 }
215
216 payload.update(self._additional_claims)
217
218 token = jwt.encode(self._signer, payload)
219
220 return token
221
222 @_helpers.copy_docstring(credentials.Credentials)
223 def refresh(self, request):
224 assertion = self._make_authorization_grant_assertion()
225 access_token, expiry, _ = _client.id_token_jwt_grant(
226 request, self._token_uri, assertion
227 )
228 self.token = access_token
229 self.expiry = expiry
230
231 @property
232 @_helpers.copy_docstring(credentials.Signing)
233 def signer(self):
234 return self._signer
235
236 @_helpers.copy_docstring(credentials.Signing)
237 def sign_bytes(self, message):
238 return self._signer.sign(message)
239
240 @property
241 def service_account_email(self):
242 """The service account email."""
243 return self._service_account_email
244
245 @property
246 def signer_email(self):
247 return self._service_account_email
248
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/google/auth/compute_engine/credentials.py b/google/auth/compute_engine/credentials.py
--- a/google/auth/compute_engine/credentials.py
+++ b/google/auth/compute_engine/credentials.py
@@ -105,7 +105,7 @@
def service_account_email(self):
"""The service account email.
- .. note: This is not guaranteed to be set until :meth`refresh` has been
+ .. note:: This is not guaranteed to be set until :meth:`refresh` has been
called.
"""
return self._service_account_email
|
{"golden_diff": "diff --git a/google/auth/compute_engine/credentials.py b/google/auth/compute_engine/credentials.py\n--- a/google/auth/compute_engine/credentials.py\n+++ b/google/auth/compute_engine/credentials.py\n@@ -105,7 +105,7 @@\n def service_account_email(self):\n \"\"\"The service account email.\n \n- .. note: This is not guaranteed to be set until :meth`refresh` has been\n+ .. note:: This is not guaranteed to be set until :meth:`refresh` has been\n called.\n \"\"\"\n return self._service_account_email\n", "issue": "Docs: compute_engine.credentials doesn't render note for service_account_email\nOn this doc item: https://google-auth.readthedocs.io/en/latest/reference/google.auth.compute_engine.credentials.html#google.auth.compute_engine.credentials.Credentials.service_account_email\r\n\r\nThe rendered docs say simply `The service account email.`\r\n\r\nHowever, the [docstring](https://google-auth.readthedocs.io/en/latest/_modules/google/auth/compute_engine/credentials.html#Credentials.refresh) has more information:\r\n\r\n```\r\n \"\"\"The service account email.\r\n\r\n .. note: This is not guaranteed to be set until :meth`refresh` has been\r\n called.\r\n \"\"\"\r\n```\r\n\r\nWhy is this important note not rendered?\n", "before_files": [{"content": "# Copyright 2016 Google Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Google Compute Engine credentials.\n\nThis module provides authentication for application running on Google Compute\nEngine using the Compute Engine metadata server.\n\n\"\"\"\n\nimport datetime\n\nimport six\n\nfrom google.auth import _helpers\nfrom google.auth import credentials\nfrom google.auth import exceptions\nfrom google.auth import iam\nfrom google.auth import jwt\nfrom google.auth.compute_engine import _metadata\nfrom google.oauth2 import _client\n\n\nclass Credentials(credentials.ReadOnlyScoped, credentials.Credentials):\n \"\"\"Compute Engine Credentials.\n\n These credentials use the Google Compute Engine metadata server to obtain\n OAuth 2.0 access tokens associated with the instance's service account.\n\n For more information about Compute Engine authentication, including how\n to configure scopes, see the `Compute Engine authentication\n documentation`_.\n\n .. note:: Compute Engine instances can be created with scopes and therefore\n these credentials are considered to be 'scoped'. However, you can\n not use :meth:`~google.auth.credentials.ScopedCredentials.with_scopes`\n because it is not possible to change the scopes that the instance\n has. Also note that\n :meth:`~google.auth.credentials.ScopedCredentials.has_scopes` will not\n work until the credentials have been refreshed.\n\n .. _Compute Engine authentication documentation:\n https://cloud.google.com/compute/docs/authentication#using\n \"\"\"\n\n def __init__(self, service_account_email=\"default\"):\n \"\"\"\n Args:\n service_account_email (str): The service account email to use, or\n 'default'. A Compute Engine instance may have multiple service\n accounts.\n \"\"\"\n super(Credentials, self).__init__()\n self._service_account_email = service_account_email\n\n def _retrieve_info(self, request):\n \"\"\"Retrieve information about the service account.\n\n Updates the scopes and retrieves the full service account email.\n\n Args:\n request (google.auth.transport.Request): The object used to make\n HTTP requests.\n \"\"\"\n info = _metadata.get_service_account_info(\n request, service_account=self._service_account_email\n )\n\n self._service_account_email = info[\"email\"]\n self._scopes = info[\"scopes\"]\n\n def refresh(self, request):\n \"\"\"Refresh the access token and scopes.\n\n Args:\n request (google.auth.transport.Request): The object used to make\n HTTP requests.\n\n Raises:\n google.auth.exceptions.RefreshError: If the Compute Engine metadata\n service can't be reached if if the instance has not\n credentials.\n \"\"\"\n try:\n self._retrieve_info(request)\n self.token, self.expiry = _metadata.get_service_account_token(\n request, service_account=self._service_account_email\n )\n except exceptions.TransportError as caught_exc:\n new_exc = exceptions.RefreshError(caught_exc)\n six.raise_from(new_exc, caught_exc)\n\n @property\n def service_account_email(self):\n \"\"\"The service account email.\n\n .. note: This is not guaranteed to be set until :meth`refresh` has been\n called.\n \"\"\"\n return self._service_account_email\n\n @property\n def requires_scopes(self):\n \"\"\"False: Compute Engine credentials can not be scoped.\"\"\"\n return False\n\n\n_DEFAULT_TOKEN_LIFETIME_SECS = 3600 # 1 hour in seconds\n_DEFAULT_TOKEN_URI = \"https://www.googleapis.com/oauth2/v4/token\"\n\n\nclass IDTokenCredentials(credentials.Credentials, credentials.Signing):\n \"\"\"Open ID Connect ID Token-based service account credentials.\n\n These credentials relies on the default service account of a GCE instance.\n\n In order for this to work, the GCE instance must have been started with\n a service account that has access to the IAM Cloud API.\n \"\"\"\n\n def __init__(\n self,\n request,\n target_audience,\n token_uri=_DEFAULT_TOKEN_URI,\n additional_claims=None,\n service_account_email=None,\n ):\n \"\"\"\n Args:\n request (google.auth.transport.Request): The object used to make\n HTTP requests.\n target_audience (str): The intended audience for these credentials,\n used when requesting the ID Token. The ID Token's ``aud`` claim\n will be set to this string.\n token_uri (str): The OAuth 2.0 Token URI.\n additional_claims (Mapping[str, str]): Any additional claims for\n the JWT assertion used in the authorization grant.\n service_account_email (str): Optional explicit service account to\n use to sign JWT tokens.\n By default, this is the default GCE service account.\n \"\"\"\n super(IDTokenCredentials, self).__init__()\n\n if service_account_email is None:\n sa_info = _metadata.get_service_account_info(request)\n service_account_email = sa_info[\"email\"]\n self._service_account_email = service_account_email\n\n self._signer = iam.Signer(\n request=request,\n credentials=Credentials(),\n service_account_email=service_account_email,\n )\n\n self._token_uri = token_uri\n self._target_audience = target_audience\n\n if additional_claims is not None:\n self._additional_claims = additional_claims\n else:\n self._additional_claims = {}\n\n def with_target_audience(self, target_audience):\n \"\"\"Create a copy of these credentials with the specified target\n audience.\n Args:\n target_audience (str): The intended audience for these credentials,\n used when requesting the ID Token.\n Returns:\n google.auth.service_account.IDTokenCredentials: A new credentials\n instance.\n \"\"\"\n return self.__class__(\n self._signer,\n service_account_email=self._service_account_email,\n token_uri=self._token_uri,\n target_audience=target_audience,\n additional_claims=self._additional_claims.copy(),\n )\n\n def _make_authorization_grant_assertion(self):\n \"\"\"Create the OAuth 2.0 assertion.\n This assertion is used during the OAuth 2.0 grant to acquire an\n ID token.\n Returns:\n bytes: The authorization grant assertion.\n \"\"\"\n now = _helpers.utcnow()\n lifetime = datetime.timedelta(seconds=_DEFAULT_TOKEN_LIFETIME_SECS)\n expiry = now + lifetime\n\n payload = {\n \"iat\": _helpers.datetime_to_secs(now),\n \"exp\": _helpers.datetime_to_secs(expiry),\n # The issuer must be the service account email.\n \"iss\": self.service_account_email,\n # The audience must be the auth token endpoint's URI\n \"aud\": self._token_uri,\n # The target audience specifies which service the ID token is\n # intended for.\n \"target_audience\": self._target_audience,\n }\n\n payload.update(self._additional_claims)\n\n token = jwt.encode(self._signer, payload)\n\n return token\n\n @_helpers.copy_docstring(credentials.Credentials)\n def refresh(self, request):\n assertion = self._make_authorization_grant_assertion()\n access_token, expiry, _ = _client.id_token_jwt_grant(\n request, self._token_uri, assertion\n )\n self.token = access_token\n self.expiry = expiry\n\n @property\n @_helpers.copy_docstring(credentials.Signing)\n def signer(self):\n return self._signer\n\n @_helpers.copy_docstring(credentials.Signing)\n def sign_bytes(self, message):\n return self._signer.sign(message)\n\n @property\n def service_account_email(self):\n \"\"\"The service account email.\"\"\"\n return self._service_account_email\n\n @property\n def signer_email(self):\n return self._service_account_email\n", "path": "google/auth/compute_engine/credentials.py"}], "after_files": [{"content": "# Copyright 2016 Google Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Google Compute Engine credentials.\n\nThis module provides authentication for application running on Google Compute\nEngine using the Compute Engine metadata server.\n\n\"\"\"\n\nimport datetime\n\nimport six\n\nfrom google.auth import _helpers\nfrom google.auth import credentials\nfrom google.auth import exceptions\nfrom google.auth import iam\nfrom google.auth import jwt\nfrom google.auth.compute_engine import _metadata\nfrom google.oauth2 import _client\n\n\nclass Credentials(credentials.ReadOnlyScoped, credentials.Credentials):\n \"\"\"Compute Engine Credentials.\n\n These credentials use the Google Compute Engine metadata server to obtain\n OAuth 2.0 access tokens associated with the instance's service account.\n\n For more information about Compute Engine authentication, including how\n to configure scopes, see the `Compute Engine authentication\n documentation`_.\n\n .. note:: Compute Engine instances can be created with scopes and therefore\n these credentials are considered to be 'scoped'. However, you can\n not use :meth:`~google.auth.credentials.ScopedCredentials.with_scopes`\n because it is not possible to change the scopes that the instance\n has. Also note that\n :meth:`~google.auth.credentials.ScopedCredentials.has_scopes` will not\n work until the credentials have been refreshed.\n\n .. _Compute Engine authentication documentation:\n https://cloud.google.com/compute/docs/authentication#using\n \"\"\"\n\n def __init__(self, service_account_email=\"default\"):\n \"\"\"\n Args:\n service_account_email (str): The service account email to use, or\n 'default'. A Compute Engine instance may have multiple service\n accounts.\n \"\"\"\n super(Credentials, self).__init__()\n self._service_account_email = service_account_email\n\n def _retrieve_info(self, request):\n \"\"\"Retrieve information about the service account.\n\n Updates the scopes and retrieves the full service account email.\n\n Args:\n request (google.auth.transport.Request): The object used to make\n HTTP requests.\n \"\"\"\n info = _metadata.get_service_account_info(\n request, service_account=self._service_account_email\n )\n\n self._service_account_email = info[\"email\"]\n self._scopes = info[\"scopes\"]\n\n def refresh(self, request):\n \"\"\"Refresh the access token and scopes.\n\n Args:\n request (google.auth.transport.Request): The object used to make\n HTTP requests.\n\n Raises:\n google.auth.exceptions.RefreshError: If the Compute Engine metadata\n service can't be reached if if the instance has not\n credentials.\n \"\"\"\n try:\n self._retrieve_info(request)\n self.token, self.expiry = _metadata.get_service_account_token(\n request, service_account=self._service_account_email\n )\n except exceptions.TransportError as caught_exc:\n new_exc = exceptions.RefreshError(caught_exc)\n six.raise_from(new_exc, caught_exc)\n\n @property\n def service_account_email(self):\n \"\"\"The service account email.\n\n .. note:: This is not guaranteed to be set until :meth:`refresh` has been\n called.\n \"\"\"\n return self._service_account_email\n\n @property\n def requires_scopes(self):\n \"\"\"False: Compute Engine credentials can not be scoped.\"\"\"\n return False\n\n\n_DEFAULT_TOKEN_LIFETIME_SECS = 3600 # 1 hour in seconds\n_DEFAULT_TOKEN_URI = \"https://www.googleapis.com/oauth2/v4/token\"\n\n\nclass IDTokenCredentials(credentials.Credentials, credentials.Signing):\n \"\"\"Open ID Connect ID Token-based service account credentials.\n\n These credentials relies on the default service account of a GCE instance.\n\n In order for this to work, the GCE instance must have been started with\n a service account that has access to the IAM Cloud API.\n \"\"\"\n\n def __init__(\n self,\n request,\n target_audience,\n token_uri=_DEFAULT_TOKEN_URI,\n additional_claims=None,\n service_account_email=None,\n ):\n \"\"\"\n Args:\n request (google.auth.transport.Request): The object used to make\n HTTP requests.\n target_audience (str): The intended audience for these credentials,\n used when requesting the ID Token. The ID Token's ``aud`` claim\n will be set to this string.\n token_uri (str): The OAuth 2.0 Token URI.\n additional_claims (Mapping[str, str]): Any additional claims for\n the JWT assertion used in the authorization grant.\n service_account_email (str): Optional explicit service account to\n use to sign JWT tokens.\n By default, this is the default GCE service account.\n \"\"\"\n super(IDTokenCredentials, self).__init__()\n\n if service_account_email is None:\n sa_info = _metadata.get_service_account_info(request)\n service_account_email = sa_info[\"email\"]\n self._service_account_email = service_account_email\n\n self._signer = iam.Signer(\n request=request,\n credentials=Credentials(),\n service_account_email=service_account_email,\n )\n\n self._token_uri = token_uri\n self._target_audience = target_audience\n\n if additional_claims is not None:\n self._additional_claims = additional_claims\n else:\n self._additional_claims = {}\n\n def with_target_audience(self, target_audience):\n \"\"\"Create a copy of these credentials with the specified target\n audience.\n Args:\n target_audience (str): The intended audience for these credentials,\n used when requesting the ID Token.\n Returns:\n google.auth.service_account.IDTokenCredentials: A new credentials\n instance.\n \"\"\"\n return self.__class__(\n self._signer,\n service_account_email=self._service_account_email,\n token_uri=self._token_uri,\n target_audience=target_audience,\n additional_claims=self._additional_claims.copy(),\n )\n\n def _make_authorization_grant_assertion(self):\n \"\"\"Create the OAuth 2.0 assertion.\n This assertion is used during the OAuth 2.0 grant to acquire an\n ID token.\n Returns:\n bytes: The authorization grant assertion.\n \"\"\"\n now = _helpers.utcnow()\n lifetime = datetime.timedelta(seconds=_DEFAULT_TOKEN_LIFETIME_SECS)\n expiry = now + lifetime\n\n payload = {\n \"iat\": _helpers.datetime_to_secs(now),\n \"exp\": _helpers.datetime_to_secs(expiry),\n # The issuer must be the service account email.\n \"iss\": self.service_account_email,\n # The audience must be the auth token endpoint's URI\n \"aud\": self._token_uri,\n # The target audience specifies which service the ID token is\n # intended for.\n \"target_audience\": self._target_audience,\n }\n\n payload.update(self._additional_claims)\n\n token = jwt.encode(self._signer, payload)\n\n return token\n\n @_helpers.copy_docstring(credentials.Credentials)\n def refresh(self, request):\n assertion = self._make_authorization_grant_assertion()\n access_token, expiry, _ = _client.id_token_jwt_grant(\n request, self._token_uri, assertion\n )\n self.token = access_token\n self.expiry = expiry\n\n @property\n @_helpers.copy_docstring(credentials.Signing)\n def signer(self):\n return self._signer\n\n @_helpers.copy_docstring(credentials.Signing)\n def sign_bytes(self, message):\n return self._signer.sign(message)\n\n @property\n def service_account_email(self):\n \"\"\"The service account email.\"\"\"\n return self._service_account_email\n\n @property\n def signer_email(self):\n return self._service_account_email\n", "path": "google/auth/compute_engine/credentials.py"}]}
| 2,802 | 128 |
gh_patches_debug_57973
|
rasdani/github-patches
|
git_diff
|
pyjanitor-devs__pyjanitor-1191
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[INF/CI] Add `--cov-append` for `pytest`
<!-- Thank you for your PR!
BEFORE YOU CONTINUE! Please add the appropriate three-letter abbreviation to your title.
The abbreviations can be:
- [DOC]: Documentation fixes.
- [ENH]: Code contributions and new features.
- [TST]: Test-related contributions.
- [INF]: Infrastructure-related contributions.
Also, do not forget to tag the relevant issue here as well.
Finally, as commits come in, don't forget to regularly rebase!
-->
# PR Description
Please describe the changes proposed in the pull request:
> Another reason code coverage failed is that pytest doesn't add `--cov-append` option.
`--cov-append` can get a sum coverage. I'll add this option in the next PR.
First let us merge `codecov.yml` into `tests.yml`. Keep the same test logic for the dev branch or a PR.
_Originally posted by @Zeroto521 in https://github.com/pyjanitor-devs/pyjanitor/issues/1185#issuecomment-1296479926_
<!-- Doing so provides maintainers with context on what the PR is, and can help us more effectively review your PR. -->
<!-- Please also identify below which issue that has been raised that you are going to close. -->
<!-- As you go down the PR template, please feel free to delete sections that are irrelevant. -->
# PR Checklist
<!-- This checklist exists for newcomers who are not yet familiar with our requirements. If you are experienced with
the project, please feel free to delete this section. -->
Please ensure that you have done the following:
1. [x] PR in from a fork off your branch. Do not PR from `<your_username>`:`dev`, but rather from `<your_username>`:`<feature-branch_name>`.
<!-- Doing this helps us keep the commit history much cleaner than it would otherwise be. -->
2. [x] If you're not on the contributors list, add yourself to `AUTHORS.md`.
<!-- We'd like to acknowledge your contributions! -->
3. [x] Add a line to `CHANGELOG.md` under the latest version header (i.e. the one that is "on deck") describing the contribution.
- Do use some discretion here; if there are multiple PRs that are related, keep them in a single line.
# Automatic checks
There will be automatic checks run on the PR. These include:
- Building a preview of the docs on Netlify
- Automatically linting the code
- Making sure the code is documented
- Making sure that all tests are passed
- Making sure that code coverage doesn't go down.
# Relevant Reviewers
<!-- Finally, please tag relevant maintainers to review. -->
Please tag maintainers to review.
- @ericmjl
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `janitor/accessors/__init__.py`
Content:
```
1 """Miscellaneous mathematical operators.
2
3 Lazy loading used here to speed up imports.
4 """
5
6 import warnings
7 from typing import Tuple
8
9
10 import lazy_loader as lazy
11
12 scipy_special = lazy.load("scipy.special")
13 ss = lazy.load("scipy.stats")
14 pf = lazy.load("pandas_flavor")
15 pd = lazy.load("pandas")
16 np = lazy.load("numpy")
17 pdtypes = lazy.load("pandas.api.types")
18
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/janitor/accessors/__init__.py b/janitor/accessors/__init__.py
--- a/janitor/accessors/__init__.py
+++ b/janitor/accessors/__init__.py
@@ -1,17 +1,3 @@
-"""Miscellaneous mathematical operators.
+"""Miscellaneous mathematical operators."""
-Lazy loading used here to speed up imports.
-"""
-
-import warnings
-from typing import Tuple
-
-
-import lazy_loader as lazy
-
-scipy_special = lazy.load("scipy.special")
-ss = lazy.load("scipy.stats")
-pf = lazy.load("pandas_flavor")
-pd = lazy.load("pandas")
-np = lazy.load("numpy")
-pdtypes = lazy.load("pandas.api.types")
+from janitor.accessors.data_description import DataDescription # noqa: F401
|
{"golden_diff": "diff --git a/janitor/accessors/__init__.py b/janitor/accessors/__init__.py\n--- a/janitor/accessors/__init__.py\n+++ b/janitor/accessors/__init__.py\n@@ -1,17 +1,3 @@\n-\"\"\"Miscellaneous mathematical operators.\n+\"\"\"Miscellaneous mathematical operators.\"\"\"\n \n-Lazy loading used here to speed up imports.\n-\"\"\"\n-\n-import warnings\n-from typing import Tuple\n-\n-\n-import lazy_loader as lazy\n-\n-scipy_special = lazy.load(\"scipy.special\")\n-ss = lazy.load(\"scipy.stats\")\n-pf = lazy.load(\"pandas_flavor\")\n-pd = lazy.load(\"pandas\")\n-np = lazy.load(\"numpy\")\n-pdtypes = lazy.load(\"pandas.api.types\")\n+from janitor.accessors.data_description import DataDescription # noqa: F401\n", "issue": "[INF/CI] Add `--cov-append` for `pytest`\n<!-- Thank you for your PR!\r\n\r\nBEFORE YOU CONTINUE! Please add the appropriate three-letter abbreviation to your title.\r\n\r\nThe abbreviations can be:\r\n- [DOC]: Documentation fixes.\r\n- [ENH]: Code contributions and new features.\r\n- [TST]: Test-related contributions.\r\n- [INF]: Infrastructure-related contributions.\r\n\r\nAlso, do not forget to tag the relevant issue here as well.\r\n\r\nFinally, as commits come in, don't forget to regularly rebase!\r\n-->\r\n\r\n# PR Description\r\n\r\nPlease describe the changes proposed in the pull request:\r\n\r\n> Another reason code coverage failed is that pytest doesn't add `--cov-append` option.\r\n`--cov-append` can get a sum coverage. I'll add this option in the next PR.\r\nFirst let us merge `codecov.yml` into `tests.yml`. Keep the same test logic for the dev branch or a PR.\r\n\r\n_Originally posted by @Zeroto521 in https://github.com/pyjanitor-devs/pyjanitor/issues/1185#issuecomment-1296479926_\r\n\r\n<!-- Doing so provides maintainers with context on what the PR is, and can help us more effectively review your PR. -->\r\n\r\n<!-- Please also identify below which issue that has been raised that you are going to close. -->\r\n\r\n<!-- As you go down the PR template, please feel free to delete sections that are irrelevant. -->\r\n\r\n# PR Checklist\r\n\r\n<!-- This checklist exists for newcomers who are not yet familiar with our requirements. If you are experienced with\r\nthe project, please feel free to delete this section. -->\r\n\r\nPlease ensure that you have done the following:\r\n\r\n1. [x] PR in from a fork off your branch. Do not PR from `<your_username>`:`dev`, but rather from `<your_username>`:`<feature-branch_name>`.\r\n<!-- Doing this helps us keep the commit history much cleaner than it would otherwise be. -->\r\n2. [x] If you're not on the contributors list, add yourself to `AUTHORS.md`.\r\n<!-- We'd like to acknowledge your contributions! -->\r\n3. [x] Add a line to `CHANGELOG.md` under the latest version header (i.e. the one that is \"on deck\") describing the contribution.\r\n - Do use some discretion here; if there are multiple PRs that are related, keep them in a single line.\r\n\r\n# Automatic checks\r\n\r\nThere will be automatic checks run on the PR. These include:\r\n\r\n- Building a preview of the docs on Netlify\r\n- Automatically linting the code\r\n- Making sure the code is documented\r\n- Making sure that all tests are passed\r\n- Making sure that code coverage doesn't go down.\r\n\r\n# Relevant Reviewers\r\n\r\n<!-- Finally, please tag relevant maintainers to review. -->\r\n\r\nPlease tag maintainers to review.\r\n\r\n- @ericmjl\r\n\n", "before_files": [{"content": "\"\"\"Miscellaneous mathematical operators.\n\nLazy loading used here to speed up imports.\n\"\"\"\n\nimport warnings\nfrom typing import Tuple\n\n\nimport lazy_loader as lazy\n\nscipy_special = lazy.load(\"scipy.special\")\nss = lazy.load(\"scipy.stats\")\npf = lazy.load(\"pandas_flavor\")\npd = lazy.load(\"pandas\")\nnp = lazy.load(\"numpy\")\npdtypes = lazy.load(\"pandas.api.types\")\n", "path": "janitor/accessors/__init__.py"}], "after_files": [{"content": "\"\"\"Miscellaneous mathematical operators.\"\"\"\n\nfrom janitor.accessors.data_description import DataDescription # noqa: F401\n", "path": "janitor/accessors/__init__.py"}]}
| 972 | 185 |
gh_patches_debug_38001
|
rasdani/github-patches
|
git_diff
|
biolab__orange3-1907
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
TypeError: OneClassSVMLearner doesn't support multiple class variables
https://sentry.io/biolab/orange3/issues/202498152/
```
TypeError: OneClassSVMLearner doesn't support multiple class variables
Module "Orange.widgets.data.owoutliers", line 141, in commit
y_pred = self.detect_outliers()
Module "Orange.widgets.data.owoutliers", line 169, in detect_outliers
model = learner(self.data)
Module "Orange.base", line 253, in __call__
m = super().__call__(data)
Module "Orange.base", line 52, in __call__
self.__class__.__name__)
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `Orange/widgets/data/owoutliers.py`
Content:
```
1 import sys
2
3 import numpy as np
4 from AnyQt.QtWidgets import QLayout
5
6 from Orange.base import SklLearner
7 from Orange.classification import OneClassSVMLearner, EllipticEnvelopeLearner
8 from Orange.data import Table, Domain, ContinuousVariable
9 from Orange.widgets import widget, gui
10 from Orange.widgets.settings import Setting
11 from Orange.widgets.utils.sql import check_sql_input
12
13
14 class OWOutliers(widget.OWWidget):
15 name = "Outliers"
16 description = "Detect outliers."
17 icon = "icons/Outliers.svg"
18 priority = 3000
19 category = "Data"
20 keywords = ["data", "outlier", "inlier"]
21
22 inputs = [("Data", Table, "set_data")]
23 outputs = [("Inliers", Table), ("Outliers", Table)]
24
25 want_main_area = False
26
27 OneClassSVM, Covariance = range(2)
28
29 outlier_method = Setting(OneClassSVM)
30 nu = Setting(50)
31 gamma = Setting(0.01)
32 cont = Setting(10)
33 empirical_covariance = Setting(False)
34 support_fraction = Setting(1)
35
36 data_info_default = 'No data on input.'
37 in_out_info_default = ' '
38
39 def __init__(self):
40 super().__init__()
41 self.data = None
42 self.n_inliers = self.n_outliers = None
43
44 box = gui.vBox(self.controlArea, "Information")
45 self.data_info_label = gui.widgetLabel(box, self.data_info_default)
46 self.in_out_info_label = gui.widgetLabel(box,
47 self.in_out_info_default)
48
49 box = gui.vBox(self.controlArea, "Outlier Detection Method")
50 detection = gui.radioButtons(box, self, "outlier_method")
51
52 gui.appendRadioButton(detection,
53 "One class SVM with non-linear kernel (RBF)")
54 ibox = gui.indentedBox(detection)
55 tooltip = "An upper bound on the fraction of training errors and a " \
56 "lower bound of the fraction of support vectors"
57 gui.widgetLabel(ibox, 'Nu:', tooltip=tooltip)
58 self.nu_slider = gui.hSlider(
59 ibox, self, "nu", minValue=1, maxValue=100, ticks=10,
60 labelFormat="%d %%", callback=self.nu_changed, tooltip=tooltip)
61 self.gamma_spin = gui.spin(
62 ibox, self, "gamma", label="Kernel coefficient:", step=1e-2,
63 spinType=float, minv=0.01, maxv=10, callback=self.gamma_changed)
64 gui.separator(detection, 12)
65
66 self.rb_cov = gui.appendRadioButton(detection, "Covariance estimator")
67 ibox = gui.indentedBox(detection)
68 self.l_cov = gui.widgetLabel(ibox, 'Contamination:')
69 self.cont_slider = gui.hSlider(
70 ibox, self, "cont", minValue=0, maxValue=100, ticks=10,
71 labelFormat="%d %%", callback=self.cont_changed)
72
73 ebox = gui.hBox(ibox)
74 self.cb_emp_cov = gui.checkBox(
75 ebox, self, "empirical_covariance",
76 "Support fraction:", callback=self.empirical_changed)
77 self.support_fraction_spin = gui.spin(
78 ebox, self, "support_fraction", step=1e-1, spinType=float,
79 minv=0.1, maxv=10, callback=self.support_fraction_changed)
80
81 gui.separator(detection, 12)
82
83 gui.button(self.buttonsArea, self, "Detect Outliers",
84 callback=self.commit)
85 self.layout().setSizeConstraint(QLayout.SetFixedSize)
86
87 def nu_changed(self):
88 self.outlier_method = self.OneClassSVM
89
90 def gamma_changed(self):
91 self.outlier_method = self.OneClassSVM
92
93 def cont_changed(self):
94 self.outlier_method = self.Covariance
95
96 def support_fraction_changed(self):
97 self.outlier_method = self.Covariance
98
99 def empirical_changed(self):
100 self.outlier_method = self.Covariance
101
102 def disable_covariance(self):
103 self.outlier_method = self.OneClassSVM
104 self.rb_cov.setDisabled(True)
105 self.l_cov.setDisabled(True)
106 self.cont_slider.setDisabled(True)
107 self.cb_emp_cov.setDisabled(True)
108 self.support_fraction_spin.setDisabled(True)
109 self.warning('Too many features for covariance estimation.')
110
111 def enable_covariance(self):
112 self.rb_cov.setDisabled(False)
113 self.l_cov.setDisabled(False)
114 self.cont_slider.setDisabled(False)
115 self.cb_emp_cov.setDisabled(False)
116 self.support_fraction_spin.setDisabled(False)
117 self.warning()
118
119 @check_sql_input
120 def set_data(self, dataset):
121 self.data = dataset
122 if self.data is None:
123 self.data_info_label.setText(self.data_info_default)
124 self.in_out_info_label.setText(self.in_out_info_default)
125 else:
126 self.data_info_label.setText('%d instances' % len(self.data))
127 self.in_out_info_label.setText(' ')
128
129 self.enable_covariance()
130 if self.data and len(self.data.domain.attributes) > 1500:
131 self.disable_covariance()
132
133 self.commit()
134
135 def commit(self):
136 self.error()
137 inliers = outliers = None
138 self.n_inliers = self.n_outliers = None
139 if self.data is not None and len(self.data) > 0:
140 try:
141 y_pred = self.detect_outliers()
142 except ValueError:
143 self.error("Singular covariance matrix.")
144 self.in_out_info_label.setText(self.in_out_info_default)
145 else:
146 inliers_ind = np.where(y_pred == 1)[0]
147 outliers_ind = np.where(y_pred == -1)[0]
148 inliers = Table(self.new_domain, self.new_data, inliers_ind)
149 outliers = Table(self.new_domain,
150 self.new_data, outliers_ind)
151 self.in_out_info_label.setText('%d inliers, %d outliers' %
152 (len(inliers), len(outliers)))
153 self.n_inliers = len(inliers)
154 self.n_outliers = len(outliers)
155
156 self.send("Inliers", inliers)
157 self.send("Outliers", outliers)
158
159 def detect_outliers(self):
160 if self.outlier_method == self.OneClassSVM:
161 learner = OneClassSVMLearner(
162 gamma=self.gamma, nu=self.nu / 100,
163 preprocessors=SklLearner.preprocessors)
164 else:
165 learner = EllipticEnvelopeLearner(
166 support_fraction=self.support_fraction
167 if self.empirical_covariance else None,
168 contamination=self.cont / 100.)
169 model = learner(self.data)
170 y_pred = model(self.data)
171 self.add_metas(model)
172 return np.array(y_pred)
173
174 def add_metas(self, model):
175 if self.outlier_method == self.Covariance:
176 mahal = model.mahalanobis(self.data.X)
177 mahal = mahal.reshape(len(self.data), 1)
178 attrs = self.data.domain.attributes
179 classes = self.data.domain.class_vars
180 new_metas = list(self.data.domain.metas) + \
181 [ContinuousVariable(name="Mahalanobis")]
182 self.new_domain = Domain(attrs, classes, new_metas)
183 self.new_data = Table(self.new_domain, self.data)
184 self.new_data.metas = np.hstack((self.data.metas, mahal))
185 else:
186 self.new_domain = self.data.domain
187 self.new_data = self.data
188
189 def send_report(self):
190 if self.n_outliers is None or self.n_inliers is None:
191 return
192 self.report_items("Data",
193 (("Input instances", len(self.data)),
194 ("Inliers", self.n_inliers),
195 ("Outliers", self.n_outliers)))
196 if self.outlier_method == 0:
197 self.report_items(
198 "Detection",
199 (("Detection method",
200 "One class SVM with non-linear kernel (RBF)"),
201 ("Regularization (nu)", self.nu),
202 ("Kernel coefficient", self.gamma)))
203 else:
204 self.report_items(
205 "Detection",
206 (("Detection method", "Covariance estimator"),
207 ("Contamination", self.cont),
208 ("Support fraction", self.support_fraction)))
209
210 def test_main():
211 from AnyQt.QtWidgets import QApplication
212 app = QApplication([])
213 data = Table("iris")
214 w = OWOutliers()
215 w.set_data(data)
216 w.commit()
217 w.show()
218 return app.exec_()
219
220
221 if __name__ == "__main__":
222 sys.exit(test_main())
223
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/Orange/widgets/data/owoutliers.py b/Orange/widgets/data/owoutliers.py
--- a/Orange/widgets/data/owoutliers.py
+++ b/Orange/widgets/data/owoutliers.py
@@ -8,6 +8,7 @@
from Orange.data import Table, Domain, ContinuousVariable
from Orange.widgets import widget, gui
from Orange.widgets.settings import Setting
+from Orange.widgets.widget import Msg
from Orange.widgets.utils.sql import check_sql_input
@@ -36,6 +37,10 @@
data_info_default = 'No data on input.'
in_out_info_default = ' '
+ class Error(widget.OWWidget.Error):
+ singular_cov = Msg("Singular covariance matrix.")
+ multiclass_error = Msg("Multiple class data is not supported")
+
def __init__(self):
super().__init__()
self.data = None
@@ -133,25 +138,29 @@
self.commit()
def commit(self):
- self.error()
+ self.clear_messages()
inliers = outliers = None
self.n_inliers = self.n_outliers = None
if self.data is not None and len(self.data) > 0:
- try:
- y_pred = self.detect_outliers()
- except ValueError:
- self.error("Singular covariance matrix.")
- self.in_out_info_label.setText(self.in_out_info_default)
+ if self.data.Y.ndim > 1:
+ self.Error.multiclass_error()
else:
- inliers_ind = np.where(y_pred == 1)[0]
- outliers_ind = np.where(y_pred == -1)[0]
- inliers = Table(self.new_domain, self.new_data, inliers_ind)
- outliers = Table(self.new_domain,
- self.new_data, outliers_ind)
- self.in_out_info_label.setText('%d inliers, %d outliers' %
- (len(inliers), len(outliers)))
- self.n_inliers = len(inliers)
- self.n_outliers = len(outliers)
+ try:
+ y_pred = self.detect_outliers()
+ except ValueError:
+ self.Error.singular_cov()
+ self.in_out_info_label.setText(self.in_out_info_default)
+ else:
+ inliers_ind = np.where(y_pred == 1)[0]
+ outliers_ind = np.where(y_pred == -1)[0]
+ inliers = Table(self.new_domain, self.new_data, inliers_ind)
+ outliers = Table(self.new_domain,
+ self.new_data, outliers_ind)
+ self.in_out_info_label.setText(
+ "{} inliers, {} outliers".format(len(inliers),
+ len(outliers)))
+ self.n_inliers = len(inliers)
+ self.n_outliers = len(outliers)
self.send("Inliers", inliers)
self.send("Outliers", outliers)
|
{"golden_diff": "diff --git a/Orange/widgets/data/owoutliers.py b/Orange/widgets/data/owoutliers.py\n--- a/Orange/widgets/data/owoutliers.py\n+++ b/Orange/widgets/data/owoutliers.py\n@@ -8,6 +8,7 @@\n from Orange.data import Table, Domain, ContinuousVariable\n from Orange.widgets import widget, gui\n from Orange.widgets.settings import Setting\n+from Orange.widgets.widget import Msg\n from Orange.widgets.utils.sql import check_sql_input\n \n \n@@ -36,6 +37,10 @@\n data_info_default = 'No data on input.'\n in_out_info_default = ' '\n \n+ class Error(widget.OWWidget.Error):\n+ singular_cov = Msg(\"Singular covariance matrix.\")\n+ multiclass_error = Msg(\"Multiple class data is not supported\")\n+\n def __init__(self):\n super().__init__()\n self.data = None\n@@ -133,25 +138,29 @@\n self.commit()\n \n def commit(self):\n- self.error()\n+ self.clear_messages()\n inliers = outliers = None\n self.n_inliers = self.n_outliers = None\n if self.data is not None and len(self.data) > 0:\n- try:\n- y_pred = self.detect_outliers()\n- except ValueError:\n- self.error(\"Singular covariance matrix.\")\n- self.in_out_info_label.setText(self.in_out_info_default)\n+ if self.data.Y.ndim > 1:\n+ self.Error.multiclass_error()\n else:\n- inliers_ind = np.where(y_pred == 1)[0]\n- outliers_ind = np.where(y_pred == -1)[0]\n- inliers = Table(self.new_domain, self.new_data, inliers_ind)\n- outliers = Table(self.new_domain,\n- self.new_data, outliers_ind)\n- self.in_out_info_label.setText('%d inliers, %d outliers' %\n- (len(inliers), len(outliers)))\n- self.n_inliers = len(inliers)\n- self.n_outliers = len(outliers)\n+ try:\n+ y_pred = self.detect_outliers()\n+ except ValueError:\n+ self.Error.singular_cov()\n+ self.in_out_info_label.setText(self.in_out_info_default)\n+ else:\n+ inliers_ind = np.where(y_pred == 1)[0]\n+ outliers_ind = np.where(y_pred == -1)[0]\n+ inliers = Table(self.new_domain, self.new_data, inliers_ind)\n+ outliers = Table(self.new_domain,\n+ self.new_data, outliers_ind)\n+ self.in_out_info_label.setText(\n+ \"{} inliers, {} outliers\".format(len(inliers),\n+ len(outliers)))\n+ self.n_inliers = len(inliers)\n+ self.n_outliers = len(outliers)\n \n self.send(\"Inliers\", inliers)\n self.send(\"Outliers\", outliers)\n", "issue": "TypeError: OneClassSVMLearner doesn't support multiple class variables\nhttps://sentry.io/biolab/orange3/issues/202498152/\n\n```\nTypeError: OneClassSVMLearner doesn't support multiple class variables\n Module \"Orange.widgets.data.owoutliers\", line 141, in commit\n\n y_pred = self.detect_outliers()\n Module \"Orange.widgets.data.owoutliers\", line 169, in detect_outliers\n\n model = learner(self.data)\n Module \"Orange.base\", line 253, in __call__\n\n m = super().__call__(data)\n Module \"Orange.base\", line 52, in __call__\n\n self.__class__.__name__)\n```\n", "before_files": [{"content": "import sys\n\nimport numpy as np\nfrom AnyQt.QtWidgets import QLayout\n\nfrom Orange.base import SklLearner\nfrom Orange.classification import OneClassSVMLearner, EllipticEnvelopeLearner\nfrom Orange.data import Table, Domain, ContinuousVariable\nfrom Orange.widgets import widget, gui\nfrom Orange.widgets.settings import Setting\nfrom Orange.widgets.utils.sql import check_sql_input\n\n\nclass OWOutliers(widget.OWWidget):\n name = \"Outliers\"\n description = \"Detect outliers.\"\n icon = \"icons/Outliers.svg\"\n priority = 3000\n category = \"Data\"\n keywords = [\"data\", \"outlier\", \"inlier\"]\n\n inputs = [(\"Data\", Table, \"set_data\")]\n outputs = [(\"Inliers\", Table), (\"Outliers\", Table)]\n\n want_main_area = False\n\n OneClassSVM, Covariance = range(2)\n\n outlier_method = Setting(OneClassSVM)\n nu = Setting(50)\n gamma = Setting(0.01)\n cont = Setting(10)\n empirical_covariance = Setting(False)\n support_fraction = Setting(1)\n\n data_info_default = 'No data on input.'\n in_out_info_default = ' '\n\n def __init__(self):\n super().__init__()\n self.data = None\n self.n_inliers = self.n_outliers = None\n\n box = gui.vBox(self.controlArea, \"Information\")\n self.data_info_label = gui.widgetLabel(box, self.data_info_default)\n self.in_out_info_label = gui.widgetLabel(box,\n self.in_out_info_default)\n\n box = gui.vBox(self.controlArea, \"Outlier Detection Method\")\n detection = gui.radioButtons(box, self, \"outlier_method\")\n\n gui.appendRadioButton(detection,\n \"One class SVM with non-linear kernel (RBF)\")\n ibox = gui.indentedBox(detection)\n tooltip = \"An upper bound on the fraction of training errors and a \" \\\n \"lower bound of the fraction of support vectors\"\n gui.widgetLabel(ibox, 'Nu:', tooltip=tooltip)\n self.nu_slider = gui.hSlider(\n ibox, self, \"nu\", minValue=1, maxValue=100, ticks=10,\n labelFormat=\"%d %%\", callback=self.nu_changed, tooltip=tooltip)\n self.gamma_spin = gui.spin(\n ibox, self, \"gamma\", label=\"Kernel coefficient:\", step=1e-2,\n spinType=float, minv=0.01, maxv=10, callback=self.gamma_changed)\n gui.separator(detection, 12)\n\n self.rb_cov = gui.appendRadioButton(detection, \"Covariance estimator\")\n ibox = gui.indentedBox(detection)\n self.l_cov = gui.widgetLabel(ibox, 'Contamination:')\n self.cont_slider = gui.hSlider(\n ibox, self, \"cont\", minValue=0, maxValue=100, ticks=10,\n labelFormat=\"%d %%\", callback=self.cont_changed)\n\n ebox = gui.hBox(ibox)\n self.cb_emp_cov = gui.checkBox(\n ebox, self, \"empirical_covariance\",\n \"Support fraction:\", callback=self.empirical_changed)\n self.support_fraction_spin = gui.spin(\n ebox, self, \"support_fraction\", step=1e-1, spinType=float,\n minv=0.1, maxv=10, callback=self.support_fraction_changed)\n\n gui.separator(detection, 12)\n\n gui.button(self.buttonsArea, self, \"Detect Outliers\",\n callback=self.commit)\n self.layout().setSizeConstraint(QLayout.SetFixedSize)\n\n def nu_changed(self):\n self.outlier_method = self.OneClassSVM\n\n def gamma_changed(self):\n self.outlier_method = self.OneClassSVM\n\n def cont_changed(self):\n self.outlier_method = self.Covariance\n\n def support_fraction_changed(self):\n self.outlier_method = self.Covariance\n\n def empirical_changed(self):\n self.outlier_method = self.Covariance\n\n def disable_covariance(self):\n self.outlier_method = self.OneClassSVM\n self.rb_cov.setDisabled(True)\n self.l_cov.setDisabled(True)\n self.cont_slider.setDisabled(True)\n self.cb_emp_cov.setDisabled(True)\n self.support_fraction_spin.setDisabled(True)\n self.warning('Too many features for covariance estimation.')\n\n def enable_covariance(self):\n self.rb_cov.setDisabled(False)\n self.l_cov.setDisabled(False)\n self.cont_slider.setDisabled(False)\n self.cb_emp_cov.setDisabled(False)\n self.support_fraction_spin.setDisabled(False)\n self.warning()\n\n @check_sql_input\n def set_data(self, dataset):\n self.data = dataset\n if self.data is None:\n self.data_info_label.setText(self.data_info_default)\n self.in_out_info_label.setText(self.in_out_info_default)\n else:\n self.data_info_label.setText('%d instances' % len(self.data))\n self.in_out_info_label.setText(' ')\n\n self.enable_covariance()\n if self.data and len(self.data.domain.attributes) > 1500:\n self.disable_covariance()\n\n self.commit()\n\n def commit(self):\n self.error()\n inliers = outliers = None\n self.n_inliers = self.n_outliers = None\n if self.data is not None and len(self.data) > 0:\n try:\n y_pred = self.detect_outliers()\n except ValueError:\n self.error(\"Singular covariance matrix.\")\n self.in_out_info_label.setText(self.in_out_info_default)\n else:\n inliers_ind = np.where(y_pred == 1)[0]\n outliers_ind = np.where(y_pred == -1)[0]\n inliers = Table(self.new_domain, self.new_data, inliers_ind)\n outliers = Table(self.new_domain,\n self.new_data, outliers_ind)\n self.in_out_info_label.setText('%d inliers, %d outliers' %\n (len(inliers), len(outliers)))\n self.n_inliers = len(inliers)\n self.n_outliers = len(outliers)\n\n self.send(\"Inliers\", inliers)\n self.send(\"Outliers\", outliers)\n\n def detect_outliers(self):\n if self.outlier_method == self.OneClassSVM:\n learner = OneClassSVMLearner(\n gamma=self.gamma, nu=self.nu / 100,\n preprocessors=SklLearner.preprocessors)\n else:\n learner = EllipticEnvelopeLearner(\n support_fraction=self.support_fraction\n if self.empirical_covariance else None,\n contamination=self.cont / 100.)\n model = learner(self.data)\n y_pred = model(self.data)\n self.add_metas(model)\n return np.array(y_pred)\n\n def add_metas(self, model):\n if self.outlier_method == self.Covariance:\n mahal = model.mahalanobis(self.data.X)\n mahal = mahal.reshape(len(self.data), 1)\n attrs = self.data.domain.attributes\n classes = self.data.domain.class_vars\n new_metas = list(self.data.domain.metas) + \\\n [ContinuousVariable(name=\"Mahalanobis\")]\n self.new_domain = Domain(attrs, classes, new_metas)\n self.new_data = Table(self.new_domain, self.data)\n self.new_data.metas = np.hstack((self.data.metas, mahal))\n else:\n self.new_domain = self.data.domain\n self.new_data = self.data\n\n def send_report(self):\n if self.n_outliers is None or self.n_inliers is None:\n return\n self.report_items(\"Data\",\n ((\"Input instances\", len(self.data)),\n (\"Inliers\", self.n_inliers),\n (\"Outliers\", self.n_outliers)))\n if self.outlier_method == 0:\n self.report_items(\n \"Detection\",\n ((\"Detection method\",\n \"One class SVM with non-linear kernel (RBF)\"),\n (\"Regularization (nu)\", self.nu),\n (\"Kernel coefficient\", self.gamma)))\n else:\n self.report_items(\n \"Detection\",\n ((\"Detection method\", \"Covariance estimator\"),\n (\"Contamination\", self.cont),\n (\"Support fraction\", self.support_fraction)))\n\ndef test_main():\n from AnyQt.QtWidgets import QApplication\n app = QApplication([])\n data = Table(\"iris\")\n w = OWOutliers()\n w.set_data(data)\n w.commit()\n w.show()\n return app.exec_()\n\n\nif __name__ == \"__main__\":\n sys.exit(test_main())\n", "path": "Orange/widgets/data/owoutliers.py"}], "after_files": [{"content": "import sys\n\nimport numpy as np\nfrom AnyQt.QtWidgets import QLayout\n\nfrom Orange.base import SklLearner\nfrom Orange.classification import OneClassSVMLearner, EllipticEnvelopeLearner\nfrom Orange.data import Table, Domain, ContinuousVariable\nfrom Orange.widgets import widget, gui\nfrom Orange.widgets.settings import Setting\nfrom Orange.widgets.widget import Msg\nfrom Orange.widgets.utils.sql import check_sql_input\n\n\nclass OWOutliers(widget.OWWidget):\n name = \"Outliers\"\n description = \"Detect outliers.\"\n icon = \"icons/Outliers.svg\"\n priority = 3000\n category = \"Data\"\n keywords = [\"data\", \"outlier\", \"inlier\"]\n\n inputs = [(\"Data\", Table, \"set_data\")]\n outputs = [(\"Inliers\", Table), (\"Outliers\", Table)]\n\n want_main_area = False\n\n OneClassSVM, Covariance = range(2)\n\n outlier_method = Setting(OneClassSVM)\n nu = Setting(50)\n gamma = Setting(0.01)\n cont = Setting(10)\n empirical_covariance = Setting(False)\n support_fraction = Setting(1)\n\n data_info_default = 'No data on input.'\n in_out_info_default = ' '\n\n class Error(widget.OWWidget.Error):\n singular_cov = Msg(\"Singular covariance matrix.\")\n multiclass_error = Msg(\"Multiple class data is not supported\")\n\n def __init__(self):\n super().__init__()\n self.data = None\n self.n_inliers = self.n_outliers = None\n\n box = gui.vBox(self.controlArea, \"Information\")\n self.data_info_label = gui.widgetLabel(box, self.data_info_default)\n self.in_out_info_label = gui.widgetLabel(box,\n self.in_out_info_default)\n\n box = gui.vBox(self.controlArea, \"Outlier Detection Method\")\n detection = gui.radioButtons(box, self, \"outlier_method\")\n\n gui.appendRadioButton(detection,\n \"One class SVM with non-linear kernel (RBF)\")\n ibox = gui.indentedBox(detection)\n tooltip = \"An upper bound on the fraction of training errors and a \" \\\n \"lower bound of the fraction of support vectors\"\n gui.widgetLabel(ibox, 'Nu:', tooltip=tooltip)\n self.nu_slider = gui.hSlider(\n ibox, self, \"nu\", minValue=1, maxValue=100, ticks=10,\n labelFormat=\"%d %%\", callback=self.nu_changed, tooltip=tooltip)\n self.gamma_spin = gui.spin(\n ibox, self, \"gamma\", label=\"Kernel coefficient:\", step=1e-2,\n spinType=float, minv=0.01, maxv=10, callback=self.gamma_changed)\n gui.separator(detection, 12)\n\n self.rb_cov = gui.appendRadioButton(detection, \"Covariance estimator\")\n ibox = gui.indentedBox(detection)\n self.l_cov = gui.widgetLabel(ibox, 'Contamination:')\n self.cont_slider = gui.hSlider(\n ibox, self, \"cont\", minValue=0, maxValue=100, ticks=10,\n labelFormat=\"%d %%\", callback=self.cont_changed)\n\n ebox = gui.hBox(ibox)\n self.cb_emp_cov = gui.checkBox(\n ebox, self, \"empirical_covariance\",\n \"Support fraction:\", callback=self.empirical_changed)\n self.support_fraction_spin = gui.spin(\n ebox, self, \"support_fraction\", step=1e-1, spinType=float,\n minv=0.1, maxv=10, callback=self.support_fraction_changed)\n\n gui.separator(detection, 12)\n\n gui.button(self.buttonsArea, self, \"Detect Outliers\",\n callback=self.commit)\n self.layout().setSizeConstraint(QLayout.SetFixedSize)\n\n def nu_changed(self):\n self.outlier_method = self.OneClassSVM\n\n def gamma_changed(self):\n self.outlier_method = self.OneClassSVM\n\n def cont_changed(self):\n self.outlier_method = self.Covariance\n\n def support_fraction_changed(self):\n self.outlier_method = self.Covariance\n\n def empirical_changed(self):\n self.outlier_method = self.Covariance\n\n def disable_covariance(self):\n self.outlier_method = self.OneClassSVM\n self.rb_cov.setDisabled(True)\n self.l_cov.setDisabled(True)\n self.cont_slider.setDisabled(True)\n self.cb_emp_cov.setDisabled(True)\n self.support_fraction_spin.setDisabled(True)\n self.warning('Too many features for covariance estimation.')\n\n def enable_covariance(self):\n self.rb_cov.setDisabled(False)\n self.l_cov.setDisabled(False)\n self.cont_slider.setDisabled(False)\n self.cb_emp_cov.setDisabled(False)\n self.support_fraction_spin.setDisabled(False)\n self.warning()\n\n @check_sql_input\n def set_data(self, dataset):\n self.data = dataset\n if self.data is None:\n self.data_info_label.setText(self.data_info_default)\n self.in_out_info_label.setText(self.in_out_info_default)\n else:\n self.data_info_label.setText('%d instances' % len(self.data))\n self.in_out_info_label.setText(' ')\n\n self.enable_covariance()\n if self.data and len(self.data.domain.attributes) > 1500:\n self.disable_covariance()\n\n self.commit()\n\n def commit(self):\n self.clear_messages()\n inliers = outliers = None\n self.n_inliers = self.n_outliers = None\n if self.data is not None and len(self.data) > 0:\n if self.data.Y.ndim > 1:\n self.Error.multiclass_error()\n else:\n try:\n y_pred = self.detect_outliers()\n except ValueError:\n self.Error.singular_cov()\n self.in_out_info_label.setText(self.in_out_info_default)\n else:\n inliers_ind = np.where(y_pred == 1)[0]\n outliers_ind = np.where(y_pred == -1)[0]\n inliers = Table(self.new_domain, self.new_data, inliers_ind)\n outliers = Table(self.new_domain,\n self.new_data, outliers_ind)\n self.in_out_info_label.setText(\n \"{} inliers, {} outliers\".format(len(inliers),\n len(outliers)))\n self.n_inliers = len(inliers)\n self.n_outliers = len(outliers)\n\n self.send(\"Inliers\", inliers)\n self.send(\"Outliers\", outliers)\n\n def detect_outliers(self):\n if self.outlier_method == self.OneClassSVM:\n learner = OneClassSVMLearner(\n gamma=self.gamma, nu=self.nu / 100,\n preprocessors=SklLearner.preprocessors)\n else:\n learner = EllipticEnvelopeLearner(\n support_fraction=self.support_fraction\n if self.empirical_covariance else None,\n contamination=self.cont / 100.)\n model = learner(self.data)\n y_pred = model(self.data)\n self.add_metas(model)\n return np.array(y_pred)\n\n def add_metas(self, model):\n if self.outlier_method == self.Covariance:\n mahal = model.mahalanobis(self.data.X)\n mahal = mahal.reshape(len(self.data), 1)\n attrs = self.data.domain.attributes\n classes = self.data.domain.class_vars\n new_metas = list(self.data.domain.metas) + \\\n [ContinuousVariable(name=\"Mahalanobis\")]\n self.new_domain = Domain(attrs, classes, new_metas)\n self.new_data = Table(self.new_domain, self.data)\n self.new_data.metas = np.hstack((self.data.metas, mahal))\n else:\n self.new_domain = self.data.domain\n self.new_data = self.data\n\n def send_report(self):\n if self.n_outliers is None or self.n_inliers is None:\n return\n self.report_items(\"Data\",\n ((\"Input instances\", len(self.data)),\n (\"Inliers\", self.n_inliers),\n (\"Outliers\", self.n_outliers)))\n if self.outlier_method == 0:\n self.report_items(\n \"Detection\",\n ((\"Detection method\",\n \"One class SVM with non-linear kernel (RBF)\"),\n (\"Regularization (nu)\", self.nu),\n (\"Kernel coefficient\", self.gamma)))\n else:\n self.report_items(\n \"Detection\",\n ((\"Detection method\", \"Covariance estimator\"),\n (\"Contamination\", self.cont),\n (\"Support fraction\", self.support_fraction)))\n\ndef test_main():\n from AnyQt.QtWidgets import QApplication\n app = QApplication([])\n data = Table(\"iris\")\n w = OWOutliers()\n w.set_data(data)\n w.commit()\n w.show()\n return app.exec_()\n\n\nif __name__ == \"__main__\":\n sys.exit(test_main())\n", "path": "Orange/widgets/data/owoutliers.py"}]}
| 2,848 | 632 |
gh_patches_debug_6944
|
rasdani/github-patches
|
git_diff
|
OpenNMT__OpenNMT-py-1805
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Logger is not passed to translator
When building the translator, there is a logger created but not passed to the translator:
https://github.com/OpenNMT/OpenNMT-py/blob/35cf4f0ae774a4aa500318879a1a4d53408ac129/onmt/bin/translate.py#L18
This results in a log file that only contains a single entry:
https://github.com/OpenNMT/OpenNMT-py/blob/35cf4f0ae774a4aa500318879a1a4d53408ac129/onmt/bin/translate.py#L24
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `onmt/bin/translate.py`
Content:
```
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 from __future__ import unicode_literals
5
6 from onmt.utils.logging import init_logger
7 from onmt.utils.misc import split_corpus
8 from onmt.translate.translator import build_translator
9
10 import onmt.opts as opts
11 from onmt.utils.parse import ArgumentParser
12
13
14 def translate(opt):
15 ArgumentParser.validate_translate_opts(opt)
16 logger = init_logger(opt.log_file)
17
18 translator = build_translator(opt, report_score=True)
19 src_shards = split_corpus(opt.src, opt.shard_size)
20 tgt_shards = split_corpus(opt.tgt, opt.shard_size)
21 shard_pairs = zip(src_shards, tgt_shards)
22
23 for i, (src_shard, tgt_shard) in enumerate(shard_pairs):
24 logger.info("Translating shard %d." % i)
25 translator.translate(
26 src=src_shard,
27 tgt=tgt_shard,
28 src_dir=opt.src_dir,
29 batch_size=opt.batch_size,
30 batch_type=opt.batch_type,
31 attn_debug=opt.attn_debug,
32 align_debug=opt.align_debug
33 )
34
35
36 def _get_parser():
37 parser = ArgumentParser(description='translate.py')
38
39 opts.config_opts(parser)
40 opts.translate_opts(parser)
41 return parser
42
43
44 def main():
45 parser = _get_parser()
46
47 opt = parser.parse_args()
48 translate(opt)
49
50
51 if __name__ == "__main__":
52 main()
53
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/onmt/bin/translate.py b/onmt/bin/translate.py
--- a/onmt/bin/translate.py
+++ b/onmt/bin/translate.py
@@ -15,7 +15,7 @@
ArgumentParser.validate_translate_opts(opt)
logger = init_logger(opt.log_file)
- translator = build_translator(opt, report_score=True)
+ translator = build_translator(opt, logger=logger, report_score=True)
src_shards = split_corpus(opt.src, opt.shard_size)
tgt_shards = split_corpus(opt.tgt, opt.shard_size)
shard_pairs = zip(src_shards, tgt_shards)
|
{"golden_diff": "diff --git a/onmt/bin/translate.py b/onmt/bin/translate.py\n--- a/onmt/bin/translate.py\n+++ b/onmt/bin/translate.py\n@@ -15,7 +15,7 @@\n ArgumentParser.validate_translate_opts(opt)\n logger = init_logger(opt.log_file)\n \n- translator = build_translator(opt, report_score=True)\n+ translator = build_translator(opt, logger=logger, report_score=True)\n src_shards = split_corpus(opt.src, opt.shard_size)\n tgt_shards = split_corpus(opt.tgt, opt.shard_size)\n shard_pairs = zip(src_shards, tgt_shards)\n", "issue": "Logger is not passed to translator\nWhen building the translator, there is a logger created but not passed to the translator:\r\nhttps://github.com/OpenNMT/OpenNMT-py/blob/35cf4f0ae774a4aa500318879a1a4d53408ac129/onmt/bin/translate.py#L18\r\nThis results in a log file that only contains a single entry:\r\nhttps://github.com/OpenNMT/OpenNMT-py/blob/35cf4f0ae774a4aa500318879a1a4d53408ac129/onmt/bin/translate.py#L24\n", "before_files": [{"content": "#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\nfrom __future__ import unicode_literals\n\nfrom onmt.utils.logging import init_logger\nfrom onmt.utils.misc import split_corpus\nfrom onmt.translate.translator import build_translator\n\nimport onmt.opts as opts\nfrom onmt.utils.parse import ArgumentParser\n\n\ndef translate(opt):\n ArgumentParser.validate_translate_opts(opt)\n logger = init_logger(opt.log_file)\n\n translator = build_translator(opt, report_score=True)\n src_shards = split_corpus(opt.src, opt.shard_size)\n tgt_shards = split_corpus(opt.tgt, opt.shard_size)\n shard_pairs = zip(src_shards, tgt_shards)\n\n for i, (src_shard, tgt_shard) in enumerate(shard_pairs):\n logger.info(\"Translating shard %d.\" % i)\n translator.translate(\n src=src_shard,\n tgt=tgt_shard,\n src_dir=opt.src_dir,\n batch_size=opt.batch_size,\n batch_type=opt.batch_type,\n attn_debug=opt.attn_debug,\n align_debug=opt.align_debug\n )\n\n\ndef _get_parser():\n parser = ArgumentParser(description='translate.py')\n\n opts.config_opts(parser)\n opts.translate_opts(parser)\n return parser\n\n\ndef main():\n parser = _get_parser()\n\n opt = parser.parse_args()\n translate(opt)\n\n\nif __name__ == \"__main__\":\n main()\n", "path": "onmt/bin/translate.py"}], "after_files": [{"content": "#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\nfrom __future__ import unicode_literals\n\nfrom onmt.utils.logging import init_logger\nfrom onmt.utils.misc import split_corpus\nfrom onmt.translate.translator import build_translator\n\nimport onmt.opts as opts\nfrom onmt.utils.parse import ArgumentParser\n\n\ndef translate(opt):\n ArgumentParser.validate_translate_opts(opt)\n logger = init_logger(opt.log_file)\n\n translator = build_translator(opt, logger=logger, report_score=True)\n src_shards = split_corpus(opt.src, opt.shard_size)\n tgt_shards = split_corpus(opt.tgt, opt.shard_size)\n shard_pairs = zip(src_shards, tgt_shards)\n\n for i, (src_shard, tgt_shard) in enumerate(shard_pairs):\n logger.info(\"Translating shard %d.\" % i)\n translator.translate(\n src=src_shard,\n tgt=tgt_shard,\n src_dir=opt.src_dir,\n batch_size=opt.batch_size,\n batch_type=opt.batch_type,\n attn_debug=opt.attn_debug,\n align_debug=opt.align_debug\n )\n\n\ndef _get_parser():\n parser = ArgumentParser(description='translate.py')\n\n opts.config_opts(parser)\n opts.translate_opts(parser)\n return parser\n\n\ndef main():\n parser = _get_parser()\n\n opt = parser.parse_args()\n translate(opt)\n\n\nif __name__ == \"__main__\":\n main()\n", "path": "onmt/bin/translate.py"}]}
| 833 | 140 |
gh_patches_debug_15331
|
rasdani/github-patches
|
git_diff
|
napari__napari-1578
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Plugin Errors not work in develop
## 🐛 Bug
<!-- A clear and concise description of what the bug is. -->
$ NAPARI_CATCH_ERRORS=0 python -m napari
16:11:17 ERROR Unhandled exception:
Traceback (most recent call last):
File "/home/czaki/Dokumenty/projekty/napari/napari/_qt/qt_main_window.py", line 300, in _show_plugin_err_reporter
plugin_sorter = QtPluginErrReporter(parent=self._qt_window)
File "/home/czaki/Dokumenty/projekty/napari/napari/_qt/dialogs/qt_plugin_report.py", line 62, in __init__
from ..plugins import plugin_manager as _pm
ModuleNotFoundError: No module named 'napari._qt.plugins'
## To Reproduce
Steps to reproduce the behavior:
1. install last napari from github
2. try open "Plugin Errors" dialog
<!-- If you have a code sample, error messages, stack traces, please provide it here as well -->
## Expected behavior
<!-- A clear and concise description of what you expected to happen. -->
## Environment
- Please copy and paste the information at napari info option in help menubar here:
napari: 0.3.7.dev30+gf101ef7
Platform: Linux-4.15.0-112-generic-x86_64-with-debian-buster-sid
Python: 3.7.6 (default, Feb 20 2020, 10:04:45) [GCC 7.4.0]
Qt: 5.14.2
PyQt5: 5.14.2
NumPy: 1.18.5
SciPy: 1.4.1
Dask: 2.17.2
VisPy: 0.6.4
GL version: 4.6.0 NVIDIA 440.100
MAX_TEXTURE_SIZE: 32768
Plugins:
- napari-plugin-engine: 0.1.5
- svg: 0.1.3
- Any other relevant information:
## Additional context
<!-- Add any other context about the problem here. -->
@sofroniewn @jni
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `napari/_qt/dialogs/qt_plugin_report.py`
Content:
```
1 """Provides a QtPluginErrReporter that allows the user report plugin errors.
2 """
3 from typing import Optional
4
5 from napari_plugin_engine import PluginManager, standard_metadata
6 from qtpy.QtCore import Qt
7 from qtpy.QtGui import QGuiApplication
8 from qtpy.QtWidgets import (
9 QComboBox,
10 QDialog,
11 QHBoxLayout,
12 QLabel,
13 QPushButton,
14 QTextEdit,
15 QVBoxLayout,
16 QWidget,
17 )
18
19 from ...plugins.exceptions import format_exceptions
20
21
22 class QtPluginErrReporter(QDialog):
23 """Dialog that allows users to review and report PluginError tracebacks.
24
25 Parameters
26 ----------
27 parent : QWidget, optional
28 Optional parent widget for this widget.
29 initial_plugin : str, optional
30 If provided, errors from ``initial_plugin`` will be shown when the
31 dialog is created, by default None
32
33 Attributes
34 ----------
35 text_area : qtpy.QtWidgets.QTextEdit
36 The text area where traceback information will be shown.
37 plugin_combo : qtpy.QtWidgets.QComboBox
38 The dropdown menu used to select the current plugin
39 github_button : qtpy.QtWidgets.QPushButton
40 A button that, when pressed, will open an issue at the current plugin's
41 github issue tracker, prepopulated with a formatted traceback. Button
42 is only visible if a github URL is detected in the package metadata for
43 the current plugin.
44 clipboard_button : qtpy.QtWidgets.QPushButton
45 A button that, when pressed, copies the current traceback information
46 to the clipboard. (HTML tags are removed in the copied text.)
47 plugin_meta : qtpy.QtWidgets.QLabel
48 A label that will show available plugin metadata (such as home page).
49 """
50
51 NULL_OPTION = 'select plugin... '
52
53 def __init__(
54 self,
55 plugin_manager: Optional[PluginManager] = None,
56 *,
57 parent: Optional[QWidget] = None,
58 initial_plugin: Optional[str] = None,
59 ) -> None:
60 super().__init__(parent)
61 if not plugin_manager:
62 from ..plugins import plugin_manager as _pm
63
64 self.plugin_manager = _pm
65 else:
66 self.plugin_manager = plugin_manager
67
68 self.setWindowTitle('Recorded Plugin Exceptions')
69 self.setWindowModality(Qt.NonModal)
70 self.layout = QVBoxLayout()
71 self.layout.setSpacing(0)
72 self.layout.setContentsMargins(10, 10, 10, 10)
73 self.setLayout(self.layout)
74
75 self.text_area = QTextEdit()
76 self.text_area.setTextInteractionFlags(Qt.TextSelectableByMouse)
77 self.text_area.setMinimumWidth(360)
78
79 # Create plugin dropdown menu
80 self.plugin_combo = QComboBox()
81 self.plugin_combo.addItem(self.NULL_OPTION)
82 bad_plugins = [e.plugin_name for e in self.plugin_manager.get_errors()]
83 self.plugin_combo.addItems(list(sorted(set(bad_plugins))))
84 self.plugin_combo.currentTextChanged.connect(self.set_plugin)
85 self.plugin_combo.setCurrentText(self.NULL_OPTION)
86
87 # create github button (gets connected in self.set_plugin)
88 self.github_button = QPushButton('Open issue on GitHub', self)
89 self.github_button.setToolTip(
90 "Open a web browser to submit this error log\n"
91 "to the developer's GitHub issue tracker"
92 )
93 self.github_button.hide()
94
95 # create copy to clipboard button
96 self.clipboard_button = QPushButton()
97 self.clipboard_button.hide()
98 self.clipboard_button.setObjectName("QtCopyToClipboardButton")
99 self.clipboard_button.setToolTip("Copy error log to clipboard")
100 self.clipboard_button.clicked.connect(self.copyToClipboard)
101
102 # plugin_meta contains a URL to the home page, (and/or other details)
103 self.plugin_meta = QLabel('', parent=self)
104 self.plugin_meta.setObjectName("pluginInfo")
105 self.plugin_meta.setTextFormat(Qt.RichText)
106 self.plugin_meta.setTextInteractionFlags(Qt.TextBrowserInteraction)
107 self.plugin_meta.setOpenExternalLinks(True)
108 self.plugin_meta.setAlignment(Qt.AlignRight)
109
110 # make layout
111 row_1_layout = QHBoxLayout()
112 row_1_layout.setContentsMargins(11, 5, 10, 0)
113 row_1_layout.addStretch(1)
114 row_1_layout.addWidget(self.plugin_meta)
115 row_2_layout = QHBoxLayout()
116 row_2_layout.setContentsMargins(11, 5, 10, 0)
117 row_2_layout.addWidget(self.plugin_combo)
118 row_2_layout.addStretch(1)
119 row_2_layout.addWidget(self.github_button)
120 row_2_layout.addWidget(self.clipboard_button)
121 row_2_layout.setSpacing(5)
122 self.layout.addLayout(row_1_layout)
123 self.layout.addLayout(row_2_layout)
124 self.layout.addWidget(self.text_area, 1)
125 self.setMinimumWidth(750)
126 self.setMinimumHeight(600)
127
128 if initial_plugin:
129 self.set_plugin(initial_plugin)
130
131 def set_plugin(self, plugin: str) -> None:
132 """Set the current plugin shown in the dropdown and text area.
133
134 Parameters
135 ----------
136 plugin : str
137 name of a plugin that has created an error this session.
138 """
139 self.github_button.hide()
140 self.clipboard_button.hide()
141 try:
142 self.github_button.clicked.disconnect()
143 # when disconnecting a non-existent signal
144 # PySide2 raises runtimeError, PyQt5 raises TypeError
145 except (RuntimeError, TypeError):
146 pass
147
148 if not plugin or (plugin == self.NULL_OPTION):
149 self.plugin_meta.setText('')
150 self.text_area.setHtml('')
151 return
152
153 if not self.plugin_manager.get_errors(plugin):
154 raise ValueError(f"No errors reported for plugin '{plugin}'")
155 self.plugin_combo.setCurrentText(plugin)
156
157 err_string = format_exceptions(plugin, as_html=True)
158 self.text_area.setHtml(err_string)
159 self.clipboard_button.show()
160
161 # set metadata and outbound links/buttons
162 err0 = self.plugin_manager.get_errors(plugin)[0]
163 meta = standard_metadata(err0.plugin) if err0.plugin else {}
164 meta_text = ''
165 if not meta:
166 self.plugin_meta.setText(meta_text)
167 return
168
169 url = meta.get('url')
170 if url:
171 meta_text += (
172 '<span style="color:#999;">plugin home page: '
173 f'</span><a href="{url}" style="color:#999">{url}</a>'
174 )
175 if 'github.com' in url:
176
177 def onclick():
178 import webbrowser
179
180 err = format_exceptions(plugin, as_html=False)
181 err = (
182 "<!--Provide detail on the error here-->\n\n\n\n"
183 "<details>\n<summary>Traceback from napari</summary>"
184 f"\n\n```\n{err}\n```\n</details>"
185 )
186 url = f'{meta.get("url")}/issues/new?&body={err}'
187 webbrowser.open(url, new=2)
188
189 self.github_button.clicked.connect(onclick)
190 self.github_button.show()
191 self.plugin_meta.setText(meta_text)
192
193 def copyToClipboard(self) -> None:
194 """Copy current plugin traceback info to clipboard as plain text."""
195 plugin = self.plugin_combo.currentText()
196 err_string = format_exceptions(plugin, as_html=False)
197 cb = QGuiApplication.clipboard()
198 cb.setText(err_string)
199
```
Path: `napari/_qt/dialogs/qt_plugin_table.py`
Content:
```
1 from qtpy.QtCore import Qt
2 from qtpy.QtWidgets import QAbstractItemView, QDialog, QLabel, QVBoxLayout
3
4 from ..widgets.qt_dict_table import QtDictTable
5
6
7 class QtPluginTable(QDialog):
8 def __init__(self, parent, plugin_manager=None):
9 super().__init__(parent)
10 if not plugin_manager:
11 from ..plugins import plugin_manager
12
13 self.setMaximumHeight(800)
14 self.setMaximumWidth(1280)
15 layout = QVBoxLayout()
16 # maybe someday add a search bar here?
17 title = QLabel("Installed Plugins")
18 title.setObjectName("h2")
19 layout.addWidget(title)
20 # get metadata for successfully registered plugins
21 plugin_manager.discover()
22 data = plugin_manager.list_plugin_metadata()
23 data = list(filter(lambda x: x['plugin_name'] != 'builtins', data))
24 # create a table for it
25 self.table = QtDictTable(
26 parent,
27 data,
28 headers=[
29 'plugin_name',
30 'package',
31 'version',
32 'url',
33 'author',
34 'license',
35 ],
36 min_section_width=60,
37 )
38 self.table.setObjectName("pluginTable")
39 self.table.horizontalHeader().setObjectName("pluginTableHeader")
40 self.table.verticalHeader().setObjectName("pluginTableHeader")
41 self.table.setGridStyle(Qt.NoPen)
42 # prevent editing of table
43 self.table.setEditTriggers(QAbstractItemView.NoEditTriggers)
44 layout.addWidget(self.table)
45 self.setLayout(layout)
46 self.setAttribute(Qt.WA_DeleteOnClose)
47
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/napari/_qt/dialogs/qt_plugin_report.py b/napari/_qt/dialogs/qt_plugin_report.py
--- a/napari/_qt/dialogs/qt_plugin_report.py
+++ b/napari/_qt/dialogs/qt_plugin_report.py
@@ -59,7 +59,7 @@
) -> None:
super().__init__(parent)
if not plugin_manager:
- from ..plugins import plugin_manager as _pm
+ from ...plugins import plugin_manager as _pm
self.plugin_manager = _pm
else:
diff --git a/napari/_qt/dialogs/qt_plugin_table.py b/napari/_qt/dialogs/qt_plugin_table.py
--- a/napari/_qt/dialogs/qt_plugin_table.py
+++ b/napari/_qt/dialogs/qt_plugin_table.py
@@ -8,7 +8,7 @@
def __init__(self, parent, plugin_manager=None):
super().__init__(parent)
if not plugin_manager:
- from ..plugins import plugin_manager
+ from ...plugins import plugin_manager
self.setMaximumHeight(800)
self.setMaximumWidth(1280)
|
{"golden_diff": "diff --git a/napari/_qt/dialogs/qt_plugin_report.py b/napari/_qt/dialogs/qt_plugin_report.py\n--- a/napari/_qt/dialogs/qt_plugin_report.py\n+++ b/napari/_qt/dialogs/qt_plugin_report.py\n@@ -59,7 +59,7 @@\n ) -> None:\n super().__init__(parent)\n if not plugin_manager:\n- from ..plugins import plugin_manager as _pm\n+ from ...plugins import plugin_manager as _pm\n \n self.plugin_manager = _pm\n else:\ndiff --git a/napari/_qt/dialogs/qt_plugin_table.py b/napari/_qt/dialogs/qt_plugin_table.py\n--- a/napari/_qt/dialogs/qt_plugin_table.py\n+++ b/napari/_qt/dialogs/qt_plugin_table.py\n@@ -8,7 +8,7 @@\n def __init__(self, parent, plugin_manager=None):\n super().__init__(parent)\n if not plugin_manager:\n- from ..plugins import plugin_manager\n+ from ...plugins import plugin_manager\n \n self.setMaximumHeight(800)\n self.setMaximumWidth(1280)\n", "issue": "Plugin Errors not work in develop \n## \ud83d\udc1b Bug\r\n\r\n<!-- A clear and concise description of what the bug is. -->\r\n\r\n$ NAPARI_CATCH_ERRORS=0 python -m napari\r\n16:11:17 ERROR Unhandled exception:\r\nTraceback (most recent call last):\r\n File \"/home/czaki/Dokumenty/projekty/napari/napari/_qt/qt_main_window.py\", line 300, in _show_plugin_err_reporter\r\n plugin_sorter = QtPluginErrReporter(parent=self._qt_window)\r\n File \"/home/czaki/Dokumenty/projekty/napari/napari/_qt/dialogs/qt_plugin_report.py\", line 62, in __init__\r\n from ..plugins import plugin_manager as _pm\r\nModuleNotFoundError: No module named 'napari._qt.plugins'\r\n\r\n\r\n## To Reproduce\r\n\r\nSteps to reproduce the behavior:\r\n\r\n1. install last napari from github\r\n2. try open \"Plugin Errors\" dialog\r\n\r\n\r\n<!-- If you have a code sample, error messages, stack traces, please provide it here as well -->\r\n\r\n## Expected behavior\r\n\r\n<!-- A clear and concise description of what you expected to happen. -->\r\n\r\n## Environment\r\n\r\n - Please copy and paste the information at napari info option in help menubar here:\r\n\r\nnapari: 0.3.7.dev30+gf101ef7\r\nPlatform: Linux-4.15.0-112-generic-x86_64-with-debian-buster-sid\r\nPython: 3.7.6 (default, Feb 20 2020, 10:04:45) [GCC 7.4.0]\r\nQt: 5.14.2\r\nPyQt5: 5.14.2\r\nNumPy: 1.18.5\r\nSciPy: 1.4.1\r\nDask: 2.17.2\r\nVisPy: 0.6.4\r\n\r\nGL version: 4.6.0 NVIDIA 440.100\r\nMAX_TEXTURE_SIZE: 32768\r\n\r\nPlugins:\r\n- napari-plugin-engine: 0.1.5\r\n- svg: 0.1.3\r\n\r\n - Any other relevant information:\r\n\r\n## Additional context\r\n\r\n<!-- Add any other context about the problem here. -->\r\n@sofroniewn @jni \n", "before_files": [{"content": "\"\"\"Provides a QtPluginErrReporter that allows the user report plugin errors.\n\"\"\"\nfrom typing import Optional\n\nfrom napari_plugin_engine import PluginManager, standard_metadata\nfrom qtpy.QtCore import Qt\nfrom qtpy.QtGui import QGuiApplication\nfrom qtpy.QtWidgets import (\n QComboBox,\n QDialog,\n QHBoxLayout,\n QLabel,\n QPushButton,\n QTextEdit,\n QVBoxLayout,\n QWidget,\n)\n\nfrom ...plugins.exceptions import format_exceptions\n\n\nclass QtPluginErrReporter(QDialog):\n \"\"\"Dialog that allows users to review and report PluginError tracebacks.\n\n Parameters\n ----------\n parent : QWidget, optional\n Optional parent widget for this widget.\n initial_plugin : str, optional\n If provided, errors from ``initial_plugin`` will be shown when the\n dialog is created, by default None\n\n Attributes\n ----------\n text_area : qtpy.QtWidgets.QTextEdit\n The text area where traceback information will be shown.\n plugin_combo : qtpy.QtWidgets.QComboBox\n The dropdown menu used to select the current plugin\n github_button : qtpy.QtWidgets.QPushButton\n A button that, when pressed, will open an issue at the current plugin's\n github issue tracker, prepopulated with a formatted traceback. Button\n is only visible if a github URL is detected in the package metadata for\n the current plugin.\n clipboard_button : qtpy.QtWidgets.QPushButton\n A button that, when pressed, copies the current traceback information\n to the clipboard. (HTML tags are removed in the copied text.)\n plugin_meta : qtpy.QtWidgets.QLabel\n A label that will show available plugin metadata (such as home page).\n \"\"\"\n\n NULL_OPTION = 'select plugin... '\n\n def __init__(\n self,\n plugin_manager: Optional[PluginManager] = None,\n *,\n parent: Optional[QWidget] = None,\n initial_plugin: Optional[str] = None,\n ) -> None:\n super().__init__(parent)\n if not plugin_manager:\n from ..plugins import plugin_manager as _pm\n\n self.plugin_manager = _pm\n else:\n self.plugin_manager = plugin_manager\n\n self.setWindowTitle('Recorded Plugin Exceptions')\n self.setWindowModality(Qt.NonModal)\n self.layout = QVBoxLayout()\n self.layout.setSpacing(0)\n self.layout.setContentsMargins(10, 10, 10, 10)\n self.setLayout(self.layout)\n\n self.text_area = QTextEdit()\n self.text_area.setTextInteractionFlags(Qt.TextSelectableByMouse)\n self.text_area.setMinimumWidth(360)\n\n # Create plugin dropdown menu\n self.plugin_combo = QComboBox()\n self.plugin_combo.addItem(self.NULL_OPTION)\n bad_plugins = [e.plugin_name for e in self.plugin_manager.get_errors()]\n self.plugin_combo.addItems(list(sorted(set(bad_plugins))))\n self.plugin_combo.currentTextChanged.connect(self.set_plugin)\n self.plugin_combo.setCurrentText(self.NULL_OPTION)\n\n # create github button (gets connected in self.set_plugin)\n self.github_button = QPushButton('Open issue on GitHub', self)\n self.github_button.setToolTip(\n \"Open a web browser to submit this error log\\n\"\n \"to the developer's GitHub issue tracker\"\n )\n self.github_button.hide()\n\n # create copy to clipboard button\n self.clipboard_button = QPushButton()\n self.clipboard_button.hide()\n self.clipboard_button.setObjectName(\"QtCopyToClipboardButton\")\n self.clipboard_button.setToolTip(\"Copy error log to clipboard\")\n self.clipboard_button.clicked.connect(self.copyToClipboard)\n\n # plugin_meta contains a URL to the home page, (and/or other details)\n self.plugin_meta = QLabel('', parent=self)\n self.plugin_meta.setObjectName(\"pluginInfo\")\n self.plugin_meta.setTextFormat(Qt.RichText)\n self.plugin_meta.setTextInteractionFlags(Qt.TextBrowserInteraction)\n self.plugin_meta.setOpenExternalLinks(True)\n self.plugin_meta.setAlignment(Qt.AlignRight)\n\n # make layout\n row_1_layout = QHBoxLayout()\n row_1_layout.setContentsMargins(11, 5, 10, 0)\n row_1_layout.addStretch(1)\n row_1_layout.addWidget(self.plugin_meta)\n row_2_layout = QHBoxLayout()\n row_2_layout.setContentsMargins(11, 5, 10, 0)\n row_2_layout.addWidget(self.plugin_combo)\n row_2_layout.addStretch(1)\n row_2_layout.addWidget(self.github_button)\n row_2_layout.addWidget(self.clipboard_button)\n row_2_layout.setSpacing(5)\n self.layout.addLayout(row_1_layout)\n self.layout.addLayout(row_2_layout)\n self.layout.addWidget(self.text_area, 1)\n self.setMinimumWidth(750)\n self.setMinimumHeight(600)\n\n if initial_plugin:\n self.set_plugin(initial_plugin)\n\n def set_plugin(self, plugin: str) -> None:\n \"\"\"Set the current plugin shown in the dropdown and text area.\n\n Parameters\n ----------\n plugin : str\n name of a plugin that has created an error this session.\n \"\"\"\n self.github_button.hide()\n self.clipboard_button.hide()\n try:\n self.github_button.clicked.disconnect()\n # when disconnecting a non-existent signal\n # PySide2 raises runtimeError, PyQt5 raises TypeError\n except (RuntimeError, TypeError):\n pass\n\n if not plugin or (plugin == self.NULL_OPTION):\n self.plugin_meta.setText('')\n self.text_area.setHtml('')\n return\n\n if not self.plugin_manager.get_errors(plugin):\n raise ValueError(f\"No errors reported for plugin '{plugin}'\")\n self.plugin_combo.setCurrentText(plugin)\n\n err_string = format_exceptions(plugin, as_html=True)\n self.text_area.setHtml(err_string)\n self.clipboard_button.show()\n\n # set metadata and outbound links/buttons\n err0 = self.plugin_manager.get_errors(plugin)[0]\n meta = standard_metadata(err0.plugin) if err0.plugin else {}\n meta_text = ''\n if not meta:\n self.plugin_meta.setText(meta_text)\n return\n\n url = meta.get('url')\n if url:\n meta_text += (\n '<span style=\"color:#999;\">plugin home page: '\n f'</span><a href=\"{url}\" style=\"color:#999\">{url}</a>'\n )\n if 'github.com' in url:\n\n def onclick():\n import webbrowser\n\n err = format_exceptions(plugin, as_html=False)\n err = (\n \"<!--Provide detail on the error here-->\\n\\n\\n\\n\"\n \"<details>\\n<summary>Traceback from napari</summary>\"\n f\"\\n\\n```\\n{err}\\n```\\n</details>\"\n )\n url = f'{meta.get(\"url\")}/issues/new?&body={err}'\n webbrowser.open(url, new=2)\n\n self.github_button.clicked.connect(onclick)\n self.github_button.show()\n self.plugin_meta.setText(meta_text)\n\n def copyToClipboard(self) -> None:\n \"\"\"Copy current plugin traceback info to clipboard as plain text.\"\"\"\n plugin = self.plugin_combo.currentText()\n err_string = format_exceptions(plugin, as_html=False)\n cb = QGuiApplication.clipboard()\n cb.setText(err_string)\n", "path": "napari/_qt/dialogs/qt_plugin_report.py"}, {"content": "from qtpy.QtCore import Qt\nfrom qtpy.QtWidgets import QAbstractItemView, QDialog, QLabel, QVBoxLayout\n\nfrom ..widgets.qt_dict_table import QtDictTable\n\n\nclass QtPluginTable(QDialog):\n def __init__(self, parent, plugin_manager=None):\n super().__init__(parent)\n if not plugin_manager:\n from ..plugins import plugin_manager\n\n self.setMaximumHeight(800)\n self.setMaximumWidth(1280)\n layout = QVBoxLayout()\n # maybe someday add a search bar here?\n title = QLabel(\"Installed Plugins\")\n title.setObjectName(\"h2\")\n layout.addWidget(title)\n # get metadata for successfully registered plugins\n plugin_manager.discover()\n data = plugin_manager.list_plugin_metadata()\n data = list(filter(lambda x: x['plugin_name'] != 'builtins', data))\n # create a table for it\n self.table = QtDictTable(\n parent,\n data,\n headers=[\n 'plugin_name',\n 'package',\n 'version',\n 'url',\n 'author',\n 'license',\n ],\n min_section_width=60,\n )\n self.table.setObjectName(\"pluginTable\")\n self.table.horizontalHeader().setObjectName(\"pluginTableHeader\")\n self.table.verticalHeader().setObjectName(\"pluginTableHeader\")\n self.table.setGridStyle(Qt.NoPen)\n # prevent editing of table\n self.table.setEditTriggers(QAbstractItemView.NoEditTriggers)\n layout.addWidget(self.table)\n self.setLayout(layout)\n self.setAttribute(Qt.WA_DeleteOnClose)\n", "path": "napari/_qt/dialogs/qt_plugin_table.py"}], "after_files": [{"content": "\"\"\"Provides a QtPluginErrReporter that allows the user report plugin errors.\n\"\"\"\nfrom typing import Optional\n\nfrom napari_plugin_engine import PluginManager, standard_metadata\nfrom qtpy.QtCore import Qt\nfrom qtpy.QtGui import QGuiApplication\nfrom qtpy.QtWidgets import (\n QComboBox,\n QDialog,\n QHBoxLayout,\n QLabel,\n QPushButton,\n QTextEdit,\n QVBoxLayout,\n QWidget,\n)\n\nfrom ...plugins.exceptions import format_exceptions\n\n\nclass QtPluginErrReporter(QDialog):\n \"\"\"Dialog that allows users to review and report PluginError tracebacks.\n\n Parameters\n ----------\n parent : QWidget, optional\n Optional parent widget for this widget.\n initial_plugin : str, optional\n If provided, errors from ``initial_plugin`` will be shown when the\n dialog is created, by default None\n\n Attributes\n ----------\n text_area : qtpy.QtWidgets.QTextEdit\n The text area where traceback information will be shown.\n plugin_combo : qtpy.QtWidgets.QComboBox\n The dropdown menu used to select the current plugin\n github_button : qtpy.QtWidgets.QPushButton\n A button that, when pressed, will open an issue at the current plugin's\n github issue tracker, prepopulated with a formatted traceback. Button\n is only visible if a github URL is detected in the package metadata for\n the current plugin.\n clipboard_button : qtpy.QtWidgets.QPushButton\n A button that, when pressed, copies the current traceback information\n to the clipboard. (HTML tags are removed in the copied text.)\n plugin_meta : qtpy.QtWidgets.QLabel\n A label that will show available plugin metadata (such as home page).\n \"\"\"\n\n NULL_OPTION = 'select plugin... '\n\n def __init__(\n self,\n plugin_manager: Optional[PluginManager] = None,\n *,\n parent: Optional[QWidget] = None,\n initial_plugin: Optional[str] = None,\n ) -> None:\n super().__init__(parent)\n if not plugin_manager:\n from ...plugins import plugin_manager as _pm\n\n self.plugin_manager = _pm\n else:\n self.plugin_manager = plugin_manager\n\n self.setWindowTitle('Recorded Plugin Exceptions')\n self.setWindowModality(Qt.NonModal)\n self.layout = QVBoxLayout()\n self.layout.setSpacing(0)\n self.layout.setContentsMargins(10, 10, 10, 10)\n self.setLayout(self.layout)\n\n self.text_area = QTextEdit()\n self.text_area.setTextInteractionFlags(Qt.TextSelectableByMouse)\n self.text_area.setMinimumWidth(360)\n\n # Create plugin dropdown menu\n self.plugin_combo = QComboBox()\n self.plugin_combo.addItem(self.NULL_OPTION)\n bad_plugins = [e.plugin_name for e in self.plugin_manager.get_errors()]\n self.plugin_combo.addItems(list(sorted(set(bad_plugins))))\n self.plugin_combo.currentTextChanged.connect(self.set_plugin)\n self.plugin_combo.setCurrentText(self.NULL_OPTION)\n\n # create github button (gets connected in self.set_plugin)\n self.github_button = QPushButton('Open issue on GitHub', self)\n self.github_button.setToolTip(\n \"Open a web browser to submit this error log\\n\"\n \"to the developer's GitHub issue tracker\"\n )\n self.github_button.hide()\n\n # create copy to clipboard button\n self.clipboard_button = QPushButton()\n self.clipboard_button.hide()\n self.clipboard_button.setObjectName(\"QtCopyToClipboardButton\")\n self.clipboard_button.setToolTip(\"Copy error log to clipboard\")\n self.clipboard_button.clicked.connect(self.copyToClipboard)\n\n # plugin_meta contains a URL to the home page, (and/or other details)\n self.plugin_meta = QLabel('', parent=self)\n self.plugin_meta.setObjectName(\"pluginInfo\")\n self.plugin_meta.setTextFormat(Qt.RichText)\n self.plugin_meta.setTextInteractionFlags(Qt.TextBrowserInteraction)\n self.plugin_meta.setOpenExternalLinks(True)\n self.plugin_meta.setAlignment(Qt.AlignRight)\n\n # make layout\n row_1_layout = QHBoxLayout()\n row_1_layout.setContentsMargins(11, 5, 10, 0)\n row_1_layout.addStretch(1)\n row_1_layout.addWidget(self.plugin_meta)\n row_2_layout = QHBoxLayout()\n row_2_layout.setContentsMargins(11, 5, 10, 0)\n row_2_layout.addWidget(self.plugin_combo)\n row_2_layout.addStretch(1)\n row_2_layout.addWidget(self.github_button)\n row_2_layout.addWidget(self.clipboard_button)\n row_2_layout.setSpacing(5)\n self.layout.addLayout(row_1_layout)\n self.layout.addLayout(row_2_layout)\n self.layout.addWidget(self.text_area, 1)\n self.setMinimumWidth(750)\n self.setMinimumHeight(600)\n\n if initial_plugin:\n self.set_plugin(initial_plugin)\n\n def set_plugin(self, plugin: str) -> None:\n \"\"\"Set the current plugin shown in the dropdown and text area.\n\n Parameters\n ----------\n plugin : str\n name of a plugin that has created an error this session.\n \"\"\"\n self.github_button.hide()\n self.clipboard_button.hide()\n try:\n self.github_button.clicked.disconnect()\n # when disconnecting a non-existent signal\n # PySide2 raises runtimeError, PyQt5 raises TypeError\n except (RuntimeError, TypeError):\n pass\n\n if not plugin or (plugin == self.NULL_OPTION):\n self.plugin_meta.setText('')\n self.text_area.setHtml('')\n return\n\n if not self.plugin_manager.get_errors(plugin):\n raise ValueError(f\"No errors reported for plugin '{plugin}'\")\n self.plugin_combo.setCurrentText(plugin)\n\n err_string = format_exceptions(plugin, as_html=True)\n self.text_area.setHtml(err_string)\n self.clipboard_button.show()\n\n # set metadata and outbound links/buttons\n err0 = self.plugin_manager.get_errors(plugin)[0]\n meta = standard_metadata(err0.plugin) if err0.plugin else {}\n meta_text = ''\n if not meta:\n self.plugin_meta.setText(meta_text)\n return\n\n url = meta.get('url')\n if url:\n meta_text += (\n '<span style=\"color:#999;\">plugin home page: '\n f'</span><a href=\"{url}\" style=\"color:#999\">{url}</a>'\n )\n if 'github.com' in url:\n\n def onclick():\n import webbrowser\n\n err = format_exceptions(plugin, as_html=False)\n err = (\n \"<!--Provide detail on the error here-->\\n\\n\\n\\n\"\n \"<details>\\n<summary>Traceback from napari</summary>\"\n f\"\\n\\n```\\n{err}\\n```\\n</details>\"\n )\n url = f'{meta.get(\"url\")}/issues/new?&body={err}'\n webbrowser.open(url, new=2)\n\n self.github_button.clicked.connect(onclick)\n self.github_button.show()\n self.plugin_meta.setText(meta_text)\n\n def copyToClipboard(self) -> None:\n \"\"\"Copy current plugin traceback info to clipboard as plain text.\"\"\"\n plugin = self.plugin_combo.currentText()\n err_string = format_exceptions(plugin, as_html=False)\n cb = QGuiApplication.clipboard()\n cb.setText(err_string)\n", "path": "napari/_qt/dialogs/qt_plugin_report.py"}, {"content": "from qtpy.QtCore import Qt\nfrom qtpy.QtWidgets import QAbstractItemView, QDialog, QLabel, QVBoxLayout\n\nfrom ..widgets.qt_dict_table import QtDictTable\n\n\nclass QtPluginTable(QDialog):\n def __init__(self, parent, plugin_manager=None):\n super().__init__(parent)\n if not plugin_manager:\n from ...plugins import plugin_manager\n\n self.setMaximumHeight(800)\n self.setMaximumWidth(1280)\n layout = QVBoxLayout()\n # maybe someday add a search bar here?\n title = QLabel(\"Installed Plugins\")\n title.setObjectName(\"h2\")\n layout.addWidget(title)\n # get metadata for successfully registered plugins\n plugin_manager.discover()\n data = plugin_manager.list_plugin_metadata()\n data = list(filter(lambda x: x['plugin_name'] != 'builtins', data))\n # create a table for it\n self.table = QtDictTable(\n parent,\n data,\n headers=[\n 'plugin_name',\n 'package',\n 'version',\n 'url',\n 'author',\n 'license',\n ],\n min_section_width=60,\n )\n self.table.setObjectName(\"pluginTable\")\n self.table.horizontalHeader().setObjectName(\"pluginTableHeader\")\n self.table.verticalHeader().setObjectName(\"pluginTableHeader\")\n self.table.setGridStyle(Qt.NoPen)\n # prevent editing of table\n self.table.setEditTriggers(QAbstractItemView.NoEditTriggers)\n layout.addWidget(self.table)\n self.setLayout(layout)\n self.setAttribute(Qt.WA_DeleteOnClose)\n", "path": "napari/_qt/dialogs/qt_plugin_table.py"}]}
| 3,268 | 250 |
gh_patches_debug_17769
|
rasdani/github-patches
|
git_diff
|
kivy__python-for-android-2340
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Webview app crashes when trying to request permissions
### Checklist
- [X] the issue is indeed a bug and not a support request
- [X] issue doesn't already exist: https://github.com/kivy/python-for-android/issues
- [X] I have a short, runnable example that reproduces the issue
- [X] I reproduced the problem with the latest development version (`p4a.branch = develop`)
- [X] I used the grave accent (aka backticks) to format code or logs when appropriated
### Versions
- Python: 3.6.6
- OS: Ubuntu 20.04
- python-for-android: 2020.6.2
### Description
I'm building with:
```
HERE=$(pwd)
cd app
export ANDROIDSDK="$HERE/android_sdks"
# Have also tried with
# export ANDROIDNDK="$HERE/android_sdks/android-ndk-r19c"
export ANDROIDNDK="$HERE/android_sdks/android-ndk-r21d"
export ANDROIDAPI="27" # Target API version of your application
export NDKAPI="21" # Minimum supported API version of your application
p4a apk --private "." --package=org.anarres.pdfreader --name "pdf reader" --version 0.1 --bootstrap=webview --requirements=python3,flask --port=5000 --orientation=sensor --blacklist="../blacklist.txt" --permission READ_EXTERNAL_STORAGE --permission WRITE_EXTERNAL_STORAGE
```
My python code is just:
```
from android.permissions import request_permissions, Permission
request_permissions([Permission.READ_EXTERNAL_STORAGE, Permission.WRITE_EXTERNAL_STORAGE])
from flask import Flask, render_template
app = Flask(__name__)
@app.route('/')
def index():
return render_template('index.html')
if __name__ == '__main__':
app.run(port=5000)
```
If I comment out:
```
from android.permissions import request_permissions, Permission
request_permissions([Permission.READ_EXTERNAL_STORAGE, Permission.WRITE_EXTERNAL_STORAGE])
```
I don't see the error, but then of course I can't access the external storage.
### Logs
```
ImportError: dlopen failed: cannot locate symbol "SDL_ANDROID_GetJNIEnv" referenced by "/data/data/org.anarres.pdfreader/files/app/_python_bundle/site-packages/android/_android.so"...
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `pythonforandroid/recipes/android/src/setup.py`
Content:
```
1 from distutils.core import setup, Extension
2 import os
3
4 library_dirs = ['libs/' + os.environ['ARCH']]
5 lib_dict = {
6 'sdl2': ['SDL2', 'SDL2_image', 'SDL2_mixer', 'SDL2_ttf']
7 }
8 sdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], [])
9
10 modules = [Extension('android._android',
11 ['android/_android.c', 'android/_android_jni.c'],
12 libraries=sdl_libs + ['log'],
13 library_dirs=library_dirs),
14 Extension('android._android_billing',
15 ['android/_android_billing.c', 'android/_android_billing_jni.c'],
16 libraries=['log'],
17 library_dirs=library_dirs)]
18
19 setup(name='android',
20 version='1.0',
21 packages=['android'],
22 package_dir={'android': 'android'},
23 ext_modules=modules
24 )
25
```
Path: `pythonforandroid/recipes/android/__init__.py`
Content:
```
1 from pythonforandroid.recipe import CythonRecipe, IncludedFilesBehaviour
2 from pythonforandroid.util import current_directory
3 from pythonforandroid import logger
4
5 from os.path import join
6
7
8 class AndroidRecipe(IncludedFilesBehaviour, CythonRecipe):
9 # name = 'android'
10 version = None
11 url = None
12
13 src_filename = 'src'
14
15 depends = [('sdl2', 'genericndkbuild'), 'pyjnius']
16
17 config_env = {}
18
19 def get_recipe_env(self, arch):
20 env = super().get_recipe_env(arch)
21 env.update(self.config_env)
22 return env
23
24 def prebuild_arch(self, arch):
25 super().prebuild_arch(arch)
26 ctx_bootstrap = self.ctx.bootstrap.name
27
28 # define macros for Cython, C, Python
29 tpxi = 'DEF {} = {}\n'
30 th = '#define {} {}\n'
31 tpy = '{} = {}\n'
32
33 # make sure bootstrap name is in unicode
34 if isinstance(ctx_bootstrap, bytes):
35 ctx_bootstrap = ctx_bootstrap.decode('utf-8')
36 bootstrap = bootstrap_name = ctx_bootstrap
37 is_sdl2 = (bootstrap_name == "sdl2")
38 if bootstrap_name in ["sdl2", "webview", "service_only", "service_library"]:
39 java_ns = u'org.kivy.android'
40 jni_ns = u'org/kivy/android'
41 else:
42 logger.error((
43 'unsupported bootstrap for android recipe: {}'
44 ''.format(bootstrap_name)
45 ))
46 exit(1)
47
48 config = {
49 'BOOTSTRAP': bootstrap,
50 'IS_SDL2': int(is_sdl2),
51 'PY2': 0,
52 'JAVA_NAMESPACE': java_ns,
53 'JNI_NAMESPACE': jni_ns,
54 'ACTIVITY_CLASS_NAME': self.ctx.activity_class_name,
55 'ACTIVITY_CLASS_NAMESPACE': self.ctx.activity_class_name.replace('.', '/'),
56 }
57
58 # create config files for Cython, C and Python
59 with (
60 current_directory(self.get_build_dir(arch.arch))), (
61 open(join('android', 'config.pxi'), 'w')) as fpxi, (
62 open(join('android', 'config.h'), 'w')) as fh, (
63 open(join('android', 'config.py'), 'w')) as fpy:
64
65 for key, value in config.items():
66 fpxi.write(tpxi.format(key, repr(value)))
67 fpy.write(tpy.format(key, repr(value)))
68
69 fh.write(th.format(
70 key,
71 value if isinstance(value, int) else '"{}"'.format(value)
72 ))
73 self.config_env[key] = str(value)
74
75 if is_sdl2:
76 fh.write('JNIEnv *SDL_AndroidGetJNIEnv(void);\n')
77 fh.write(
78 '#define SDL_ANDROID_GetJNIEnv SDL_AndroidGetJNIEnv\n'
79 )
80
81
82 recipe = AndroidRecipe()
83
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/pythonforandroid/recipes/android/__init__.py b/pythonforandroid/recipes/android/__init__.py
--- a/pythonforandroid/recipes/android/__init__.py
+++ b/pythonforandroid/recipes/android/__init__.py
@@ -77,6 +77,11 @@
fh.write(
'#define SDL_ANDROID_GetJNIEnv SDL_AndroidGetJNIEnv\n'
)
+ else:
+ fh.write('JNIEnv *WebView_AndroidGetJNIEnv(void);\n')
+ fh.write(
+ '#define SDL_ANDROID_GetJNIEnv WebView_AndroidGetJNIEnv\n'
+ )
recipe = AndroidRecipe()
diff --git a/pythonforandroid/recipes/android/src/setup.py b/pythonforandroid/recipes/android/src/setup.py
--- a/pythonforandroid/recipes/android/src/setup.py
+++ b/pythonforandroid/recipes/android/src/setup.py
@@ -5,7 +5,7 @@
lib_dict = {
'sdl2': ['SDL2', 'SDL2_image', 'SDL2_mixer', 'SDL2_ttf']
}
-sdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], [])
+sdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], ['main'])
modules = [Extension('android._android',
['android/_android.c', 'android/_android_jni.c'],
|
{"golden_diff": "diff --git a/pythonforandroid/recipes/android/__init__.py b/pythonforandroid/recipes/android/__init__.py\n--- a/pythonforandroid/recipes/android/__init__.py\n+++ b/pythonforandroid/recipes/android/__init__.py\n@@ -77,6 +77,11 @@\n fh.write(\n '#define SDL_ANDROID_GetJNIEnv SDL_AndroidGetJNIEnv\\n'\n )\n+ else:\n+ fh.write('JNIEnv *WebView_AndroidGetJNIEnv(void);\\n')\n+ fh.write(\n+ '#define SDL_ANDROID_GetJNIEnv WebView_AndroidGetJNIEnv\\n'\n+ )\n \n \n recipe = AndroidRecipe()\ndiff --git a/pythonforandroid/recipes/android/src/setup.py b/pythonforandroid/recipes/android/src/setup.py\n--- a/pythonforandroid/recipes/android/src/setup.py\n+++ b/pythonforandroid/recipes/android/src/setup.py\n@@ -5,7 +5,7 @@\n lib_dict = {\n 'sdl2': ['SDL2', 'SDL2_image', 'SDL2_mixer', 'SDL2_ttf']\n }\n-sdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], [])\n+sdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], ['main'])\n \n modules = [Extension('android._android',\n ['android/_android.c', 'android/_android_jni.c'],\n", "issue": "Webview app crashes when trying to request permissions\n### Checklist\r\n\r\n- [X] the issue is indeed a bug and not a support request\r\n- [X] issue doesn't already exist: https://github.com/kivy/python-for-android/issues\r\n- [X] I have a short, runnable example that reproduces the issue\r\n- [X] I reproduced the problem with the latest development version (`p4a.branch = develop`)\r\n- [X] I used the grave accent (aka backticks) to format code or logs when appropriated\r\n\r\n### Versions\r\n\r\n- Python: 3.6.6\r\n- OS: Ubuntu 20.04\r\n- python-for-android: 2020.6.2\r\n\r\n### Description\r\n\r\nI'm building with:\r\n\r\n```\r\nHERE=$(pwd)\r\ncd app\r\n\r\nexport ANDROIDSDK=\"$HERE/android_sdks\"\r\n# Have also tried with\r\n# export ANDROIDNDK=\"$HERE/android_sdks/android-ndk-r19c\"\r\nexport ANDROIDNDK=\"$HERE/android_sdks/android-ndk-r21d\"\r\nexport ANDROIDAPI=\"27\" # Target API version of your application\r\nexport NDKAPI=\"21\" # Minimum supported API version of your application\r\n\r\np4a apk --private \".\" --package=org.anarres.pdfreader --name \"pdf reader\" --version 0.1 --bootstrap=webview --requirements=python3,flask --port=5000 --orientation=sensor --blacklist=\"../blacklist.txt\" --permission READ_EXTERNAL_STORAGE --permission WRITE_EXTERNAL_STORAGE\r\n```\r\n\r\nMy python code is just:\r\n\r\n```\r\nfrom android.permissions import request_permissions, Permission\r\nrequest_permissions([Permission.READ_EXTERNAL_STORAGE, Permission.WRITE_EXTERNAL_STORAGE])\r\n\r\nfrom flask import Flask, render_template\r\n\r\napp = Flask(__name__)\r\n\r\[email protected]('/')\r\ndef index():\r\n return render_template('index.html')\r\n\r\nif __name__ == '__main__':\r\n app.run(port=5000)\r\n```\r\n\r\nIf I comment out:\r\n\r\n```\r\nfrom android.permissions import request_permissions, Permission\r\nrequest_permissions([Permission.READ_EXTERNAL_STORAGE, Permission.WRITE_EXTERNAL_STORAGE])\r\n```\r\n\r\nI don't see the error, but then of course I can't access the external storage.\r\n\r\n### Logs\r\n\r\n```\r\nImportError: dlopen failed: cannot locate symbol \"SDL_ANDROID_GetJNIEnv\" referenced by \"/data/data/org.anarres.pdfreader/files/app/_python_bundle/site-packages/android/_android.so\"...\r\n```\r\n\n", "before_files": [{"content": "from distutils.core import setup, Extension\nimport os\n\nlibrary_dirs = ['libs/' + os.environ['ARCH']]\nlib_dict = {\n 'sdl2': ['SDL2', 'SDL2_image', 'SDL2_mixer', 'SDL2_ttf']\n}\nsdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], [])\n\nmodules = [Extension('android._android',\n ['android/_android.c', 'android/_android_jni.c'],\n libraries=sdl_libs + ['log'],\n library_dirs=library_dirs),\n Extension('android._android_billing',\n ['android/_android_billing.c', 'android/_android_billing_jni.c'],\n libraries=['log'],\n library_dirs=library_dirs)]\n\nsetup(name='android',\n version='1.0',\n packages=['android'],\n package_dir={'android': 'android'},\n ext_modules=modules\n )\n", "path": "pythonforandroid/recipes/android/src/setup.py"}, {"content": "from pythonforandroid.recipe import CythonRecipe, IncludedFilesBehaviour\nfrom pythonforandroid.util import current_directory\nfrom pythonforandroid import logger\n\nfrom os.path import join\n\n\nclass AndroidRecipe(IncludedFilesBehaviour, CythonRecipe):\n # name = 'android'\n version = None\n url = None\n\n src_filename = 'src'\n\n depends = [('sdl2', 'genericndkbuild'), 'pyjnius']\n\n config_env = {}\n\n def get_recipe_env(self, arch):\n env = super().get_recipe_env(arch)\n env.update(self.config_env)\n return env\n\n def prebuild_arch(self, arch):\n super().prebuild_arch(arch)\n ctx_bootstrap = self.ctx.bootstrap.name\n\n # define macros for Cython, C, Python\n tpxi = 'DEF {} = {}\\n'\n th = '#define {} {}\\n'\n tpy = '{} = {}\\n'\n\n # make sure bootstrap name is in unicode\n if isinstance(ctx_bootstrap, bytes):\n ctx_bootstrap = ctx_bootstrap.decode('utf-8')\n bootstrap = bootstrap_name = ctx_bootstrap\n is_sdl2 = (bootstrap_name == \"sdl2\")\n if bootstrap_name in [\"sdl2\", \"webview\", \"service_only\", \"service_library\"]:\n java_ns = u'org.kivy.android'\n jni_ns = u'org/kivy/android'\n else:\n logger.error((\n 'unsupported bootstrap for android recipe: {}'\n ''.format(bootstrap_name)\n ))\n exit(1)\n\n config = {\n 'BOOTSTRAP': bootstrap,\n 'IS_SDL2': int(is_sdl2),\n 'PY2': 0,\n 'JAVA_NAMESPACE': java_ns,\n 'JNI_NAMESPACE': jni_ns,\n 'ACTIVITY_CLASS_NAME': self.ctx.activity_class_name,\n 'ACTIVITY_CLASS_NAMESPACE': self.ctx.activity_class_name.replace('.', '/'),\n }\n\n # create config files for Cython, C and Python\n with (\n current_directory(self.get_build_dir(arch.arch))), (\n open(join('android', 'config.pxi'), 'w')) as fpxi, (\n open(join('android', 'config.h'), 'w')) as fh, (\n open(join('android', 'config.py'), 'w')) as fpy:\n\n for key, value in config.items():\n fpxi.write(tpxi.format(key, repr(value)))\n fpy.write(tpy.format(key, repr(value)))\n\n fh.write(th.format(\n key,\n value if isinstance(value, int) else '\"{}\"'.format(value)\n ))\n self.config_env[key] = str(value)\n\n if is_sdl2:\n fh.write('JNIEnv *SDL_AndroidGetJNIEnv(void);\\n')\n fh.write(\n '#define SDL_ANDROID_GetJNIEnv SDL_AndroidGetJNIEnv\\n'\n )\n\n\nrecipe = AndroidRecipe()\n", "path": "pythonforandroid/recipes/android/__init__.py"}], "after_files": [{"content": "from distutils.core import setup, Extension\nimport os\n\nlibrary_dirs = ['libs/' + os.environ['ARCH']]\nlib_dict = {\n 'sdl2': ['SDL2', 'SDL2_image', 'SDL2_mixer', 'SDL2_ttf']\n}\nsdl_libs = lib_dict.get(os.environ['BOOTSTRAP'], ['main'])\n\nmodules = [Extension('android._android',\n ['android/_android.c', 'android/_android_jni.c'],\n libraries=sdl_libs + ['log'],\n library_dirs=library_dirs),\n Extension('android._android_billing',\n ['android/_android_billing.c', 'android/_android_billing_jni.c'],\n libraries=['log'],\n library_dirs=library_dirs)]\n\nsetup(name='android',\n version='1.0',\n packages=['android'],\n package_dir={'android': 'android'},\n ext_modules=modules\n )\n", "path": "pythonforandroid/recipes/android/src/setup.py"}, {"content": "from pythonforandroid.recipe import CythonRecipe, IncludedFilesBehaviour\nfrom pythonforandroid.util import current_directory\nfrom pythonforandroid import logger\n\nfrom os.path import join\n\n\nclass AndroidRecipe(IncludedFilesBehaviour, CythonRecipe):\n # name = 'android'\n version = None\n url = None\n\n src_filename = 'src'\n\n depends = [('sdl2', 'genericndkbuild'), 'pyjnius']\n\n config_env = {}\n\n def get_recipe_env(self, arch):\n env = super().get_recipe_env(arch)\n env.update(self.config_env)\n return env\n\n def prebuild_arch(self, arch):\n super().prebuild_arch(arch)\n ctx_bootstrap = self.ctx.bootstrap.name\n\n # define macros for Cython, C, Python\n tpxi = 'DEF {} = {}\\n'\n th = '#define {} {}\\n'\n tpy = '{} = {}\\n'\n\n # make sure bootstrap name is in unicode\n if isinstance(ctx_bootstrap, bytes):\n ctx_bootstrap = ctx_bootstrap.decode('utf-8')\n bootstrap = bootstrap_name = ctx_bootstrap\n is_sdl2 = (bootstrap_name == \"sdl2\")\n if bootstrap_name in [\"sdl2\", \"webview\", \"service_only\", \"service_library\"]:\n java_ns = u'org.kivy.android'\n jni_ns = u'org/kivy/android'\n else:\n logger.error((\n 'unsupported bootstrap for android recipe: {}'\n ''.format(bootstrap_name)\n ))\n exit(1)\n\n config = {\n 'BOOTSTRAP': bootstrap,\n 'IS_SDL2': int(is_sdl2),\n 'PY2': 0,\n 'JAVA_NAMESPACE': java_ns,\n 'JNI_NAMESPACE': jni_ns,\n 'ACTIVITY_CLASS_NAME': self.ctx.activity_class_name,\n 'ACTIVITY_CLASS_NAMESPACE': self.ctx.activity_class_name.replace('.', '/'),\n }\n\n # create config files for Cython, C and Python\n with (\n current_directory(self.get_build_dir(arch.arch))), (\n open(join('android', 'config.pxi'), 'w')) as fpxi, (\n open(join('android', 'config.h'), 'w')) as fh, (\n open(join('android', 'config.py'), 'w')) as fpy:\n\n for key, value in config.items():\n fpxi.write(tpxi.format(key, repr(value)))\n fpy.write(tpy.format(key, repr(value)))\n\n fh.write(th.format(\n key,\n value if isinstance(value, int) else '\"{}\"'.format(value)\n ))\n self.config_env[key] = str(value)\n\n if is_sdl2:\n fh.write('JNIEnv *SDL_AndroidGetJNIEnv(void);\\n')\n fh.write(\n '#define SDL_ANDROID_GetJNIEnv SDL_AndroidGetJNIEnv\\n'\n )\n else:\n fh.write('JNIEnv *WebView_AndroidGetJNIEnv(void);\\n')\n fh.write(\n '#define SDL_ANDROID_GetJNIEnv WebView_AndroidGetJNIEnv\\n'\n )\n\n\nrecipe = AndroidRecipe()\n", "path": "pythonforandroid/recipes/android/__init__.py"}]}
| 1,800 | 283 |
gh_patches_debug_40385
|
rasdani/github-patches
|
git_diff
|
learningequality__kolibri-8277
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Make learner polling indicator conditional for only SoUD
For the new polling indicator on the dropdown menu, this should be updated to appear and poll only when the user is a learner who is logged in on a subset of users device.
<img width="270" alt="Screen Shot 2021-08-05 at 10 58 50 AM" src="https://user-images.githubusercontent.com/17235236/128372343-da85c951-2258-4d5e-ade3-a15b753e6806.png">
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `kolibri/plugins/facility/kolibri_plugin.py`
Content:
```
1 from __future__ import absolute_import
2 from __future__ import print_function
3 from __future__ import unicode_literals
4
5 from kolibri.core.auth.constants.user_kinds import ADMIN
6 from kolibri.core.hooks import NavigationHook
7 from kolibri.core.hooks import RoleBasedRedirectHook
8 from kolibri.core.webpack.hooks import WebpackBundleHook
9 from kolibri.plugins import KolibriPluginBase
10 from kolibri.plugins.hooks import register_hook
11
12
13 class FacilityManagementPlugin(KolibriPluginBase):
14 translated_view_urls = "urls"
15 untranslated_view_urls = "api_urls"
16
17
18 @register_hook
19 class FacilityManagementAsset(WebpackBundleHook):
20 bundle_id = "app"
21
22
23 @register_hook
24 class FacilityRedirect(RoleBasedRedirectHook):
25 roles = (ADMIN,)
26
27 @property
28 def url(self):
29 return self.plugin_url(FacilityManagementPlugin, "facility_management")
30
31
32 @register_hook
33 class FacilityManagementNavItem(NavigationHook):
34 bundle_id = "side_nav"
35
```
Path: `kolibri/plugins/coach/kolibri_plugin.py`
Content:
```
1 from __future__ import absolute_import
2 from __future__ import print_function
3 from __future__ import unicode_literals
4
5 from kolibri.core.auth.constants.user_kinds import COACH
6 from kolibri.core.hooks import NavigationHook
7 from kolibri.core.hooks import RoleBasedRedirectHook
8 from kolibri.core.webpack import hooks as webpack_hooks
9 from kolibri.plugins import KolibriPluginBase
10 from kolibri.plugins.hooks import register_hook
11
12
13 class Coach(KolibriPluginBase):
14 untranslated_view_urls = "api_urls"
15 translated_view_urls = "urls"
16
17
18 @register_hook
19 class CoachRedirect(RoleBasedRedirectHook):
20 roles = (COACH,)
21
22 @property
23 def url(self):
24 return self.plugin_url(Coach, "coach")
25
26
27 @register_hook
28 class CoachNavItem(NavigationHook):
29 bundle_id = "side_nav"
30
31
32 @register_hook
33 class CoachAsset(webpack_hooks.WebpackBundleHook):
34 bundle_id = "app"
35
```
Path: `kolibri/core/kolibri_plugin.py`
Content:
```
1 from __future__ import absolute_import
2 from __future__ import print_function
3 from __future__ import unicode_literals
4
5 from django.conf import settings
6 from django.contrib.staticfiles.templatetags.staticfiles import static
7 from django.core.urlresolvers import get_resolver
8 from django.core.urlresolvers import reverse
9 from django.template.loader import render_to_string
10 from django.utils.html import mark_safe
11 from django.utils.translation import get_language
12 from django.utils.translation import get_language_bidi
13 from django.utils.translation import get_language_info
14 from django_js_reverse.core import _safe_json
15 from django_js_reverse.core import generate_json
16 from django_js_reverse.rjsmin import jsmin
17
18 import kolibri
19 from kolibri.core.content.utils.paths import get_content_storage_url
20 from kolibri.core.content.utils.paths import get_hashi_path
21 from kolibri.core.content.utils.paths import get_zip_content_base_path
22 from kolibri.core.content.utils.paths import get_zip_content_config
23 from kolibri.core.device.models import ContentCacheKey
24 from kolibri.core.device.utils import allow_other_browsers_to_connect
25 from kolibri.core.hooks import NavigationHook
26 from kolibri.core.oidc_provider_hook import OIDCProviderHook
27 from kolibri.core.theme_hook import ThemeHook
28 from kolibri.core.webpack.hooks import WebpackBundleHook
29 from kolibri.plugins.app.utils import interface
30 from kolibri.plugins.hooks import register_hook
31 from kolibri.utils import i18n
32 from kolibri.utils.conf import OPTIONS
33
34
35 @register_hook
36 class FrontEndCoreAppAssetHook(WebpackBundleHook):
37 bundle_id = "default_frontend"
38
39 def url_tag(self):
40 # Modified from:
41 # https://github.com/ierror/django-js-reverse/blob/master/django_js_reverse/core.py#L101
42 js_name = "window.kolibriPluginDataGlobal['{bundle}'].urls".format(
43 bundle=self.unique_id
44 )
45 default_urlresolver = get_resolver(None)
46
47 data = generate_json(default_urlresolver)
48
49 # Generate the JS that exposes functions to reverse all Django URLs
50 # in the frontend.
51 js = render_to_string(
52 "django_js_reverse/urls_js.tpl",
53 {"data": _safe_json(data), "js_name": "__placeholder__"},
54 # For some reason the js_name gets escaped going into the template
55 # so this was the easiest way to inject it.
56 ).replace("__placeholder__", js_name)
57 zip_content_origin, zip_content_port = get_zip_content_config()
58 return [
59 mark_safe(
60 """<script type="text/javascript">"""
61 # Minify the generated Javascript
62 + jsmin(js)
63 # Add URL references for our base static URL, the Django media URL
64 # and our content storage URL - this allows us to calculate
65 # the path at which to access a local file on the frontend if needed.
66 + """
67 {js_name}.__staticUrl = '{static_url}';
68 {js_name}.__mediaUrl = '{media_url}';
69 {js_name}.__contentUrl = '{content_url}';
70 {js_name}.__zipContentUrl = '{zip_content_url}';
71 {js_name}.__hashiUrl = '{hashi_url}';
72 {js_name}.__zipContentOrigin = '{zip_content_origin}';
73 {js_name}.__zipContentPort = {zip_content_port};
74 </script>
75 """.format(
76 js_name=js_name,
77 static_url=settings.STATIC_URL,
78 media_url=settings.MEDIA_URL,
79 content_url=get_content_storage_url(
80 baseurl=OPTIONS["Deployment"]["URL_PATH_PREFIX"]
81 ),
82 zip_content_url=get_zip_content_base_path(),
83 hashi_url=get_hashi_path(),
84 zip_content_origin=zip_content_origin,
85 zip_content_port=zip_content_port,
86 )
87 )
88 ]
89
90 def navigation_tags(self):
91 return [
92 hook.render_to_page_load_sync_html()
93 for hook in NavigationHook.registered_hooks
94 ]
95
96 def render_to_page_load_sync_html(self):
97 """
98 Don't render the frontend message files in the usual way
99 as the global object to register them does not exist yet.
100 Instead they are loaded through plugin data.
101 """
102 tags = (
103 self.plugin_data_tag()
104 + self.url_tag()
105 + list(self.js_and_css_tags())
106 + self.navigation_tags()
107 )
108
109 return mark_safe("\n".join(tags))
110
111 @property
112 def plugin_data(self):
113 language_code = get_language()
114 static_root = static("assets/fonts/noto-full")
115 full_file = "{}.{}.{}.css?v={}"
116 return {
117 "fullCSSFileModern": full_file.format(
118 static_root, language_code, "modern", kolibri.__version__
119 ),
120 "fullCSSFileBasic": full_file.format(
121 static_root, language_code, "basic", kolibri.__version__
122 ),
123 "allowRemoteAccess": allow_other_browsers_to_connect()
124 or not interface.enabled,
125 "appCapabilities": interface.capabilities,
126 "contentCacheKey": ContentCacheKey.get_cache_key(),
127 "languageGlobals": self.language_globals(),
128 "oidcProviderEnabled": OIDCProviderHook.is_enabled(),
129 "kolibriTheme": ThemeHook.get_theme(),
130 }
131
132 def language_globals(self):
133 language_code = get_language()
134 lang_dir = "rtl" if get_language_bidi() else "ltr"
135
136 languages = {}
137 for code, language_name in settings.LANGUAGES:
138 lang_info = i18n.KOLIBRI_LANGUAGE_INFO[code]
139 languages[code] = {
140 # Format to match the schema of the content Language model
141 "id": code,
142 "lang_name": language_name,
143 "english_name": lang_info["english_name"]
144 if lang_info
145 else get_language_info(code)["name"],
146 "lang_direction": get_language_info(code)["bidi"],
147 }
148 return {
149 "coreLanguageMessages": self.frontend_messages(),
150 "languageCode": language_code,
151 "languageDir": lang_dir,
152 "languages": languages,
153 }
154
155
156 @register_hook
157 class FrontendHeadAssetsHook(WebpackBundleHook):
158 """
159 Render these assets in the <head> tag of base.html, before other JS and assets.
160 """
161
162 bundle_id = "frontend_head_assets"
163 inline = True
164
165 def render_to_page_load_sync_html(self):
166 """
167 Add in the extra language font file tags needed
168 for preloading our custom font files.
169 """
170 tags = (
171 self.plugin_data_tag()
172 + self.language_font_file_tags()
173 + self.frontend_message_tag()
174 + list(self.js_and_css_tags())
175 )
176
177 return mark_safe("\n".join(tags))
178
179 def language_font_file_tags(self):
180 language_code = get_language()
181 common_file = static("assets/fonts/noto-common.css")
182 subset_file = static("assets/fonts/noto-subset.{}.css".format(language_code))
183 return [
184 '<link type="text/css" href="{common_css_file}?v={version}" rel="stylesheet"/>'.format(
185 common_css_file=common_file, version=kolibri.__version__
186 ),
187 '<link type="text/css" href="{subset_css_file}?v={version}" rel="stylesheet"/>'.format(
188 subset_css_file=subset_file, version=kolibri.__version__
189 ),
190 ]
191
192 @property
193 def plugin_data(self):
194 return {"unsupportedUrl": reverse("kolibri:core:unsupported")}
195
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/kolibri/core/kolibri_plugin.py b/kolibri/core/kolibri_plugin.py
--- a/kolibri/core/kolibri_plugin.py
+++ b/kolibri/core/kolibri_plugin.py
@@ -22,6 +22,7 @@
from kolibri.core.content.utils.paths import get_zip_content_config
from kolibri.core.device.models import ContentCacheKey
from kolibri.core.device.utils import allow_other_browsers_to_connect
+from kolibri.core.device.utils import get_device_setting
from kolibri.core.hooks import NavigationHook
from kolibri.core.oidc_provider_hook import OIDCProviderHook
from kolibri.core.theme_hook import ThemeHook
@@ -127,6 +128,7 @@
"languageGlobals": self.language_globals(),
"oidcProviderEnabled": OIDCProviderHook.is_enabled(),
"kolibriTheme": ThemeHook.get_theme(),
+ "isSubsetOfUsersDevice": get_device_setting("subset_of_users_device"),
}
def language_globals(self):
diff --git a/kolibri/plugins/coach/kolibri_plugin.py b/kolibri/plugins/coach/kolibri_plugin.py
--- a/kolibri/plugins/coach/kolibri_plugin.py
+++ b/kolibri/plugins/coach/kolibri_plugin.py
@@ -3,6 +3,7 @@
from __future__ import unicode_literals
from kolibri.core.auth.constants.user_kinds import COACH
+from kolibri.core.device.utils import get_device_setting
from kolibri.core.hooks import NavigationHook
from kolibri.core.hooks import RoleBasedRedirectHook
from kolibri.core.webpack import hooks as webpack_hooks
@@ -12,7 +13,14 @@
class Coach(KolibriPluginBase):
untranslated_view_urls = "api_urls"
- translated_view_urls = "urls"
+
+ @property
+ def translated_view_urls(self):
+ # On an SoUD this plugin should be disabled. In lieu of properly
+ # disabling the plugin, we will just not register any urls for now
+ if not get_device_setting("subset_of_users_device", False):
+ return "urls"
+ return None
@register_hook
diff --git a/kolibri/plugins/facility/kolibri_plugin.py b/kolibri/plugins/facility/kolibri_plugin.py
--- a/kolibri/plugins/facility/kolibri_plugin.py
+++ b/kolibri/plugins/facility/kolibri_plugin.py
@@ -3,6 +3,7 @@
from __future__ import unicode_literals
from kolibri.core.auth.constants.user_kinds import ADMIN
+from kolibri.core.device.utils import get_device_setting
from kolibri.core.hooks import NavigationHook
from kolibri.core.hooks import RoleBasedRedirectHook
from kolibri.core.webpack.hooks import WebpackBundleHook
@@ -11,9 +12,16 @@
class FacilityManagementPlugin(KolibriPluginBase):
- translated_view_urls = "urls"
untranslated_view_urls = "api_urls"
+ @property
+ def translated_view_urls(self):
+ # On an SoUD this plugin should be disabled. In lieu of properly
+ # disabling the plugin, we will just not register any urls for now
+ if not get_device_setting("subset_of_users_device", False):
+ return "urls"
+ return None
+
@register_hook
class FacilityManagementAsset(WebpackBundleHook):
|
{"golden_diff": "diff --git a/kolibri/core/kolibri_plugin.py b/kolibri/core/kolibri_plugin.py\n--- a/kolibri/core/kolibri_plugin.py\n+++ b/kolibri/core/kolibri_plugin.py\n@@ -22,6 +22,7 @@\n from kolibri.core.content.utils.paths import get_zip_content_config\n from kolibri.core.device.models import ContentCacheKey\n from kolibri.core.device.utils import allow_other_browsers_to_connect\n+from kolibri.core.device.utils import get_device_setting\n from kolibri.core.hooks import NavigationHook\n from kolibri.core.oidc_provider_hook import OIDCProviderHook\n from kolibri.core.theme_hook import ThemeHook\n@@ -127,6 +128,7 @@\n \"languageGlobals\": self.language_globals(),\n \"oidcProviderEnabled\": OIDCProviderHook.is_enabled(),\n \"kolibriTheme\": ThemeHook.get_theme(),\n+ \"isSubsetOfUsersDevice\": get_device_setting(\"subset_of_users_device\"),\n }\n \n def language_globals(self):\ndiff --git a/kolibri/plugins/coach/kolibri_plugin.py b/kolibri/plugins/coach/kolibri_plugin.py\n--- a/kolibri/plugins/coach/kolibri_plugin.py\n+++ b/kolibri/plugins/coach/kolibri_plugin.py\n@@ -3,6 +3,7 @@\n from __future__ import unicode_literals\n \n from kolibri.core.auth.constants.user_kinds import COACH\n+from kolibri.core.device.utils import get_device_setting\n from kolibri.core.hooks import NavigationHook\n from kolibri.core.hooks import RoleBasedRedirectHook\n from kolibri.core.webpack import hooks as webpack_hooks\n@@ -12,7 +13,14 @@\n \n class Coach(KolibriPluginBase):\n untranslated_view_urls = \"api_urls\"\n- translated_view_urls = \"urls\"\n+\n+ @property\n+ def translated_view_urls(self):\n+ # On an SoUD this plugin should be disabled. In lieu of properly\n+ # disabling the plugin, we will just not register any urls for now\n+ if not get_device_setting(\"subset_of_users_device\", False):\n+ return \"urls\"\n+ return None\n \n \n @register_hook\ndiff --git a/kolibri/plugins/facility/kolibri_plugin.py b/kolibri/plugins/facility/kolibri_plugin.py\n--- a/kolibri/plugins/facility/kolibri_plugin.py\n+++ b/kolibri/plugins/facility/kolibri_plugin.py\n@@ -3,6 +3,7 @@\n from __future__ import unicode_literals\n \n from kolibri.core.auth.constants.user_kinds import ADMIN\n+from kolibri.core.device.utils import get_device_setting\n from kolibri.core.hooks import NavigationHook\n from kolibri.core.hooks import RoleBasedRedirectHook\n from kolibri.core.webpack.hooks import WebpackBundleHook\n@@ -11,9 +12,16 @@\n \n \n class FacilityManagementPlugin(KolibriPluginBase):\n- translated_view_urls = \"urls\"\n untranslated_view_urls = \"api_urls\"\n \n+ @property\n+ def translated_view_urls(self):\n+ # On an SoUD this plugin should be disabled. In lieu of properly\n+ # disabling the plugin, we will just not register any urls for now\n+ if not get_device_setting(\"subset_of_users_device\", False):\n+ return \"urls\"\n+ return None\n+\n \n @register_hook\n class FacilityManagementAsset(WebpackBundleHook):\n", "issue": "Make learner polling indicator conditional for only SoUD\nFor the new polling indicator on the dropdown menu, this should be updated to appear and poll only when the user is a learner who is logged in on a subset of users device. \r\n\r\n<img width=\"270\" alt=\"Screen Shot 2021-08-05 at 10 58 50 AM\" src=\"https://user-images.githubusercontent.com/17235236/128372343-da85c951-2258-4d5e-ade3-a15b753e6806.png\">\r\n\n", "before_files": [{"content": "from __future__ import absolute_import\nfrom __future__ import print_function\nfrom __future__ import unicode_literals\n\nfrom kolibri.core.auth.constants.user_kinds import ADMIN\nfrom kolibri.core.hooks import NavigationHook\nfrom kolibri.core.hooks import RoleBasedRedirectHook\nfrom kolibri.core.webpack.hooks import WebpackBundleHook\nfrom kolibri.plugins import KolibriPluginBase\nfrom kolibri.plugins.hooks import register_hook\n\n\nclass FacilityManagementPlugin(KolibriPluginBase):\n translated_view_urls = \"urls\"\n untranslated_view_urls = \"api_urls\"\n\n\n@register_hook\nclass FacilityManagementAsset(WebpackBundleHook):\n bundle_id = \"app\"\n\n\n@register_hook\nclass FacilityRedirect(RoleBasedRedirectHook):\n roles = (ADMIN,)\n\n @property\n def url(self):\n return self.plugin_url(FacilityManagementPlugin, \"facility_management\")\n\n\n@register_hook\nclass FacilityManagementNavItem(NavigationHook):\n bundle_id = \"side_nav\"\n", "path": "kolibri/plugins/facility/kolibri_plugin.py"}, {"content": "from __future__ import absolute_import\nfrom __future__ import print_function\nfrom __future__ import unicode_literals\n\nfrom kolibri.core.auth.constants.user_kinds import COACH\nfrom kolibri.core.hooks import NavigationHook\nfrom kolibri.core.hooks import RoleBasedRedirectHook\nfrom kolibri.core.webpack import hooks as webpack_hooks\nfrom kolibri.plugins import KolibriPluginBase\nfrom kolibri.plugins.hooks import register_hook\n\n\nclass Coach(KolibriPluginBase):\n untranslated_view_urls = \"api_urls\"\n translated_view_urls = \"urls\"\n\n\n@register_hook\nclass CoachRedirect(RoleBasedRedirectHook):\n roles = (COACH,)\n\n @property\n def url(self):\n return self.plugin_url(Coach, \"coach\")\n\n\n@register_hook\nclass CoachNavItem(NavigationHook):\n bundle_id = \"side_nav\"\n\n\n@register_hook\nclass CoachAsset(webpack_hooks.WebpackBundleHook):\n bundle_id = \"app\"\n", "path": "kolibri/plugins/coach/kolibri_plugin.py"}, {"content": "from __future__ import absolute_import\nfrom __future__ import print_function\nfrom __future__ import unicode_literals\n\nfrom django.conf import settings\nfrom django.contrib.staticfiles.templatetags.staticfiles import static\nfrom django.core.urlresolvers import get_resolver\nfrom django.core.urlresolvers import reverse\nfrom django.template.loader import render_to_string\nfrom django.utils.html import mark_safe\nfrom django.utils.translation import get_language\nfrom django.utils.translation import get_language_bidi\nfrom django.utils.translation import get_language_info\nfrom django_js_reverse.core import _safe_json\nfrom django_js_reverse.core import generate_json\nfrom django_js_reverse.rjsmin import jsmin\n\nimport kolibri\nfrom kolibri.core.content.utils.paths import get_content_storage_url\nfrom kolibri.core.content.utils.paths import get_hashi_path\nfrom kolibri.core.content.utils.paths import get_zip_content_base_path\nfrom kolibri.core.content.utils.paths import get_zip_content_config\nfrom kolibri.core.device.models import ContentCacheKey\nfrom kolibri.core.device.utils import allow_other_browsers_to_connect\nfrom kolibri.core.hooks import NavigationHook\nfrom kolibri.core.oidc_provider_hook import OIDCProviderHook\nfrom kolibri.core.theme_hook import ThemeHook\nfrom kolibri.core.webpack.hooks import WebpackBundleHook\nfrom kolibri.plugins.app.utils import interface\nfrom kolibri.plugins.hooks import register_hook\nfrom kolibri.utils import i18n\nfrom kolibri.utils.conf import OPTIONS\n\n\n@register_hook\nclass FrontEndCoreAppAssetHook(WebpackBundleHook):\n bundle_id = \"default_frontend\"\n\n def url_tag(self):\n # Modified from:\n # https://github.com/ierror/django-js-reverse/blob/master/django_js_reverse/core.py#L101\n js_name = \"window.kolibriPluginDataGlobal['{bundle}'].urls\".format(\n bundle=self.unique_id\n )\n default_urlresolver = get_resolver(None)\n\n data = generate_json(default_urlresolver)\n\n # Generate the JS that exposes functions to reverse all Django URLs\n # in the frontend.\n js = render_to_string(\n \"django_js_reverse/urls_js.tpl\",\n {\"data\": _safe_json(data), \"js_name\": \"__placeholder__\"},\n # For some reason the js_name gets escaped going into the template\n # so this was the easiest way to inject it.\n ).replace(\"__placeholder__\", js_name)\n zip_content_origin, zip_content_port = get_zip_content_config()\n return [\n mark_safe(\n \"\"\"<script type=\"text/javascript\">\"\"\"\n # Minify the generated Javascript\n + jsmin(js)\n # Add URL references for our base static URL, the Django media URL\n # and our content storage URL - this allows us to calculate\n # the path at which to access a local file on the frontend if needed.\n + \"\"\"\n {js_name}.__staticUrl = '{static_url}';\n {js_name}.__mediaUrl = '{media_url}';\n {js_name}.__contentUrl = '{content_url}';\n {js_name}.__zipContentUrl = '{zip_content_url}';\n {js_name}.__hashiUrl = '{hashi_url}';\n {js_name}.__zipContentOrigin = '{zip_content_origin}';\n {js_name}.__zipContentPort = {zip_content_port};\n </script>\n \"\"\".format(\n js_name=js_name,\n static_url=settings.STATIC_URL,\n media_url=settings.MEDIA_URL,\n content_url=get_content_storage_url(\n baseurl=OPTIONS[\"Deployment\"][\"URL_PATH_PREFIX\"]\n ),\n zip_content_url=get_zip_content_base_path(),\n hashi_url=get_hashi_path(),\n zip_content_origin=zip_content_origin,\n zip_content_port=zip_content_port,\n )\n )\n ]\n\n def navigation_tags(self):\n return [\n hook.render_to_page_load_sync_html()\n for hook in NavigationHook.registered_hooks\n ]\n\n def render_to_page_load_sync_html(self):\n \"\"\"\n Don't render the frontend message files in the usual way\n as the global object to register them does not exist yet.\n Instead they are loaded through plugin data.\n \"\"\"\n tags = (\n self.plugin_data_tag()\n + self.url_tag()\n + list(self.js_and_css_tags())\n + self.navigation_tags()\n )\n\n return mark_safe(\"\\n\".join(tags))\n\n @property\n def plugin_data(self):\n language_code = get_language()\n static_root = static(\"assets/fonts/noto-full\")\n full_file = \"{}.{}.{}.css?v={}\"\n return {\n \"fullCSSFileModern\": full_file.format(\n static_root, language_code, \"modern\", kolibri.__version__\n ),\n \"fullCSSFileBasic\": full_file.format(\n static_root, language_code, \"basic\", kolibri.__version__\n ),\n \"allowRemoteAccess\": allow_other_browsers_to_connect()\n or not interface.enabled,\n \"appCapabilities\": interface.capabilities,\n \"contentCacheKey\": ContentCacheKey.get_cache_key(),\n \"languageGlobals\": self.language_globals(),\n \"oidcProviderEnabled\": OIDCProviderHook.is_enabled(),\n \"kolibriTheme\": ThemeHook.get_theme(),\n }\n\n def language_globals(self):\n language_code = get_language()\n lang_dir = \"rtl\" if get_language_bidi() else \"ltr\"\n\n languages = {}\n for code, language_name in settings.LANGUAGES:\n lang_info = i18n.KOLIBRI_LANGUAGE_INFO[code]\n languages[code] = {\n # Format to match the schema of the content Language model\n \"id\": code,\n \"lang_name\": language_name,\n \"english_name\": lang_info[\"english_name\"]\n if lang_info\n else get_language_info(code)[\"name\"],\n \"lang_direction\": get_language_info(code)[\"bidi\"],\n }\n return {\n \"coreLanguageMessages\": self.frontend_messages(),\n \"languageCode\": language_code,\n \"languageDir\": lang_dir,\n \"languages\": languages,\n }\n\n\n@register_hook\nclass FrontendHeadAssetsHook(WebpackBundleHook):\n \"\"\"\n Render these assets in the <head> tag of base.html, before other JS and assets.\n \"\"\"\n\n bundle_id = \"frontend_head_assets\"\n inline = True\n\n def render_to_page_load_sync_html(self):\n \"\"\"\n Add in the extra language font file tags needed\n for preloading our custom font files.\n \"\"\"\n tags = (\n self.plugin_data_tag()\n + self.language_font_file_tags()\n + self.frontend_message_tag()\n + list(self.js_and_css_tags())\n )\n\n return mark_safe(\"\\n\".join(tags))\n\n def language_font_file_tags(self):\n language_code = get_language()\n common_file = static(\"assets/fonts/noto-common.css\")\n subset_file = static(\"assets/fonts/noto-subset.{}.css\".format(language_code))\n return [\n '<link type=\"text/css\" href=\"{common_css_file}?v={version}\" rel=\"stylesheet\"/>'.format(\n common_css_file=common_file, version=kolibri.__version__\n ),\n '<link type=\"text/css\" href=\"{subset_css_file}?v={version}\" rel=\"stylesheet\"/>'.format(\n subset_css_file=subset_file, version=kolibri.__version__\n ),\n ]\n\n @property\n def plugin_data(self):\n return {\"unsupportedUrl\": reverse(\"kolibri:core:unsupported\")}\n", "path": "kolibri/core/kolibri_plugin.py"}], "after_files": [{"content": "from __future__ import absolute_import\nfrom __future__ import print_function\nfrom __future__ import unicode_literals\n\nfrom kolibri.core.auth.constants.user_kinds import ADMIN\nfrom kolibri.core.device.utils import get_device_setting\nfrom kolibri.core.hooks import NavigationHook\nfrom kolibri.core.hooks import RoleBasedRedirectHook\nfrom kolibri.core.webpack.hooks import WebpackBundleHook\nfrom kolibri.plugins import KolibriPluginBase\nfrom kolibri.plugins.hooks import register_hook\n\n\nclass FacilityManagementPlugin(KolibriPluginBase):\n untranslated_view_urls = \"api_urls\"\n\n @property\n def translated_view_urls(self):\n # On an SoUD this plugin should be disabled. In lieu of properly\n # disabling the plugin, we will just not register any urls for now\n if not get_device_setting(\"subset_of_users_device\", False):\n return \"urls\"\n return None\n\n\n@register_hook\nclass FacilityManagementAsset(WebpackBundleHook):\n bundle_id = \"app\"\n\n\n@register_hook\nclass FacilityRedirect(RoleBasedRedirectHook):\n roles = (ADMIN,)\n\n @property\n def url(self):\n return self.plugin_url(FacilityManagementPlugin, \"facility_management\")\n\n\n@register_hook\nclass FacilityManagementNavItem(NavigationHook):\n bundle_id = \"side_nav\"\n", "path": "kolibri/plugins/facility/kolibri_plugin.py"}, {"content": "from __future__ import absolute_import\nfrom __future__ import print_function\nfrom __future__ import unicode_literals\n\nfrom kolibri.core.auth.constants.user_kinds import COACH\nfrom kolibri.core.device.utils import get_device_setting\nfrom kolibri.core.hooks import NavigationHook\nfrom kolibri.core.hooks import RoleBasedRedirectHook\nfrom kolibri.core.webpack import hooks as webpack_hooks\nfrom kolibri.plugins import KolibriPluginBase\nfrom kolibri.plugins.hooks import register_hook\n\n\nclass Coach(KolibriPluginBase):\n untranslated_view_urls = \"api_urls\"\n\n @property\n def translated_view_urls(self):\n # On an SoUD this plugin should be disabled. In lieu of properly\n # disabling the plugin, we will just not register any urls for now\n if not get_device_setting(\"subset_of_users_device\", False):\n return \"urls\"\n return None\n\n\n@register_hook\nclass CoachRedirect(RoleBasedRedirectHook):\n roles = (COACH,)\n\n @property\n def url(self):\n return self.plugin_url(Coach, \"coach\")\n\n\n@register_hook\nclass CoachNavItem(NavigationHook):\n bundle_id = \"side_nav\"\n\n\n@register_hook\nclass CoachAsset(webpack_hooks.WebpackBundleHook):\n bundle_id = \"app\"\n", "path": "kolibri/plugins/coach/kolibri_plugin.py"}, {"content": "from __future__ import absolute_import\nfrom __future__ import print_function\nfrom __future__ import unicode_literals\n\nfrom django.conf import settings\nfrom django.contrib.staticfiles.templatetags.staticfiles import static\nfrom django.core.urlresolvers import get_resolver\nfrom django.core.urlresolvers import reverse\nfrom django.template.loader import render_to_string\nfrom django.utils.html import mark_safe\nfrom django.utils.translation import get_language\nfrom django.utils.translation import get_language_bidi\nfrom django.utils.translation import get_language_info\nfrom django_js_reverse.core import _safe_json\nfrom django_js_reverse.core import generate_json\nfrom django_js_reverse.rjsmin import jsmin\n\nimport kolibri\nfrom kolibri.core.content.utils.paths import get_content_storage_url\nfrom kolibri.core.content.utils.paths import get_hashi_path\nfrom kolibri.core.content.utils.paths import get_zip_content_base_path\nfrom kolibri.core.content.utils.paths import get_zip_content_config\nfrom kolibri.core.device.models import ContentCacheKey\nfrom kolibri.core.device.utils import allow_other_browsers_to_connect\nfrom kolibri.core.device.utils import get_device_setting\nfrom kolibri.core.hooks import NavigationHook\nfrom kolibri.core.oidc_provider_hook import OIDCProviderHook\nfrom kolibri.core.theme_hook import ThemeHook\nfrom kolibri.core.webpack.hooks import WebpackBundleHook\nfrom kolibri.plugins.app.utils import interface\nfrom kolibri.plugins.hooks import register_hook\nfrom kolibri.utils import i18n\nfrom kolibri.utils.conf import OPTIONS\n\n\n@register_hook\nclass FrontEndCoreAppAssetHook(WebpackBundleHook):\n bundle_id = \"default_frontend\"\n\n def url_tag(self):\n # Modified from:\n # https://github.com/ierror/django-js-reverse/blob/master/django_js_reverse/core.py#L101\n js_name = \"window.kolibriPluginDataGlobal['{bundle}'].urls\".format(\n bundle=self.unique_id\n )\n default_urlresolver = get_resolver(None)\n\n data = generate_json(default_urlresolver)\n\n # Generate the JS that exposes functions to reverse all Django URLs\n # in the frontend.\n js = render_to_string(\n \"django_js_reverse/urls_js.tpl\",\n {\"data\": _safe_json(data), \"js_name\": \"__placeholder__\"},\n # For some reason the js_name gets escaped going into the template\n # so this was the easiest way to inject it.\n ).replace(\"__placeholder__\", js_name)\n zip_content_origin, zip_content_port = get_zip_content_config()\n return [\n mark_safe(\n \"\"\"<script type=\"text/javascript\">\"\"\"\n # Minify the generated Javascript\n + jsmin(js)\n # Add URL references for our base static URL, the Django media URL\n # and our content storage URL - this allows us to calculate\n # the path at which to access a local file on the frontend if needed.\n + \"\"\"\n {js_name}.__staticUrl = '{static_url}';\n {js_name}.__mediaUrl = '{media_url}';\n {js_name}.__contentUrl = '{content_url}';\n {js_name}.__zipContentUrl = '{zip_content_url}';\n {js_name}.__hashiUrl = '{hashi_url}';\n {js_name}.__zipContentOrigin = '{zip_content_origin}';\n {js_name}.__zipContentPort = {zip_content_port};\n </script>\n \"\"\".format(\n js_name=js_name,\n static_url=settings.STATIC_URL,\n media_url=settings.MEDIA_URL,\n content_url=get_content_storage_url(\n baseurl=OPTIONS[\"Deployment\"][\"URL_PATH_PREFIX\"]\n ),\n zip_content_url=get_zip_content_base_path(),\n hashi_url=get_hashi_path(),\n zip_content_origin=zip_content_origin,\n zip_content_port=zip_content_port,\n )\n )\n ]\n\n def navigation_tags(self):\n return [\n hook.render_to_page_load_sync_html()\n for hook in NavigationHook.registered_hooks\n ]\n\n def render_to_page_load_sync_html(self):\n \"\"\"\n Don't render the frontend message files in the usual way\n as the global object to register them does not exist yet.\n Instead they are loaded through plugin data.\n \"\"\"\n tags = (\n self.plugin_data_tag()\n + self.url_tag()\n + list(self.js_and_css_tags())\n + self.navigation_tags()\n )\n\n return mark_safe(\"\\n\".join(tags))\n\n @property\n def plugin_data(self):\n language_code = get_language()\n static_root = static(\"assets/fonts/noto-full\")\n full_file = \"{}.{}.{}.css?v={}\"\n return {\n \"fullCSSFileModern\": full_file.format(\n static_root, language_code, \"modern\", kolibri.__version__\n ),\n \"fullCSSFileBasic\": full_file.format(\n static_root, language_code, \"basic\", kolibri.__version__\n ),\n \"allowRemoteAccess\": allow_other_browsers_to_connect()\n or not interface.enabled,\n \"appCapabilities\": interface.capabilities,\n \"contentCacheKey\": ContentCacheKey.get_cache_key(),\n \"languageGlobals\": self.language_globals(),\n \"oidcProviderEnabled\": OIDCProviderHook.is_enabled(),\n \"kolibriTheme\": ThemeHook.get_theme(),\n \"isSubsetOfUsersDevice\": get_device_setting(\"subset_of_users_device\"),\n }\n\n def language_globals(self):\n language_code = get_language()\n lang_dir = \"rtl\" if get_language_bidi() else \"ltr\"\n\n languages = {}\n for code, language_name in settings.LANGUAGES:\n lang_info = i18n.KOLIBRI_LANGUAGE_INFO[code]\n languages[code] = {\n # Format to match the schema of the content Language model\n \"id\": code,\n \"lang_name\": language_name,\n \"english_name\": lang_info[\"english_name\"]\n if lang_info\n else get_language_info(code)[\"name\"],\n \"lang_direction\": get_language_info(code)[\"bidi\"],\n }\n return {\n \"coreLanguageMessages\": self.frontend_messages(),\n \"languageCode\": language_code,\n \"languageDir\": lang_dir,\n \"languages\": languages,\n }\n\n\n@register_hook\nclass FrontendHeadAssetsHook(WebpackBundleHook):\n \"\"\"\n Render these assets in the <head> tag of base.html, before other JS and assets.\n \"\"\"\n\n bundle_id = \"frontend_head_assets\"\n inline = True\n\n def render_to_page_load_sync_html(self):\n \"\"\"\n Add in the extra language font file tags needed\n for preloading our custom font files.\n \"\"\"\n tags = (\n self.plugin_data_tag()\n + self.language_font_file_tags()\n + self.frontend_message_tag()\n + list(self.js_and_css_tags())\n )\n\n return mark_safe(\"\\n\".join(tags))\n\n def language_font_file_tags(self):\n language_code = get_language()\n common_file = static(\"assets/fonts/noto-common.css\")\n subset_file = static(\"assets/fonts/noto-subset.{}.css\".format(language_code))\n return [\n '<link type=\"text/css\" href=\"{common_css_file}?v={version}\" rel=\"stylesheet\"/>'.format(\n common_css_file=common_file, version=kolibri.__version__\n ),\n '<link type=\"text/css\" href=\"{subset_css_file}?v={version}\" rel=\"stylesheet\"/>'.format(\n subset_css_file=subset_file, version=kolibri.__version__\n ),\n ]\n\n @property\n def plugin_data(self):\n return {\"unsupportedUrl\": reverse(\"kolibri:core:unsupported\")}\n", "path": "kolibri/core/kolibri_plugin.py"}]}
| 3,050 | 743 |
gh_patches_debug_35092
|
rasdani/github-patches
|
git_diff
|
lightly-ai__lightly-539
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
data.LightlyDataset.from_torch_dataset does not work properly
Hello,
I am trying to use Lightly with a dataset of images in `.npz` format. I have created a torch dataset class that loads the sample images and use `data.LightlyDataset.from_torch_dataset ` to create a Lightly dataset from it. However, it seems that the transformations that are passed to the `data.LightlyDataset.from_torch_dataset ` function are not properly performed. and subsequently the `Dataloader` does not work as expected. Can you help me figure out how to handle this? thanks
```
dataset_test_pl = data.LightlyDataset.from_torch_dataset(dataset_test, transform=test_transform)
dataloader_test = torch.utils.data.DataLoader(
dataset_test_pl,
batch_size=batch_size,
shuffle=False,
drop_last=False,
num_workers=num_workers
)
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `lightly/data/dataset.py`
Content:
```
1 """ Lightly Dataset """
2
3 # Copyright (c) 2020. Lightly AG and its affiliates.
4 # All Rights Reserved
5
6 import os
7 import bisect
8 import shutil
9 import tempfile
10
11 from PIL import Image
12 from typing import List, Union, Callable
13
14 import torchvision.datasets as datasets
15 from torchvision import transforms
16
17 from lightly.data._helpers import _load_dataset_from_folder
18 from lightly.data._helpers import DatasetFolder
19 from lightly.data._video import VideoDataset
20 from lightly.utils.io import check_filenames
21
22
23 def _get_filename_by_index(dataset, index):
24 """Default function which maps the index of an image to a filename.
25
26 """
27 if isinstance(dataset, datasets.ImageFolder):
28 # filename is the path of the image relative to the dataset root
29 full_path = dataset.imgs[index][0]
30 return os.path.relpath(full_path, dataset.root)
31 elif isinstance(dataset, DatasetFolder):
32 # filename is the path of the image relative to the dataset root
33 full_path = dataset.samples[index][0]
34 return os.path.relpath(full_path, dataset.root)
35 elif isinstance(dataset, VideoDataset):
36 # filename is constructed by the video dataset
37 return dataset.get_filename(index)
38 else:
39 # dummy to prevent crashes
40 return str(index)
41
42
43 def _ensure_dir(path):
44 """Makes sure that the directory at path exists.
45
46 """
47 dirname = os.path.dirname(path)
48 os.makedirs(dirname, exist_ok=True)
49
50
51 def _copy_image(input_dir, output_dir, filename):
52 """Copies an image from the input directory to the output directory.
53
54 """
55 source = os.path.join(input_dir, filename)
56 target = os.path.join(output_dir, filename)
57 _ensure_dir(target)
58 shutil.copyfile(source, target)
59
60
61 def _save_image(image, output_dir, filename, fmt):
62 """Saves an image in the output directory.
63
64 """
65 target = os.path.join(output_dir, filename)
66 _ensure_dir(target)
67 try:
68 # try to save the image with the specified format or
69 # derive the format from the filename (if format=None)
70 image.save(target, format=fmt)
71 except ValueError:
72 # could not determine format from filename
73 image.save(target, format='png')
74
75
76 def _dump_image(dataset, output_dir, filename, index, fmt):
77 """Saves a single image to the output directory.
78
79 Will copy the image from the input directory to the output directory
80 if possible. If not (e.g. for VideoDatasets), will load the image and
81 then save it to the output directory with the specified format.
82
83 """
84
85 if isinstance(dataset, datasets.ImageFolder):
86 # can safely copy the image from the input to the output directory
87 _copy_image(dataset.root, output_dir, filename)
88 elif isinstance(dataset, DatasetFolder):
89 # can safely copy the image from the input to the output directory
90 _copy_image(dataset.root, output_dir, filename)
91 else:
92 # need to load the image and save it to the output directory
93 image, _ = dataset[index]
94 _save_image(image, output_dir, filename, fmt)
95
96
97 class LightlyDataset:
98 """Provides a uniform data interface for the embedding models.
99
100 Should be used for all models and functions in the lightly package.
101 Returns a tuple (sample, target, fname) when accessed using __getitem__.
102
103 The LightlyDataset supports different input sources. You can use it
104 on a folder of images. You can also use it on a folder with subfolders
105 with images (ImageNet style). If the input_dir has subfolders,
106 each subfolder gets its own target label.
107 You can also work with videos (requires pyav).
108 If there are multiple videos in the input_dir each video gets a different
109 target label assigned. If input_dir contains images and videos
110 only the videos are used.
111
112 Can also be used in combination with the `from_torch_dataset` method
113 to load a dataset offered by torchvision (e.g. cifar10).
114
115 Args:
116 input_dir:
117 Path to directory holding the images or videos to load.
118 transform:
119 Image transforms (as in torchvision).
120 index_to_filename:
121 Function which takes the dataset and index as input and returns
122 the filename of the file at the index. If None, uses default.
123 filenames:
124 If not None, it filters the dataset in the input directory
125 by the given filenames.
126
127 Examples:
128 >>> # load a dataset consisting of images from a local folder
129 >>> # mydata/
130 >>> # `- img1.png
131 >>> # `- img2.png
132 >>> # `- ...
133 >>> import lightly.data as data
134 >>> dataset = data.LightlyDataset(input_dir='path/to/mydata/')
135 >>> sample, target, fname = dataset[0]
136 >>>
137 >>> # also works with subfolders
138 >>> # mydata/
139 >>> # `- subfolder1
140 >>> # `- img1.png
141 >>> # `- subfolder2
142 >>> # ...
143 >>>
144 >>> # also works with videos
145 >>> # mydata/
146 >>> # `- video1.mp4
147 >>> # `- video2.mp4
148 >>> # `- ...
149 """
150
151 def __init__(self,
152 input_dir: Union[str, None],
153 transform: transforms.Compose = None,
154 index_to_filename:
155 Callable[[datasets.VisionDataset, int], str] = None,
156 filenames: List[str] = None,
157 ):
158
159 # can pass input_dir=None to create an "empty" dataset
160 self.input_dir = input_dir
161 if filenames is not None:
162 filepaths = [
163 os.path.join(input_dir, filename)
164 for filename in filenames
165 ]
166 filepaths = set(filepaths)
167
168 def is_valid_file(filepath: str):
169 return filepath in filepaths
170 else:
171 is_valid_file = None
172 if self.input_dir is not None:
173 self.dataset = _load_dataset_from_folder(
174 self.input_dir, transform, is_valid_file=is_valid_file
175 )
176
177 # initialize function to get filename of image
178 self.index_to_filename = _get_filename_by_index
179 if index_to_filename is not None:
180 self.index_to_filename = index_to_filename
181
182 # if created from an input directory with filenames, check if they
183 # are valid
184 if input_dir:
185 check_filenames(self.get_filenames())
186
187 @classmethod
188 def from_torch_dataset(cls,
189 dataset,
190 transform=None,
191 index_to_filename=None):
192 """Builds a LightlyDataset from a PyTorch (or torchvision) dataset.
193
194 Args:
195 dataset:
196 PyTorch/torchvision dataset.
197 transform:
198 Image transforms (as in torchvision).
199 index_to_filename:
200 Function which takes the dataset and index as input and returns
201 the filename of the file at the index. If None, uses default.
202
203 Returns:
204 A LightlyDataset object.
205
206 Examples:
207 >>> # load cifar10 from torchvision
208 >>> import torchvision
209 >>> import lightly.data as data
210 >>> base = torchvision.datasets.CIFAR10(root='./')
211 >>> dataset = data.LightlyDataset.from_torch_dataset(base)
212
213 """
214 # create an "empty" dataset object
215 dataset_obj = cls(
216 None,
217 transform=transform,
218 index_to_filename=index_to_filename
219 )
220
221 # populate it with the torch dataset
222 dataset_obj.dataset = dataset
223 return dataset_obj
224
225 def __getitem__(self, index: int):
226 """Returns (sample, target, fname) of item at index.
227
228 Args:
229 index:
230 Index of the queried item.
231
232 Returns:
233 The image, target, and filename of the item at index.
234
235 """
236 fname = self.index_to_filename(self.dataset, index)
237 sample, target = self.dataset.__getitem__(index)
238
239 return sample, target, fname
240
241 def __len__(self):
242 """Returns the length of the dataset.
243
244 """
245 return len(self.dataset)
246
247 def __add__(self, other):
248 """Adds another item to the dataset.
249
250 """
251 raise NotImplementedError()
252
253 def get_filenames(self) -> List[str]:
254 """Returns all filenames in the dataset.
255
256 """
257 list_of_filenames = []
258 for index in range(len(self)):
259 fname = self.index_to_filename(self.dataset, index)
260 list_of_filenames.append(fname)
261 return list_of_filenames
262
263 def dump(self,
264 output_dir: str,
265 filenames: Union[List[str], None] = None,
266 format: Union[str, None] = None):
267 """Saves images in the dataset to the output directory.
268
269 Will copy the images from the input directory to the output directory
270 if possible. If not (e.g. for VideoDatasets), will load the images and
271 then save them to the output directory with the specified format.
272
273 Args:
274 output_dir:
275 Output directory where the image is stored.
276 filenames:
277 Filenames of the images to store. If None, stores all images.
278 format:
279 Image format. Can be any pillow image format (png, jpg, ...).
280 By default we try to use the same format as the input data. If
281 not possible (e.g. for videos) we dump the image
282 as a png image to prevent compression artifacts.
283
284 """
285
286 if self.dataset.transform is not None:
287 raise RuntimeError('Cannot dump dataset which applies transforms!')
288
289 # create directory if it doesn't exist yet
290 os.makedirs(output_dir, exist_ok=True)
291
292 # dump all the files if no filenames were passed, otherwise dump only
293 # the ones referenced in the list
294 if filenames is None:
295 indices = [i for i in range(self.__len__())]
296 filenames = self.get_filenames()
297 else:
298 indices = []
299 filenames = sorted(filenames)
300 all_filenames = self.get_filenames()
301 for index, filename in enumerate(all_filenames):
302 filename_index = bisect.bisect_left(filenames, filename)
303 # make sure the filename exists in filenames
304 if filename_index < len(filenames) and \
305 filenames[filename_index] == filename:
306 indices.append(index)
307
308 # dump images
309 for i, filename in zip(indices, filenames):
310 _dump_image(self.dataset, output_dir, filename, i, fmt=format)
311
312 def get_filepath_from_filename(self, filename: str, image: Image = None):
313 """Returns the filepath given the filename of the image
314
315 There are three cases:
316 - The dataset is a regular dataset with the images in the input dir.
317 - The dataset is a video dataset, thus the images have to be saved in a
318 temporary folder.
319 - The dataset is a torch dataset, thus the images have to be saved in a
320 temporary folder.
321 Args:
322 filename:
323 The filename of the image
324 image:
325 The image corresponding to the filename
326
327 Returns:
328 The filename to the image, either the existing one (case 1) or a
329 newly created jpg (case 2, 3)
330
331 """
332
333 has_input_dir = hasattr(self, 'input_dir') and \
334 isinstance(self.input_dir, str)
335 if has_input_dir:
336 path_to_image = os.path.join(self.input_dir, filename)
337 if os.path.isfile(path_to_image):
338 # the file exists, return its filepath
339 return path_to_image
340
341 if image is None:
342 raise ValueError(
343 'The parameter image must not be None for'
344 'VideoDatasets and TorchDatasets'
345 )
346
347 # the file doesn't exist, save it as a jpg and return filepath
348 folder_path = tempfile.mkdtemp()
349 filepath = os.path.join(folder_path, filename) + '.jpg'
350
351 if os.path.dirname(filepath):
352 os.makedirs(os.path.dirname(filepath), exist_ok=True)
353
354 image.save(filepath)
355 return filepath
356
357 @property
358 def transform(self):
359 """Getter for the transform of the dataset.
360
361 """
362 return self.dataset.transform
363
364 @transform.setter
365 def transform(self, t):
366 """Setter for the transform of the dataset.
367
368 """
369 self.dataset.transform = t
370
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/lightly/data/dataset.py b/lightly/data/dataset.py
--- a/lightly/data/dataset.py
+++ b/lightly/data/dataset.py
@@ -10,6 +10,7 @@
from PIL import Image
from typing import List, Union, Callable
+from torch._C import Value
import torchvision.datasets as datasets
from torchvision import transforms
@@ -153,8 +154,7 @@
transform: transforms.Compose = None,
index_to_filename:
Callable[[datasets.VisionDataset, int], str] = None,
- filenames: List[str] = None,
- ):
+ filenames: List[str] = None):
# can pass input_dir=None to create an "empty" dataset
self.input_dir = input_dir
@@ -169,10 +169,16 @@
return filepath in filepaths
else:
is_valid_file = None
+
if self.input_dir is not None:
self.dataset = _load_dataset_from_folder(
self.input_dir, transform, is_valid_file=is_valid_file
)
+ elif transform is not None:
+ raise ValueError(
+ 'transform must be None when input_dir is None but is '
+ f'{transform}',
+ )
# initialize function to get filename of image
self.index_to_filename = _get_filename_by_index
@@ -214,12 +220,12 @@
# create an "empty" dataset object
dataset_obj = cls(
None,
- transform=transform,
- index_to_filename=index_to_filename
+ index_to_filename=index_to_filename,
)
# populate it with the torch dataset
dataset_obj.dataset = dataset
+ dataset_obj.transform = transform
return dataset_obj
def __getitem__(self, index: int):
|
{"golden_diff": "diff --git a/lightly/data/dataset.py b/lightly/data/dataset.py\n--- a/lightly/data/dataset.py\n+++ b/lightly/data/dataset.py\n@@ -10,6 +10,7 @@\n \n from PIL import Image\n from typing import List, Union, Callable\n+from torch._C import Value\n \n import torchvision.datasets as datasets\n from torchvision import transforms\n@@ -153,8 +154,7 @@\n transform: transforms.Compose = None,\n index_to_filename:\n Callable[[datasets.VisionDataset, int], str] = None,\n- filenames: List[str] = None,\n- ):\n+ filenames: List[str] = None):\n \n # can pass input_dir=None to create an \"empty\" dataset\n self.input_dir = input_dir\n@@ -169,10 +169,16 @@\n return filepath in filepaths\n else:\n is_valid_file = None\n+\n if self.input_dir is not None:\n self.dataset = _load_dataset_from_folder(\n self.input_dir, transform, is_valid_file=is_valid_file\n )\n+ elif transform is not None:\n+ raise ValueError(\n+ 'transform must be None when input_dir is None but is '\n+ f'{transform}',\n+ )\n \n # initialize function to get filename of image\n self.index_to_filename = _get_filename_by_index\n@@ -214,12 +220,12 @@\n # create an \"empty\" dataset object\n dataset_obj = cls(\n None,\n- transform=transform,\n- index_to_filename=index_to_filename\n+ index_to_filename=index_to_filename,\n )\n \n # populate it with the torch dataset\n dataset_obj.dataset = dataset\n+ dataset_obj.transform = transform\n return dataset_obj\n \n def __getitem__(self, index: int):\n", "issue": "data.LightlyDataset.from_torch_dataset does not work properly\nHello,\r\n\r\nI am trying to use Lightly with a dataset of images in `.npz` format. I have created a torch dataset class that loads the sample images and use `data.LightlyDataset.from_torch_dataset ` to create a Lightly dataset from it. However, it seems that the transformations that are passed to the `data.LightlyDataset.from_torch_dataset ` function are not properly performed. and subsequently the `Dataloader` does not work as expected. Can you help me figure out how to handle this? thanks\r\n\r\n```\r\ndataset_test_pl = data.LightlyDataset.from_torch_dataset(dataset_test, transform=test_transform)\r\ndataloader_test = torch.utils.data.DataLoader(\r\n dataset_test_pl,\r\n batch_size=batch_size,\r\n shuffle=False,\r\n drop_last=False,\r\n num_workers=num_workers\r\n)\r\n```\n", "before_files": [{"content": "\"\"\" Lightly Dataset \"\"\"\n\n# Copyright (c) 2020. Lightly AG and its affiliates.\n# All Rights Reserved\n\nimport os\nimport bisect\nimport shutil\nimport tempfile\n\nfrom PIL import Image\nfrom typing import List, Union, Callable\n\nimport torchvision.datasets as datasets\nfrom torchvision import transforms\n\nfrom lightly.data._helpers import _load_dataset_from_folder\nfrom lightly.data._helpers import DatasetFolder\nfrom lightly.data._video import VideoDataset\nfrom lightly.utils.io import check_filenames\n\n\ndef _get_filename_by_index(dataset, index):\n \"\"\"Default function which maps the index of an image to a filename.\n\n \"\"\"\n if isinstance(dataset, datasets.ImageFolder):\n # filename is the path of the image relative to the dataset root\n full_path = dataset.imgs[index][0]\n return os.path.relpath(full_path, dataset.root)\n elif isinstance(dataset, DatasetFolder):\n # filename is the path of the image relative to the dataset root\n full_path = dataset.samples[index][0]\n return os.path.relpath(full_path, dataset.root)\n elif isinstance(dataset, VideoDataset):\n # filename is constructed by the video dataset\n return dataset.get_filename(index)\n else:\n # dummy to prevent crashes\n return str(index)\n\n\ndef _ensure_dir(path):\n \"\"\"Makes sure that the directory at path exists.\n\n \"\"\"\n dirname = os.path.dirname(path)\n os.makedirs(dirname, exist_ok=True)\n\n\ndef _copy_image(input_dir, output_dir, filename):\n \"\"\"Copies an image from the input directory to the output directory.\n\n \"\"\"\n source = os.path.join(input_dir, filename)\n target = os.path.join(output_dir, filename)\n _ensure_dir(target)\n shutil.copyfile(source, target)\n\n\ndef _save_image(image, output_dir, filename, fmt):\n \"\"\"Saves an image in the output directory.\n\n \"\"\"\n target = os.path.join(output_dir, filename)\n _ensure_dir(target)\n try:\n # try to save the image with the specified format or\n # derive the format from the filename (if format=None)\n image.save(target, format=fmt)\n except ValueError:\n # could not determine format from filename\n image.save(target, format='png')\n\n\ndef _dump_image(dataset, output_dir, filename, index, fmt):\n \"\"\"Saves a single image to the output directory.\n\n Will copy the image from the input directory to the output directory\n if possible. If not (e.g. for VideoDatasets), will load the image and\n then save it to the output directory with the specified format.\n\n \"\"\"\n\n if isinstance(dataset, datasets.ImageFolder):\n # can safely copy the image from the input to the output directory\n _copy_image(dataset.root, output_dir, filename)\n elif isinstance(dataset, DatasetFolder):\n # can safely copy the image from the input to the output directory\n _copy_image(dataset.root, output_dir, filename)\n else:\n # need to load the image and save it to the output directory\n image, _ = dataset[index]\n _save_image(image, output_dir, filename, fmt)\n\n\nclass LightlyDataset:\n \"\"\"Provides a uniform data interface for the embedding models.\n\n Should be used for all models and functions in the lightly package.\n Returns a tuple (sample, target, fname) when accessed using __getitem__.\n\n The LightlyDataset supports different input sources. You can use it\n on a folder of images. You can also use it on a folder with subfolders\n with images (ImageNet style). If the input_dir has subfolders,\n each subfolder gets its own target label.\n You can also work with videos (requires pyav).\n If there are multiple videos in the input_dir each video gets a different\n target label assigned. If input_dir contains images and videos\n only the videos are used.\n\n Can also be used in combination with the `from_torch_dataset` method\n to load a dataset offered by torchvision (e.g. cifar10).\n\n Args:\n input_dir:\n Path to directory holding the images or videos to load.\n transform:\n Image transforms (as in torchvision).\n index_to_filename:\n Function which takes the dataset and index as input and returns\n the filename of the file at the index. If None, uses default.\n filenames:\n If not None, it filters the dataset in the input directory\n by the given filenames.\n\n Examples:\n >>> # load a dataset consisting of images from a local folder\n >>> # mydata/\n >>> # `- img1.png\n >>> # `- img2.png\n >>> # `- ...\n >>> import lightly.data as data\n >>> dataset = data.LightlyDataset(input_dir='path/to/mydata/')\n >>> sample, target, fname = dataset[0]\n >>>\n >>> # also works with subfolders\n >>> # mydata/\n >>> # `- subfolder1\n >>> # `- img1.png\n >>> # `- subfolder2\n >>> # ...\n >>>\n >>> # also works with videos\n >>> # mydata/\n >>> # `- video1.mp4\n >>> # `- video2.mp4\n >>> # `- ...\n \"\"\"\n\n def __init__(self,\n input_dir: Union[str, None],\n transform: transforms.Compose = None,\n index_to_filename:\n Callable[[datasets.VisionDataset, int], str] = None,\n filenames: List[str] = None,\n ):\n\n # can pass input_dir=None to create an \"empty\" dataset\n self.input_dir = input_dir\n if filenames is not None:\n filepaths = [\n os.path.join(input_dir, filename)\n for filename in filenames\n ]\n filepaths = set(filepaths)\n\n def is_valid_file(filepath: str):\n return filepath in filepaths\n else:\n is_valid_file = None\n if self.input_dir is not None:\n self.dataset = _load_dataset_from_folder(\n self.input_dir, transform, is_valid_file=is_valid_file\n )\n\n # initialize function to get filename of image\n self.index_to_filename = _get_filename_by_index\n if index_to_filename is not None:\n self.index_to_filename = index_to_filename\n\n # if created from an input directory with filenames, check if they\n # are valid\n if input_dir:\n check_filenames(self.get_filenames())\n\n @classmethod\n def from_torch_dataset(cls,\n dataset,\n transform=None,\n index_to_filename=None):\n \"\"\"Builds a LightlyDataset from a PyTorch (or torchvision) dataset.\n\n Args:\n dataset:\n PyTorch/torchvision dataset.\n transform:\n Image transforms (as in torchvision).\n index_to_filename:\n Function which takes the dataset and index as input and returns\n the filename of the file at the index. If None, uses default.\n\n Returns:\n A LightlyDataset object.\n\n Examples:\n >>> # load cifar10 from torchvision\n >>> import torchvision\n >>> import lightly.data as data\n >>> base = torchvision.datasets.CIFAR10(root='./')\n >>> dataset = data.LightlyDataset.from_torch_dataset(base)\n\n \"\"\"\n # create an \"empty\" dataset object\n dataset_obj = cls(\n None,\n transform=transform,\n index_to_filename=index_to_filename\n )\n\n # populate it with the torch dataset\n dataset_obj.dataset = dataset\n return dataset_obj\n\n def __getitem__(self, index: int):\n \"\"\"Returns (sample, target, fname) of item at index.\n\n Args:\n index:\n Index of the queried item.\n\n Returns:\n The image, target, and filename of the item at index.\n\n \"\"\"\n fname = self.index_to_filename(self.dataset, index)\n sample, target = self.dataset.__getitem__(index)\n\n return sample, target, fname\n\n def __len__(self):\n \"\"\"Returns the length of the dataset.\n\n \"\"\"\n return len(self.dataset)\n\n def __add__(self, other):\n \"\"\"Adds another item to the dataset.\n\n \"\"\"\n raise NotImplementedError()\n\n def get_filenames(self) -> List[str]:\n \"\"\"Returns all filenames in the dataset.\n\n \"\"\"\n list_of_filenames = []\n for index in range(len(self)):\n fname = self.index_to_filename(self.dataset, index)\n list_of_filenames.append(fname)\n return list_of_filenames\n\n def dump(self,\n output_dir: str,\n filenames: Union[List[str], None] = None,\n format: Union[str, None] = None):\n \"\"\"Saves images in the dataset to the output directory.\n\n Will copy the images from the input directory to the output directory\n if possible. If not (e.g. for VideoDatasets), will load the images and\n then save them to the output directory with the specified format.\n\n Args:\n output_dir:\n Output directory where the image is stored.\n filenames:\n Filenames of the images to store. If None, stores all images.\n format:\n Image format. Can be any pillow image format (png, jpg, ...).\n By default we try to use the same format as the input data. If\n not possible (e.g. for videos) we dump the image \n as a png image to prevent compression artifacts.\n\n \"\"\"\n\n if self.dataset.transform is not None:\n raise RuntimeError('Cannot dump dataset which applies transforms!')\n\n # create directory if it doesn't exist yet\n os.makedirs(output_dir, exist_ok=True)\n\n # dump all the files if no filenames were passed, otherwise dump only\n # the ones referenced in the list\n if filenames is None:\n indices = [i for i in range(self.__len__())]\n filenames = self.get_filenames()\n else:\n indices = []\n filenames = sorted(filenames)\n all_filenames = self.get_filenames()\n for index, filename in enumerate(all_filenames):\n filename_index = bisect.bisect_left(filenames, filename)\n # make sure the filename exists in filenames\n if filename_index < len(filenames) and \\\n filenames[filename_index] == filename:\n indices.append(index)\n\n # dump images\n for i, filename in zip(indices, filenames):\n _dump_image(self.dataset, output_dir, filename, i, fmt=format)\n\n def get_filepath_from_filename(self, filename: str, image: Image = None):\n \"\"\"Returns the filepath given the filename of the image\n\n There are three cases:\n - The dataset is a regular dataset with the images in the input dir.\n - The dataset is a video dataset, thus the images have to be saved in a\n temporary folder.\n - The dataset is a torch dataset, thus the images have to be saved in a\n temporary folder.\n Args:\n filename:\n The filename of the image\n image:\n The image corresponding to the filename\n\n Returns:\n The filename to the image, either the existing one (case 1) or a\n newly created jpg (case 2, 3)\n\n \"\"\"\n\n has_input_dir = hasattr(self, 'input_dir') and \\\n isinstance(self.input_dir, str)\n if has_input_dir:\n path_to_image = os.path.join(self.input_dir, filename)\n if os.path.isfile(path_to_image):\n # the file exists, return its filepath\n return path_to_image\n\n if image is None:\n raise ValueError(\n 'The parameter image must not be None for'\n 'VideoDatasets and TorchDatasets'\n )\n\n # the file doesn't exist, save it as a jpg and return filepath\n folder_path = tempfile.mkdtemp()\n filepath = os.path.join(folder_path, filename) + '.jpg'\n \n if os.path.dirname(filepath):\n os.makedirs(os.path.dirname(filepath), exist_ok=True)\n\n image.save(filepath)\n return filepath\n\n @property\n def transform(self):\n \"\"\"Getter for the transform of the dataset.\n\n \"\"\"\n return self.dataset.transform\n\n @transform.setter\n def transform(self, t):\n \"\"\"Setter for the transform of the dataset.\n\n \"\"\"\n self.dataset.transform = t\n", "path": "lightly/data/dataset.py"}], "after_files": [{"content": "\"\"\" Lightly Dataset \"\"\"\n\n# Copyright (c) 2020. Lightly AG and its affiliates.\n# All Rights Reserved\n\nimport os\nimport bisect\nimport shutil\nimport tempfile\n\nfrom PIL import Image\nfrom typing import List, Union, Callable\nfrom torch._C import Value\n\nimport torchvision.datasets as datasets\nfrom torchvision import transforms\n\nfrom lightly.data._helpers import _load_dataset_from_folder\nfrom lightly.data._helpers import DatasetFolder\nfrom lightly.data._video import VideoDataset\nfrom lightly.utils.io import check_filenames\n\n\ndef _get_filename_by_index(dataset, index):\n \"\"\"Default function which maps the index of an image to a filename.\n\n \"\"\"\n if isinstance(dataset, datasets.ImageFolder):\n # filename is the path of the image relative to the dataset root\n full_path = dataset.imgs[index][0]\n return os.path.relpath(full_path, dataset.root)\n elif isinstance(dataset, DatasetFolder):\n # filename is the path of the image relative to the dataset root\n full_path = dataset.samples[index][0]\n return os.path.relpath(full_path, dataset.root)\n elif isinstance(dataset, VideoDataset):\n # filename is constructed by the video dataset\n return dataset.get_filename(index)\n else:\n # dummy to prevent crashes\n return str(index)\n\n\ndef _ensure_dir(path):\n \"\"\"Makes sure that the directory at path exists.\n\n \"\"\"\n dirname = os.path.dirname(path)\n os.makedirs(dirname, exist_ok=True)\n\n\ndef _copy_image(input_dir, output_dir, filename):\n \"\"\"Copies an image from the input directory to the output directory.\n\n \"\"\"\n source = os.path.join(input_dir, filename)\n target = os.path.join(output_dir, filename)\n _ensure_dir(target)\n shutil.copyfile(source, target)\n\n\ndef _save_image(image, output_dir, filename, fmt):\n \"\"\"Saves an image in the output directory.\n\n \"\"\"\n target = os.path.join(output_dir, filename)\n _ensure_dir(target)\n try:\n # try to save the image with the specified format or\n # derive the format from the filename (if format=None)\n image.save(target, format=fmt)\n except ValueError:\n # could not determine format from filename\n image.save(target, format='png')\n\n\ndef _dump_image(dataset, output_dir, filename, index, fmt):\n \"\"\"Saves a single image to the output directory.\n\n Will copy the image from the input directory to the output directory\n if possible. If not (e.g. for VideoDatasets), will load the image and\n then save it to the output directory with the specified format.\n\n \"\"\"\n\n if isinstance(dataset, datasets.ImageFolder):\n # can safely copy the image from the input to the output directory\n _copy_image(dataset.root, output_dir, filename)\n elif isinstance(dataset, DatasetFolder):\n # can safely copy the image from the input to the output directory\n _copy_image(dataset.root, output_dir, filename)\n else:\n # need to load the image and save it to the output directory\n image, _ = dataset[index]\n _save_image(image, output_dir, filename, fmt)\n\n\nclass LightlyDataset:\n \"\"\"Provides a uniform data interface for the embedding models.\n\n Should be used for all models and functions in the lightly package.\n Returns a tuple (sample, target, fname) when accessed using __getitem__.\n\n The LightlyDataset supports different input sources. You can use it\n on a folder of images. You can also use it on a folder with subfolders\n with images (ImageNet style). If the input_dir has subfolders,\n each subfolder gets its own target label.\n You can also work with videos (requires pyav).\n If there are multiple videos in the input_dir each video gets a different\n target label assigned. If input_dir contains images and videos\n only the videos are used.\n\n Can also be used in combination with the `from_torch_dataset` method\n to load a dataset offered by torchvision (e.g. cifar10).\n\n Args:\n input_dir:\n Path to directory holding the images or videos to load.\n transform:\n Image transforms (as in torchvision).\n index_to_filename:\n Function which takes the dataset and index as input and returns\n the filename of the file at the index. If None, uses default.\n filenames:\n If not None, it filters the dataset in the input directory\n by the given filenames.\n\n Examples:\n >>> # load a dataset consisting of images from a local folder\n >>> # mydata/\n >>> # `- img1.png\n >>> # `- img2.png\n >>> # `- ...\n >>> import lightly.data as data\n >>> dataset = data.LightlyDataset(input_dir='path/to/mydata/')\n >>> sample, target, fname = dataset[0]\n >>>\n >>> # also works with subfolders\n >>> # mydata/\n >>> # `- subfolder1\n >>> # `- img1.png\n >>> # `- subfolder2\n >>> # ...\n >>>\n >>> # also works with videos\n >>> # mydata/\n >>> # `- video1.mp4\n >>> # `- video2.mp4\n >>> # `- ...\n \"\"\"\n\n def __init__(self,\n input_dir: Union[str, None],\n transform: transforms.Compose = None,\n index_to_filename:\n Callable[[datasets.VisionDataset, int], str] = None,\n filenames: List[str] = None):\n\n # can pass input_dir=None to create an \"empty\" dataset\n self.input_dir = input_dir\n if filenames is not None:\n filepaths = [\n os.path.join(input_dir, filename)\n for filename in filenames\n ]\n filepaths = set(filepaths)\n\n def is_valid_file(filepath: str):\n return filepath in filepaths\n else:\n is_valid_file = None\n\n if self.input_dir is not None:\n self.dataset = _load_dataset_from_folder(\n self.input_dir, transform, is_valid_file=is_valid_file\n )\n elif transform is not None:\n raise ValueError(\n 'transform must be None when input_dir is None but is '\n f'{transform}',\n )\n\n # initialize function to get filename of image\n self.index_to_filename = _get_filename_by_index\n if index_to_filename is not None:\n self.index_to_filename = index_to_filename\n\n # if created from an input directory with filenames, check if they\n # are valid\n if input_dir:\n check_filenames(self.get_filenames())\n\n @classmethod\n def from_torch_dataset(cls,\n dataset,\n transform=None,\n index_to_filename=None):\n \"\"\"Builds a LightlyDataset from a PyTorch (or torchvision) dataset.\n\n Args:\n dataset:\n PyTorch/torchvision dataset.\n transform:\n Image transforms (as in torchvision).\n index_to_filename:\n Function which takes the dataset and index as input and returns\n the filename of the file at the index. If None, uses default.\n\n Returns:\n A LightlyDataset object.\n\n Examples:\n >>> # load cifar10 from torchvision\n >>> import torchvision\n >>> import lightly.data as data\n >>> base = torchvision.datasets.CIFAR10(root='./')\n >>> dataset = data.LightlyDataset.from_torch_dataset(base)\n\n \"\"\"\n # create an \"empty\" dataset object\n dataset_obj = cls(\n None,\n index_to_filename=index_to_filename,\n )\n\n # populate it with the torch dataset\n dataset_obj.dataset = dataset\n dataset_obj.transform = transform\n return dataset_obj\n\n def __getitem__(self, index: int):\n \"\"\"Returns (sample, target, fname) of item at index.\n\n Args:\n index:\n Index of the queried item.\n\n Returns:\n The image, target, and filename of the item at index.\n\n \"\"\"\n fname = self.index_to_filename(self.dataset, index)\n sample, target = self.dataset.__getitem__(index)\n\n return sample, target, fname\n\n def __len__(self):\n \"\"\"Returns the length of the dataset.\n\n \"\"\"\n return len(self.dataset)\n\n def __add__(self, other):\n \"\"\"Adds another item to the dataset.\n\n \"\"\"\n raise NotImplementedError()\n\n def get_filenames(self) -> List[str]:\n \"\"\"Returns all filenames in the dataset.\n\n \"\"\"\n list_of_filenames = []\n for index in range(len(self)):\n fname = self.index_to_filename(self.dataset, index)\n list_of_filenames.append(fname)\n return list_of_filenames\n\n def dump(self,\n output_dir: str,\n filenames: Union[List[str], None] = None,\n format: Union[str, None] = None):\n \"\"\"Saves images in the dataset to the output directory.\n\n Will copy the images from the input directory to the output directory\n if possible. If not (e.g. for VideoDatasets), will load the images and\n then save them to the output directory with the specified format.\n\n Args:\n output_dir:\n Output directory where the image is stored.\n filenames:\n Filenames of the images to store. If None, stores all images.\n format:\n Image format. Can be any pillow image format (png, jpg, ...).\n By default we try to use the same format as the input data. If\n not possible (e.g. for videos) we dump the image \n as a png image to prevent compression artifacts.\n\n \"\"\"\n\n if self.dataset.transform is not None:\n raise RuntimeError('Cannot dump dataset which applies transforms!')\n\n # create directory if it doesn't exist yet\n os.makedirs(output_dir, exist_ok=True)\n\n # dump all the files if no filenames were passed, otherwise dump only\n # the ones referenced in the list\n if filenames is None:\n indices = [i for i in range(self.__len__())]\n filenames = self.get_filenames()\n else:\n indices = []\n filenames = sorted(filenames)\n all_filenames = self.get_filenames()\n for index, filename in enumerate(all_filenames):\n filename_index = bisect.bisect_left(filenames, filename)\n # make sure the filename exists in filenames\n if filename_index < len(filenames) and \\\n filenames[filename_index] == filename:\n indices.append(index)\n\n # dump images\n for i, filename in zip(indices, filenames):\n _dump_image(self.dataset, output_dir, filename, i, fmt=format)\n\n def get_filepath_from_filename(self, filename: str, image: Image = None):\n \"\"\"Returns the filepath given the filename of the image\n\n There are three cases:\n - The dataset is a regular dataset with the images in the input dir.\n - The dataset is a video dataset, thus the images have to be saved in a\n temporary folder.\n - The dataset is a torch dataset, thus the images have to be saved in a\n temporary folder.\n Args:\n filename:\n The filename of the image\n image:\n The image corresponding to the filename\n\n Returns:\n The filename to the image, either the existing one (case 1) or a\n newly created jpg (case 2, 3)\n\n \"\"\"\n\n has_input_dir = hasattr(self, 'input_dir') and \\\n isinstance(self.input_dir, str)\n if has_input_dir:\n path_to_image = os.path.join(self.input_dir, filename)\n if os.path.isfile(path_to_image):\n # the file exists, return its filepath\n return path_to_image\n\n if image is None:\n raise ValueError(\n 'The parameter image must not be None for'\n 'VideoDatasets and TorchDatasets'\n )\n\n # the file doesn't exist, save it as a jpg and return filepath\n folder_path = tempfile.mkdtemp()\n filepath = os.path.join(folder_path, filename) + '.jpg'\n \n if os.path.dirname(filepath):\n os.makedirs(os.path.dirname(filepath), exist_ok=True)\n\n image.save(filepath)\n return filepath\n\n @property\n def transform(self):\n \"\"\"Getter for the transform of the dataset.\n\n \"\"\"\n return self.dataset.transform\n\n @transform.setter\n def transform(self, t):\n \"\"\"Setter for the transform of the dataset.\n\n \"\"\"\n self.dataset.transform = t\n", "path": "lightly/data/dataset.py"}]}
| 4,077 | 402 |
gh_patches_debug_25408
|
rasdani/github-patches
|
git_diff
|
liberapay__liberapay.com-1241
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Paypal email is not verified. Although I verified it.
I see you added Paypal as a payment option which is great. However when I add my paypal email - which is different from liberapay email - it still says it is not verified although I received an email and clicked "verify". Is this a bug?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `liberapay/payin/paypal.py`
Content:
```
1 from __future__ import absolute_import, division, print_function, unicode_literals
2
3 import logging
4
5 import requests
6
7 from ..exceptions import PaymentError
8 from ..utils.currencies import Money
9 from ..website import website
10 from .common import update_payin, update_payin_transfer
11
12
13 PAYMENT_STATES_MAP = {
14 'approved': 'succeeded',
15 'created': 'pending',
16 'failed': 'failed',
17 }
18 SALE_STATES_MAP = {
19 'completed': 'succeeded',
20 'denied': 'failed',
21 'pending': 'pending',
22 }
23
24 logger = logging.Logger('paypal')
25
26 session = requests.Session()
27
28
29 def _init_session():
30 # TODO switch to bearer tokens to reduce the risk of exposing the long-lived secret
31 if 'Authentication' in session.headers:
32 return session
33 from base64 import b64encode
34 session.headers.update({
35 'Authorization': 'Basic ' + b64encode((
36 '%s:%s' % (website.app_conf.paypal_id, website.app_conf.paypal_secret)
37 ).encode('ascii')).decode('ascii'),
38 })
39 return session
40
41
42 def create_payment(db, payin, payer, return_url, state):
43 """Create a Payment.
44
45 Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_create
46
47 Note: even though the API expects a list of transactions it rejects the
48 request if the list contains more than one transaction.
49 """
50 transfers = db.all("""
51 SELECT pt.*
52 , recipient.username AS recipient_username
53 , team.username AS team_name
54 , a.id AS merchant_id
55 FROM payin_transfers pt
56 JOIN participants recipient ON recipient.id = pt.recipient
57 LEFT JOIN participants team ON team.id = pt.team
58 JOIN payment_accounts a ON a.pk = pt.destination
59 WHERE pt.payin = %s
60 ORDER BY pt.id
61 """, (payin.id,))
62 assert transfers
63 locale, _ = state['locale'], state['_']
64 data = {
65 "intent": "sale",
66 "application_context": {
67 "brand_name": "Liberapay",
68 "locale": locale.language,
69 "landing_page": "Login",
70 "shipping_preference": "NO_SHIPPING",
71 "user_action": "commit",
72 },
73 "payer": {
74 "payment_method": "paypal"
75 },
76 "transactions": [{
77 "amount": {
78 "total": str(pt.amount.amount),
79 "currency": pt.amount.currency
80 },
81 "description": (
82 _("donation to {0} for their role in the {1} team",
83 pt.recipient_username, pt.team_name)
84 if pt.team_name else
85 _("donation to {0}", pt.recipient_username)
86 ),
87 "invoice_number": str(pt.id),
88 "note_to_payee": (
89 "donation via Liberapay for your role in the %s team" % pt.team_name
90 if pt.team_name else
91 "donation via Liberapay"
92 ),
93 "payee": {
94 "email": pt.merchant_id,
95 },
96 "payment_options": {
97 "allowed_payment_method": "UNRESTRICTED"
98 },
99 "soft_descriptor": "Liberapay",
100 "item_list": {
101 "items": [{
102 "name":
103 _("One week of the donation") if pt.period == 'weekly' else
104 _("One month of the donation") if pt.period == 'monthly' else
105 _("One year of the donation"),
106 "quantity": pt.n_units,
107 "price": str(pt.unit_amount.amount),
108 "currency": pt.unit_amount.currency
109 }]
110 }
111 } for pt in transfers],
112 "redirect_urls": {
113 "return_url": return_url,
114 "cancel_url": return_url
115 }
116 }
117 url = 'https://api.%s/v1/payments/payment' % website.app_conf.paypal_domain
118 headers = {
119 'PayPal-Request-Id': 'payin_%i' % payin.id
120 }
121 response = _init_session().post(url, json=data, headers=headers)
122 if response.status_code != 201:
123 error = response.text # for Sentry
124 logger.debug(error)
125 raise PaymentError('PayPal', error)
126 payment = response.json()
127 status = PAYMENT_STATES_MAP[payment['state']]
128 error = payment.get('failure_reason')
129 payin = update_payin(db, payin.id, payment['id'], status, error)
130 if payin.status == 'pending':
131 redirect_url = [l['href'] for l in payment['links'] if l['rel'] == 'approval_url'][0]
132 raise state['response'].redirect(redirect_url)
133 return payin
134
135
136 def execute_payment(db, payin, payer_id):
137 """Execute a previously approved payment.
138
139 Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_execute
140 """
141 url = 'https://api.%s/v1/payments/payment/%s/execute' % (
142 website.app_conf.paypal_domain, payin.remote_id
143 )
144 headers = {'PayPal-Request-Id': 'payin_execute_%i' % payin.id}
145 data = {"payer_id": payer_id}
146 response = _init_session().post(url, json=data, headers=headers)
147 if response.status_code != 200:
148 error = response.text # for Sentry
149 logger.debug(error)
150 raise PaymentError('PayPal')
151 payment = response.json()
152
153 # Update the payin
154 status = PAYMENT_STATES_MAP[payment['state']]
155 error = payment.get('failure_reason')
156 payin = update_payin(db, payin.id, payment['id'], status, error)
157
158 # Update the payin transfers
159 for tr in payment['transactions']:
160 sale = tr.get('related_resources', [{}])[0].get('sale')
161 if sale:
162 pt_id = tr['invoice_number']
163 pt_remote_id = sale['id']
164 pt_status = SALE_STATES_MAP[sale['state']]
165 pt_error = sale.get('reason_code')
166 pt_fee = Money(sale['transaction_fee']['value'], sale['transaction_fee']['currency'])
167 charge_amount = Money(sale['amount']['total'], sale['amount']['currency'])
168 net_amount = charge_amount - pt_fee
169 update_payin_transfer(
170 db, pt_id, pt_remote_id, pt_status, pt_error,
171 amount=net_amount, fee=pt_fee
172 )
173
174 return payin
175
176
177 def sync_payment(db, payin):
178 """Fetch the payment's data and update our database.
179
180 Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_get
181 """
182 url = 'https://api.%s/v1/payments/payment/%s' % (
183 website.app_conf.paypal_domain, payin.remote_id
184 )
185 response = _init_session().get(url)
186 if response.status_code != 200:
187 error = response.text # for Sentry
188 logger.debug(error)
189 raise PaymentError('PayPal')
190 payment = response.json()
191 status = PAYMENT_STATES_MAP[payment['state']]
192 error = payment.get('failure_reason')
193 return update_payin(db, payin.id, payment['id'], status, error)
194
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/liberapay/payin/paypal.py b/liberapay/payin/paypal.py
--- a/liberapay/payin/paypal.py
+++ b/liberapay/payin/paypal.py
@@ -107,7 +107,7 @@
"price": str(pt.unit_amount.amount),
"currency": pt.unit_amount.currency
}]
- }
+ } if pt.n_units >= 1 else {}
} for pt in transfers],
"redirect_urls": {
"return_url": return_url,
@@ -163,9 +163,11 @@
pt_remote_id = sale['id']
pt_status = SALE_STATES_MAP[sale['state']]
pt_error = sale.get('reason_code')
- pt_fee = Money(sale['transaction_fee']['value'], sale['transaction_fee']['currency'])
+ pt_fee = sale.get('transaction_fee')
+ if pt_fee:
+ pt_fee = Money(pt_fee['value'], pt_fee['currency'])
charge_amount = Money(sale['amount']['total'], sale['amount']['currency'])
- net_amount = charge_amount - pt_fee
+ net_amount = charge_amount - (pt_fee or 0)
update_payin_transfer(
db, pt_id, pt_remote_id, pt_status, pt_error,
amount=net_amount, fee=pt_fee
|
{"golden_diff": "diff --git a/liberapay/payin/paypal.py b/liberapay/payin/paypal.py\n--- a/liberapay/payin/paypal.py\n+++ b/liberapay/payin/paypal.py\n@@ -107,7 +107,7 @@\n \"price\": str(pt.unit_amount.amount),\n \"currency\": pt.unit_amount.currency\n }]\n- }\n+ } if pt.n_units >= 1 else {}\n } for pt in transfers],\n \"redirect_urls\": {\n \"return_url\": return_url,\n@@ -163,9 +163,11 @@\n pt_remote_id = sale['id']\n pt_status = SALE_STATES_MAP[sale['state']]\n pt_error = sale.get('reason_code')\n- pt_fee = Money(sale['transaction_fee']['value'], sale['transaction_fee']['currency'])\n+ pt_fee = sale.get('transaction_fee')\n+ if pt_fee:\n+ pt_fee = Money(pt_fee['value'], pt_fee['currency'])\n charge_amount = Money(sale['amount']['total'], sale['amount']['currency'])\n- net_amount = charge_amount - pt_fee\n+ net_amount = charge_amount - (pt_fee or 0)\n update_payin_transfer(\n db, pt_id, pt_remote_id, pt_status, pt_error,\n amount=net_amount, fee=pt_fee\n", "issue": "Paypal email is not verified. Although I verified it.\nI see you added Paypal as a payment option which is great. However when I add my paypal email - which is different from liberapay email - it still says it is not verified although I received an email and clicked \"verify\". Is this a bug?\n", "before_files": [{"content": "from __future__ import absolute_import, division, print_function, unicode_literals\n\nimport logging\n\nimport requests\n\nfrom ..exceptions import PaymentError\nfrom ..utils.currencies import Money\nfrom ..website import website\nfrom .common import update_payin, update_payin_transfer\n\n\nPAYMENT_STATES_MAP = {\n 'approved': 'succeeded',\n 'created': 'pending',\n 'failed': 'failed',\n}\nSALE_STATES_MAP = {\n 'completed': 'succeeded',\n 'denied': 'failed',\n 'pending': 'pending',\n}\n\nlogger = logging.Logger('paypal')\n\nsession = requests.Session()\n\n\ndef _init_session():\n # TODO switch to bearer tokens to reduce the risk of exposing the long-lived secret\n if 'Authentication' in session.headers:\n return session\n from base64 import b64encode\n session.headers.update({\n 'Authorization': 'Basic ' + b64encode((\n '%s:%s' % (website.app_conf.paypal_id, website.app_conf.paypal_secret)\n ).encode('ascii')).decode('ascii'),\n })\n return session\n\n\ndef create_payment(db, payin, payer, return_url, state):\n \"\"\"Create a Payment.\n\n Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_create\n\n Note: even though the API expects a list of transactions it rejects the\n request if the list contains more than one transaction.\n \"\"\"\n transfers = db.all(\"\"\"\n SELECT pt.*\n , recipient.username AS recipient_username\n , team.username AS team_name\n , a.id AS merchant_id\n FROM payin_transfers pt\n JOIN participants recipient ON recipient.id = pt.recipient\n LEFT JOIN participants team ON team.id = pt.team\n JOIN payment_accounts a ON a.pk = pt.destination\n WHERE pt.payin = %s\n ORDER BY pt.id\n \"\"\", (payin.id,))\n assert transfers\n locale, _ = state['locale'], state['_']\n data = {\n \"intent\": \"sale\",\n \"application_context\": {\n \"brand_name\": \"Liberapay\",\n \"locale\": locale.language,\n \"landing_page\": \"Login\",\n \"shipping_preference\": \"NO_SHIPPING\",\n \"user_action\": \"commit\",\n },\n \"payer\": {\n \"payment_method\": \"paypal\"\n },\n \"transactions\": [{\n \"amount\": {\n \"total\": str(pt.amount.amount),\n \"currency\": pt.amount.currency\n },\n \"description\": (\n _(\"donation to {0} for their role in the {1} team\",\n pt.recipient_username, pt.team_name)\n if pt.team_name else\n _(\"donation to {0}\", pt.recipient_username)\n ),\n \"invoice_number\": str(pt.id),\n \"note_to_payee\": (\n \"donation via Liberapay for your role in the %s team\" % pt.team_name\n if pt.team_name else\n \"donation via Liberapay\"\n ),\n \"payee\": {\n \"email\": pt.merchant_id,\n },\n \"payment_options\": {\n \"allowed_payment_method\": \"UNRESTRICTED\"\n },\n \"soft_descriptor\": \"Liberapay\",\n \"item_list\": {\n \"items\": [{\n \"name\":\n _(\"One week of the donation\") if pt.period == 'weekly' else\n _(\"One month of the donation\") if pt.period == 'monthly' else\n _(\"One year of the donation\"),\n \"quantity\": pt.n_units,\n \"price\": str(pt.unit_amount.amount),\n \"currency\": pt.unit_amount.currency\n }]\n }\n } for pt in transfers],\n \"redirect_urls\": {\n \"return_url\": return_url,\n \"cancel_url\": return_url\n }\n }\n url = 'https://api.%s/v1/payments/payment' % website.app_conf.paypal_domain\n headers = {\n 'PayPal-Request-Id': 'payin_%i' % payin.id\n }\n response = _init_session().post(url, json=data, headers=headers)\n if response.status_code != 201:\n error = response.text # for Sentry\n logger.debug(error)\n raise PaymentError('PayPal', error)\n payment = response.json()\n status = PAYMENT_STATES_MAP[payment['state']]\n error = payment.get('failure_reason')\n payin = update_payin(db, payin.id, payment['id'], status, error)\n if payin.status == 'pending':\n redirect_url = [l['href'] for l in payment['links'] if l['rel'] == 'approval_url'][0]\n raise state['response'].redirect(redirect_url)\n return payin\n\n\ndef execute_payment(db, payin, payer_id):\n \"\"\"Execute a previously approved payment.\n\n Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_execute\n \"\"\"\n url = 'https://api.%s/v1/payments/payment/%s/execute' % (\n website.app_conf.paypal_domain, payin.remote_id\n )\n headers = {'PayPal-Request-Id': 'payin_execute_%i' % payin.id}\n data = {\"payer_id\": payer_id}\n response = _init_session().post(url, json=data, headers=headers)\n if response.status_code != 200:\n error = response.text # for Sentry\n logger.debug(error)\n raise PaymentError('PayPal')\n payment = response.json()\n\n # Update the payin\n status = PAYMENT_STATES_MAP[payment['state']]\n error = payment.get('failure_reason')\n payin = update_payin(db, payin.id, payment['id'], status, error)\n\n # Update the payin transfers\n for tr in payment['transactions']:\n sale = tr.get('related_resources', [{}])[0].get('sale')\n if sale:\n pt_id = tr['invoice_number']\n pt_remote_id = sale['id']\n pt_status = SALE_STATES_MAP[sale['state']]\n pt_error = sale.get('reason_code')\n pt_fee = Money(sale['transaction_fee']['value'], sale['transaction_fee']['currency'])\n charge_amount = Money(sale['amount']['total'], sale['amount']['currency'])\n net_amount = charge_amount - pt_fee\n update_payin_transfer(\n db, pt_id, pt_remote_id, pt_status, pt_error,\n amount=net_amount, fee=pt_fee\n )\n\n return payin\n\n\ndef sync_payment(db, payin):\n \"\"\"Fetch the payment's data and update our database.\n\n Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_get\n \"\"\"\n url = 'https://api.%s/v1/payments/payment/%s' % (\n website.app_conf.paypal_domain, payin.remote_id\n )\n response = _init_session().get(url)\n if response.status_code != 200:\n error = response.text # for Sentry\n logger.debug(error)\n raise PaymentError('PayPal')\n payment = response.json()\n status = PAYMENT_STATES_MAP[payment['state']]\n error = payment.get('failure_reason')\n return update_payin(db, payin.id, payment['id'], status, error)\n", "path": "liberapay/payin/paypal.py"}], "after_files": [{"content": "from __future__ import absolute_import, division, print_function, unicode_literals\n\nimport logging\n\nimport requests\n\nfrom ..exceptions import PaymentError\nfrom ..utils.currencies import Money\nfrom ..website import website\nfrom .common import update_payin, update_payin_transfer\n\n\nPAYMENT_STATES_MAP = {\n 'approved': 'succeeded',\n 'created': 'pending',\n 'failed': 'failed',\n}\nSALE_STATES_MAP = {\n 'completed': 'succeeded',\n 'denied': 'failed',\n 'pending': 'pending',\n}\n\nlogger = logging.Logger('paypal')\n\nsession = requests.Session()\n\n\ndef _init_session():\n # TODO switch to bearer tokens to reduce the risk of exposing the long-lived secret\n if 'Authentication' in session.headers:\n return session\n from base64 import b64encode\n session.headers.update({\n 'Authorization': 'Basic ' + b64encode((\n '%s:%s' % (website.app_conf.paypal_id, website.app_conf.paypal_secret)\n ).encode('ascii')).decode('ascii'),\n })\n return session\n\n\ndef create_payment(db, payin, payer, return_url, state):\n \"\"\"Create a Payment.\n\n Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_create\n\n Note: even though the API expects a list of transactions it rejects the\n request if the list contains more than one transaction.\n \"\"\"\n transfers = db.all(\"\"\"\n SELECT pt.*\n , recipient.username AS recipient_username\n , team.username AS team_name\n , a.id AS merchant_id\n FROM payin_transfers pt\n JOIN participants recipient ON recipient.id = pt.recipient\n LEFT JOIN participants team ON team.id = pt.team\n JOIN payment_accounts a ON a.pk = pt.destination\n WHERE pt.payin = %s\n ORDER BY pt.id\n \"\"\", (payin.id,))\n assert transfers\n locale, _ = state['locale'], state['_']\n data = {\n \"intent\": \"sale\",\n \"application_context\": {\n \"brand_name\": \"Liberapay\",\n \"locale\": locale.language,\n \"landing_page\": \"Login\",\n \"shipping_preference\": \"NO_SHIPPING\",\n \"user_action\": \"commit\",\n },\n \"payer\": {\n \"payment_method\": \"paypal\"\n },\n \"transactions\": [{\n \"amount\": {\n \"total\": str(pt.amount.amount),\n \"currency\": pt.amount.currency\n },\n \"description\": (\n _(\"donation to {0} for their role in the {1} team\",\n pt.recipient_username, pt.team_name)\n if pt.team_name else\n _(\"donation to {0}\", pt.recipient_username)\n ),\n \"invoice_number\": str(pt.id),\n \"note_to_payee\": (\n \"donation via Liberapay for your role in the %s team\" % pt.team_name\n if pt.team_name else\n \"donation via Liberapay\"\n ),\n \"payee\": {\n \"email\": pt.merchant_id,\n },\n \"payment_options\": {\n \"allowed_payment_method\": \"UNRESTRICTED\"\n },\n \"soft_descriptor\": \"Liberapay\",\n \"item_list\": {\n \"items\": [{\n \"name\":\n _(\"One week of the donation\") if pt.period == 'weekly' else\n _(\"One month of the donation\") if pt.period == 'monthly' else\n _(\"One year of the donation\"),\n \"quantity\": pt.n_units,\n \"price\": str(pt.unit_amount.amount),\n \"currency\": pt.unit_amount.currency\n }]\n } if pt.n_units >= 1 else {}\n } for pt in transfers],\n \"redirect_urls\": {\n \"return_url\": return_url,\n \"cancel_url\": return_url\n }\n }\n url = 'https://api.%s/v1/payments/payment' % website.app_conf.paypal_domain\n headers = {\n 'PayPal-Request-Id': 'payin_%i' % payin.id\n }\n response = _init_session().post(url, json=data, headers=headers)\n if response.status_code != 201:\n error = response.text # for Sentry\n logger.debug(error)\n raise PaymentError('PayPal', error)\n payment = response.json()\n status = PAYMENT_STATES_MAP[payment['state']]\n error = payment.get('failure_reason')\n payin = update_payin(db, payin.id, payment['id'], status, error)\n if payin.status == 'pending':\n redirect_url = [l['href'] for l in payment['links'] if l['rel'] == 'approval_url'][0]\n raise state['response'].redirect(redirect_url)\n return payin\n\n\ndef execute_payment(db, payin, payer_id):\n \"\"\"Execute a previously approved payment.\n\n Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_execute\n \"\"\"\n url = 'https://api.%s/v1/payments/payment/%s/execute' % (\n website.app_conf.paypal_domain, payin.remote_id\n )\n headers = {'PayPal-Request-Id': 'payin_execute_%i' % payin.id}\n data = {\"payer_id\": payer_id}\n response = _init_session().post(url, json=data, headers=headers)\n if response.status_code != 200:\n error = response.text # for Sentry\n logger.debug(error)\n raise PaymentError('PayPal')\n payment = response.json()\n\n # Update the payin\n status = PAYMENT_STATES_MAP[payment['state']]\n error = payment.get('failure_reason')\n payin = update_payin(db, payin.id, payment['id'], status, error)\n\n # Update the payin transfers\n for tr in payment['transactions']:\n sale = tr.get('related_resources', [{}])[0].get('sale')\n if sale:\n pt_id = tr['invoice_number']\n pt_remote_id = sale['id']\n pt_status = SALE_STATES_MAP[sale['state']]\n pt_error = sale.get('reason_code')\n pt_fee = sale.get('transaction_fee')\n if pt_fee:\n pt_fee = Money(pt_fee['value'], pt_fee['currency'])\n charge_amount = Money(sale['amount']['total'], sale['amount']['currency'])\n net_amount = charge_amount - (pt_fee or 0)\n update_payin_transfer(\n db, pt_id, pt_remote_id, pt_status, pt_error,\n amount=net_amount, fee=pt_fee\n )\n\n return payin\n\n\ndef sync_payment(db, payin):\n \"\"\"Fetch the payment's data and update our database.\n\n Doc: https://developer.paypal.com/docs/api/payments/v1/#payment_get\n \"\"\"\n url = 'https://api.%s/v1/payments/payment/%s' % (\n website.app_conf.paypal_domain, payin.remote_id\n )\n response = _init_session().get(url)\n if response.status_code != 200:\n error = response.text # for Sentry\n logger.debug(error)\n raise PaymentError('PayPal')\n payment = response.json()\n status = PAYMENT_STATES_MAP[payment['state']]\n error = payment.get('failure_reason')\n return update_payin(db, payin.id, payment['id'], status, error)\n", "path": "liberapay/payin/paypal.py"}]}
| 2,373 | 296 |
gh_patches_debug_19739
|
rasdani/github-patches
|
git_diff
|
cocotb__cocotb-278
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
getvalue() in handle.py should configure the returned Binary value
When getting a value from a handle a "BinaryValue()" object is created. In my case, I tried to slice that value to get the upper bits, but the call failed because the returned value is not configured.
I believe at a minimum, the Handle should set the number of bits, but ideally it would just configure everything the BinaryValue() object needs before returning it.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `cocotb/handle.py`
Content:
```
1 #!/usr/bin/env python
2
3 ''' Copyright (c) 2013 Potential Ventures Ltd
4 Copyright (c) 2013 SolarFlare Communications Inc
5 All rights reserved.
6
7 Redistribution and use in source and binary forms, with or without
8 modification, are permitted provided that the following conditions are met:
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11 * Redistributions in binary form must reproduce the above copyright
12 notice, this list of conditions and the following disclaimer in the
13 documentation and/or other materials provided with the distribution.
14 * Neither the name of Potential Ventures Ltd,
15 SolarFlare Communications Inc nor the
16 names of its contributors may be used to endorse or promote products
17 derived from this software without specific prior written permission.
18
19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
20 ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
21 WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
22 DISCLAIMED. IN NO EVENT SHALL POTENTIAL VENTURES LTD BE LIABLE FOR ANY
23 DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
24 (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
25 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
26 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
28 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. '''
29
30 # -*- coding: utf-8 -*-
31
32 import logging
33 import ctypes
34 import traceback
35 import sys
36 # from StringIO import StringIO
37
38 from io import StringIO, BytesIO
39
40 import os
41
42 # For autodocumentation don't need the extension modules
43 if "SPHINX_BUILD" in os.environ:
44 simulator = None
45 else:
46 import simulator
47
48 import cocotb
49 from cocotb.binary import BinaryValue
50 from cocotb.log import SimLog
51 from cocotb.result import TestError
52 from cocotb.triggers import _RisingEdge, _FallingEdge
53 from cocotb.utils import get_python_integer_types
54
55
56 class SimHandle(object):
57
58 def __init__(self, handle):
59 """
60 Args:
61 _handle [integer] : vpi/vhpi handle to the simulator object
62 """
63 self._handle = handle # handle used for future simulator transactions
64 self._sub_handles = {} # Dict. of SimHandle objects created by getattr
65 self._len = None
66
67 self.name = simulator.get_name_string(self._handle)
68 self.fullname = '%s(%s)' % (self.name,
69 simulator.get_type_string(self._handle))
70 self.log = SimLog('cocotb.' + self.name)
71 self.log.debug("Created!")
72 self._r_edge = _RisingEdge(self)
73 self._f_edge = _FallingEdge(self)
74
75 def __hash__(self):
76 return self._handle
77
78 def __str__(self):
79 return "%s @0x%x" % (self.name, self._handle)
80
81 def __getattr__(self, name):
82 """ Query the simulator for a object with the specified name
83 and cache the result to build a tree
84 """
85 # python's builtin dir and IPython's dir2 search for these,
86 # raise an AttributeError to avoid incorrect calls to _raise_testerror
87 if name in ["__methods__","__members__","trait_names","_getAttributeNames"]:
88 raise AttributeError(name)
89 if name in self._sub_handles:
90 return self._sub_handles[name]
91 new_handle = simulator.get_handle_by_name(self._handle, name)
92 if not new_handle:
93 self._raise_testerror("%s contains no object named %s" %
94 (self.name, name))
95 self._sub_handles[name] = SimHandle(new_handle)
96 return self._sub_handles[name]
97
98 def _raise_testerror(self, msg):
99 lastframe = sys._getframe(2)
100 if sys.version_info[0] >= 3:
101 buff = StringIO()
102 traceback.print_stack(lastframe, file=buff)
103 else:
104 buff_bytes = BytesIO()
105 traceback.print_stack(lastframe, file=buff_bytes)
106 buff = StringIO(buff_bytes.getvalue().decode("UTF8"))
107 self.log.error("%s\n%s" % (msg, buff.getvalue()))
108 exception = TestError(msg)
109 exception.stderr.write(buff.getvalue())
110 buff.close()
111 raise exception
112
113 def __setattr__(self, name, value):
114 """Provide transparent access to signals"""
115 if (not name.startswith('_') and
116 not name in ["name", "fullname", "log", "value"] and
117 self.__hasattr__(name)):
118 getattr(self, name).setcachedvalue(value)
119 return
120 object.__setattr__(self, name, value)
121
122 def __hasattr__(self, name):
123 """
124 Since calling hasattr(handle, "something") will print out a
125 backtrace to the log since usually attempting to access a
126 non-existent member is an error we provide a 'peek function
127
128 We still add the found handle to our dictionary to prevent leaking
129 handles.
130 """
131 if name in self._sub_handles:
132 return self._sub_handles[name]
133 new_handle = simulator.get_handle_by_name(self._handle, name)
134 if new_handle:
135 self._sub_handles[name] = SimHandle(new_handle)
136 return new_handle
137
138 def __getitem__(self, index):
139 if index in self._sub_handles:
140 return self._sub_handles[index]
141 new_handle = simulator.get_handle_by_index(self._handle, index)
142 if not new_handle:
143 self._raise_testerror("%s contains no object at index %d" %
144 (self.name, index))
145 self._sub_handles[index] = SimHandle(new_handle)
146 return self._sub_handles[index]
147
148 def __setitem__(self, index, value):
149 """Provide transparent assignment to bit index"""
150 self.__getitem__(index).setcachedvalue(value)
151
152 def getvalue(self):
153 result = BinaryValue()
154 result.binstr = self._get_value_str()
155 return result
156
157 def setimmediatevalue(self, value):
158 """
159 Set the value of the underlying simulation object to value.
160
161 Args:
162 value (ctypes.Structure, cocotb.binary.BinaryValue, int)
163 The value to drive onto the simulator object
164
165 Raises:
166 TypeError
167
168 This operation will fail unless the handle refers to a modifiable
169 object eg net, signal or variable.
170
171 We determine the library call to make based on the type of the value
172
173 Assigning integers less than 32-bits is faster
174 """
175 if (isinstance(value, get_python_integer_types()) and
176 value < 0x7fffffff):
177 simulator.set_signal_val(self._handle, value)
178 return
179
180 if isinstance(value, ctypes.Structure):
181 value = BinaryValue(value=cocotb.utils.pack(value), bits=len(self))
182 elif isinstance(value, get_python_integer_types()):
183 value = BinaryValue(value=value, bits=len(self), bigEndian=False)
184 elif not isinstance(value, BinaryValue):
185 self.log.critical("Unsupported type for value assignment: %s (%s)"
186 % (type(value), repr(value)))
187 raise TypeError("Unable to set simulator value with type %s" %
188 (type(value)))
189
190 simulator.set_signal_val_str(self._handle, value.binstr)
191
192 def setcachedvalue(self, value):
193 """Intercept the store of a value and hold in cache.
194
195 This operation is to enable all of the scheduled callbacks to completed
196 with the same read data and for the writes to occour on the next
197 sim time"""
198 cocotb.scheduler.save_write(self, value)
199
200 # We want to maintain compatability with python 2.5 so we can't use
201 # @property with a setter
202 value = property(getvalue, setcachedvalue, None,
203 "A reference to the value")
204
205 def _get_value_str(self):
206 return simulator.get_signal_val(self._handle)
207
208 def __le__(self, value):
209 """Overload the less than or equal to operator to
210 provide an hdl-like shortcut
211 module.signal <= 2
212 """
213 self.value = value
214
215 def __len__(self):
216 """Returns the 'length' of the underlying object.
217
218 For vectors this is the number of bits.
219
220 TODO: Handle other types (loops, generate etc)
221 """
222 if self._len is None:
223 self._len = len(self._get_value_str())
224 return self._len
225
226 def __cmp__(self, other):
227
228 # Permits comparison of handles i.e. if clk == dut.clk
229 if isinstance(other, SimHandle):
230 if self._handle == other._handle:
231 return 0
232 return 1
233
234 # Use the comparison method of the other object against our value
235 return self.value.__cmp__(other)
236
237 def __iter__(self):
238 """Iterates over all known types defined by simulator module"""
239 for handle_type in [simulator.MODULE,
240 simulator.PARAMETER,
241 simulator.REG,
242 simulator.NET,
243 simulator.NETARRAY]:
244 iterator = simulator.iterate(handle_type, self._handle)
245 while True:
246 try:
247 thing = simulator.next(iterator)
248 except StopIteration:
249 break
250 hdl = SimHandle(thing)
251 self._sub_handles[hdl.name] = hdl
252 yield hdl
253
254 def __int__(self):
255 return int(self.value)
256
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/cocotb/handle.py b/cocotb/handle.py
--- a/cocotb/handle.py
+++ b/cocotb/handle.py
@@ -82,7 +82,7 @@
""" Query the simulator for a object with the specified name
and cache the result to build a tree
"""
- # python's builtin dir and IPython's dir2 search for these,
+ # python's builtin dir and IPython's dir2 search for these,
# raise an AttributeError to avoid incorrect calls to _raise_testerror
if name in ["__methods__","__members__","trait_names","_getAttributeNames"]:
raise AttributeError(name)
@@ -150,7 +150,7 @@
self.__getitem__(index).setcachedvalue(value)
def getvalue(self):
- result = BinaryValue()
+ result = BinaryValue(bits=len(self))
result.binstr = self._get_value_str()
return result
|
{"golden_diff": "diff --git a/cocotb/handle.py b/cocotb/handle.py\n--- a/cocotb/handle.py\n+++ b/cocotb/handle.py\n@@ -82,7 +82,7 @@\n \"\"\" Query the simulator for a object with the specified name\n and cache the result to build a tree\n \"\"\"\n- # python's builtin dir and IPython's dir2 search for these, \n+ # python's builtin dir and IPython's dir2 search for these,\n # raise an AttributeError to avoid incorrect calls to _raise_testerror\n if name in [\"__methods__\",\"__members__\",\"trait_names\",\"_getAttributeNames\"]:\n raise AttributeError(name)\n@@ -150,7 +150,7 @@\n self.__getitem__(index).setcachedvalue(value)\n \n def getvalue(self):\n- result = BinaryValue()\n+ result = BinaryValue(bits=len(self))\n result.binstr = self._get_value_str()\n return result\n", "issue": "getvalue() in handle.py should configure the returned Binary value\nWhen getting a value from a handle a \"BinaryValue()\" object is created. In my case, I tried to slice that value to get the upper bits, but the call failed because the returned value is not configured.\n\nI believe at a minimum, the Handle should set the number of bits, but ideally it would just configure everything the BinaryValue() object needs before returning it.\n\n", "before_files": [{"content": "#!/usr/bin/env python\n\n''' Copyright (c) 2013 Potential Ventures Ltd\nCopyright (c) 2013 SolarFlare Communications Inc\nAll rights reserved.\n\nRedistribution and use in source and binary forms, with or without\nmodification, are permitted provided that the following conditions are met:\n * Redistributions of source code must retain the above copyright\n notice, this list of conditions and the following disclaimer.\n * Redistributions in binary form must reproduce the above copyright\n notice, this list of conditions and the following disclaimer in the\n documentation and/or other materials provided with the distribution.\n * Neither the name of Potential Ventures Ltd,\n SolarFlare Communications Inc nor the\n names of its contributors may be used to endorse or promote products\n derived from this software without specific prior written permission.\n\nTHIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\" AND\nANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED\nWARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE\nDISCLAIMED. IN NO EVENT SHALL POTENTIAL VENTURES LTD BE LIABLE FOR ANY\nDIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES\n(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;\nLOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND\nON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS\nSOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. '''\n\n# -*- coding: utf-8 -*-\n\nimport logging\nimport ctypes\nimport traceback\nimport sys\n# from StringIO import StringIO\n\nfrom io import StringIO, BytesIO\n\nimport os\n\n# For autodocumentation don't need the extension modules\nif \"SPHINX_BUILD\" in os.environ:\n simulator = None\nelse:\n import simulator\n\nimport cocotb\nfrom cocotb.binary import BinaryValue\nfrom cocotb.log import SimLog\nfrom cocotb.result import TestError\nfrom cocotb.triggers import _RisingEdge, _FallingEdge\nfrom cocotb.utils import get_python_integer_types\n\n\nclass SimHandle(object):\n\n def __init__(self, handle):\n \"\"\"\n Args:\n _handle [integer] : vpi/vhpi handle to the simulator object\n \"\"\"\n self._handle = handle # handle used for future simulator transactions\n self._sub_handles = {} # Dict. of SimHandle objects created by getattr\n self._len = None\n\n self.name = simulator.get_name_string(self._handle)\n self.fullname = '%s(%s)' % (self.name,\n simulator.get_type_string(self._handle))\n self.log = SimLog('cocotb.' + self.name)\n self.log.debug(\"Created!\")\n self._r_edge = _RisingEdge(self)\n self._f_edge = _FallingEdge(self)\n\n def __hash__(self):\n return self._handle\n\n def __str__(self):\n return \"%s @0x%x\" % (self.name, self._handle)\n\n def __getattr__(self, name):\n \"\"\" Query the simulator for a object with the specified name\n and cache the result to build a tree\n \"\"\"\n # python's builtin dir and IPython's dir2 search for these, \n # raise an AttributeError to avoid incorrect calls to _raise_testerror\n if name in [\"__methods__\",\"__members__\",\"trait_names\",\"_getAttributeNames\"]:\n raise AttributeError(name)\n if name in self._sub_handles:\n return self._sub_handles[name]\n new_handle = simulator.get_handle_by_name(self._handle, name)\n if not new_handle:\n self._raise_testerror(\"%s contains no object named %s\" %\n (self.name, name))\n self._sub_handles[name] = SimHandle(new_handle)\n return self._sub_handles[name]\n\n def _raise_testerror(self, msg):\n lastframe = sys._getframe(2)\n if sys.version_info[0] >= 3:\n buff = StringIO()\n traceback.print_stack(lastframe, file=buff)\n else:\n buff_bytes = BytesIO()\n traceback.print_stack(lastframe, file=buff_bytes)\n buff = StringIO(buff_bytes.getvalue().decode(\"UTF8\"))\n self.log.error(\"%s\\n%s\" % (msg, buff.getvalue()))\n exception = TestError(msg)\n exception.stderr.write(buff.getvalue())\n buff.close()\n raise exception\n\n def __setattr__(self, name, value):\n \"\"\"Provide transparent access to signals\"\"\"\n if (not name.startswith('_') and\n not name in [\"name\", \"fullname\", \"log\", \"value\"] and\n self.__hasattr__(name)):\n getattr(self, name).setcachedvalue(value)\n return\n object.__setattr__(self, name, value)\n\n def __hasattr__(self, name):\n \"\"\"\n Since calling hasattr(handle, \"something\") will print out a\n backtrace to the log since usually attempting to access a\n non-existent member is an error we provide a 'peek function\n\n We still add the found handle to our dictionary to prevent leaking\n handles.\n \"\"\"\n if name in self._sub_handles:\n return self._sub_handles[name]\n new_handle = simulator.get_handle_by_name(self._handle, name)\n if new_handle:\n self._sub_handles[name] = SimHandle(new_handle)\n return new_handle\n\n def __getitem__(self, index):\n if index in self._sub_handles:\n return self._sub_handles[index]\n new_handle = simulator.get_handle_by_index(self._handle, index)\n if not new_handle:\n self._raise_testerror(\"%s contains no object at index %d\" %\n (self.name, index))\n self._sub_handles[index] = SimHandle(new_handle)\n return self._sub_handles[index]\n\n def __setitem__(self, index, value):\n \"\"\"Provide transparent assignment to bit index\"\"\"\n self.__getitem__(index).setcachedvalue(value)\n\n def getvalue(self):\n result = BinaryValue()\n result.binstr = self._get_value_str()\n return result\n\n def setimmediatevalue(self, value):\n \"\"\"\n Set the value of the underlying simulation object to value.\n\n Args:\n value (ctypes.Structure, cocotb.binary.BinaryValue, int)\n The value to drive onto the simulator object\n\n Raises:\n TypeError\n\n This operation will fail unless the handle refers to a modifiable\n object eg net, signal or variable.\n\n We determine the library call to make based on the type of the value\n\n Assigning integers less than 32-bits is faster\n \"\"\"\n if (isinstance(value, get_python_integer_types()) and\n value < 0x7fffffff):\n simulator.set_signal_val(self._handle, value)\n return\n\n if isinstance(value, ctypes.Structure):\n value = BinaryValue(value=cocotb.utils.pack(value), bits=len(self))\n elif isinstance(value, get_python_integer_types()):\n value = BinaryValue(value=value, bits=len(self), bigEndian=False)\n elif not isinstance(value, BinaryValue):\n self.log.critical(\"Unsupported type for value assignment: %s (%s)\"\n % (type(value), repr(value)))\n raise TypeError(\"Unable to set simulator value with type %s\" %\n (type(value)))\n\n simulator.set_signal_val_str(self._handle, value.binstr)\n\n def setcachedvalue(self, value):\n \"\"\"Intercept the store of a value and hold in cache.\n\n This operation is to enable all of the scheduled callbacks to completed\n with the same read data and for the writes to occour on the next\n sim time\"\"\"\n cocotb.scheduler.save_write(self, value)\n\n # We want to maintain compatability with python 2.5 so we can't use\n # @property with a setter\n value = property(getvalue, setcachedvalue, None,\n \"A reference to the value\")\n\n def _get_value_str(self):\n return simulator.get_signal_val(self._handle)\n\n def __le__(self, value):\n \"\"\"Overload the less than or equal to operator to\n provide an hdl-like shortcut\n module.signal <= 2\n \"\"\"\n self.value = value\n\n def __len__(self):\n \"\"\"Returns the 'length' of the underlying object.\n\n For vectors this is the number of bits.\n\n TODO: Handle other types (loops, generate etc)\n \"\"\"\n if self._len is None:\n self._len = len(self._get_value_str())\n return self._len\n\n def __cmp__(self, other):\n\n # Permits comparison of handles i.e. if clk == dut.clk\n if isinstance(other, SimHandle):\n if self._handle == other._handle:\n return 0\n return 1\n\n # Use the comparison method of the other object against our value\n return self.value.__cmp__(other)\n\n def __iter__(self):\n \"\"\"Iterates over all known types defined by simulator module\"\"\"\n for handle_type in [simulator.MODULE,\n simulator.PARAMETER,\n simulator.REG,\n simulator.NET,\n simulator.NETARRAY]:\n iterator = simulator.iterate(handle_type, self._handle)\n while True:\n try:\n thing = simulator.next(iterator)\n except StopIteration:\n break\n hdl = SimHandle(thing)\n self._sub_handles[hdl.name] = hdl\n yield hdl\n\n def __int__(self):\n return int(self.value)\n", "path": "cocotb/handle.py"}], "after_files": [{"content": "#!/usr/bin/env python\n\n''' Copyright (c) 2013 Potential Ventures Ltd\nCopyright (c) 2013 SolarFlare Communications Inc\nAll rights reserved.\n\nRedistribution and use in source and binary forms, with or without\nmodification, are permitted provided that the following conditions are met:\n * Redistributions of source code must retain the above copyright\n notice, this list of conditions and the following disclaimer.\n * Redistributions in binary form must reproduce the above copyright\n notice, this list of conditions and the following disclaimer in the\n documentation and/or other materials provided with the distribution.\n * Neither the name of Potential Ventures Ltd,\n SolarFlare Communications Inc nor the\n names of its contributors may be used to endorse or promote products\n derived from this software without specific prior written permission.\n\nTHIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\" AND\nANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED\nWARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE\nDISCLAIMED. IN NO EVENT SHALL POTENTIAL VENTURES LTD BE LIABLE FOR ANY\nDIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES\n(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;\nLOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND\nON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS\nSOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. '''\n\n# -*- coding: utf-8 -*-\n\nimport logging\nimport ctypes\nimport traceback\nimport sys\n# from StringIO import StringIO\n\nfrom io import StringIO, BytesIO\n\nimport os\n\n# For autodocumentation don't need the extension modules\nif \"SPHINX_BUILD\" in os.environ:\n simulator = None\nelse:\n import simulator\n\nimport cocotb\nfrom cocotb.binary import BinaryValue\nfrom cocotb.log import SimLog\nfrom cocotb.result import TestError\nfrom cocotb.triggers import _RisingEdge, _FallingEdge\nfrom cocotb.utils import get_python_integer_types\n\n\nclass SimHandle(object):\n\n def __init__(self, handle):\n \"\"\"\n Args:\n _handle [integer] : vpi/vhpi handle to the simulator object\n \"\"\"\n self._handle = handle # handle used for future simulator transactions\n self._sub_handles = {} # Dict. of SimHandle objects created by getattr\n self._len = None\n\n self.name = simulator.get_name_string(self._handle)\n self.fullname = '%s(%s)' % (self.name,\n simulator.get_type_string(self._handle))\n self.log = SimLog('cocotb.' + self.name)\n self.log.debug(\"Created!\")\n self._r_edge = _RisingEdge(self)\n self._f_edge = _FallingEdge(self)\n\n def __hash__(self):\n return self._handle\n\n def __str__(self):\n return \"%s @0x%x\" % (self.name, self._handle)\n\n def __getattr__(self, name):\n \"\"\" Query the simulator for a object with the specified name\n and cache the result to build a tree\n \"\"\"\n # python's builtin dir and IPython's dir2 search for these,\n # raise an AttributeError to avoid incorrect calls to _raise_testerror\n if name in [\"__methods__\",\"__members__\",\"trait_names\",\"_getAttributeNames\"]:\n raise AttributeError(name)\n if name in self._sub_handles:\n return self._sub_handles[name]\n new_handle = simulator.get_handle_by_name(self._handle, name)\n if not new_handle:\n self._raise_testerror(\"%s contains no object named %s\" %\n (self.name, name))\n self._sub_handles[name] = SimHandle(new_handle)\n return self._sub_handles[name]\n\n def _raise_testerror(self, msg):\n lastframe = sys._getframe(2)\n if sys.version_info[0] >= 3:\n buff = StringIO()\n traceback.print_stack(lastframe, file=buff)\n else:\n buff_bytes = BytesIO()\n traceback.print_stack(lastframe, file=buff_bytes)\n buff = StringIO(buff_bytes.getvalue().decode(\"UTF8\"))\n self.log.error(\"%s\\n%s\" % (msg, buff.getvalue()))\n exception = TestError(msg)\n exception.stderr.write(buff.getvalue())\n buff.close()\n raise exception\n\n def __setattr__(self, name, value):\n \"\"\"Provide transparent access to signals\"\"\"\n if (not name.startswith('_') and\n not name in [\"name\", \"fullname\", \"log\", \"value\"] and\n self.__hasattr__(name)):\n getattr(self, name).setcachedvalue(value)\n return\n object.__setattr__(self, name, value)\n\n def __hasattr__(self, name):\n \"\"\"\n Since calling hasattr(handle, \"something\") will print out a\n backtrace to the log since usually attempting to access a\n non-existent member is an error we provide a 'peek function\n\n We still add the found handle to our dictionary to prevent leaking\n handles.\n \"\"\"\n if name in self._sub_handles:\n return self._sub_handles[name]\n new_handle = simulator.get_handle_by_name(self._handle, name)\n if new_handle:\n self._sub_handles[name] = SimHandle(new_handle)\n return new_handle\n\n def __getitem__(self, index):\n if index in self._sub_handles:\n return self._sub_handles[index]\n new_handle = simulator.get_handle_by_index(self._handle, index)\n if not new_handle:\n self._raise_testerror(\"%s contains no object at index %d\" %\n (self.name, index))\n self._sub_handles[index] = SimHandle(new_handle)\n return self._sub_handles[index]\n\n def __setitem__(self, index, value):\n \"\"\"Provide transparent assignment to bit index\"\"\"\n self.__getitem__(index).setcachedvalue(value)\n\n def getvalue(self):\n result = BinaryValue(bits=len(self))\n result.binstr = self._get_value_str()\n return result\n\n def setimmediatevalue(self, value):\n \"\"\"\n Set the value of the underlying simulation object to value.\n\n Args:\n value (ctypes.Structure, cocotb.binary.BinaryValue, int)\n The value to drive onto the simulator object\n\n Raises:\n TypeError\n\n This operation will fail unless the handle refers to a modifiable\n object eg net, signal or variable.\n\n We determine the library call to make based on the type of the value\n\n Assigning integers less than 32-bits is faster\n \"\"\"\n if (isinstance(value, get_python_integer_types()) and\n value < 0x7fffffff):\n simulator.set_signal_val(self._handle, value)\n return\n\n if isinstance(value, ctypes.Structure):\n value = BinaryValue(value=cocotb.utils.pack(value), bits=len(self))\n elif isinstance(value, get_python_integer_types()):\n value = BinaryValue(value=value, bits=len(self), bigEndian=False)\n elif not isinstance(value, BinaryValue):\n self.log.critical(\"Unsupported type for value assignment: %s (%s)\"\n % (type(value), repr(value)))\n raise TypeError(\"Unable to set simulator value with type %s\" %\n (type(value)))\n\n simulator.set_signal_val_str(self._handle, value.binstr)\n\n def setcachedvalue(self, value):\n \"\"\"Intercept the store of a value and hold in cache.\n\n This operation is to enable all of the scheduled callbacks to completed\n with the same read data and for the writes to occour on the next\n sim time\"\"\"\n cocotb.scheduler.save_write(self, value)\n\n # We want to maintain compatability with python 2.5 so we can't use\n # @property with a setter\n value = property(getvalue, setcachedvalue, None,\n \"A reference to the value\")\n\n def _get_value_str(self):\n return simulator.get_signal_val(self._handle)\n\n def __le__(self, value):\n \"\"\"Overload the less than or equal to operator to\n provide an hdl-like shortcut\n module.signal <= 2\n \"\"\"\n self.value = value\n\n def __len__(self):\n \"\"\"Returns the 'length' of the underlying object.\n\n For vectors this is the number of bits.\n\n TODO: Handle other types (loops, generate etc)\n \"\"\"\n if self._len is None:\n self._len = len(self._get_value_str())\n return self._len\n\n def __cmp__(self, other):\n\n # Permits comparison of handles i.e. if clk == dut.clk\n if isinstance(other, SimHandle):\n if self._handle == other._handle:\n return 0\n return 1\n\n # Use the comparison method of the other object against our value\n return self.value.__cmp__(other)\n\n def __iter__(self):\n \"\"\"Iterates over all known types defined by simulator module\"\"\"\n for handle_type in [simulator.MODULE,\n simulator.PARAMETER,\n simulator.REG,\n simulator.NET,\n simulator.NETARRAY]:\n iterator = simulator.iterate(handle_type, self._handle)\n while True:\n try:\n thing = simulator.next(iterator)\n except StopIteration:\n break\n hdl = SimHandle(thing)\n self._sub_handles[hdl.name] = hdl\n yield hdl\n\n def __int__(self):\n return int(self.value)\n", "path": "cocotb/handle.py"}]}
| 3,088 | 217 |
gh_patches_debug_42228
|
rasdani/github-patches
|
git_diff
|
easybuilders__easybuild-framework-2474
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
GC3Pie backend submits jobs even if dependency build failed
When robot-building a bunch of software via the GC3Pie job backend with SLURM, GC3Pie happily submits follow-up jobs even if building of one (or more) of the dependencies failed. I am not entirely sure whether this is an issue in EasyBuild, in GC3Pie, or in the way the two are working together. I also don't know whether this also happens with other job schedulers.
Steps to reproduce:
- Start with an empty installdir
- Edit `M4-1.4.17.eb` and add `preconfigopts='false && '`
- Run `eb GCC-5.1.0.eb -r --job` using GC3Pie with SLURM
- Both jobs will be submitted, both fail (the first for obvious reasons, the second because the M4 module can't be found)
GC3Pie backend submits jobs even if dependency build failed
When robot-building a bunch of software via the GC3Pie job backend with SLURM, GC3Pie happily submits follow-up jobs even if building of one (or more) of the dependencies failed. I am not entirely sure whether this is an issue in EasyBuild, in GC3Pie, or in the way the two are working together. I also don't know whether this also happens with other job schedulers.
Steps to reproduce:
- Start with an empty installdir
- Edit `M4-1.4.17.eb` and add `preconfigopts='false && '`
- Run `eb GCC-5.1.0.eb -r --job` using GC3Pie with SLURM
- Both jobs will be submitted, both fail (the first for obvious reasons, the second because the M4 module can't be found)
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `easybuild/tools/job/gc3pie.py`
Content:
```
1 ##
2 # Copyright 2015-2018 Ghent University
3 # Copyright 2015 S3IT, University of Zurich
4 #
5 # This file is part of EasyBuild,
6 # originally created by the HPC team of Ghent University (http://ugent.be/hpc/en),
7 # with support of Ghent University (http://ugent.be/hpc),
8 # the Flemish Supercomputer Centre (VSC) (https://www.vscentrum.be),
9 # Flemish Research Foundation (FWO) (http://www.fwo.be/en)
10 # and the Department of Economy, Science and Innovation (EWI) (http://www.ewi-vlaanderen.be/en).
11 #
12 # https://github.com/easybuilders/easybuild
13 #
14 # EasyBuild is free software: you can redistribute it and/or modify
15 # it under the terms of the GNU General Public License as published by
16 # the Free Software Foundation v2.
17 #
18 # EasyBuild is distributed in the hope that it will be useful,
19 # but WITHOUT ANY WARRANTY; without even the implied warranty of
20 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 # GNU General Public License for more details.
22 #
23 # You should have received a copy of the GNU General Public License
24 # along with EasyBuild. If not, see <http://www.gnu.org/licenses/>.
25 ##
26 """
27 Interface for submitting jobs via GC3Pie.
28
29 :author: Riccardo Murri (University of Zurich)
30 :author: Kenneth Hoste (Ghent University)
31 """
32 from distutils.version import LooseVersion
33 from time import gmtime, strftime
34 import re
35 import time
36
37 from vsc.utils import fancylogger
38
39 from easybuild.tools.build_log import EasyBuildError, print_msg
40 from easybuild.tools.config import build_option
41 from easybuild.tools.job.backend import JobBackend
42 from easybuild.tools.utilities import only_if_module_is_available
43
44
45 _log = fancylogger.getLogger('gc3pie', fname=False)
46
47
48 try:
49 import gc3libs
50 import gc3libs.exceptions
51 from gc3libs import Application, Run, create_engine
52 from gc3libs.core import Engine
53 from gc3libs.quantity import hours as hr
54 from gc3libs.workflow import DependentTaskCollection
55
56 # inject EasyBuild logger into GC3Pie
57 gc3libs.log = fancylogger.getLogger('gc3pie', fname=False)
58 # make handling of log.error compatible with stdlib logging
59 gc3libs.log.raiseError = False
60
61 # instruct GC3Pie to not ignore errors, but raise exceptions instead
62 gc3libs.UNIGNORE_ALL_ERRORS = True
63
64 except ImportError as err:
65 _log.debug("Failed to import gc3libs from GC3Pie."
66 " Silently ignoring, this is a real issue only when GC3Pie is used as backend for --job")
67
68
69 # eb --job --job-backend=GC3Pie
70 class GC3Pie(JobBackend):
71 """
72 Use the GC3Pie framework to submit and monitor compilation jobs,
73 see http://gc3pie.readthedocs.org/.
74
75 In contrast with accessing an external service, GC3Pie implements
76 its own workflow manager, which means ``eb --job
77 --job-backend=GC3Pie`` will keep running until all jobs have
78 terminated.
79 """
80
81 REQ_VERSION = '2.4.0'
82 VERSION_REGEX = re.compile(r'^(?P<version>\S*) version')
83
84 @only_if_module_is_available('gc3libs', pkgname='gc3pie')
85 def __init__(self, *args, **kwargs):
86 """GC3Pie JobBackend constructor."""
87 super(GC3Pie, self).__init__(*args, **kwargs)
88
89 # _check_version is called by __init__, so guard it (too) with the decorator
90 @only_if_module_is_available('gc3libs', pkgname='gc3pie')
91 def _check_version(self):
92 """Check whether GC3Pie version complies with required version."""
93 # location of __version__ to use may change, depending on the minimal required SVN revision for development versions
94 version_str = gc3libs.core.__version__
95
96 match = self.VERSION_REGEX.search(version_str)
97 if match:
98 version = match.group('version')
99 self.log.debug("Parsed GC3Pie version info: '%s'", version)
100
101 if version == 'development':
102 # presume it's OK -- there's no way to check since GC3Pie switched to git
103 return True
104
105 if LooseVersion(version) < LooseVersion(self.REQ_VERSION):
106 raise EasyBuildError("Found GC3Pie version %s, but version %s or more recent is required",
107 version, self.REQ_VERSION)
108 else:
109 raise EasyBuildError("Failed to parse GC3Pie version string '%s' using pattern %s",
110 version_str, self.VERSION_REGEX.pattern)
111
112 def init(self):
113 """
114 Initialise the GC3Pie job backend.
115 """
116 # List of config files for GC3Pie; non-existing ones will be
117 # silently ignored. The list here copies GC3Pie's default,
118 # for the principle of minimal surprise, but there is no
119 # strict requirement that this be done and EB could actually
120 # choose to use a completely distinct set of conf. files.
121 self.config_files = gc3libs.Default.CONFIG_FILE_LOCATIONS[:]
122 cfgfile = build_option('job_backend_config')
123 if cfgfile:
124 self.config_files.append(cfgfile)
125
126 self.output_dir = build_option('job_output_dir')
127 self.jobs = DependentTaskCollection(output_dir=self.output_dir)
128 self.job_cnt = 0
129
130 # after polling for job status, sleep for this time duration
131 # before polling again (in seconds)
132 self.poll_interval = build_option('job_polling_interval')
133
134 def make_job(self, script, name, env_vars=None, hours=None, cores=None):
135 """
136 Create and return a job object with the given parameters.
137
138 First argument `server` is an instance of the corresponding
139 `JobBackend` class, i.e., a `GC3Pie`:class: instance in this case.
140
141 Second argument `script` is the content of the job script
142 itself, i.e., the sequence of shell commands that will be
143 executed.
144
145 Third argument `name` sets the job human-readable name.
146
147 Fourth (optional) argument `env_vars` is a dictionary with
148 key-value pairs of environment variables that should be passed
149 on to the job.
150
151 Fifth and sixth (optional) arguments `hours` and `cores` should be
152 integer values:
153 * hours must be in the range 1 .. MAX_WALLTIME;
154 * cores depends on which cluster the job is being run.
155 """
156 named_args = {
157 'jobname': name, # job name in GC3Pie
158 'name': name, # job name in EasyBuild
159 }
160
161 # environment
162 if env_vars:
163 named_args['environment'] = env_vars
164
165 # input/output files for job (none)
166 named_args['inputs'] = []
167 named_args['outputs'] = []
168
169 # job logs
170 named_args.update({
171 # join stdout/stderr in a single log
172 'join': True,
173 # location for log file
174 'output_dir': self.output_dir,
175 # log file name (including timestamp to try and ensure unique filename)
176 'stdout': 'eb-%s-gc3pie-job-%s.log' % (name, strftime("%Y%M%d-UTC-%H-%M-%S", gmtime()))
177 })
178
179 # walltime
180 max_walltime = build_option('job_max_walltime')
181 if hours is None:
182 hours = max_walltime
183 if hours > max_walltime:
184 self.log.warn("Specified %s hours, but this is impossible. (resetting to %s hours)" % (hours, max_walltime))
185 hours = max_walltime
186 named_args['requested_walltime'] = hours * hr
187
188 if cores:
189 named_args['requested_cores'] = cores
190 else:
191 self.log.warn("Number of cores to request not specified, falling back to whatever GC3Pie does by default")
192
193 return Application(['/bin/sh', '-c', script], **named_args)
194
195 def queue(self, job, dependencies=frozenset()):
196 """
197 Add a job to the queue, optionally specifying dependencies.
198
199 :param dependencies: jobs on which this job depends.
200 """
201 self.jobs.add(job, dependencies)
202 # since it's not trivial to determine the correct job count from self.jobs, we keep track of a count ourselves
203 self.job_cnt += 1
204
205 def complete(self):
206 """
207 Complete a bulk job submission.
208
209 Create engine, and progress it until all jobs have terminated.
210 """
211 # create an instance of `Engine` using the list of configuration files
212 try:
213 self._engine = create_engine(*self.config_files, resource_errors_are_fatal=True)
214
215 except gc3libs.exceptions.Error as err:
216 raise EasyBuildError("Failed to create GC3Pie engine: %s", err)
217
218 # make sure that all job log files end up in the same directory, rather than renaming the output directory
219 # see https://gc3pie.readthedocs.org/en/latest/programmers/api/gc3libs/core.html#gc3libs.core.Engine
220 self._engine.retrieve_overwrites = True
221
222 # some sites may not be happy with flooding the cluster with build jobs...
223 self._engine.max_in_flight = build_option('job_max_jobs')
224
225 # `Engine.stats()` (which is used later on in `_print_status_report()`)
226 # changed between 2.4.2 and 2.5.0.dev -- make sure we stay compatible
227 # with both
228 try:
229 self._engine.init_stats_for(Application)
230 except AttributeError:
231 _log.debug("No `init_stats_for` method in the Engine class;"
232 " assuming pre-2.5.0 GC3Pie and ignoring error.")
233
234 # Add your application to the engine. This will NOT submit
235 # your application yet, but will make the engine *aware* of
236 # the application.
237 self._engine.add(self.jobs)
238
239 # in case you want to select a specific resource, call
240 target_resource = build_option('job_target_resource')
241 if target_resource:
242 res = self._engine.select_resource(target_resource)
243 if res == 0:
244 raise EasyBuildError("Failed to select target resource '%s' in GC3Pie", target_resource)
245
246 # Periodically check the status of your application.
247 while self.jobs.execution.state != Run.State.TERMINATED:
248 # `Engine.progress()` will do the GC3Pie magic:
249 # submit new jobs, update status of submitted jobs, get
250 # results of terminating jobs etc...
251 self._engine.progress()
252
253 # report progress
254 self._print_status_report()
255
256 # Wait a few seconds...
257 time.sleep(self.poll_interval)
258
259 # final status report
260 print_msg("Done processing jobs", log=self.log, silent=build_option('silent'))
261 self._print_status_report()
262
263 def _print_status_report(self):
264 """
265 Print a job status report to STDOUT and the log file.
266
267 The number of jobs in each state is reported; the
268 figures are extracted from the `stats()` method of the
269 currently-running GC3Pie engine.
270 """
271 stats = self._engine.stats(only=Application)
272 states = ', '.join(["%d %s" % (stats[s], s.lower()) for s in stats if s != 'total' and stats[s]])
273 print_msg("GC3Pie job overview: %s (total: %s)" % (states, self.job_cnt),
274 log=self.log, silent=build_option('silent'))
275
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/easybuild/tools/job/gc3pie.py b/easybuild/tools/job/gc3pie.py
--- a/easybuild/tools/job/gc3pie.py
+++ b/easybuild/tools/job/gc3pie.py
@@ -51,7 +51,7 @@
from gc3libs import Application, Run, create_engine
from gc3libs.core import Engine
from gc3libs.quantity import hours as hr
- from gc3libs.workflow import DependentTaskCollection
+ from gc3libs.workflow import AbortOnError, DependentTaskCollection
# inject EasyBuild logger into GC3Pie
gc3libs.log = fancylogger.getLogger('gc3pie', fname=False)
@@ -61,6 +61,16 @@
# instruct GC3Pie to not ignore errors, but raise exceptions instead
gc3libs.UNIGNORE_ALL_ERRORS = True
+ # note: order of class inheritance is important!
+ class _BuildTaskCollection(AbortOnError, DependentTaskCollection):
+ """
+ A `DependentTaskCollection`:class: that aborts execution upon error.
+
+ This is used to stop the build process in case some dependency
+ fails. See also `<https://github.com/easybuilders/easybuild-framework/issues/1441>`_
+ """
+ pass
+
except ImportError as err:
_log.debug("Failed to import gc3libs from GC3Pie."
" Silently ignoring, this is a real issue only when GC3Pie is used as backend for --job")
@@ -124,7 +134,7 @@
self.config_files.append(cfgfile)
self.output_dir = build_option('job_output_dir')
- self.jobs = DependentTaskCollection(output_dir=self.output_dir)
+ self.jobs = _BuildTaskCollection(output_dir=self.output_dir)
self.job_cnt = 0
# after polling for job status, sleep for this time duration
@@ -135,23 +145,20 @@
"""
Create and return a job object with the given parameters.
- First argument `server` is an instance of the corresponding
- `JobBackend` class, i.e., a `GC3Pie`:class: instance in this case.
-
- Second argument `script` is the content of the job script
+ Argument *script* is the content of the job script
itself, i.e., the sequence of shell commands that will be
executed.
- Third argument `name` sets the job human-readable name.
+ Argument *name* sets the job's human-readable name.
- Fourth (optional) argument `env_vars` is a dictionary with
+ Optional argument *env_vars* is a dictionary with
key-value pairs of environment variables that should be passed
on to the job.
- Fifth and sixth (optional) arguments `hours` and `cores` should be
+ Optional arguments *hours* and *cores* should be
integer values:
- * hours must be in the range 1 .. MAX_WALLTIME;
- * cores depends on which cluster the job is being run.
+ - *hours* must be in the range 1 .. ``MAX_WALLTIME``;
+ - *cores* depends on which cluster the job is being run.
"""
named_args = {
'jobname': name, # job name in GC3Pie
@@ -236,7 +243,7 @@
# the application.
self._engine.add(self.jobs)
- # in case you want to select a specific resource, call
+ # select a specific execution resource?
target_resource = build_option('job_target_resource')
if target_resource:
res = self._engine.select_resource(target_resource)
|
{"golden_diff": "diff --git a/easybuild/tools/job/gc3pie.py b/easybuild/tools/job/gc3pie.py\n--- a/easybuild/tools/job/gc3pie.py\n+++ b/easybuild/tools/job/gc3pie.py\n@@ -51,7 +51,7 @@\n from gc3libs import Application, Run, create_engine\n from gc3libs.core import Engine\n from gc3libs.quantity import hours as hr\n- from gc3libs.workflow import DependentTaskCollection\n+ from gc3libs.workflow import AbortOnError, DependentTaskCollection\n \n # inject EasyBuild logger into GC3Pie\n gc3libs.log = fancylogger.getLogger('gc3pie', fname=False)\n@@ -61,6 +61,16 @@\n # instruct GC3Pie to not ignore errors, but raise exceptions instead\n gc3libs.UNIGNORE_ALL_ERRORS = True\n \n+ # note: order of class inheritance is important!\n+ class _BuildTaskCollection(AbortOnError, DependentTaskCollection):\n+ \"\"\"\n+ A `DependentTaskCollection`:class: that aborts execution upon error.\n+\n+ This is used to stop the build process in case some dependency\n+ fails. See also `<https://github.com/easybuilders/easybuild-framework/issues/1441>`_\n+ \"\"\"\n+ pass\n+\n except ImportError as err:\n _log.debug(\"Failed to import gc3libs from GC3Pie.\"\n \" Silently ignoring, this is a real issue only when GC3Pie is used as backend for --job\")\n@@ -124,7 +134,7 @@\n self.config_files.append(cfgfile)\n \n self.output_dir = build_option('job_output_dir')\n- self.jobs = DependentTaskCollection(output_dir=self.output_dir)\n+ self.jobs = _BuildTaskCollection(output_dir=self.output_dir)\n self.job_cnt = 0\n \n # after polling for job status, sleep for this time duration\n@@ -135,23 +145,20 @@\n \"\"\"\n Create and return a job object with the given parameters.\n \n- First argument `server` is an instance of the corresponding\n- `JobBackend` class, i.e., a `GC3Pie`:class: instance in this case.\n-\n- Second argument `script` is the content of the job script\n+ Argument *script* is the content of the job script\n itself, i.e., the sequence of shell commands that will be\n executed.\n \n- Third argument `name` sets the job human-readable name.\n+ Argument *name* sets the job's human-readable name.\n \n- Fourth (optional) argument `env_vars` is a dictionary with\n+ Optional argument *env_vars* is a dictionary with\n key-value pairs of environment variables that should be passed\n on to the job.\n \n- Fifth and sixth (optional) arguments `hours` and `cores` should be\n+ Optional arguments *hours* and *cores* should be\n integer values:\n- * hours must be in the range 1 .. MAX_WALLTIME;\n- * cores depends on which cluster the job is being run.\n+ - *hours* must be in the range 1 .. ``MAX_WALLTIME``;\n+ - *cores* depends on which cluster the job is being run.\n \"\"\"\n named_args = {\n 'jobname': name, # job name in GC3Pie\n@@ -236,7 +243,7 @@\n # the application.\n self._engine.add(self.jobs)\n \n- # in case you want to select a specific resource, call\n+ # select a specific execution resource?\n target_resource = build_option('job_target_resource')\n if target_resource:\n res = self._engine.select_resource(target_resource)\n", "issue": "GC3Pie backend submits jobs even if dependency build failed\nWhen robot-building a bunch of software via the GC3Pie job backend with SLURM, GC3Pie happily submits follow-up jobs even if building of one (or more) of the dependencies failed. I am not entirely sure whether this is an issue in EasyBuild, in GC3Pie, or in the way the two are working together. I also don't know whether this also happens with other job schedulers.\n\nSteps to reproduce:\n- Start with an empty installdir\n- Edit `M4-1.4.17.eb` and add `preconfigopts='false && '`\n- Run `eb GCC-5.1.0.eb -r --job` using GC3Pie with SLURM\n- Both jobs will be submitted, both fail (the first for obvious reasons, the second because the M4 module can't be found)\n\nGC3Pie backend submits jobs even if dependency build failed\nWhen robot-building a bunch of software via the GC3Pie job backend with SLURM, GC3Pie happily submits follow-up jobs even if building of one (or more) of the dependencies failed. I am not entirely sure whether this is an issue in EasyBuild, in GC3Pie, or in the way the two are working together. I also don't know whether this also happens with other job schedulers.\n\nSteps to reproduce:\n- Start with an empty installdir\n- Edit `M4-1.4.17.eb` and add `preconfigopts='false && '`\n- Run `eb GCC-5.1.0.eb -r --job` using GC3Pie with SLURM\n- Both jobs will be submitted, both fail (the first for obvious reasons, the second because the M4 module can't be found)\n\n", "before_files": [{"content": "##\n# Copyright 2015-2018 Ghent University\n# Copyright 2015 S3IT, University of Zurich\n#\n# This file is part of EasyBuild,\n# originally created by the HPC team of Ghent University (http://ugent.be/hpc/en),\n# with support of Ghent University (http://ugent.be/hpc),\n# the Flemish Supercomputer Centre (VSC) (https://www.vscentrum.be),\n# Flemish Research Foundation (FWO) (http://www.fwo.be/en)\n# and the Department of Economy, Science and Innovation (EWI) (http://www.ewi-vlaanderen.be/en).\n#\n# https://github.com/easybuilders/easybuild\n#\n# EasyBuild is free software: you can redistribute it and/or modify\n# it under the terms of the GNU General Public License as published by\n# the Free Software Foundation v2.\n#\n# EasyBuild is distributed in the hope that it will be useful,\n# but WITHOUT ANY WARRANTY; without even the implied warranty of\n# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n# GNU General Public License for more details.\n#\n# You should have received a copy of the GNU General Public License\n# along with EasyBuild. If not, see <http://www.gnu.org/licenses/>.\n##\n\"\"\"\nInterface for submitting jobs via GC3Pie.\n\n:author: Riccardo Murri (University of Zurich)\n:author: Kenneth Hoste (Ghent University)\n\"\"\"\nfrom distutils.version import LooseVersion\nfrom time import gmtime, strftime\nimport re\nimport time\n\nfrom vsc.utils import fancylogger\n\nfrom easybuild.tools.build_log import EasyBuildError, print_msg\nfrom easybuild.tools.config import build_option\nfrom easybuild.tools.job.backend import JobBackend\nfrom easybuild.tools.utilities import only_if_module_is_available\n\n\n_log = fancylogger.getLogger('gc3pie', fname=False)\n\n\ntry:\n import gc3libs\n import gc3libs.exceptions\n from gc3libs import Application, Run, create_engine\n from gc3libs.core import Engine\n from gc3libs.quantity import hours as hr\n from gc3libs.workflow import DependentTaskCollection\n\n # inject EasyBuild logger into GC3Pie\n gc3libs.log = fancylogger.getLogger('gc3pie', fname=False)\n # make handling of log.error compatible with stdlib logging\n gc3libs.log.raiseError = False\n\n # instruct GC3Pie to not ignore errors, but raise exceptions instead\n gc3libs.UNIGNORE_ALL_ERRORS = True\n\nexcept ImportError as err:\n _log.debug(\"Failed to import gc3libs from GC3Pie.\"\n \" Silently ignoring, this is a real issue only when GC3Pie is used as backend for --job\")\n\n\n# eb --job --job-backend=GC3Pie\nclass GC3Pie(JobBackend):\n \"\"\"\n Use the GC3Pie framework to submit and monitor compilation jobs,\n see http://gc3pie.readthedocs.org/.\n\n In contrast with accessing an external service, GC3Pie implements\n its own workflow manager, which means ``eb --job\n --job-backend=GC3Pie`` will keep running until all jobs have\n terminated.\n \"\"\"\n\n REQ_VERSION = '2.4.0'\n VERSION_REGEX = re.compile(r'^(?P<version>\\S*) version')\n\n @only_if_module_is_available('gc3libs', pkgname='gc3pie')\n def __init__(self, *args, **kwargs):\n \"\"\"GC3Pie JobBackend constructor.\"\"\"\n super(GC3Pie, self).__init__(*args, **kwargs)\n\n # _check_version is called by __init__, so guard it (too) with the decorator\n @only_if_module_is_available('gc3libs', pkgname='gc3pie')\n def _check_version(self):\n \"\"\"Check whether GC3Pie version complies with required version.\"\"\"\n # location of __version__ to use may change, depending on the minimal required SVN revision for development versions\n version_str = gc3libs.core.__version__\n\n match = self.VERSION_REGEX.search(version_str)\n if match:\n version = match.group('version')\n self.log.debug(\"Parsed GC3Pie version info: '%s'\", version)\n\n if version == 'development':\n # presume it's OK -- there's no way to check since GC3Pie switched to git\n return True\n\n if LooseVersion(version) < LooseVersion(self.REQ_VERSION):\n raise EasyBuildError(\"Found GC3Pie version %s, but version %s or more recent is required\",\n version, self.REQ_VERSION)\n else:\n raise EasyBuildError(\"Failed to parse GC3Pie version string '%s' using pattern %s\",\n version_str, self.VERSION_REGEX.pattern)\n\n def init(self):\n \"\"\"\n Initialise the GC3Pie job backend.\n \"\"\"\n # List of config files for GC3Pie; non-existing ones will be\n # silently ignored. The list here copies GC3Pie's default,\n # for the principle of minimal surprise, but there is no\n # strict requirement that this be done and EB could actually\n # choose to use a completely distinct set of conf. files.\n self.config_files = gc3libs.Default.CONFIG_FILE_LOCATIONS[:]\n cfgfile = build_option('job_backend_config')\n if cfgfile:\n self.config_files.append(cfgfile)\n\n self.output_dir = build_option('job_output_dir')\n self.jobs = DependentTaskCollection(output_dir=self.output_dir)\n self.job_cnt = 0\n\n # after polling for job status, sleep for this time duration\n # before polling again (in seconds)\n self.poll_interval = build_option('job_polling_interval')\n\n def make_job(self, script, name, env_vars=None, hours=None, cores=None):\n \"\"\"\n Create and return a job object with the given parameters.\n\n First argument `server` is an instance of the corresponding\n `JobBackend` class, i.e., a `GC3Pie`:class: instance in this case.\n\n Second argument `script` is the content of the job script\n itself, i.e., the sequence of shell commands that will be\n executed.\n\n Third argument `name` sets the job human-readable name.\n\n Fourth (optional) argument `env_vars` is a dictionary with\n key-value pairs of environment variables that should be passed\n on to the job.\n\n Fifth and sixth (optional) arguments `hours` and `cores` should be\n integer values:\n * hours must be in the range 1 .. MAX_WALLTIME;\n * cores depends on which cluster the job is being run.\n \"\"\"\n named_args = {\n 'jobname': name, # job name in GC3Pie\n 'name': name, # job name in EasyBuild\n }\n\n # environment\n if env_vars:\n named_args['environment'] = env_vars\n\n # input/output files for job (none)\n named_args['inputs'] = []\n named_args['outputs'] = []\n\n # job logs\n named_args.update({\n # join stdout/stderr in a single log\n 'join': True,\n # location for log file\n 'output_dir': self.output_dir,\n # log file name (including timestamp to try and ensure unique filename)\n 'stdout': 'eb-%s-gc3pie-job-%s.log' % (name, strftime(\"%Y%M%d-UTC-%H-%M-%S\", gmtime()))\n })\n\n # walltime\n max_walltime = build_option('job_max_walltime')\n if hours is None:\n hours = max_walltime\n if hours > max_walltime:\n self.log.warn(\"Specified %s hours, but this is impossible. (resetting to %s hours)\" % (hours, max_walltime))\n hours = max_walltime\n named_args['requested_walltime'] = hours * hr\n\n if cores:\n named_args['requested_cores'] = cores\n else:\n self.log.warn(\"Number of cores to request not specified, falling back to whatever GC3Pie does by default\")\n\n return Application(['/bin/sh', '-c', script], **named_args)\n\n def queue(self, job, dependencies=frozenset()):\n \"\"\"\n Add a job to the queue, optionally specifying dependencies.\n\n :param dependencies: jobs on which this job depends.\n \"\"\"\n self.jobs.add(job, dependencies)\n # since it's not trivial to determine the correct job count from self.jobs, we keep track of a count ourselves\n self.job_cnt += 1\n\n def complete(self):\n \"\"\"\n Complete a bulk job submission.\n\n Create engine, and progress it until all jobs have terminated.\n \"\"\"\n # create an instance of `Engine` using the list of configuration files\n try:\n self._engine = create_engine(*self.config_files, resource_errors_are_fatal=True)\n\n except gc3libs.exceptions.Error as err:\n raise EasyBuildError(\"Failed to create GC3Pie engine: %s\", err)\n\n # make sure that all job log files end up in the same directory, rather than renaming the output directory\n # see https://gc3pie.readthedocs.org/en/latest/programmers/api/gc3libs/core.html#gc3libs.core.Engine\n self._engine.retrieve_overwrites = True\n\n # some sites may not be happy with flooding the cluster with build jobs...\n self._engine.max_in_flight = build_option('job_max_jobs')\n\n # `Engine.stats()` (which is used later on in `_print_status_report()`)\n # changed between 2.4.2 and 2.5.0.dev -- make sure we stay compatible\n # with both\n try:\n self._engine.init_stats_for(Application)\n except AttributeError:\n _log.debug(\"No `init_stats_for` method in the Engine class;\"\n \" assuming pre-2.5.0 GC3Pie and ignoring error.\")\n\n # Add your application to the engine. This will NOT submit\n # your application yet, but will make the engine *aware* of\n # the application.\n self._engine.add(self.jobs)\n\n # in case you want to select a specific resource, call\n target_resource = build_option('job_target_resource')\n if target_resource:\n res = self._engine.select_resource(target_resource)\n if res == 0:\n raise EasyBuildError(\"Failed to select target resource '%s' in GC3Pie\", target_resource)\n\n # Periodically check the status of your application.\n while self.jobs.execution.state != Run.State.TERMINATED:\n # `Engine.progress()` will do the GC3Pie magic:\n # submit new jobs, update status of submitted jobs, get\n # results of terminating jobs etc...\n self._engine.progress()\n\n # report progress\n self._print_status_report()\n\n # Wait a few seconds...\n time.sleep(self.poll_interval)\n\n # final status report\n print_msg(\"Done processing jobs\", log=self.log, silent=build_option('silent'))\n self._print_status_report()\n\n def _print_status_report(self):\n \"\"\"\n Print a job status report to STDOUT and the log file.\n\n The number of jobs in each state is reported; the\n figures are extracted from the `stats()` method of the\n currently-running GC3Pie engine.\n \"\"\"\n stats = self._engine.stats(only=Application)\n states = ', '.join([\"%d %s\" % (stats[s], s.lower()) for s in stats if s != 'total' and stats[s]])\n print_msg(\"GC3Pie job overview: %s (total: %s)\" % (states, self.job_cnt),\n log=self.log, silent=build_option('silent'))\n", "path": "easybuild/tools/job/gc3pie.py"}], "after_files": [{"content": "##\n# Copyright 2015-2018 Ghent University\n# Copyright 2015 S3IT, University of Zurich\n#\n# This file is part of EasyBuild,\n# originally created by the HPC team of Ghent University (http://ugent.be/hpc/en),\n# with support of Ghent University (http://ugent.be/hpc),\n# the Flemish Supercomputer Centre (VSC) (https://www.vscentrum.be),\n# Flemish Research Foundation (FWO) (http://www.fwo.be/en)\n# and the Department of Economy, Science and Innovation (EWI) (http://www.ewi-vlaanderen.be/en).\n#\n# https://github.com/easybuilders/easybuild\n#\n# EasyBuild is free software: you can redistribute it and/or modify\n# it under the terms of the GNU General Public License as published by\n# the Free Software Foundation v2.\n#\n# EasyBuild is distributed in the hope that it will be useful,\n# but WITHOUT ANY WARRANTY; without even the implied warranty of\n# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n# GNU General Public License for more details.\n#\n# You should have received a copy of the GNU General Public License\n# along with EasyBuild. If not, see <http://www.gnu.org/licenses/>.\n##\n\"\"\"\nInterface for submitting jobs via GC3Pie.\n\n:author: Riccardo Murri (University of Zurich)\n:author: Kenneth Hoste (Ghent University)\n\"\"\"\nfrom distutils.version import LooseVersion\nfrom time import gmtime, strftime\nimport re\nimport time\n\nfrom vsc.utils import fancylogger\n\nfrom easybuild.tools.build_log import EasyBuildError, print_msg\nfrom easybuild.tools.config import build_option\nfrom easybuild.tools.job.backend import JobBackend\nfrom easybuild.tools.utilities import only_if_module_is_available\n\n\n_log = fancylogger.getLogger('gc3pie', fname=False)\n\n\ntry:\n import gc3libs\n import gc3libs.exceptions\n from gc3libs import Application, Run, create_engine\n from gc3libs.core import Engine\n from gc3libs.quantity import hours as hr\n from gc3libs.workflow import AbortOnError, DependentTaskCollection\n\n # inject EasyBuild logger into GC3Pie\n gc3libs.log = fancylogger.getLogger('gc3pie', fname=False)\n # make handling of log.error compatible with stdlib logging\n gc3libs.log.raiseError = False\n\n # instruct GC3Pie to not ignore errors, but raise exceptions instead\n gc3libs.UNIGNORE_ALL_ERRORS = True\n\n # note: order of class inheritance is important!\n class _BuildTaskCollection(AbortOnError, DependentTaskCollection):\n \"\"\"\n A `DependentTaskCollection`:class: that aborts execution upon error.\n\n This is used to stop the build process in case some dependency\n fails. See also `<https://github.com/easybuilders/easybuild-framework/issues/1441>`_\n \"\"\"\n pass\n\nexcept ImportError as err:\n _log.debug(\"Failed to import gc3libs from GC3Pie.\"\n \" Silently ignoring, this is a real issue only when GC3Pie is used as backend for --job\")\n\n\n# eb --job --job-backend=GC3Pie\nclass GC3Pie(JobBackend):\n \"\"\"\n Use the GC3Pie framework to submit and monitor compilation jobs,\n see http://gc3pie.readthedocs.org/.\n\n In contrast with accessing an external service, GC3Pie implements\n its own workflow manager, which means ``eb --job\n --job-backend=GC3Pie`` will keep running until all jobs have\n terminated.\n \"\"\"\n\n REQ_VERSION = '2.4.0'\n VERSION_REGEX = re.compile(r'^(?P<version>\\S*) version')\n\n @only_if_module_is_available('gc3libs', pkgname='gc3pie')\n def __init__(self, *args, **kwargs):\n \"\"\"GC3Pie JobBackend constructor.\"\"\"\n super(GC3Pie, self).__init__(*args, **kwargs)\n\n # _check_version is called by __init__, so guard it (too) with the decorator\n @only_if_module_is_available('gc3libs', pkgname='gc3pie')\n def _check_version(self):\n \"\"\"Check whether GC3Pie version complies with required version.\"\"\"\n # location of __version__ to use may change, depending on the minimal required SVN revision for development versions\n version_str = gc3libs.core.__version__\n\n match = self.VERSION_REGEX.search(version_str)\n if match:\n version = match.group('version')\n self.log.debug(\"Parsed GC3Pie version info: '%s'\", version)\n\n if version == 'development':\n # presume it's OK -- there's no way to check since GC3Pie switched to git\n return True\n\n if LooseVersion(version) < LooseVersion(self.REQ_VERSION):\n raise EasyBuildError(\"Found GC3Pie version %s, but version %s or more recent is required\",\n version, self.REQ_VERSION)\n else:\n raise EasyBuildError(\"Failed to parse GC3Pie version string '%s' using pattern %s\",\n version_str, self.VERSION_REGEX.pattern)\n\n def init(self):\n \"\"\"\n Initialise the GC3Pie job backend.\n \"\"\"\n # List of config files for GC3Pie; non-existing ones will be\n # silently ignored. The list here copies GC3Pie's default,\n # for the principle of minimal surprise, but there is no\n # strict requirement that this be done and EB could actually\n # choose to use a completely distinct set of conf. files.\n self.config_files = gc3libs.Default.CONFIG_FILE_LOCATIONS[:]\n cfgfile = build_option('job_backend_config')\n if cfgfile:\n self.config_files.append(cfgfile)\n\n self.output_dir = build_option('job_output_dir')\n self.jobs = _BuildTaskCollection(output_dir=self.output_dir)\n self.job_cnt = 0\n\n # after polling for job status, sleep for this time duration\n # before polling again (in seconds)\n self.poll_interval = build_option('job_polling_interval')\n\n def make_job(self, script, name, env_vars=None, hours=None, cores=None):\n \"\"\"\n Create and return a job object with the given parameters.\n\n Argument *script* is the content of the job script\n itself, i.e., the sequence of shell commands that will be\n executed.\n\n Argument *name* sets the job's human-readable name.\n\n Optional argument *env_vars* is a dictionary with\n key-value pairs of environment variables that should be passed\n on to the job.\n\n Optional arguments *hours* and *cores* should be\n integer values:\n - *hours* must be in the range 1 .. ``MAX_WALLTIME``;\n - *cores* depends on which cluster the job is being run.\n \"\"\"\n named_args = {\n 'jobname': name, # job name in GC3Pie\n 'name': name, # job name in EasyBuild\n }\n\n # environment\n if env_vars:\n named_args['environment'] = env_vars\n\n # input/output files for job (none)\n named_args['inputs'] = []\n named_args['outputs'] = []\n\n # job logs\n named_args.update({\n # join stdout/stderr in a single log\n 'join': True,\n # location for log file\n 'output_dir': self.output_dir,\n # log file name (including timestamp to try and ensure unique filename)\n 'stdout': 'eb-%s-gc3pie-job-%s.log' % (name, strftime(\"%Y%M%d-UTC-%H-%M-%S\", gmtime()))\n })\n\n # walltime\n max_walltime = build_option('job_max_walltime')\n if hours is None:\n hours = max_walltime\n if hours > max_walltime:\n self.log.warn(\"Specified %s hours, but this is impossible. (resetting to %s hours)\" % (hours, max_walltime))\n hours = max_walltime\n named_args['requested_walltime'] = hours * hr\n\n if cores:\n named_args['requested_cores'] = cores\n else:\n self.log.warn(\"Number of cores to request not specified, falling back to whatever GC3Pie does by default\")\n\n return Application(['/bin/sh', '-c', script], **named_args)\n\n def queue(self, job, dependencies=frozenset()):\n \"\"\"\n Add a job to the queue, optionally specifying dependencies.\n\n :param dependencies: jobs on which this job depends.\n \"\"\"\n self.jobs.add(job, dependencies)\n # since it's not trivial to determine the correct job count from self.jobs, we keep track of a count ourselves\n self.job_cnt += 1\n\n def complete(self):\n \"\"\"\n Complete a bulk job submission.\n\n Create engine, and progress it until all jobs have terminated.\n \"\"\"\n # create an instance of `Engine` using the list of configuration files\n try:\n self._engine = create_engine(*self.config_files, resource_errors_are_fatal=True)\n\n except gc3libs.exceptions.Error as err:\n raise EasyBuildError(\"Failed to create GC3Pie engine: %s\", err)\n\n # make sure that all job log files end up in the same directory, rather than renaming the output directory\n # see https://gc3pie.readthedocs.org/en/latest/programmers/api/gc3libs/core.html#gc3libs.core.Engine\n self._engine.retrieve_overwrites = True\n\n # some sites may not be happy with flooding the cluster with build jobs...\n self._engine.max_in_flight = build_option('job_max_jobs')\n\n # `Engine.stats()` (which is used later on in `_print_status_report()`)\n # changed between 2.4.2 and 2.5.0.dev -- make sure we stay compatible\n # with both\n try:\n self._engine.init_stats_for(Application)\n except AttributeError:\n _log.debug(\"No `init_stats_for` method in the Engine class;\"\n \" assuming pre-2.5.0 GC3Pie and ignoring error.\")\n\n # Add your application to the engine. This will NOT submit\n # your application yet, but will make the engine *aware* of\n # the application.\n self._engine.add(self.jobs)\n\n # select a specific execution resource?\n target_resource = build_option('job_target_resource')\n if target_resource:\n res = self._engine.select_resource(target_resource)\n if res == 0:\n raise EasyBuildError(\"Failed to select target resource '%s' in GC3Pie\", target_resource)\n\n # Periodically check the status of your application.\n while self.jobs.execution.state != Run.State.TERMINATED:\n # `Engine.progress()` will do the GC3Pie magic:\n # submit new jobs, update status of submitted jobs, get\n # results of terminating jobs etc...\n self._engine.progress()\n\n # report progress\n self._print_status_report()\n\n # Wait a few seconds...\n time.sleep(self.poll_interval)\n\n # final status report\n print_msg(\"Done processing jobs\", log=self.log, silent=build_option('silent'))\n self._print_status_report()\n\n def _print_status_report(self):\n \"\"\"\n Print a job status report to STDOUT and the log file.\n\n The number of jobs in each state is reported; the\n figures are extracted from the `stats()` method of the\n currently-running GC3Pie engine.\n \"\"\"\n stats = self._engine.stats(only=Application)\n states = ', '.join([\"%d %s\" % (stats[s], s.lower()) for s in stats if s != 'total' and stats[s]])\n print_msg(\"GC3Pie job overview: %s (total: %s)\" % (states, self.job_cnt),\n log=self.log, silent=build_option('silent'))\n", "path": "easybuild/tools/job/gc3pie.py"}]}
| 3,914 | 826 |
gh_patches_debug_20978
|
rasdani/github-patches
|
git_diff
|
python-poetry__poetry-1635
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
1.0.0b5 removes my private source from the lockfile
<!--
Hi there! Thank you for discovering and submitting an issue.
Before you submit this; let's make sure of a few things.
Please make sure the following boxes are ticked if they are correct.
If not, please try and fulfill these first.
-->
<!-- Checked checkbox should look like this: [x] -->
- [x] I am on the [latest](https://github.com/sdispater/poetry/releases/latest) Poetry version.
- [x] I have searched the [issues](https://github.com/sdispater/poetry/issues) of this repo and believe that this is not a duplicate.
- [x] If an exception occurs when executing a command, I executed it again in debug mode (`-vvv` option).
<!--
Once those are done, if you're able to fill in the following list with your information,
it'd be very helpful to whoever handles the issue.
-->
- **OS version and name**: macOS 10.14.6 (18G103)
- **Poetry version**: <!-- 1.0.0b5
- **Link of a [Gist](https://gist.github.com/) with the contents of your pyproject.toml file**: <!-- Gist Link Here --> https://gist.github.com/JBKahn/4bbb040c0181d974e0b71407ad764b6c
## Issue
When moving from `1.0.0b4` to `1.0.0b5` `poetry lock` is removing the
```
[package.source]
reference = "private"
type = "legacy"
url = "https://private.url"
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `poetry/packages/locker.py`
Content:
```
1 import json
2 import re
3
4 from hashlib import sha256
5 from typing import List
6
7 from tomlkit import document
8 from tomlkit import inline_table
9 from tomlkit import item
10 from tomlkit import table
11 from tomlkit.exceptions import TOMLKitError
12
13 import poetry.packages
14 import poetry.repositories
15
16 from poetry.utils._compat import Path
17 from poetry.utils.toml_file import TomlFile
18 from poetry.version.markers import parse_marker
19
20
21 class Locker(object):
22
23 _relevant_keys = ["dependencies", "dev-dependencies", "source", "extras"]
24
25 def __init__(self, lock, local_config): # type: (Path, dict) -> None
26 self._lock = TomlFile(lock)
27 self._local_config = local_config
28 self._lock_data = None
29 self._content_hash = self._get_content_hash()
30
31 @property
32 def lock(self): # type: () -> TomlFile
33 return self._lock
34
35 @property
36 def lock_data(self):
37 if self._lock_data is None:
38 self._lock_data = self._get_lock_data()
39
40 return self._lock_data
41
42 def is_locked(self): # type: () -> bool
43 """
44 Checks whether the locker has been locked (lockfile found).
45 """
46 if not self._lock.exists():
47 return False
48
49 return "package" in self.lock_data
50
51 def is_fresh(self): # type: () -> bool
52 """
53 Checks whether the lock file is still up to date with the current hash.
54 """
55 lock = self._lock.read()
56 metadata = lock.get("metadata", {})
57
58 if "content-hash" in metadata:
59 return self._content_hash == lock["metadata"]["content-hash"]
60
61 return False
62
63 def locked_repository(
64 self, with_dev_reqs=False
65 ): # type: (bool) -> poetry.repositories.Repository
66 """
67 Searches and returns a repository of locked packages.
68 """
69 if not self.is_locked():
70 return poetry.repositories.Repository()
71
72 lock_data = self.lock_data
73 packages = poetry.repositories.Repository()
74
75 if with_dev_reqs:
76 locked_packages = lock_data["package"]
77 else:
78 locked_packages = [
79 p for p in lock_data["package"] if p["category"] == "main"
80 ]
81
82 if not locked_packages:
83 return packages
84
85 for info in locked_packages:
86 package = poetry.packages.Package(
87 info["name"], info["version"], info["version"]
88 )
89 package.description = info.get("description", "")
90 package.category = info["category"]
91 package.optional = info["optional"]
92 if "hashes" in lock_data["metadata"]:
93 # Old lock so we create dummy files from the hashes
94 package.files = [
95 {"name": h, "hash": h}
96 for h in lock_data["metadata"]["hashes"][info["name"]]
97 ]
98 else:
99 package.files = lock_data["metadata"]["files"][info["name"]]
100
101 package.python_versions = info["python-versions"]
102 extras = info.get("extras", {})
103 if extras:
104 for name, deps in extras.items():
105 package.extras[name] = []
106
107 for dep in deps:
108 m = re.match(r"^(.+?)(?:\s+\((.+)\))?$", dep)
109 dep_name = m.group(1)
110 constraint = m.group(2) or "*"
111
112 package.extras[name].append(
113 poetry.packages.Dependency(dep_name, constraint)
114 )
115
116 if "marker" in info:
117 package.marker = parse_marker(info["marker"])
118 else:
119 # Compatibility for old locks
120 if "requirements" in info:
121 dep = poetry.packages.Dependency("foo", "0.0.0")
122 for name, value in info["requirements"].items():
123 if name == "python":
124 dep.python_versions = value
125 elif name == "platform":
126 dep.platform = value
127
128 split_dep = dep.to_pep_508(False).split(";")
129 if len(split_dep) > 1:
130 package.marker = parse_marker(split_dep[1].strip())
131
132 for dep_name, constraint in info.get("dependencies", {}).items():
133 if isinstance(constraint, list):
134 for c in constraint:
135 package.add_dependency(dep_name, c)
136
137 continue
138
139 package.add_dependency(dep_name, constraint)
140
141 if "source" in info:
142 package.source_type = info["source"]["type"]
143 package.source_url = info["source"]["url"]
144 package.source_reference = info["source"]["reference"]
145
146 packages.add_package(package)
147
148 return packages
149
150 def set_lock_data(self, root, packages): # type: (...) -> bool
151 files = table()
152 packages = self._lock_packages(packages)
153 # Retrieving hashes
154 for package in packages:
155 if package["name"] not in files:
156 files[package["name"]] = []
157
158 for f in package["files"]:
159 file_metadata = inline_table()
160 for k, v in sorted(f.items()):
161 file_metadata[k] = v
162
163 files[package["name"]].append(file_metadata)
164
165 if files[package["name"]]:
166 files[package["name"]] = item(files[package["name"]]).multiline(True)
167
168 del package["files"]
169
170 lock = document()
171 lock["package"] = packages
172
173 if root.extras:
174 lock["extras"] = {
175 extra: [dep.pretty_name for dep in deps]
176 for extra, deps in root.extras.items()
177 }
178
179 lock["metadata"] = {
180 "python-versions": root.python_versions,
181 "content-hash": self._content_hash,
182 "files": files,
183 }
184
185 if not self.is_locked() or lock != self.lock_data:
186 self._write_lock_data(lock)
187
188 return True
189
190 return False
191
192 def _write_lock_data(self, data):
193 self.lock.write(data)
194
195 # Checking lock file data consistency
196 if data != self.lock.read():
197 raise RuntimeError("Inconsistent lock file data.")
198
199 self._lock_data = None
200
201 def _get_content_hash(self): # type: () -> str
202 """
203 Returns the sha256 hash of the sorted content of the pyproject file.
204 """
205 content = self._local_config
206
207 relevant_content = {}
208 for key in self._relevant_keys:
209 relevant_content[key] = content.get(key)
210
211 content_hash = sha256(
212 json.dumps(relevant_content, sort_keys=True).encode()
213 ).hexdigest()
214
215 return content_hash
216
217 def _get_lock_data(self): # type: () -> dict
218 if not self._lock.exists():
219 raise RuntimeError("No lockfile found. Unable to read locked packages")
220
221 try:
222 return self._lock.read()
223 except TOMLKitError as e:
224 raise RuntimeError("Unable to read the lock file ({}).".format(e))
225
226 def _lock_packages(
227 self, packages
228 ): # type: (List['poetry.packages.Package']) -> list
229 locked = []
230
231 for package in sorted(packages, key=lambda x: x.name):
232 spec = self._dump_package(package)
233
234 locked.append(spec)
235
236 return locked
237
238 def _dump_package(self, package): # type: (poetry.packages.Package) -> dict
239 dependencies = {}
240 for dependency in sorted(package.requires, key=lambda d: d.name):
241 if dependency.is_optional() and not dependency.is_activated():
242 continue
243
244 if dependency.pretty_name not in dependencies:
245 dependencies[dependency.pretty_name] = []
246
247 constraint = {"version": str(dependency.pretty_constraint)}
248
249 if dependency.extras:
250 constraint["extras"] = dependency.extras
251
252 if dependency.is_optional():
253 constraint["optional"] = True
254
255 if not dependency.python_constraint.is_any():
256 constraint["python"] = str(dependency.python_constraint)
257
258 dependencies[dependency.pretty_name].append(constraint)
259
260 # All the constraints should have the same type,
261 # but we want to simplify them if it's possible
262 for dependency, constraints in tuple(dependencies.items()):
263 if all(len(constraint) == 1 for constraint in constraints):
264 dependencies[dependency] = [
265 constraint["version"] for constraint in constraints
266 ]
267
268 data = {
269 "name": package.pretty_name,
270 "version": package.pretty_version,
271 "description": package.description or "",
272 "category": package.category,
273 "optional": package.optional,
274 "python-versions": package.python_versions,
275 "files": sorted(package.files, key=lambda x: x["file"]),
276 }
277 if not package.marker.is_any():
278 data["marker"] = str(package.marker)
279
280 if package.extras:
281 extras = {}
282 for name, deps in package.extras.items():
283 extras[name] = [
284 str(dep) if not dep.constraint.is_any() else dep.name
285 for dep in deps
286 ]
287
288 data["extras"] = extras
289
290 if dependencies:
291 for k, constraints in dependencies.items():
292 if len(constraints) == 1:
293 dependencies[k] = constraints[0]
294
295 data["dependencies"] = dependencies
296
297 if package.source_type:
298 data["source"] = {
299 "type": package.source_type,
300 "url": package.source_url,
301 "reference": package.source_reference,
302 }
303
304 return data
305
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/poetry/packages/locker.py b/poetry/packages/locker.py
--- a/poetry/packages/locker.py
+++ b/poetry/packages/locker.py
@@ -139,7 +139,7 @@
package.add_dependency(dep_name, constraint)
if "source" in info:
- package.source_type = info["source"]["type"]
+ package.source_type = info["source"].get("type", "")
package.source_url = info["source"]["url"]
package.source_reference = info["source"]["reference"]
@@ -294,11 +294,12 @@
data["dependencies"] = dependencies
- if package.source_type:
+ if package.source_url:
data["source"] = {
- "type": package.source_type,
"url": package.source_url,
"reference": package.source_reference,
}
+ if package.source_type:
+ data["source"]["type"] = package.source_type
return data
|
{"golden_diff": "diff --git a/poetry/packages/locker.py b/poetry/packages/locker.py\n--- a/poetry/packages/locker.py\n+++ b/poetry/packages/locker.py\n@@ -139,7 +139,7 @@\n package.add_dependency(dep_name, constraint)\n \n if \"source\" in info:\n- package.source_type = info[\"source\"][\"type\"]\n+ package.source_type = info[\"source\"].get(\"type\", \"\")\n package.source_url = info[\"source\"][\"url\"]\n package.source_reference = info[\"source\"][\"reference\"]\n \n@@ -294,11 +294,12 @@\n \n data[\"dependencies\"] = dependencies\n \n- if package.source_type:\n+ if package.source_url:\n data[\"source\"] = {\n- \"type\": package.source_type,\n \"url\": package.source_url,\n \"reference\": package.source_reference,\n }\n+ if package.source_type:\n+ data[\"source\"][\"type\"] = package.source_type\n \n return data\n", "issue": "1.0.0b5 removes my private source from the lockfile\n<!--\r\n Hi there! Thank you for discovering and submitting an issue.\r\n\r\n Before you submit this; let's make sure of a few things.\r\n Please make sure the following boxes are ticked if they are correct.\r\n If not, please try and fulfill these first.\r\n-->\r\n\r\n<!-- Checked checkbox should look like this: [x] -->\r\n- [x] I am on the [latest](https://github.com/sdispater/poetry/releases/latest) Poetry version.\r\n- [x] I have searched the [issues](https://github.com/sdispater/poetry/issues) of this repo and believe that this is not a duplicate.\r\n- [x] If an exception occurs when executing a command, I executed it again in debug mode (`-vvv` option).\r\n\r\n<!--\r\n Once those are done, if you're able to fill in the following list with your information,\r\n it'd be very helpful to whoever handles the issue.\r\n-->\r\n\r\n- **OS version and name**: macOS 10.14.6 (18G103)\r\n- **Poetry version**: <!-- 1.0.0b5\r\n- **Link of a [Gist](https://gist.github.com/) with the contents of your pyproject.toml file**: <!-- Gist Link Here --> https://gist.github.com/JBKahn/4bbb040c0181d974e0b71407ad764b6c\r\n\r\n\r\n## Issue\r\nWhen moving from `1.0.0b4` to `1.0.0b5` `poetry lock` is removing the \r\n```\r\n[package.source]\r\nreference = \"private\"\r\ntype = \"legacy\"\r\nurl = \"https://private.url\"\r\n```\r\n\n", "before_files": [{"content": "import json\nimport re\n\nfrom hashlib import sha256\nfrom typing import List\n\nfrom tomlkit import document\nfrom tomlkit import inline_table\nfrom tomlkit import item\nfrom tomlkit import table\nfrom tomlkit.exceptions import TOMLKitError\n\nimport poetry.packages\nimport poetry.repositories\n\nfrom poetry.utils._compat import Path\nfrom poetry.utils.toml_file import TomlFile\nfrom poetry.version.markers import parse_marker\n\n\nclass Locker(object):\n\n _relevant_keys = [\"dependencies\", \"dev-dependencies\", \"source\", \"extras\"]\n\n def __init__(self, lock, local_config): # type: (Path, dict) -> None\n self._lock = TomlFile(lock)\n self._local_config = local_config\n self._lock_data = None\n self._content_hash = self._get_content_hash()\n\n @property\n def lock(self): # type: () -> TomlFile\n return self._lock\n\n @property\n def lock_data(self):\n if self._lock_data is None:\n self._lock_data = self._get_lock_data()\n\n return self._lock_data\n\n def is_locked(self): # type: () -> bool\n \"\"\"\n Checks whether the locker has been locked (lockfile found).\n \"\"\"\n if not self._lock.exists():\n return False\n\n return \"package\" in self.lock_data\n\n def is_fresh(self): # type: () -> bool\n \"\"\"\n Checks whether the lock file is still up to date with the current hash.\n \"\"\"\n lock = self._lock.read()\n metadata = lock.get(\"metadata\", {})\n\n if \"content-hash\" in metadata:\n return self._content_hash == lock[\"metadata\"][\"content-hash\"]\n\n return False\n\n def locked_repository(\n self, with_dev_reqs=False\n ): # type: (bool) -> poetry.repositories.Repository\n \"\"\"\n Searches and returns a repository of locked packages.\n \"\"\"\n if not self.is_locked():\n return poetry.repositories.Repository()\n\n lock_data = self.lock_data\n packages = poetry.repositories.Repository()\n\n if with_dev_reqs:\n locked_packages = lock_data[\"package\"]\n else:\n locked_packages = [\n p for p in lock_data[\"package\"] if p[\"category\"] == \"main\"\n ]\n\n if not locked_packages:\n return packages\n\n for info in locked_packages:\n package = poetry.packages.Package(\n info[\"name\"], info[\"version\"], info[\"version\"]\n )\n package.description = info.get(\"description\", \"\")\n package.category = info[\"category\"]\n package.optional = info[\"optional\"]\n if \"hashes\" in lock_data[\"metadata\"]:\n # Old lock so we create dummy files from the hashes\n package.files = [\n {\"name\": h, \"hash\": h}\n for h in lock_data[\"metadata\"][\"hashes\"][info[\"name\"]]\n ]\n else:\n package.files = lock_data[\"metadata\"][\"files\"][info[\"name\"]]\n\n package.python_versions = info[\"python-versions\"]\n extras = info.get(\"extras\", {})\n if extras:\n for name, deps in extras.items():\n package.extras[name] = []\n\n for dep in deps:\n m = re.match(r\"^(.+?)(?:\\s+\\((.+)\\))?$\", dep)\n dep_name = m.group(1)\n constraint = m.group(2) or \"*\"\n\n package.extras[name].append(\n poetry.packages.Dependency(dep_name, constraint)\n )\n\n if \"marker\" in info:\n package.marker = parse_marker(info[\"marker\"])\n else:\n # Compatibility for old locks\n if \"requirements\" in info:\n dep = poetry.packages.Dependency(\"foo\", \"0.0.0\")\n for name, value in info[\"requirements\"].items():\n if name == \"python\":\n dep.python_versions = value\n elif name == \"platform\":\n dep.platform = value\n\n split_dep = dep.to_pep_508(False).split(\";\")\n if len(split_dep) > 1:\n package.marker = parse_marker(split_dep[1].strip())\n\n for dep_name, constraint in info.get(\"dependencies\", {}).items():\n if isinstance(constraint, list):\n for c in constraint:\n package.add_dependency(dep_name, c)\n\n continue\n\n package.add_dependency(dep_name, constraint)\n\n if \"source\" in info:\n package.source_type = info[\"source\"][\"type\"]\n package.source_url = info[\"source\"][\"url\"]\n package.source_reference = info[\"source\"][\"reference\"]\n\n packages.add_package(package)\n\n return packages\n\n def set_lock_data(self, root, packages): # type: (...) -> bool\n files = table()\n packages = self._lock_packages(packages)\n # Retrieving hashes\n for package in packages:\n if package[\"name\"] not in files:\n files[package[\"name\"]] = []\n\n for f in package[\"files\"]:\n file_metadata = inline_table()\n for k, v in sorted(f.items()):\n file_metadata[k] = v\n\n files[package[\"name\"]].append(file_metadata)\n\n if files[package[\"name\"]]:\n files[package[\"name\"]] = item(files[package[\"name\"]]).multiline(True)\n\n del package[\"files\"]\n\n lock = document()\n lock[\"package\"] = packages\n\n if root.extras:\n lock[\"extras\"] = {\n extra: [dep.pretty_name for dep in deps]\n for extra, deps in root.extras.items()\n }\n\n lock[\"metadata\"] = {\n \"python-versions\": root.python_versions,\n \"content-hash\": self._content_hash,\n \"files\": files,\n }\n\n if not self.is_locked() or lock != self.lock_data:\n self._write_lock_data(lock)\n\n return True\n\n return False\n\n def _write_lock_data(self, data):\n self.lock.write(data)\n\n # Checking lock file data consistency\n if data != self.lock.read():\n raise RuntimeError(\"Inconsistent lock file data.\")\n\n self._lock_data = None\n\n def _get_content_hash(self): # type: () -> str\n \"\"\"\n Returns the sha256 hash of the sorted content of the pyproject file.\n \"\"\"\n content = self._local_config\n\n relevant_content = {}\n for key in self._relevant_keys:\n relevant_content[key] = content.get(key)\n\n content_hash = sha256(\n json.dumps(relevant_content, sort_keys=True).encode()\n ).hexdigest()\n\n return content_hash\n\n def _get_lock_data(self): # type: () -> dict\n if not self._lock.exists():\n raise RuntimeError(\"No lockfile found. Unable to read locked packages\")\n\n try:\n return self._lock.read()\n except TOMLKitError as e:\n raise RuntimeError(\"Unable to read the lock file ({}).\".format(e))\n\n def _lock_packages(\n self, packages\n ): # type: (List['poetry.packages.Package']) -> list\n locked = []\n\n for package in sorted(packages, key=lambda x: x.name):\n spec = self._dump_package(package)\n\n locked.append(spec)\n\n return locked\n\n def _dump_package(self, package): # type: (poetry.packages.Package) -> dict\n dependencies = {}\n for dependency in sorted(package.requires, key=lambda d: d.name):\n if dependency.is_optional() and not dependency.is_activated():\n continue\n\n if dependency.pretty_name not in dependencies:\n dependencies[dependency.pretty_name] = []\n\n constraint = {\"version\": str(dependency.pretty_constraint)}\n\n if dependency.extras:\n constraint[\"extras\"] = dependency.extras\n\n if dependency.is_optional():\n constraint[\"optional\"] = True\n\n if not dependency.python_constraint.is_any():\n constraint[\"python\"] = str(dependency.python_constraint)\n\n dependencies[dependency.pretty_name].append(constraint)\n\n # All the constraints should have the same type,\n # but we want to simplify them if it's possible\n for dependency, constraints in tuple(dependencies.items()):\n if all(len(constraint) == 1 for constraint in constraints):\n dependencies[dependency] = [\n constraint[\"version\"] for constraint in constraints\n ]\n\n data = {\n \"name\": package.pretty_name,\n \"version\": package.pretty_version,\n \"description\": package.description or \"\",\n \"category\": package.category,\n \"optional\": package.optional,\n \"python-versions\": package.python_versions,\n \"files\": sorted(package.files, key=lambda x: x[\"file\"]),\n }\n if not package.marker.is_any():\n data[\"marker\"] = str(package.marker)\n\n if package.extras:\n extras = {}\n for name, deps in package.extras.items():\n extras[name] = [\n str(dep) if not dep.constraint.is_any() else dep.name\n for dep in deps\n ]\n\n data[\"extras\"] = extras\n\n if dependencies:\n for k, constraints in dependencies.items():\n if len(constraints) == 1:\n dependencies[k] = constraints[0]\n\n data[\"dependencies\"] = dependencies\n\n if package.source_type:\n data[\"source\"] = {\n \"type\": package.source_type,\n \"url\": package.source_url,\n \"reference\": package.source_reference,\n }\n\n return data\n", "path": "poetry/packages/locker.py"}], "after_files": [{"content": "import json\nimport re\n\nfrom hashlib import sha256\nfrom typing import List\n\nfrom tomlkit import document\nfrom tomlkit import inline_table\nfrom tomlkit import item\nfrom tomlkit import table\nfrom tomlkit.exceptions import TOMLKitError\n\nimport poetry.packages\nimport poetry.repositories\n\nfrom poetry.utils._compat import Path\nfrom poetry.utils.toml_file import TomlFile\nfrom poetry.version.markers import parse_marker\n\n\nclass Locker(object):\n\n _relevant_keys = [\"dependencies\", \"dev-dependencies\", \"source\", \"extras\"]\n\n def __init__(self, lock, local_config): # type: (Path, dict) -> None\n self._lock = TomlFile(lock)\n self._local_config = local_config\n self._lock_data = None\n self._content_hash = self._get_content_hash()\n\n @property\n def lock(self): # type: () -> TomlFile\n return self._lock\n\n @property\n def lock_data(self):\n if self._lock_data is None:\n self._lock_data = self._get_lock_data()\n\n return self._lock_data\n\n def is_locked(self): # type: () -> bool\n \"\"\"\n Checks whether the locker has been locked (lockfile found).\n \"\"\"\n if not self._lock.exists():\n return False\n\n return \"package\" in self.lock_data\n\n def is_fresh(self): # type: () -> bool\n \"\"\"\n Checks whether the lock file is still up to date with the current hash.\n \"\"\"\n lock = self._lock.read()\n metadata = lock.get(\"metadata\", {})\n\n if \"content-hash\" in metadata:\n return self._content_hash == lock[\"metadata\"][\"content-hash\"]\n\n return False\n\n def locked_repository(\n self, with_dev_reqs=False\n ): # type: (bool) -> poetry.repositories.Repository\n \"\"\"\n Searches and returns a repository of locked packages.\n \"\"\"\n if not self.is_locked():\n return poetry.repositories.Repository()\n\n lock_data = self.lock_data\n packages = poetry.repositories.Repository()\n\n if with_dev_reqs:\n locked_packages = lock_data[\"package\"]\n else:\n locked_packages = [\n p for p in lock_data[\"package\"] if p[\"category\"] == \"main\"\n ]\n\n if not locked_packages:\n return packages\n\n for info in locked_packages:\n package = poetry.packages.Package(\n info[\"name\"], info[\"version\"], info[\"version\"]\n )\n package.description = info.get(\"description\", \"\")\n package.category = info[\"category\"]\n package.optional = info[\"optional\"]\n if \"hashes\" in lock_data[\"metadata\"]:\n # Old lock so we create dummy files from the hashes\n package.files = [\n {\"name\": h, \"hash\": h}\n for h in lock_data[\"metadata\"][\"hashes\"][info[\"name\"]]\n ]\n else:\n package.files = lock_data[\"metadata\"][\"files\"][info[\"name\"]]\n\n package.python_versions = info[\"python-versions\"]\n extras = info.get(\"extras\", {})\n if extras:\n for name, deps in extras.items():\n package.extras[name] = []\n\n for dep in deps:\n m = re.match(r\"^(.+?)(?:\\s+\\((.+)\\))?$\", dep)\n dep_name = m.group(1)\n constraint = m.group(2) or \"*\"\n\n package.extras[name].append(\n poetry.packages.Dependency(dep_name, constraint)\n )\n\n if \"marker\" in info:\n package.marker = parse_marker(info[\"marker\"])\n else:\n # Compatibility for old locks\n if \"requirements\" in info:\n dep = poetry.packages.Dependency(\"foo\", \"0.0.0\")\n for name, value in info[\"requirements\"].items():\n if name == \"python\":\n dep.python_versions = value\n elif name == \"platform\":\n dep.platform = value\n\n split_dep = dep.to_pep_508(False).split(\";\")\n if len(split_dep) > 1:\n package.marker = parse_marker(split_dep[1].strip())\n\n for dep_name, constraint in info.get(\"dependencies\", {}).items():\n if isinstance(constraint, list):\n for c in constraint:\n package.add_dependency(dep_name, c)\n\n continue\n\n package.add_dependency(dep_name, constraint)\n\n if \"source\" in info:\n package.source_type = info[\"source\"].get(\"type\", \"\")\n package.source_url = info[\"source\"][\"url\"]\n package.source_reference = info[\"source\"][\"reference\"]\n\n packages.add_package(package)\n\n return packages\n\n def set_lock_data(self, root, packages): # type: (...) -> bool\n files = table()\n packages = self._lock_packages(packages)\n # Retrieving hashes\n for package in packages:\n if package[\"name\"] not in files:\n files[package[\"name\"]] = []\n\n for f in package[\"files\"]:\n file_metadata = inline_table()\n for k, v in sorted(f.items()):\n file_metadata[k] = v\n\n files[package[\"name\"]].append(file_metadata)\n\n if files[package[\"name\"]]:\n files[package[\"name\"]] = item(files[package[\"name\"]]).multiline(True)\n\n del package[\"files\"]\n\n lock = document()\n lock[\"package\"] = packages\n\n if root.extras:\n lock[\"extras\"] = {\n extra: [dep.pretty_name for dep in deps]\n for extra, deps in root.extras.items()\n }\n\n lock[\"metadata\"] = {\n \"python-versions\": root.python_versions,\n \"content-hash\": self._content_hash,\n \"files\": files,\n }\n\n if not self.is_locked() or lock != self.lock_data:\n self._write_lock_data(lock)\n\n return True\n\n return False\n\n def _write_lock_data(self, data):\n self.lock.write(data)\n\n # Checking lock file data consistency\n if data != self.lock.read():\n raise RuntimeError(\"Inconsistent lock file data.\")\n\n self._lock_data = None\n\n def _get_content_hash(self): # type: () -> str\n \"\"\"\n Returns the sha256 hash of the sorted content of the pyproject file.\n \"\"\"\n content = self._local_config\n\n relevant_content = {}\n for key in self._relevant_keys:\n relevant_content[key] = content.get(key)\n\n content_hash = sha256(\n json.dumps(relevant_content, sort_keys=True).encode()\n ).hexdigest()\n\n return content_hash\n\n def _get_lock_data(self): # type: () -> dict\n if not self._lock.exists():\n raise RuntimeError(\"No lockfile found. Unable to read locked packages\")\n\n try:\n return self._lock.read()\n except TOMLKitError as e:\n raise RuntimeError(\"Unable to read the lock file ({}).\".format(e))\n\n def _lock_packages(\n self, packages\n ): # type: (List['poetry.packages.Package']) -> list\n locked = []\n\n for package in sorted(packages, key=lambda x: x.name):\n spec = self._dump_package(package)\n\n locked.append(spec)\n\n return locked\n\n def _dump_package(self, package): # type: (poetry.packages.Package) -> dict\n dependencies = {}\n for dependency in sorted(package.requires, key=lambda d: d.name):\n if dependency.is_optional() and not dependency.is_activated():\n continue\n\n if dependency.pretty_name not in dependencies:\n dependencies[dependency.pretty_name] = []\n\n constraint = {\"version\": str(dependency.pretty_constraint)}\n\n if dependency.extras:\n constraint[\"extras\"] = dependency.extras\n\n if dependency.is_optional():\n constraint[\"optional\"] = True\n\n if not dependency.python_constraint.is_any():\n constraint[\"python\"] = str(dependency.python_constraint)\n\n dependencies[dependency.pretty_name].append(constraint)\n\n # All the constraints should have the same type,\n # but we want to simplify them if it's possible\n for dependency, constraints in tuple(dependencies.items()):\n if all(len(constraint) == 1 for constraint in constraints):\n dependencies[dependency] = [\n constraint[\"version\"] for constraint in constraints\n ]\n\n data = {\n \"name\": package.pretty_name,\n \"version\": package.pretty_version,\n \"description\": package.description or \"\",\n \"category\": package.category,\n \"optional\": package.optional,\n \"python-versions\": package.python_versions,\n \"files\": sorted(package.files, key=lambda x: x[\"file\"]),\n }\n if not package.marker.is_any():\n data[\"marker\"] = str(package.marker)\n\n if package.extras:\n extras = {}\n for name, deps in package.extras.items():\n extras[name] = [\n str(dep) if not dep.constraint.is_any() else dep.name\n for dep in deps\n ]\n\n data[\"extras\"] = extras\n\n if dependencies:\n for k, constraints in dependencies.items():\n if len(constraints) == 1:\n dependencies[k] = constraints[0]\n\n data[\"dependencies\"] = dependencies\n\n if package.source_url:\n data[\"source\"] = {\n \"url\": package.source_url,\n \"reference\": package.source_reference,\n }\n if package.source_type:\n data[\"source\"][\"type\"] = package.source_type\n\n return data\n", "path": "poetry/packages/locker.py"}]}
| 3,500 | 219 |
gh_patches_debug_42509
|
rasdani/github-patches
|
git_diff
|
napari__napari-1749
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Track vertex shader does not handle blending/opacity correctly
## 🐛 Bug
Two somewhat related bugs in `_vispy_tracks_shader.py` in the `Tracks` layer:
1. The opacity slider only changes the vispy node opacity, which has no effect on the vertex shader used for rendering the tracks or graph.
2. The translucent mode renders parts of the track, which should not be rendered, as dark lines:
## To Reproduce
Steps to reproduce the behavior:
1. run `examples\tracks_3d.py`
2. Change the blending mode to translucent in the `Tracks` layer
3. Change the opacity slider
## Expected behavior
`opacity` should change the track opacity, and the `translucent` blending should not render parts of the track which should not be visible.
## Environment
napari: 0.3.9.dev32+g911e095.d20201007
Platform: Linux-4.15.0-1100-oem-x86_64-with-debian-buster-sid
Python: 3.7.7 (default, May 7 2020, 21:25:33) [GCC 7.3.0]
Qt: 5.14.2
PySide2: 5.14.2.2
NumPy: 1.19.1
SciPy: 1.4.1
Dask: 2.17.2
VisPy: 0.6.4
GL version: 4.6.0 NVIDIA 450.80.02
MAX_TEXTURE_SIZE: 32768
Plugins:
- napari-plugin-engine: 0.1.5
- svg: 0.1.3
## Additional context
This relates to the fact that the shader manipulates the alpha values of the vertices directly, late in the rendering pipeline.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `napari/_vispy/vispy_tracks_layer.py`
Content:
```
1 from vispy.scene.visuals import Compound, Line, Text
2
3 from ._vispy_tracks_shader import TrackShader
4 from .vispy_base_layer import VispyBaseLayer
5
6
7 class VispyTracksLayer(VispyBaseLayer):
8 """VispyTracksLayer
9
10 Track layer for visualizing tracks.
11
12 Components:
13 - Track lines (vispy.LineVisual)
14 - Track IDs (vispy.TextVisual)
15 - Graph edges (vispy.LineVisual)
16
17 """
18
19 def __init__(self, layer):
20 node = Compound([Line(), Text(), Line()])
21 super().__init__(layer, node)
22
23 self.layer.events.tail_width.connect(self._on_appearance_change)
24 self.layer.events.tail_length.connect(self._on_appearance_change)
25 self.layer.events.display_id.connect(self._on_appearance_change)
26 self.layer.events.display_tail.connect(self._on_appearance_change)
27 self.layer.events.display_graph.connect(self._on_appearance_change)
28
29 self.layer.events.color_by.connect(self._on_appearance_change)
30 self.layer.events.colormap.connect(self._on_appearance_change)
31
32 # these events are fired when changes occur to the tracks or the
33 # graph - as the vertex buffer of the shader needs to be updated
34 # alongside the actual vertex data
35 self.layer.events.rebuild_tracks.connect(self._on_tracks_change)
36 self.layer.events.rebuild_graph.connect(self._on_graph_change)
37
38 # build and attach the shader to the track
39 self.track_shader = TrackShader()
40 self.graph_shader = TrackShader()
41 node._subvisuals[0].attach(self.track_shader)
42 node._subvisuals[2].attach(self.graph_shader)
43
44 # text label properties
45 self.node._subvisuals[1].color = 'white'
46 self.node._subvisuals[1].font_size = 8
47
48 self._reset_base()
49
50 self._on_data_change()
51 self._on_appearance_change()
52
53 def _on_data_change(self, event=None):
54 """ update the display """
55
56 # update the shaders
57 self.track_shader.current_time = self.layer.current_time
58 self.graph_shader.current_time = self.layer.current_time
59
60 # add text labels if they're visible
61 if self.node._subvisuals[1].visible:
62 labels_text, labels_pos = self.layer.track_labels
63 self.node._subvisuals[1].text = labels_text
64 self.node._subvisuals[1].pos = labels_pos
65
66 self.node.update()
67 # Call to update order of translation values with new dims:
68 self._on_matrix_change()
69
70 def _on_appearance_change(self, event=None):
71 """ change the appearance of the data """
72
73 # update shader properties related to appearance
74 self.track_shader.use_fade = self.layer.use_fade
75 self.track_shader.tail_length = self.layer.tail_length
76 self.graph_shader.use_fade = self.layer.use_fade
77 self.graph_shader.tail_length = self.layer.tail_length
78
79 # set visibility of subvisuals
80 self.node._subvisuals[0].visible = self.layer.display_tail
81 self.node._subvisuals[1].visible = self.layer.display_id
82 self.node._subvisuals[2].visible = self.layer.display_graph
83
84 # set the width of the track tails
85 self.node._subvisuals[0].set_data(
86 width=self.layer.tail_width, color=self.layer.track_colors,
87 )
88 self.node._subvisuals[2].set_data(width=self.layer.tail_width,)
89
90 def _on_tracks_change(self, event=None):
91 """ update the shader when the track data changes """
92
93 self.track_shader.use_fade = self.layer.use_fade
94 self.track_shader.tail_length = self.layer.tail_length
95 self.track_shader.vertex_time = self.layer.track_times
96
97 # change the data to the vispy line visual
98 self.node._subvisuals[0].set_data(
99 pos=self.layer._view_data,
100 connect=self.layer.track_connex,
101 width=self.layer.tail_width,
102 color=self.layer.track_colors,
103 )
104
105 # Call to update order of translation values with new dims:
106 self._on_matrix_change()
107
108 def _on_graph_change(self, event=None):
109 """ update the shader when the graph data changes """
110
111 self.graph_shader.use_fade = self.layer.use_fade
112 self.graph_shader.tail_length = self.layer.tail_length
113 self.graph_shader.vertex_time = self.layer.graph_times
114
115 # if the user clears a graph after it has been created, vispy offers
116 # no method to clear the data, therefore, we need to set private
117 # attributes to None to prevent errors
118 if self.layer._view_graph is None:
119 self.node._subvisuals[2]._pos = None
120 self.node._subvisuals[2]._connect = None
121 self.node.update()
122 return
123
124 self.node._subvisuals[2].set_data(
125 pos=self.layer._view_graph,
126 connect=self.layer.graph_connex,
127 width=self.layer.tail_width,
128 color='white',
129 )
130
131 # Call to update order of translation values with new dims:
132 self._on_matrix_change()
133
```
Path: `napari/_vispy/_vispy_tracks_shader.py`
Content:
```
1 from typing import List, Union
2
3 import numpy as np
4 from vispy.gloo import VertexBuffer
5 from vispy.visuals.filters.base_filter import Filter
6
7
8 class TrackShader(Filter):
9 """ TrackShader
10
11 Custom vertex and fragment shaders for visualizing tracks quickly with
12 vispy. The central assumption is that the tracks are rendered as a
13 continuous vispy Line segment, with connections and colors defined when
14 the visual is created.
15
16 The shader simply changes the visibility and/or fading of the data according
17 to the current_time and the associate time metadata for each vertex. This
18 is scaled according to the tail length. Points ahead of the current time
19 are rendered with alpha set to zero.
20
21 Parameters
22 ----------
23 current_time : int, float
24 the current time, which is typically the frame index, although this
25 can be an arbitrary float
26 tail_length : int, float
27 the upper limit on length of the 'tail'
28 use_fade : bool
29 this will enable/disable tail fading with time
30 vertex_time : 1D array, list
31 a vector describing the time associated with each vertex
32
33
34 TODO
35 ----
36 - the track is still displayed, albeit with fading, once the track has
37 finished but is still within the 'tail_length' window. Should it
38 disappear?
39 - check the shader positioning within the GL pipeline, currently
40 overrides layer opacity settings
41
42 vertex_mask: 1D array, list
43 a vector describing whether to mask each vertex
44
45 """
46
47 VERT_SHADER = """
48 varying vec4 v_track_color;
49 void apply_track_shading() {
50
51 float alpha;
52
53 if ($a_vertex_time > $current_time) {
54 // this is a hack to minimize the frag shader rendering ahead
55 // of the current time point due to interpolation
56 if ($a_vertex_time <= $current_time + 1){
57 alpha = -100.;
58 } else {
59 alpha = 0.;
60 }
61 } else {
62 // fade the track into the temporal distance, scaled by the
63 // maximum tail length from the gui
64 float fade = ($current_time - $a_vertex_time) / $tail_length;
65 alpha = clamp(1.0-fade, 0.0, 1.0);
66 }
67
68 // when use_fade is disabled, the entire track is visible
69 if ($use_fade == 0) {
70 alpha = 1.0;
71 }
72
73 // set the vertex alpha according to the fade
74 v_track_color.a = alpha;
75 }
76 """
77
78 FRAG_SHADER = """
79 varying vec4 v_track_color;
80 void apply_track_shading() {
81 // interpolate
82 gl_FragColor.a = clamp(v_track_color.a, 0.0, 1.0);
83 }
84 """
85
86 def __init__(
87 self,
88 current_time=0,
89 tail_length=30,
90 use_fade: bool = True,
91 vertex_time: Union[List, np.ndarray] = None,
92 ):
93
94 super().__init__(
95 vcode=self.VERT_SHADER, vpos=3, fcode=self.FRAG_SHADER, fpos=9
96 )
97
98 self.current_time = current_time
99 self.tail_length = tail_length
100 self.use_fade = use_fade
101 self.vertex_time = vertex_time
102
103 @property
104 def current_time(self) -> Union[int, float]:
105 return self._current_time
106
107 @current_time.setter
108 def current_time(self, n: Union[int, float]):
109 self._current_time = n
110 if isinstance(n, slice):
111 n = np.max(self._vertex_time)
112 self.vshader['current_time'] = float(n)
113
114 @property
115 def use_fade(self) -> bool:
116 return self._use_fade
117
118 @use_fade.setter
119 def use_fade(self, value: bool):
120 self._use_fade = value
121 self.vshader['use_fade'] = float(self._use_fade)
122
123 @property
124 def tail_length(self) -> Union[int, float]:
125 return self._tail_length
126
127 @tail_length.setter
128 def tail_length(self, tail_length: Union[int, float]):
129 self._tail_length = tail_length
130 self.vshader['tail_length'] = float(self._tail_length)
131
132 def _attach(self, visual):
133 super()._attach(visual)
134
135 @property
136 def vertex_time(self):
137 return self._vertex_time
138
139 @vertex_time.setter
140 def vertex_time(self, v_time):
141 self._vertex_time = np.array(v_time).reshape(-1, 1).astype(np.float32)
142 self.vshader['a_vertex_time'] = VertexBuffer(self.vertex_time)
143
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/napari/_vispy/_vispy_tracks_shader.py b/napari/_vispy/_vispy_tracks_shader.py
--- a/napari/_vispy/_vispy_tracks_shader.py
+++ b/napari/_vispy/_vispy_tracks_shader.py
@@ -6,7 +6,7 @@
class TrackShader(Filter):
- """ TrackShader
+ """TrackShader.
Custom vertex and fragment shaders for visualizing tracks quickly with
vispy. The central assumption is that the tracks are rendered as a
@@ -30,17 +30,11 @@
vertex_time : 1D array, list
a vector describing the time associated with each vertex
-
TODO
----
- the track is still displayed, albeit with fading, once the track has
finished but is still within the 'tail_length' window. Should it
disappear?
- - check the shader positioning within the GL pipeline, currently
- overrides layer opacity settings
-
- vertex_mask: 1D array, list
- a vector describing whether to mask each vertex
"""
@@ -78,15 +72,21 @@
FRAG_SHADER = """
varying vec4 v_track_color;
void apply_track_shading() {
+
+ // if the alpha is below the threshold, discard the fragment
+ if( v_track_color.a <= 0.0 ) {
+ discard;
+ }
+
// interpolate
- gl_FragColor.a = clamp(v_track_color.a, 0.0, 1.0);
+ gl_FragColor.a = clamp(v_track_color.a * gl_FragColor.a, 0.0, 1.0);
}
"""
def __init__(
self,
- current_time=0,
- tail_length=30,
+ current_time: Union[int, float] = 0,
+ tail_length: Union[int, float] = 30,
use_fade: bool = True,
vertex_time: Union[List, np.ndarray] = None,
):
diff --git a/napari/_vispy/vispy_tracks_layer.py b/napari/_vispy/vispy_tracks_layer.py
--- a/napari/_vispy/vispy_tracks_layer.py
+++ b/napari/_vispy/vispy_tracks_layer.py
@@ -51,7 +51,7 @@
self._on_appearance_change()
def _on_data_change(self, event=None):
- """ update the display """
+ """Update the display."""
# update the shaders
self.track_shader.current_time = self.layer.current_time
@@ -68,7 +68,7 @@
self._on_matrix_change()
def _on_appearance_change(self, event=None):
- """ change the appearance of the data """
+ """Change the appearance of the data."""
# update shader properties related to appearance
self.track_shader.use_fade = self.layer.use_fade
@@ -88,7 +88,7 @@
self.node._subvisuals[2].set_data(width=self.layer.tail_width,)
def _on_tracks_change(self, event=None):
- """ update the shader when the track data changes """
+ """Update the shader when the track data changes."""
self.track_shader.use_fade = self.layer.use_fade
self.track_shader.tail_length = self.layer.tail_length
@@ -106,7 +106,7 @@
self._on_matrix_change()
def _on_graph_change(self, event=None):
- """ update the shader when the graph data changes """
+ """Update the shader when the graph data changes."""
self.graph_shader.use_fade = self.layer.use_fade
self.graph_shader.tail_length = self.layer.tail_length
|
{"golden_diff": "diff --git a/napari/_vispy/_vispy_tracks_shader.py b/napari/_vispy/_vispy_tracks_shader.py\n--- a/napari/_vispy/_vispy_tracks_shader.py\n+++ b/napari/_vispy/_vispy_tracks_shader.py\n@@ -6,7 +6,7 @@\n \n \n class TrackShader(Filter):\n- \"\"\" TrackShader\n+ \"\"\"TrackShader.\n \n Custom vertex and fragment shaders for visualizing tracks quickly with\n vispy. The central assumption is that the tracks are rendered as a\n@@ -30,17 +30,11 @@\n vertex_time : 1D array, list\n a vector describing the time associated with each vertex\n \n-\n TODO\n ----\n - the track is still displayed, albeit with fading, once the track has\n finished but is still within the 'tail_length' window. Should it\n disappear?\n- - check the shader positioning within the GL pipeline, currently\n- overrides layer opacity settings\n-\n- vertex_mask: 1D array, list\n- a vector describing whether to mask each vertex\n \n \"\"\"\n \n@@ -78,15 +72,21 @@\n FRAG_SHADER = \"\"\"\n varying vec4 v_track_color;\n void apply_track_shading() {\n+\n+ // if the alpha is below the threshold, discard the fragment\n+ if( v_track_color.a <= 0.0 ) {\n+ discard;\n+ }\n+\n // interpolate\n- gl_FragColor.a = clamp(v_track_color.a, 0.0, 1.0);\n+ gl_FragColor.a = clamp(v_track_color.a * gl_FragColor.a, 0.0, 1.0);\n }\n \"\"\"\n \n def __init__(\n self,\n- current_time=0,\n- tail_length=30,\n+ current_time: Union[int, float] = 0,\n+ tail_length: Union[int, float] = 30,\n use_fade: bool = True,\n vertex_time: Union[List, np.ndarray] = None,\n ):\ndiff --git a/napari/_vispy/vispy_tracks_layer.py b/napari/_vispy/vispy_tracks_layer.py\n--- a/napari/_vispy/vispy_tracks_layer.py\n+++ b/napari/_vispy/vispy_tracks_layer.py\n@@ -51,7 +51,7 @@\n self._on_appearance_change()\n \n def _on_data_change(self, event=None):\n- \"\"\" update the display \"\"\"\n+ \"\"\"Update the display.\"\"\"\n \n # update the shaders\n self.track_shader.current_time = self.layer.current_time\n@@ -68,7 +68,7 @@\n self._on_matrix_change()\n \n def _on_appearance_change(self, event=None):\n- \"\"\" change the appearance of the data \"\"\"\n+ \"\"\"Change the appearance of the data.\"\"\"\n \n # update shader properties related to appearance\n self.track_shader.use_fade = self.layer.use_fade\n@@ -88,7 +88,7 @@\n self.node._subvisuals[2].set_data(width=self.layer.tail_width,)\n \n def _on_tracks_change(self, event=None):\n- \"\"\" update the shader when the track data changes \"\"\"\n+ \"\"\"Update the shader when the track data changes.\"\"\"\n \n self.track_shader.use_fade = self.layer.use_fade\n self.track_shader.tail_length = self.layer.tail_length\n@@ -106,7 +106,7 @@\n self._on_matrix_change()\n \n def _on_graph_change(self, event=None):\n- \"\"\" update the shader when the graph data changes \"\"\"\n+ \"\"\"Update the shader when the graph data changes.\"\"\"\n \n self.graph_shader.use_fade = self.layer.use_fade\n self.graph_shader.tail_length = self.layer.tail_length\n", "issue": "Track vertex shader does not handle blending/opacity correctly\n## \ud83d\udc1b Bug\r\n\r\nTwo somewhat related bugs in `_vispy_tracks_shader.py` in the `Tracks` layer:\r\n1. The opacity slider only changes the vispy node opacity, which has no effect on the vertex shader used for rendering the tracks or graph.\r\n2. The translucent mode renders parts of the track, which should not be rendered, as dark lines:\r\n\r\n\r\n\r\n## To Reproduce\r\n\r\nSteps to reproduce the behavior:\r\n\r\n1. run `examples\\tracks_3d.py`\r\n2. Change the blending mode to translucent in the `Tracks` layer\r\n3. Change the opacity slider \r\n\r\n## Expected behavior\r\n\r\n`opacity` should change the track opacity, and the `translucent` blending should not render parts of the track which should not be visible.\r\n\r\n## Environment\r\n\r\nnapari: 0.3.9.dev32+g911e095.d20201007\r\nPlatform: Linux-4.15.0-1100-oem-x86_64-with-debian-buster-sid\r\nPython: 3.7.7 (default, May 7 2020, 21:25:33) [GCC 7.3.0]\r\nQt: 5.14.2\r\nPySide2: 5.14.2.2\r\nNumPy: 1.19.1\r\nSciPy: 1.4.1\r\nDask: 2.17.2\r\nVisPy: 0.6.4\r\n\r\nGL version: 4.6.0 NVIDIA 450.80.02\r\nMAX_TEXTURE_SIZE: 32768\r\n\r\nPlugins:\r\n- napari-plugin-engine: 0.1.5\r\n- svg: 0.1.3\r\n\r\n## Additional context\r\nThis relates to the fact that the shader manipulates the alpha values of the vertices directly, late in the rendering pipeline.\n", "before_files": [{"content": "from vispy.scene.visuals import Compound, Line, Text\n\nfrom ._vispy_tracks_shader import TrackShader\nfrom .vispy_base_layer import VispyBaseLayer\n\n\nclass VispyTracksLayer(VispyBaseLayer):\n \"\"\"VispyTracksLayer\n\n Track layer for visualizing tracks.\n\n Components:\n - Track lines (vispy.LineVisual)\n - Track IDs (vispy.TextVisual)\n - Graph edges (vispy.LineVisual)\n\n \"\"\"\n\n def __init__(self, layer):\n node = Compound([Line(), Text(), Line()])\n super().__init__(layer, node)\n\n self.layer.events.tail_width.connect(self._on_appearance_change)\n self.layer.events.tail_length.connect(self._on_appearance_change)\n self.layer.events.display_id.connect(self._on_appearance_change)\n self.layer.events.display_tail.connect(self._on_appearance_change)\n self.layer.events.display_graph.connect(self._on_appearance_change)\n\n self.layer.events.color_by.connect(self._on_appearance_change)\n self.layer.events.colormap.connect(self._on_appearance_change)\n\n # these events are fired when changes occur to the tracks or the\n # graph - as the vertex buffer of the shader needs to be updated\n # alongside the actual vertex data\n self.layer.events.rebuild_tracks.connect(self._on_tracks_change)\n self.layer.events.rebuild_graph.connect(self._on_graph_change)\n\n # build and attach the shader to the track\n self.track_shader = TrackShader()\n self.graph_shader = TrackShader()\n node._subvisuals[0].attach(self.track_shader)\n node._subvisuals[2].attach(self.graph_shader)\n\n # text label properties\n self.node._subvisuals[1].color = 'white'\n self.node._subvisuals[1].font_size = 8\n\n self._reset_base()\n\n self._on_data_change()\n self._on_appearance_change()\n\n def _on_data_change(self, event=None):\n \"\"\" update the display \"\"\"\n\n # update the shaders\n self.track_shader.current_time = self.layer.current_time\n self.graph_shader.current_time = self.layer.current_time\n\n # add text labels if they're visible\n if self.node._subvisuals[1].visible:\n labels_text, labels_pos = self.layer.track_labels\n self.node._subvisuals[1].text = labels_text\n self.node._subvisuals[1].pos = labels_pos\n\n self.node.update()\n # Call to update order of translation values with new dims:\n self._on_matrix_change()\n\n def _on_appearance_change(self, event=None):\n \"\"\" change the appearance of the data \"\"\"\n\n # update shader properties related to appearance\n self.track_shader.use_fade = self.layer.use_fade\n self.track_shader.tail_length = self.layer.tail_length\n self.graph_shader.use_fade = self.layer.use_fade\n self.graph_shader.tail_length = self.layer.tail_length\n\n # set visibility of subvisuals\n self.node._subvisuals[0].visible = self.layer.display_tail\n self.node._subvisuals[1].visible = self.layer.display_id\n self.node._subvisuals[2].visible = self.layer.display_graph\n\n # set the width of the track tails\n self.node._subvisuals[0].set_data(\n width=self.layer.tail_width, color=self.layer.track_colors,\n )\n self.node._subvisuals[2].set_data(width=self.layer.tail_width,)\n\n def _on_tracks_change(self, event=None):\n \"\"\" update the shader when the track data changes \"\"\"\n\n self.track_shader.use_fade = self.layer.use_fade\n self.track_shader.tail_length = self.layer.tail_length\n self.track_shader.vertex_time = self.layer.track_times\n\n # change the data to the vispy line visual\n self.node._subvisuals[0].set_data(\n pos=self.layer._view_data,\n connect=self.layer.track_connex,\n width=self.layer.tail_width,\n color=self.layer.track_colors,\n )\n\n # Call to update order of translation values with new dims:\n self._on_matrix_change()\n\n def _on_graph_change(self, event=None):\n \"\"\" update the shader when the graph data changes \"\"\"\n\n self.graph_shader.use_fade = self.layer.use_fade\n self.graph_shader.tail_length = self.layer.tail_length\n self.graph_shader.vertex_time = self.layer.graph_times\n\n # if the user clears a graph after it has been created, vispy offers\n # no method to clear the data, therefore, we need to set private\n # attributes to None to prevent errors\n if self.layer._view_graph is None:\n self.node._subvisuals[2]._pos = None\n self.node._subvisuals[2]._connect = None\n self.node.update()\n return\n\n self.node._subvisuals[2].set_data(\n pos=self.layer._view_graph,\n connect=self.layer.graph_connex,\n width=self.layer.tail_width,\n color='white',\n )\n\n # Call to update order of translation values with new dims:\n self._on_matrix_change()\n", "path": "napari/_vispy/vispy_tracks_layer.py"}, {"content": "from typing import List, Union\n\nimport numpy as np\nfrom vispy.gloo import VertexBuffer\nfrom vispy.visuals.filters.base_filter import Filter\n\n\nclass TrackShader(Filter):\n \"\"\" TrackShader\n\n Custom vertex and fragment shaders for visualizing tracks quickly with\n vispy. The central assumption is that the tracks are rendered as a\n continuous vispy Line segment, with connections and colors defined when\n the visual is created.\n\n The shader simply changes the visibility and/or fading of the data according\n to the current_time and the associate time metadata for each vertex. This\n is scaled according to the tail length. Points ahead of the current time\n are rendered with alpha set to zero.\n\n Parameters\n ----------\n current_time : int, float\n the current time, which is typically the frame index, although this\n can be an arbitrary float\n tail_length : int, float\n the upper limit on length of the 'tail'\n use_fade : bool\n this will enable/disable tail fading with time\n vertex_time : 1D array, list\n a vector describing the time associated with each vertex\n\n\n TODO\n ----\n - the track is still displayed, albeit with fading, once the track has\n finished but is still within the 'tail_length' window. Should it\n disappear?\n - check the shader positioning within the GL pipeline, currently\n overrides layer opacity settings\n\n vertex_mask: 1D array, list\n a vector describing whether to mask each vertex\n\n \"\"\"\n\n VERT_SHADER = \"\"\"\n varying vec4 v_track_color;\n void apply_track_shading() {\n\n float alpha;\n\n if ($a_vertex_time > $current_time) {\n // this is a hack to minimize the frag shader rendering ahead\n // of the current time point due to interpolation\n if ($a_vertex_time <= $current_time + 1){\n alpha = -100.;\n } else {\n alpha = 0.;\n }\n } else {\n // fade the track into the temporal distance, scaled by the\n // maximum tail length from the gui\n float fade = ($current_time - $a_vertex_time) / $tail_length;\n alpha = clamp(1.0-fade, 0.0, 1.0);\n }\n\n // when use_fade is disabled, the entire track is visible\n if ($use_fade == 0) {\n alpha = 1.0;\n }\n\n // set the vertex alpha according to the fade\n v_track_color.a = alpha;\n }\n \"\"\"\n\n FRAG_SHADER = \"\"\"\n varying vec4 v_track_color;\n void apply_track_shading() {\n // interpolate\n gl_FragColor.a = clamp(v_track_color.a, 0.0, 1.0);\n }\n \"\"\"\n\n def __init__(\n self,\n current_time=0,\n tail_length=30,\n use_fade: bool = True,\n vertex_time: Union[List, np.ndarray] = None,\n ):\n\n super().__init__(\n vcode=self.VERT_SHADER, vpos=3, fcode=self.FRAG_SHADER, fpos=9\n )\n\n self.current_time = current_time\n self.tail_length = tail_length\n self.use_fade = use_fade\n self.vertex_time = vertex_time\n\n @property\n def current_time(self) -> Union[int, float]:\n return self._current_time\n\n @current_time.setter\n def current_time(self, n: Union[int, float]):\n self._current_time = n\n if isinstance(n, slice):\n n = np.max(self._vertex_time)\n self.vshader['current_time'] = float(n)\n\n @property\n def use_fade(self) -> bool:\n return self._use_fade\n\n @use_fade.setter\n def use_fade(self, value: bool):\n self._use_fade = value\n self.vshader['use_fade'] = float(self._use_fade)\n\n @property\n def tail_length(self) -> Union[int, float]:\n return self._tail_length\n\n @tail_length.setter\n def tail_length(self, tail_length: Union[int, float]):\n self._tail_length = tail_length\n self.vshader['tail_length'] = float(self._tail_length)\n\n def _attach(self, visual):\n super()._attach(visual)\n\n @property\n def vertex_time(self):\n return self._vertex_time\n\n @vertex_time.setter\n def vertex_time(self, v_time):\n self._vertex_time = np.array(v_time).reshape(-1, 1).astype(np.float32)\n self.vshader['a_vertex_time'] = VertexBuffer(self.vertex_time)\n", "path": "napari/_vispy/_vispy_tracks_shader.py"}], "after_files": [{"content": "from vispy.scene.visuals import Compound, Line, Text\n\nfrom ._vispy_tracks_shader import TrackShader\nfrom .vispy_base_layer import VispyBaseLayer\n\n\nclass VispyTracksLayer(VispyBaseLayer):\n \"\"\"VispyTracksLayer\n\n Track layer for visualizing tracks.\n\n Components:\n - Track lines (vispy.LineVisual)\n - Track IDs (vispy.TextVisual)\n - Graph edges (vispy.LineVisual)\n\n \"\"\"\n\n def __init__(self, layer):\n node = Compound([Line(), Text(), Line()])\n super().__init__(layer, node)\n\n self.layer.events.tail_width.connect(self._on_appearance_change)\n self.layer.events.tail_length.connect(self._on_appearance_change)\n self.layer.events.display_id.connect(self._on_appearance_change)\n self.layer.events.display_tail.connect(self._on_appearance_change)\n self.layer.events.display_graph.connect(self._on_appearance_change)\n\n self.layer.events.color_by.connect(self._on_appearance_change)\n self.layer.events.colormap.connect(self._on_appearance_change)\n\n # these events are fired when changes occur to the tracks or the\n # graph - as the vertex buffer of the shader needs to be updated\n # alongside the actual vertex data\n self.layer.events.rebuild_tracks.connect(self._on_tracks_change)\n self.layer.events.rebuild_graph.connect(self._on_graph_change)\n\n # build and attach the shader to the track\n self.track_shader = TrackShader()\n self.graph_shader = TrackShader()\n node._subvisuals[0].attach(self.track_shader)\n node._subvisuals[2].attach(self.graph_shader)\n\n # text label properties\n self.node._subvisuals[1].color = 'white'\n self.node._subvisuals[1].font_size = 8\n\n self._reset_base()\n\n self._on_data_change()\n self._on_appearance_change()\n\n def _on_data_change(self, event=None):\n \"\"\"Update the display.\"\"\"\n\n # update the shaders\n self.track_shader.current_time = self.layer.current_time\n self.graph_shader.current_time = self.layer.current_time\n\n # add text labels if they're visible\n if self.node._subvisuals[1].visible:\n labels_text, labels_pos = self.layer.track_labels\n self.node._subvisuals[1].text = labels_text\n self.node._subvisuals[1].pos = labels_pos\n\n self.node.update()\n # Call to update order of translation values with new dims:\n self._on_matrix_change()\n\n def _on_appearance_change(self, event=None):\n \"\"\"Change the appearance of the data.\"\"\"\n\n # update shader properties related to appearance\n self.track_shader.use_fade = self.layer.use_fade\n self.track_shader.tail_length = self.layer.tail_length\n self.graph_shader.use_fade = self.layer.use_fade\n self.graph_shader.tail_length = self.layer.tail_length\n\n # set visibility of subvisuals\n self.node._subvisuals[0].visible = self.layer.display_tail\n self.node._subvisuals[1].visible = self.layer.display_id\n self.node._subvisuals[2].visible = self.layer.display_graph\n\n # set the width of the track tails\n self.node._subvisuals[0].set_data(\n width=self.layer.tail_width, color=self.layer.track_colors,\n )\n self.node._subvisuals[2].set_data(width=self.layer.tail_width,)\n\n def _on_tracks_change(self, event=None):\n \"\"\"Update the shader when the track data changes.\"\"\"\n\n self.track_shader.use_fade = self.layer.use_fade\n self.track_shader.tail_length = self.layer.tail_length\n self.track_shader.vertex_time = self.layer.track_times\n\n # change the data to the vispy line visual\n self.node._subvisuals[0].set_data(\n pos=self.layer._view_data,\n connect=self.layer.track_connex,\n width=self.layer.tail_width,\n color=self.layer.track_colors,\n )\n\n # Call to update order of translation values with new dims:\n self._on_matrix_change()\n\n def _on_graph_change(self, event=None):\n \"\"\"Update the shader when the graph data changes.\"\"\"\n\n self.graph_shader.use_fade = self.layer.use_fade\n self.graph_shader.tail_length = self.layer.tail_length\n self.graph_shader.vertex_time = self.layer.graph_times\n\n # if the user clears a graph after it has been created, vispy offers\n # no method to clear the data, therefore, we need to set private\n # attributes to None to prevent errors\n if self.layer._view_graph is None:\n self.node._subvisuals[2]._pos = None\n self.node._subvisuals[2]._connect = None\n self.node.update()\n return\n\n self.node._subvisuals[2].set_data(\n pos=self.layer._view_graph,\n connect=self.layer.graph_connex,\n width=self.layer.tail_width,\n color='white',\n )\n\n # Call to update order of translation values with new dims:\n self._on_matrix_change()\n", "path": "napari/_vispy/vispy_tracks_layer.py"}, {"content": "from typing import List, Union\n\nimport numpy as np\nfrom vispy.gloo import VertexBuffer\nfrom vispy.visuals.filters.base_filter import Filter\n\n\nclass TrackShader(Filter):\n \"\"\"TrackShader.\n\n Custom vertex and fragment shaders for visualizing tracks quickly with\n vispy. The central assumption is that the tracks are rendered as a\n continuous vispy Line segment, with connections and colors defined when\n the visual is created.\n\n The shader simply changes the visibility and/or fading of the data according\n to the current_time and the associate time metadata for each vertex. This\n is scaled according to the tail length. Points ahead of the current time\n are rendered with alpha set to zero.\n\n Parameters\n ----------\n current_time : int, float\n the current time, which is typically the frame index, although this\n can be an arbitrary float\n tail_length : int, float\n the upper limit on length of the 'tail'\n use_fade : bool\n this will enable/disable tail fading with time\n vertex_time : 1D array, list\n a vector describing the time associated with each vertex\n\n TODO\n ----\n - the track is still displayed, albeit with fading, once the track has\n finished but is still within the 'tail_length' window. Should it\n disappear?\n\n \"\"\"\n\n VERT_SHADER = \"\"\"\n varying vec4 v_track_color;\n void apply_track_shading() {\n\n float alpha;\n\n if ($a_vertex_time > $current_time) {\n // this is a hack to minimize the frag shader rendering ahead\n // of the current time point due to interpolation\n if ($a_vertex_time <= $current_time + 1){\n alpha = -100.;\n } else {\n alpha = 0.;\n }\n } else {\n // fade the track into the temporal distance, scaled by the\n // maximum tail length from the gui\n float fade = ($current_time - $a_vertex_time) / $tail_length;\n alpha = clamp(1.0-fade, 0.0, 1.0);\n }\n\n // when use_fade is disabled, the entire track is visible\n if ($use_fade == 0) {\n alpha = 1.0;\n }\n\n // set the vertex alpha according to the fade\n v_track_color.a = alpha;\n }\n \"\"\"\n\n FRAG_SHADER = \"\"\"\n varying vec4 v_track_color;\n void apply_track_shading() {\n\n // if the alpha is below the threshold, discard the fragment\n if( v_track_color.a <= 0.0 ) {\n discard;\n }\n\n // interpolate\n gl_FragColor.a = clamp(v_track_color.a * gl_FragColor.a, 0.0, 1.0);\n }\n \"\"\"\n\n def __init__(\n self,\n current_time: Union[int, float] = 0,\n tail_length: Union[int, float] = 30,\n use_fade: bool = True,\n vertex_time: Union[List, np.ndarray] = None,\n ):\n\n super().__init__(\n vcode=self.VERT_SHADER, vpos=3, fcode=self.FRAG_SHADER, fpos=9\n )\n\n self.current_time = current_time\n self.tail_length = tail_length\n self.use_fade = use_fade\n self.vertex_time = vertex_time\n\n @property\n def current_time(self) -> Union[int, float]:\n return self._current_time\n\n @current_time.setter\n def current_time(self, n: Union[int, float]):\n self._current_time = n\n if isinstance(n, slice):\n n = np.max(self._vertex_time)\n self.vshader['current_time'] = float(n)\n\n @property\n def use_fade(self) -> bool:\n return self._use_fade\n\n @use_fade.setter\n def use_fade(self, value: bool):\n self._use_fade = value\n self.vshader['use_fade'] = float(self._use_fade)\n\n @property\n def tail_length(self) -> Union[int, float]:\n return self._tail_length\n\n @tail_length.setter\n def tail_length(self, tail_length: Union[int, float]):\n self._tail_length = tail_length\n self.vshader['tail_length'] = float(self._tail_length)\n\n def _attach(self, visual):\n super()._attach(visual)\n\n @property\n def vertex_time(self):\n return self._vertex_time\n\n @vertex_time.setter\n def vertex_time(self, v_time):\n self._vertex_time = np.array(v_time).reshape(-1, 1).astype(np.float32)\n self.vshader['a_vertex_time'] = VertexBuffer(self.vertex_time)\n", "path": "napari/_vispy/_vispy_tracks_shader.py"}]}
| 3,538 | 837 |
gh_patches_debug_32652
|
rasdani/github-patches
|
git_diff
|
getnikola__nikola-1267
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Unable to use Tidy on html
Hi,
I enabled the tidy filter on html file:
from nikola import filters
FILTERS = {
".html": [filters.tidy],
}
and now NIkola refuses to build my site:
TaskError - taskid:render_tags:../categories/index.html
PythonAction Error
Traceback (most recent call last):
File "/usr/lib64/python3.3/site-packages/doit/action.py", line 360, in execute
returned_value = self.py_callable(_self.args, *_kwargs)
File "/usr/lib64/python3.3/site-packages/nikola/utils.py", line 529, in unlessLink
action(target)
File "/usr/lib64/python3.3/site-packages/nikola/filters.py", line 144, in tidy
for line in output.split("\n"):
TypeError: Type str doesn't support the buffer AP
Is there a problem with tidy ? Can I use another thing as a replacement ?
Unable to use Tidy on html
Hi,
I enabled the tidy filter on html file:
from nikola import filters
FILTERS = {
".html": [filters.tidy],
}
and now NIkola refuses to build my site:
TaskError - taskid:render_tags:../categories/index.html
PythonAction Error
Traceback (most recent call last):
File "/usr/lib64/python3.3/site-packages/doit/action.py", line 360, in execute
returned_value = self.py_callable(_self.args, *_kwargs)
File "/usr/lib64/python3.3/site-packages/nikola/utils.py", line 529, in unlessLink
action(target)
File "/usr/lib64/python3.3/site-packages/nikola/filters.py", line 144, in tidy
for line in output.split("\n"):
TypeError: Type str doesn't support the buffer AP
Is there a problem with tidy ? Can I use another thing as a replacement ?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `nikola/filters.py`
Content:
```
1 # -*- coding: utf-8 -*-
2
3 # Copyright © 2012-2014 Roberto Alsina and others.
4
5 # Permission is hereby granted, free of charge, to any
6 # person obtaining a copy of this software and associated
7 # documentation files (the "Software"), to deal in the
8 # Software without restriction, including without limitation
9 # the rights to use, copy, modify, merge, publish,
10 # distribute, sublicense, and/or sell copies of the
11 # Software, and to permit persons to whom the Software is
12 # furnished to do so, subject to the following conditions:
13 #
14 # The above copyright notice and this permission notice
15 # shall be included in all copies or substantial portions of
16 # the Software.
17 #
18 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
19 # KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
20 # WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
21 # PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
22 # OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
23 # OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
24 # OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
25 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
26
27 """Utility functions to help you run filters on files."""
28
29 from .utils import req_missing
30 from functools import wraps
31 import os
32 import codecs
33 import re
34 import shutil
35 import subprocess
36 import tempfile
37 import shlex
38
39 try:
40 import typogrify.filters as typo
41 except ImportError:
42 typo = None # NOQA
43
44
45 def apply_to_binary_file(f):
46 """Take a function f that transforms a data argument, and returns
47 a function that takes a filename and applies f to the contents,
48 in place. Reads files in binary mode."""
49 @wraps(f)
50 def f_in_file(fname):
51 with open(fname, 'rb') as inf:
52 data = inf.read()
53 data = f(data)
54 with open(fname, 'wb+') as outf:
55 outf.write(data)
56
57 return f_in_file
58
59
60 def apply_to_text_file(f):
61 """Take a function f that transforms a data argument, and returns
62 a function that takes a filename and applies f to the contents,
63 in place. Reads files in UTF-8."""
64 @wraps(f)
65 def f_in_file(fname):
66 with codecs.open(fname, 'r', 'utf-8') as inf:
67 data = inf.read()
68 data = f(data)
69 with codecs.open(fname, 'w+', 'utf-8') as outf:
70 outf.write(data)
71
72 return f_in_file
73
74
75 def list_replace(the_list, find, replacement):
76 "Replace all occurrences of ``find`` with ``replacement`` in ``the_list``"
77 for i, v in enumerate(the_list):
78 if v == find:
79 the_list[i] = replacement
80
81
82 def runinplace(command, infile):
83 """Run a command in-place on a file.
84
85 command is a string of the form: "commandname %1 %2" and
86 it will be execed with infile as %1 and a temporary file
87 as %2. Then, that temporary file will be moved over %1.
88
89 Example usage:
90
91 runinplace("yui-compressor %1 -o %2", "myfile.css")
92
93 That will replace myfile.css with a minified version.
94
95 You can also supply command as a list.
96 """
97
98 if not isinstance(command, list):
99 command = shlex.split(command)
100
101 tmpdir = None
102
103 if "%2" in command:
104 tmpdir = tempfile.mkdtemp(prefix="nikola")
105 tmpfname = os.path.join(tmpdir, os.path.basename(infile))
106
107 try:
108 list_replace(command, "%1", infile)
109 if tmpdir:
110 list_replace(command, "%2", tmpfname)
111
112 subprocess.check_call(command)
113
114 if tmpdir:
115 shutil.move(tmpfname, infile)
116 finally:
117 if tmpdir:
118 shutil.rmtree(tmpdir)
119
120
121 def yui_compressor(infile):
122 yuicompressor = False
123 try:
124 subprocess.call('yui-compressor', stdout=open(os.devnull, 'w'), stderr=open(os.devnull, 'w'))
125 yuicompressor = 'yui-compressor'
126 except Exception:
127 pass
128 if not yuicompressor:
129 try:
130 subprocess.call('yuicompressor', stdout=open(os.devnull, 'w'), stderr=open(os.devnull, 'w'))
131 yuicompressor = 'yuicompressor'
132 except:
133 raise Exception("yui-compressor is not installed.")
134 return False
135
136 return runinplace(r'{} --nomunge %1 -o %2'.format(yuicompressor), infile)
137
138
139 def optipng(infile):
140 return runinplace(r"optipng -preserve -o2 -quiet %1", infile)
141
142
143 def jpegoptim(infile):
144 return runinplace(r"jpegoptim -p --strip-all -q %1", infile)
145
146
147 def tidy(inplace):
148 # Google site verifcation files are not HTML
149 if re.match(r"google[a-f0-9]+.html", os.path.basename(inplace)) \
150 and open(inplace).readline().startswith(
151 "google-site-verification:"):
152 return
153
154 # Tidy will give error exits, that we will ignore.
155 output = subprocess.check_output(
156 "tidy -m -w 90 --indent no --quote-marks"
157 "no --keep-time yes --tidy-mark no "
158 "--force-output yes '{0}'; exit 0".format(inplace), stderr=subprocess.STDOUT, shell=True)
159
160 for line in output.split("\n"):
161 if "Warning:" in line:
162 if '<meta> proprietary attribute "charset"' in line:
163 # We want to set it though.
164 continue
165 elif '<meta> lacks "content" attribute' in line:
166 # False alarm to me.
167 continue
168 elif '<div> anchor' in line and 'already defined' in line:
169 # Some seeming problem with JavaScript terminators.
170 continue
171 elif '<img> lacks "alt" attribute' in line:
172 # Happens in gallery code, probably can be tolerated.
173 continue
174 elif '<table> lacks "summary" attribute' in line:
175 # Happens for tables, TODO: Check this is normal.
176 continue
177 elif 'proprietary attribute "data-toggle"' in line or \
178 'proprietary attribute "data-target"':
179 # Some of our own tricks
180 continue
181 else:
182 assert False, (inplace, line)
183 elif "Error:" in line:
184 if '<time> is not recognized' in line:
185 # False alarm, time is proper HTML5.
186 continue
187 else:
188 assert False, line
189
190
191 @apply_to_text_file
192 def typogrify(data):
193 if typo is None:
194 req_missing(['typogrify'], 'use the typogrify filter')
195
196 data = typo.amp(data)
197 data = typo.widont(data)
198 data = typo.smartypants(data)
199 # Disabled because of typogrify bug where it breaks <title>
200 # data = typo.caps(data)
201 data = typo.initial_quotes(data)
202 return data
203
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/nikola/filters.py b/nikola/filters.py
--- a/nikola/filters.py
+++ b/nikola/filters.py
@@ -30,7 +30,6 @@
from functools import wraps
import os
import codecs
-import re
import shutil
import subprocess
import tempfile
@@ -144,50 +143,6 @@
return runinplace(r"jpegoptim -p --strip-all -q %1", infile)
-def tidy(inplace):
- # Google site verifcation files are not HTML
- if re.match(r"google[a-f0-9]+.html", os.path.basename(inplace)) \
- and open(inplace).readline().startswith(
- "google-site-verification:"):
- return
-
- # Tidy will give error exits, that we will ignore.
- output = subprocess.check_output(
- "tidy -m -w 90 --indent no --quote-marks"
- "no --keep-time yes --tidy-mark no "
- "--force-output yes '{0}'; exit 0".format(inplace), stderr=subprocess.STDOUT, shell=True)
-
- for line in output.split("\n"):
- if "Warning:" in line:
- if '<meta> proprietary attribute "charset"' in line:
- # We want to set it though.
- continue
- elif '<meta> lacks "content" attribute' in line:
- # False alarm to me.
- continue
- elif '<div> anchor' in line and 'already defined' in line:
- # Some seeming problem with JavaScript terminators.
- continue
- elif '<img> lacks "alt" attribute' in line:
- # Happens in gallery code, probably can be tolerated.
- continue
- elif '<table> lacks "summary" attribute' in line:
- # Happens for tables, TODO: Check this is normal.
- continue
- elif 'proprietary attribute "data-toggle"' in line or \
- 'proprietary attribute "data-target"':
- # Some of our own tricks
- continue
- else:
- assert False, (inplace, line)
- elif "Error:" in line:
- if '<time> is not recognized' in line:
- # False alarm, time is proper HTML5.
- continue
- else:
- assert False, line
-
-
@apply_to_text_file
def typogrify(data):
if typo is None:
|
{"golden_diff": "diff --git a/nikola/filters.py b/nikola/filters.py\n--- a/nikola/filters.py\n+++ b/nikola/filters.py\n@@ -30,7 +30,6 @@\n from functools import wraps\n import os\n import codecs\n-import re\n import shutil\n import subprocess\n import tempfile\n@@ -144,50 +143,6 @@\n return runinplace(r\"jpegoptim -p --strip-all -q %1\", infile)\n \n \n-def tidy(inplace):\n- # Google site verifcation files are not HTML\n- if re.match(r\"google[a-f0-9]+.html\", os.path.basename(inplace)) \\\n- and open(inplace).readline().startswith(\n- \"google-site-verification:\"):\n- return\n-\n- # Tidy will give error exits, that we will ignore.\n- output = subprocess.check_output(\n- \"tidy -m -w 90 --indent no --quote-marks\"\n- \"no --keep-time yes --tidy-mark no \"\n- \"--force-output yes '{0}'; exit 0\".format(inplace), stderr=subprocess.STDOUT, shell=True)\n-\n- for line in output.split(\"\\n\"):\n- if \"Warning:\" in line:\n- if '<meta> proprietary attribute \"charset\"' in line:\n- # We want to set it though.\n- continue\n- elif '<meta> lacks \"content\" attribute' in line:\n- # False alarm to me.\n- continue\n- elif '<div> anchor' in line and 'already defined' in line:\n- # Some seeming problem with JavaScript terminators.\n- continue\n- elif '<img> lacks \"alt\" attribute' in line:\n- # Happens in gallery code, probably can be tolerated.\n- continue\n- elif '<table> lacks \"summary\" attribute' in line:\n- # Happens for tables, TODO: Check this is normal.\n- continue\n- elif 'proprietary attribute \"data-toggle\"' in line or \\\n- 'proprietary attribute \"data-target\"':\n- # Some of our own tricks\n- continue\n- else:\n- assert False, (inplace, line)\n- elif \"Error:\" in line:\n- if '<time> is not recognized' in line:\n- # False alarm, time is proper HTML5.\n- continue\n- else:\n- assert False, line\n-\n-\n @apply_to_text_file\n def typogrify(data):\n if typo is None:\n", "issue": "Unable to use Tidy on html\nHi, \n\nI enabled the tidy filter on html file:\n\nfrom nikola import filters\nFILTERS = {\n \".html\": [filters.tidy],\n }\n\nand now NIkola refuses to build my site: \n\nTaskError - taskid:render_tags:../categories/index.html\nPythonAction Error\nTraceback (most recent call last):\n File \"/usr/lib64/python3.3/site-packages/doit/action.py\", line 360, in execute\n returned_value = self.py_callable(_self.args, *_kwargs)\n File \"/usr/lib64/python3.3/site-packages/nikola/utils.py\", line 529, in unlessLink\n action(target)\n File \"/usr/lib64/python3.3/site-packages/nikola/filters.py\", line 144, in tidy\n for line in output.split(\"\\n\"):\nTypeError: Type str doesn't support the buffer AP\n\nIs there a problem with tidy ? Can I use another thing as a replacement ?\n\nUnable to use Tidy on html\nHi, \n\nI enabled the tidy filter on html file:\n\nfrom nikola import filters\nFILTERS = {\n \".html\": [filters.tidy],\n }\n\nand now NIkola refuses to build my site: \n\nTaskError - taskid:render_tags:../categories/index.html\nPythonAction Error\nTraceback (most recent call last):\n File \"/usr/lib64/python3.3/site-packages/doit/action.py\", line 360, in execute\n returned_value = self.py_callable(_self.args, *_kwargs)\n File \"/usr/lib64/python3.3/site-packages/nikola/utils.py\", line 529, in unlessLink\n action(target)\n File \"/usr/lib64/python3.3/site-packages/nikola/filters.py\", line 144, in tidy\n for line in output.split(\"\\n\"):\nTypeError: Type str doesn't support the buffer AP\n\nIs there a problem with tidy ? Can I use another thing as a replacement ?\n\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n\n# Copyright \u00a9 2012-2014 Roberto Alsina and others.\n\n# Permission is hereby granted, free of charge, to any\n# person obtaining a copy of this software and associated\n# documentation files (the \"Software\"), to deal in the\n# Software without restriction, including without limitation\n# the rights to use, copy, modify, merge, publish,\n# distribute, sublicense, and/or sell copies of the\n# Software, and to permit persons to whom the Software is\n# furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice\n# shall be included in all copies or substantial portions of\n# the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY\n# KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE\n# WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR\n# PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS\n# OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR\n# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR\n# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE\n# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\n\"\"\"Utility functions to help you run filters on files.\"\"\"\n\nfrom .utils import req_missing\nfrom functools import wraps\nimport os\nimport codecs\nimport re\nimport shutil\nimport subprocess\nimport tempfile\nimport shlex\n\ntry:\n import typogrify.filters as typo\nexcept ImportError:\n typo = None # NOQA\n\n\ndef apply_to_binary_file(f):\n \"\"\"Take a function f that transforms a data argument, and returns\n a function that takes a filename and applies f to the contents,\n in place. Reads files in binary mode.\"\"\"\n @wraps(f)\n def f_in_file(fname):\n with open(fname, 'rb') as inf:\n data = inf.read()\n data = f(data)\n with open(fname, 'wb+') as outf:\n outf.write(data)\n\n return f_in_file\n\n\ndef apply_to_text_file(f):\n \"\"\"Take a function f that transforms a data argument, and returns\n a function that takes a filename and applies f to the contents,\n in place. Reads files in UTF-8.\"\"\"\n @wraps(f)\n def f_in_file(fname):\n with codecs.open(fname, 'r', 'utf-8') as inf:\n data = inf.read()\n data = f(data)\n with codecs.open(fname, 'w+', 'utf-8') as outf:\n outf.write(data)\n\n return f_in_file\n\n\ndef list_replace(the_list, find, replacement):\n \"Replace all occurrences of ``find`` with ``replacement`` in ``the_list``\"\n for i, v in enumerate(the_list):\n if v == find:\n the_list[i] = replacement\n\n\ndef runinplace(command, infile):\n \"\"\"Run a command in-place on a file.\n\n command is a string of the form: \"commandname %1 %2\" and\n it will be execed with infile as %1 and a temporary file\n as %2. Then, that temporary file will be moved over %1.\n\n Example usage:\n\n runinplace(\"yui-compressor %1 -o %2\", \"myfile.css\")\n\n That will replace myfile.css with a minified version.\n\n You can also supply command as a list.\n \"\"\"\n\n if not isinstance(command, list):\n command = shlex.split(command)\n\n tmpdir = None\n\n if \"%2\" in command:\n tmpdir = tempfile.mkdtemp(prefix=\"nikola\")\n tmpfname = os.path.join(tmpdir, os.path.basename(infile))\n\n try:\n list_replace(command, \"%1\", infile)\n if tmpdir:\n list_replace(command, \"%2\", tmpfname)\n\n subprocess.check_call(command)\n\n if tmpdir:\n shutil.move(tmpfname, infile)\n finally:\n if tmpdir:\n shutil.rmtree(tmpdir)\n\n\ndef yui_compressor(infile):\n yuicompressor = False\n try:\n subprocess.call('yui-compressor', stdout=open(os.devnull, 'w'), stderr=open(os.devnull, 'w'))\n yuicompressor = 'yui-compressor'\n except Exception:\n pass\n if not yuicompressor:\n try:\n subprocess.call('yuicompressor', stdout=open(os.devnull, 'w'), stderr=open(os.devnull, 'w'))\n yuicompressor = 'yuicompressor'\n except:\n raise Exception(\"yui-compressor is not installed.\")\n return False\n\n return runinplace(r'{} --nomunge %1 -o %2'.format(yuicompressor), infile)\n\n\ndef optipng(infile):\n return runinplace(r\"optipng -preserve -o2 -quiet %1\", infile)\n\n\ndef jpegoptim(infile):\n return runinplace(r\"jpegoptim -p --strip-all -q %1\", infile)\n\n\ndef tidy(inplace):\n # Google site verifcation files are not HTML\n if re.match(r\"google[a-f0-9]+.html\", os.path.basename(inplace)) \\\n and open(inplace).readline().startswith(\n \"google-site-verification:\"):\n return\n\n # Tidy will give error exits, that we will ignore.\n output = subprocess.check_output(\n \"tidy -m -w 90 --indent no --quote-marks\"\n \"no --keep-time yes --tidy-mark no \"\n \"--force-output yes '{0}'; exit 0\".format(inplace), stderr=subprocess.STDOUT, shell=True)\n\n for line in output.split(\"\\n\"):\n if \"Warning:\" in line:\n if '<meta> proprietary attribute \"charset\"' in line:\n # We want to set it though.\n continue\n elif '<meta> lacks \"content\" attribute' in line:\n # False alarm to me.\n continue\n elif '<div> anchor' in line and 'already defined' in line:\n # Some seeming problem with JavaScript terminators.\n continue\n elif '<img> lacks \"alt\" attribute' in line:\n # Happens in gallery code, probably can be tolerated.\n continue\n elif '<table> lacks \"summary\" attribute' in line:\n # Happens for tables, TODO: Check this is normal.\n continue\n elif 'proprietary attribute \"data-toggle\"' in line or \\\n 'proprietary attribute \"data-target\"':\n # Some of our own tricks\n continue\n else:\n assert False, (inplace, line)\n elif \"Error:\" in line:\n if '<time> is not recognized' in line:\n # False alarm, time is proper HTML5.\n continue\n else:\n assert False, line\n\n\n@apply_to_text_file\ndef typogrify(data):\n if typo is None:\n req_missing(['typogrify'], 'use the typogrify filter')\n\n data = typo.amp(data)\n data = typo.widont(data)\n data = typo.smartypants(data)\n # Disabled because of typogrify bug where it breaks <title>\n # data = typo.caps(data)\n data = typo.initial_quotes(data)\n return data\n", "path": "nikola/filters.py"}], "after_files": [{"content": "# -*- coding: utf-8 -*-\n\n# Copyright \u00a9 2012-2014 Roberto Alsina and others.\n\n# Permission is hereby granted, free of charge, to any\n# person obtaining a copy of this software and associated\n# documentation files (the \"Software\"), to deal in the\n# Software without restriction, including without limitation\n# the rights to use, copy, modify, merge, publish,\n# distribute, sublicense, and/or sell copies of the\n# Software, and to permit persons to whom the Software is\n# furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice\n# shall be included in all copies or substantial portions of\n# the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY\n# KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE\n# WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR\n# PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS\n# OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR\n# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR\n# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE\n# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\n\"\"\"Utility functions to help you run filters on files.\"\"\"\n\nfrom .utils import req_missing\nfrom functools import wraps\nimport os\nimport codecs\nimport shutil\nimport subprocess\nimport tempfile\nimport shlex\n\ntry:\n import typogrify.filters as typo\nexcept ImportError:\n typo = None # NOQA\n\n\ndef apply_to_binary_file(f):\n \"\"\"Take a function f that transforms a data argument, and returns\n a function that takes a filename and applies f to the contents,\n in place. Reads files in binary mode.\"\"\"\n @wraps(f)\n def f_in_file(fname):\n with open(fname, 'rb') as inf:\n data = inf.read()\n data = f(data)\n with open(fname, 'wb+') as outf:\n outf.write(data)\n\n return f_in_file\n\n\ndef apply_to_text_file(f):\n \"\"\"Take a function f that transforms a data argument, and returns\n a function that takes a filename and applies f to the contents,\n in place. Reads files in UTF-8.\"\"\"\n @wraps(f)\n def f_in_file(fname):\n with codecs.open(fname, 'r', 'utf-8') as inf:\n data = inf.read()\n data = f(data)\n with codecs.open(fname, 'w+', 'utf-8') as outf:\n outf.write(data)\n\n return f_in_file\n\n\ndef list_replace(the_list, find, replacement):\n \"Replace all occurrences of ``find`` with ``replacement`` in ``the_list``\"\n for i, v in enumerate(the_list):\n if v == find:\n the_list[i] = replacement\n\n\ndef runinplace(command, infile):\n \"\"\"Run a command in-place on a file.\n\n command is a string of the form: \"commandname %1 %2\" and\n it will be execed with infile as %1 and a temporary file\n as %2. Then, that temporary file will be moved over %1.\n\n Example usage:\n\n runinplace(\"yui-compressor %1 -o %2\", \"myfile.css\")\n\n That will replace myfile.css with a minified version.\n\n You can also supply command as a list.\n \"\"\"\n\n if not isinstance(command, list):\n command = shlex.split(command)\n\n tmpdir = None\n\n if \"%2\" in command:\n tmpdir = tempfile.mkdtemp(prefix=\"nikola\")\n tmpfname = os.path.join(tmpdir, os.path.basename(infile))\n\n try:\n list_replace(command, \"%1\", infile)\n if tmpdir:\n list_replace(command, \"%2\", tmpfname)\n\n subprocess.check_call(command)\n\n if tmpdir:\n shutil.move(tmpfname, infile)\n finally:\n if tmpdir:\n shutil.rmtree(tmpdir)\n\n\ndef yui_compressor(infile):\n yuicompressor = False\n try:\n subprocess.call('yui-compressor', stdout=open(os.devnull, 'w'), stderr=open(os.devnull, 'w'))\n yuicompressor = 'yui-compressor'\n except Exception:\n pass\n if not yuicompressor:\n try:\n subprocess.call('yuicompressor', stdout=open(os.devnull, 'w'), stderr=open(os.devnull, 'w'))\n yuicompressor = 'yuicompressor'\n except:\n raise Exception(\"yui-compressor is not installed.\")\n return False\n\n return runinplace(r'{} --nomunge %1 -o %2'.format(yuicompressor), infile)\n\n\ndef optipng(infile):\n return runinplace(r\"optipng -preserve -o2 -quiet %1\", infile)\n\n\ndef jpegoptim(infile):\n return runinplace(r\"jpegoptim -p --strip-all -q %1\", infile)\n\n\n@apply_to_text_file\ndef typogrify(data):\n if typo is None:\n req_missing(['typogrify'], 'use the typogrify filter')\n\n data = typo.amp(data)\n data = typo.widont(data)\n data = typo.smartypants(data)\n # Disabled because of typogrify bug where it breaks <title>\n # data = typo.caps(data)\n data = typo.initial_quotes(data)\n return data\n", "path": "nikola/filters.py"}]}
| 2,767 | 554 |
gh_patches_debug_20428
|
rasdani/github-patches
|
git_diff
|
pyodide__pyodide-1231
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Minor fix: add parameter for shallowCopyToJavascript
Follow #1202
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `conftest.py`
Content:
```
1 """
2 Various common utilities for testing.
3 """
4
5 import contextlib
6 import multiprocessing
7 import textwrap
8 import tempfile
9 import time
10 import os
11 import pathlib
12 import queue
13 import sys
14 import shutil
15
16 ROOT_PATH = pathlib.Path(__file__).parents[0].resolve()
17 TEST_PATH = ROOT_PATH / "src" / "tests"
18 BUILD_PATH = ROOT_PATH / "build"
19
20 sys.path.append(str(ROOT_PATH))
21
22 from pyodide_build._fixes import _selenium_is_connectable # noqa: E402
23 import selenium.webdriver.common.utils # noqa: E402
24
25 # XXX: Temporary fix for ConnectionError in selenium
26
27 selenium.webdriver.common.utils.is_connectable = _selenium_is_connectable
28
29 try:
30 import pytest
31
32 def pytest_addoption(parser):
33 group = parser.getgroup("general")
34 group.addoption(
35 "--build-dir",
36 action="store",
37 default=BUILD_PATH,
38 help="Path to the build directory",
39 )
40 group.addoption(
41 "--run-xfail",
42 action="store_true",
43 help="If provided, tests marked as xfail will be run",
44 )
45
46
47 except ImportError:
48 pytest = None # type: ignore
49
50
51 class JavascriptException(Exception):
52 def __init__(self, msg, stack):
53 self.msg = msg
54 self.stack = stack
55 # In chrome the stack contains the message
56 if self.stack and self.stack.startswith(self.msg):
57 self.msg = ""
58
59 def __str__(self):
60 return "\n\n".join(x for x in [self.msg, self.stack] if x)
61
62
63 class SeleniumWrapper:
64 JavascriptException = JavascriptException
65
66 def __init__(
67 self, server_port, server_hostname="127.0.0.1", server_log=None, build_dir=None
68 ):
69 if build_dir is None:
70 build_dir = BUILD_PATH
71
72 self.driver = self.get_driver()
73 self.server_port = server_port
74 self.server_hostname = server_hostname
75 self.server_log = server_log
76
77 if not (pathlib.Path(build_dir) / "test.html").exists():
78 # selenium does not expose HTTP response codes
79 raise ValueError(
80 f"{(build_dir / 'test.html').resolve()} " f"does not exist!"
81 )
82 self.driver.get(f"http://{server_hostname}:{server_port}/test.html")
83 self.run_js("Error.stackTraceLimit = Infinity")
84 self.run_js("await languagePluginLoader")
85
86 @property
87 def logs(self):
88 logs = self.driver.execute_script("return window.logs")
89 if logs is not None:
90 return "\n".join(str(x) for x in logs)
91 else:
92 return ""
93
94 def clean_logs(self):
95 self.driver.execute_script("window.logs = []")
96
97 def run(self, code):
98 return self.run_js(
99 f"""
100 let result = pyodide.runPython({code!r});
101 if(result && result.deepCopyToJavascript){{
102 let converted_result = result.deepCopyToJavascript();
103 result.destroy();
104 return converted_result;
105 }}
106 return result;
107 """
108 )
109
110 def run_async(self, code):
111 return self.run_js(
112 f"""
113 let result = await pyodide.runPythonAsync({code!r});
114 if(result && result.deepCopyToJavascript){{
115 let converted_result = result.deepCopyToJavascript();
116 result.destroy();
117 return converted_result;
118 }}
119 return result;
120 """
121 )
122
123 def run_js(self, code):
124 if isinstance(code, str) and code.startswith("\n"):
125 # we have a multiline string, fix indentation
126 code = textwrap.dedent(code)
127
128 wrapper = """
129 let cb = arguments[arguments.length - 1];
130 let run = async () => { %s }
131 (async () => {
132 try {
133 let result = await run();
134 if(pyodide && pyodide._module && pyodide._module._PyErr_Occurred()){
135 try {
136 pyodide._module._pythonexc2js();
137 } catch(e){
138 console.error(`Python exited with error flag set! Error was:\n{e.message}`);
139 // Don't put original error message in new one: we want
140 // "pytest.raises(xxx, match=msg)" to fail
141 throw new Error(`Python exited with error flag set!`);
142 }
143 }
144 cb([0, result]);
145 } catch (e) {
146 cb([1, e.toString(), e.stack]);
147 }
148 })()
149 """
150
151 retval = self.driver.execute_async_script(wrapper % code)
152
153 if retval[0] == 0:
154 return retval[1]
155 else:
156 raise JavascriptException(retval[1], retval[2])
157
158 def run_webworker(self, code):
159 if isinstance(code, str) and code.startswith("\n"):
160 # we have a multiline string, fix indentation
161 code = textwrap.dedent(code)
162
163 return self.run_js(
164 """
165 let worker = new Worker( '{}' );
166 worker.postMessage({{ python: {!r} }});
167 return new Promise((res, rej) => {{
168 worker.onerror = e => rej(e);
169 worker.onmessage = e => {{
170 if (e.data.results) {{
171 res(e.data.results);
172 }} else {{
173 rej(e.data.error);
174 }}
175 }};
176 }})
177 """.format(
178 f"http://{self.server_hostname}:{self.server_port}/webworker_dev.js",
179 code,
180 )
181 )
182
183 def load_package(self, packages):
184 self.run_js("await pyodide.loadPackage({!r})".format(packages))
185
186 @property
187 def urls(self):
188 for handle in self.driver.window_handles:
189 self.driver.switch_to.window(handle)
190 yield self.driver.current_url
191
192
193 class FirefoxWrapper(SeleniumWrapper):
194
195 browser = "firefox"
196
197 def get_driver(self):
198 from selenium.webdriver import Firefox
199 from selenium.webdriver.firefox.options import Options
200
201 options = Options()
202 options.add_argument("-headless")
203
204 return Firefox(executable_path="geckodriver", options=options)
205
206
207 class ChromeWrapper(SeleniumWrapper):
208
209 browser = "chrome"
210
211 def get_driver(self):
212 from selenium.webdriver import Chrome
213 from selenium.webdriver.chrome.options import Options
214
215 options = Options()
216 options.add_argument("--headless")
217 options.add_argument("--no-sandbox")
218
219 return Chrome(options=options)
220
221
222 if pytest is not None:
223
224 @pytest.fixture(params=["firefox", "chrome"])
225 def selenium_standalone(request, web_server_main):
226 server_hostname, server_port, server_log = web_server_main
227 if request.param == "firefox":
228 cls = FirefoxWrapper
229 elif request.param == "chrome":
230 cls = ChromeWrapper
231 selenium = cls(
232 build_dir=request.config.option.build_dir,
233 server_port=server_port,
234 server_hostname=server_hostname,
235 server_log=server_log,
236 )
237 try:
238 yield selenium
239 finally:
240 print(selenium.logs)
241 selenium.driver.quit()
242
243 @pytest.fixture(params=["firefox", "chrome"], scope="module")
244 def _selenium_cached(request, web_server_main):
245 # Cached selenium instance. This is a copy-paste of
246 # selenium_standalone to avoid fixture scope issues
247 server_hostname, server_port, server_log = web_server_main
248 if request.param == "firefox":
249 cls = FirefoxWrapper
250 elif request.param == "chrome":
251 cls = ChromeWrapper
252 selenium = cls(
253 build_dir=request.config.option.build_dir,
254 server_port=server_port,
255 server_hostname=server_hostname,
256 server_log=server_log,
257 )
258 try:
259 yield selenium
260 finally:
261 selenium.driver.quit()
262
263 @pytest.fixture
264 def selenium(_selenium_cached):
265 # selenium instance cached at the module level
266 try:
267 _selenium_cached.clean_logs()
268 yield _selenium_cached
269 finally:
270 print(_selenium_cached.logs)
271
272
273 @pytest.fixture(scope="session")
274 def web_server_main(request):
275 """Web server that serves files in the build/ directory"""
276 with spawn_web_server(request.config.option.build_dir) as output:
277 yield output
278
279
280 @pytest.fixture(scope="session")
281 def web_server_secondary(request):
282 """Secondary web server that serves files build/ directory"""
283 with spawn_web_server(request.config.option.build_dir) as output:
284 yield output
285
286
287 @pytest.fixture(scope="session")
288 def web_server_tst_data(request):
289 """Web server that serves files in the src/tests/data/ directory"""
290 with spawn_web_server(TEST_PATH / "data") as output:
291 yield output
292
293
294 @contextlib.contextmanager
295 def spawn_web_server(build_dir=None):
296
297 if build_dir is None:
298 build_dir = BUILD_PATH
299
300 tmp_dir = tempfile.mkdtemp()
301 log_path = pathlib.Path(tmp_dir) / "http-server.log"
302 q = multiprocessing.Queue()
303 p = multiprocessing.Process(target=run_web_server, args=(q, log_path, build_dir))
304
305 try:
306 p.start()
307 port = q.get()
308 hostname = "127.0.0.1"
309
310 print(
311 f"Spawning webserver at http://{hostname}:{port} "
312 f"(see logs in {log_path})"
313 )
314 yield hostname, port, log_path
315 finally:
316 q.put("TERMINATE")
317 p.join()
318 shutil.rmtree(tmp_dir)
319
320
321 def run_web_server(q, log_filepath, build_dir):
322 """Start the HTTP web server
323
324 Parameters
325 ----------
326 q : Queue
327 communication queue
328 log_path : pathlib.Path
329 path to the file where to store the logs
330 """
331 import http.server
332 import socketserver
333
334 os.chdir(build_dir)
335
336 log_fh = log_filepath.open("w", buffering=1)
337 sys.stdout = log_fh
338 sys.stderr = log_fh
339
340 test_prefix = "/src/tests/"
341
342 class Handler(http.server.SimpleHTTPRequestHandler):
343 def log_message(self, format_, *args):
344 print(
345 "[%s] source: %s:%s - %s"
346 % (self.log_date_time_string(), *self.client_address, format_ % args)
347 )
348
349 def end_headers(self):
350 # Enable Cross-Origin Resource Sharing (CORS)
351 self.send_header("Access-Control-Allow-Origin", "*")
352 super().end_headers()
353
354 with socketserver.TCPServer(("", 0), Handler) as httpd:
355 host, port = httpd.server_address
356 print(f"Starting webserver at http://{host}:{port}")
357 httpd.server_name = "test-server"
358 httpd.server_port = port
359 q.put(port)
360
361 def service_actions():
362 try:
363 if q.get(False) == "TERMINATE":
364 print("Stopping server...")
365 sys.exit(0)
366 except queue.Empty:
367 pass
368
369 httpd.service_actions = service_actions
370 httpd.serve_forever()
371
372
373 if (
374 __name__ == "__main__"
375 and multiprocessing.current_process().name == "MainProcess"
376 and not hasattr(sys, "_pytest_session")
377 ):
378 with spawn_web_server():
379 # run forever
380 while True:
381 time.sleep(1)
382
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/conftest.py b/conftest.py
--- a/conftest.py
+++ b/conftest.py
@@ -98,8 +98,8 @@
return self.run_js(
f"""
let result = pyodide.runPython({code!r});
- if(result && result.deepCopyToJavascript){{
- let converted_result = result.deepCopyToJavascript();
+ if(result && result.toJs){{
+ let converted_result = result.toJs();
result.destroy();
return converted_result;
}}
@@ -111,8 +111,8 @@
return self.run_js(
f"""
let result = await pyodide.runPythonAsync({code!r});
- if(result && result.deepCopyToJavascript){{
- let converted_result = result.deepCopyToJavascript();
+ if(result && result.toJs){{
+ let converted_result = result.toJs();
result.destroy();
return converted_result;
}}
|
{"golden_diff": "diff --git a/conftest.py b/conftest.py\n--- a/conftest.py\n+++ b/conftest.py\n@@ -98,8 +98,8 @@\n return self.run_js(\n f\"\"\"\n let result = pyodide.runPython({code!r});\n- if(result && result.deepCopyToJavascript){{\n- let converted_result = result.deepCopyToJavascript();\n+ if(result && result.toJs){{\n+ let converted_result = result.toJs();\n result.destroy();\n return converted_result;\n }}\n@@ -111,8 +111,8 @@\n return self.run_js(\n f\"\"\"\n let result = await pyodide.runPythonAsync({code!r});\n- if(result && result.deepCopyToJavascript){{\n- let converted_result = result.deepCopyToJavascript();\n+ if(result && result.toJs){{\n+ let converted_result = result.toJs();\n result.destroy();\n return converted_result;\n }}\n", "issue": "Minor fix: add parameter for shallowCopyToJavascript \nFollow #1202 \r\n\r\n\n", "before_files": [{"content": "\"\"\"\nVarious common utilities for testing.\n\"\"\"\n\nimport contextlib\nimport multiprocessing\nimport textwrap\nimport tempfile\nimport time\nimport os\nimport pathlib\nimport queue\nimport sys\nimport shutil\n\nROOT_PATH = pathlib.Path(__file__).parents[0].resolve()\nTEST_PATH = ROOT_PATH / \"src\" / \"tests\"\nBUILD_PATH = ROOT_PATH / \"build\"\n\nsys.path.append(str(ROOT_PATH))\n\nfrom pyodide_build._fixes import _selenium_is_connectable # noqa: E402\nimport selenium.webdriver.common.utils # noqa: E402\n\n# XXX: Temporary fix for ConnectionError in selenium\n\nselenium.webdriver.common.utils.is_connectable = _selenium_is_connectable\n\ntry:\n import pytest\n\n def pytest_addoption(parser):\n group = parser.getgroup(\"general\")\n group.addoption(\n \"--build-dir\",\n action=\"store\",\n default=BUILD_PATH,\n help=\"Path to the build directory\",\n )\n group.addoption(\n \"--run-xfail\",\n action=\"store_true\",\n help=\"If provided, tests marked as xfail will be run\",\n )\n\n\nexcept ImportError:\n pytest = None # type: ignore\n\n\nclass JavascriptException(Exception):\n def __init__(self, msg, stack):\n self.msg = msg\n self.stack = stack\n # In chrome the stack contains the message\n if self.stack and self.stack.startswith(self.msg):\n self.msg = \"\"\n\n def __str__(self):\n return \"\\n\\n\".join(x for x in [self.msg, self.stack] if x)\n\n\nclass SeleniumWrapper:\n JavascriptException = JavascriptException\n\n def __init__(\n self, server_port, server_hostname=\"127.0.0.1\", server_log=None, build_dir=None\n ):\n if build_dir is None:\n build_dir = BUILD_PATH\n\n self.driver = self.get_driver()\n self.server_port = server_port\n self.server_hostname = server_hostname\n self.server_log = server_log\n\n if not (pathlib.Path(build_dir) / \"test.html\").exists():\n # selenium does not expose HTTP response codes\n raise ValueError(\n f\"{(build_dir / 'test.html').resolve()} \" f\"does not exist!\"\n )\n self.driver.get(f\"http://{server_hostname}:{server_port}/test.html\")\n self.run_js(\"Error.stackTraceLimit = Infinity\")\n self.run_js(\"await languagePluginLoader\")\n\n @property\n def logs(self):\n logs = self.driver.execute_script(\"return window.logs\")\n if logs is not None:\n return \"\\n\".join(str(x) for x in logs)\n else:\n return \"\"\n\n def clean_logs(self):\n self.driver.execute_script(\"window.logs = []\")\n\n def run(self, code):\n return self.run_js(\n f\"\"\"\n let result = pyodide.runPython({code!r});\n if(result && result.deepCopyToJavascript){{\n let converted_result = result.deepCopyToJavascript();\n result.destroy();\n return converted_result;\n }}\n return result;\n \"\"\"\n )\n\n def run_async(self, code):\n return self.run_js(\n f\"\"\"\n let result = await pyodide.runPythonAsync({code!r});\n if(result && result.deepCopyToJavascript){{\n let converted_result = result.deepCopyToJavascript();\n result.destroy();\n return converted_result;\n }}\n return result;\n \"\"\"\n )\n\n def run_js(self, code):\n if isinstance(code, str) and code.startswith(\"\\n\"):\n # we have a multiline string, fix indentation\n code = textwrap.dedent(code)\n\n wrapper = \"\"\"\n let cb = arguments[arguments.length - 1];\n let run = async () => { %s }\n (async () => {\n try {\n let result = await run();\n if(pyodide && pyodide._module && pyodide._module._PyErr_Occurred()){\n try {\n pyodide._module._pythonexc2js();\n } catch(e){\n console.error(`Python exited with error flag set! Error was:\\n{e.message}`);\n // Don't put original error message in new one: we want\n // \"pytest.raises(xxx, match=msg)\" to fail\n throw new Error(`Python exited with error flag set!`);\n }\n }\n cb([0, result]);\n } catch (e) {\n cb([1, e.toString(), e.stack]);\n }\n })()\n \"\"\"\n\n retval = self.driver.execute_async_script(wrapper % code)\n\n if retval[0] == 0:\n return retval[1]\n else:\n raise JavascriptException(retval[1], retval[2])\n\n def run_webworker(self, code):\n if isinstance(code, str) and code.startswith(\"\\n\"):\n # we have a multiline string, fix indentation\n code = textwrap.dedent(code)\n\n return self.run_js(\n \"\"\"\n let worker = new Worker( '{}' );\n worker.postMessage({{ python: {!r} }});\n return new Promise((res, rej) => {{\n worker.onerror = e => rej(e);\n worker.onmessage = e => {{\n if (e.data.results) {{\n res(e.data.results);\n }} else {{\n rej(e.data.error);\n }}\n }};\n }})\n \"\"\".format(\n f\"http://{self.server_hostname}:{self.server_port}/webworker_dev.js\",\n code,\n )\n )\n\n def load_package(self, packages):\n self.run_js(\"await pyodide.loadPackage({!r})\".format(packages))\n\n @property\n def urls(self):\n for handle in self.driver.window_handles:\n self.driver.switch_to.window(handle)\n yield self.driver.current_url\n\n\nclass FirefoxWrapper(SeleniumWrapper):\n\n browser = \"firefox\"\n\n def get_driver(self):\n from selenium.webdriver import Firefox\n from selenium.webdriver.firefox.options import Options\n\n options = Options()\n options.add_argument(\"-headless\")\n\n return Firefox(executable_path=\"geckodriver\", options=options)\n\n\nclass ChromeWrapper(SeleniumWrapper):\n\n browser = \"chrome\"\n\n def get_driver(self):\n from selenium.webdriver import Chrome\n from selenium.webdriver.chrome.options import Options\n\n options = Options()\n options.add_argument(\"--headless\")\n options.add_argument(\"--no-sandbox\")\n\n return Chrome(options=options)\n\n\nif pytest is not None:\n\n @pytest.fixture(params=[\"firefox\", \"chrome\"])\n def selenium_standalone(request, web_server_main):\n server_hostname, server_port, server_log = web_server_main\n if request.param == \"firefox\":\n cls = FirefoxWrapper\n elif request.param == \"chrome\":\n cls = ChromeWrapper\n selenium = cls(\n build_dir=request.config.option.build_dir,\n server_port=server_port,\n server_hostname=server_hostname,\n server_log=server_log,\n )\n try:\n yield selenium\n finally:\n print(selenium.logs)\n selenium.driver.quit()\n\n @pytest.fixture(params=[\"firefox\", \"chrome\"], scope=\"module\")\n def _selenium_cached(request, web_server_main):\n # Cached selenium instance. This is a copy-paste of\n # selenium_standalone to avoid fixture scope issues\n server_hostname, server_port, server_log = web_server_main\n if request.param == \"firefox\":\n cls = FirefoxWrapper\n elif request.param == \"chrome\":\n cls = ChromeWrapper\n selenium = cls(\n build_dir=request.config.option.build_dir,\n server_port=server_port,\n server_hostname=server_hostname,\n server_log=server_log,\n )\n try:\n yield selenium\n finally:\n selenium.driver.quit()\n\n @pytest.fixture\n def selenium(_selenium_cached):\n # selenium instance cached at the module level\n try:\n _selenium_cached.clean_logs()\n yield _selenium_cached\n finally:\n print(_selenium_cached.logs)\n\n\[email protected](scope=\"session\")\ndef web_server_main(request):\n \"\"\"Web server that serves files in the build/ directory\"\"\"\n with spawn_web_server(request.config.option.build_dir) as output:\n yield output\n\n\[email protected](scope=\"session\")\ndef web_server_secondary(request):\n \"\"\"Secondary web server that serves files build/ directory\"\"\"\n with spawn_web_server(request.config.option.build_dir) as output:\n yield output\n\n\[email protected](scope=\"session\")\ndef web_server_tst_data(request):\n \"\"\"Web server that serves files in the src/tests/data/ directory\"\"\"\n with spawn_web_server(TEST_PATH / \"data\") as output:\n yield output\n\n\[email protected]\ndef spawn_web_server(build_dir=None):\n\n if build_dir is None:\n build_dir = BUILD_PATH\n\n tmp_dir = tempfile.mkdtemp()\n log_path = pathlib.Path(tmp_dir) / \"http-server.log\"\n q = multiprocessing.Queue()\n p = multiprocessing.Process(target=run_web_server, args=(q, log_path, build_dir))\n\n try:\n p.start()\n port = q.get()\n hostname = \"127.0.0.1\"\n\n print(\n f\"Spawning webserver at http://{hostname}:{port} \"\n f\"(see logs in {log_path})\"\n )\n yield hostname, port, log_path\n finally:\n q.put(\"TERMINATE\")\n p.join()\n shutil.rmtree(tmp_dir)\n\n\ndef run_web_server(q, log_filepath, build_dir):\n \"\"\"Start the HTTP web server\n\n Parameters\n ----------\n q : Queue\n communication queue\n log_path : pathlib.Path\n path to the file where to store the logs\n \"\"\"\n import http.server\n import socketserver\n\n os.chdir(build_dir)\n\n log_fh = log_filepath.open(\"w\", buffering=1)\n sys.stdout = log_fh\n sys.stderr = log_fh\n\n test_prefix = \"/src/tests/\"\n\n class Handler(http.server.SimpleHTTPRequestHandler):\n def log_message(self, format_, *args):\n print(\n \"[%s] source: %s:%s - %s\"\n % (self.log_date_time_string(), *self.client_address, format_ % args)\n )\n\n def end_headers(self):\n # Enable Cross-Origin Resource Sharing (CORS)\n self.send_header(\"Access-Control-Allow-Origin\", \"*\")\n super().end_headers()\n\n with socketserver.TCPServer((\"\", 0), Handler) as httpd:\n host, port = httpd.server_address\n print(f\"Starting webserver at http://{host}:{port}\")\n httpd.server_name = \"test-server\"\n httpd.server_port = port\n q.put(port)\n\n def service_actions():\n try:\n if q.get(False) == \"TERMINATE\":\n print(\"Stopping server...\")\n sys.exit(0)\n except queue.Empty:\n pass\n\n httpd.service_actions = service_actions\n httpd.serve_forever()\n\n\nif (\n __name__ == \"__main__\"\n and multiprocessing.current_process().name == \"MainProcess\"\n and not hasattr(sys, \"_pytest_session\")\n):\n with spawn_web_server():\n # run forever\n while True:\n time.sleep(1)\n", "path": "conftest.py"}], "after_files": [{"content": "\"\"\"\nVarious common utilities for testing.\n\"\"\"\n\nimport contextlib\nimport multiprocessing\nimport textwrap\nimport tempfile\nimport time\nimport os\nimport pathlib\nimport queue\nimport sys\nimport shutil\n\nROOT_PATH = pathlib.Path(__file__).parents[0].resolve()\nTEST_PATH = ROOT_PATH / \"src\" / \"tests\"\nBUILD_PATH = ROOT_PATH / \"build\"\n\nsys.path.append(str(ROOT_PATH))\n\nfrom pyodide_build._fixes import _selenium_is_connectable # noqa: E402\nimport selenium.webdriver.common.utils # noqa: E402\n\n# XXX: Temporary fix for ConnectionError in selenium\n\nselenium.webdriver.common.utils.is_connectable = _selenium_is_connectable\n\ntry:\n import pytest\n\n def pytest_addoption(parser):\n group = parser.getgroup(\"general\")\n group.addoption(\n \"--build-dir\",\n action=\"store\",\n default=BUILD_PATH,\n help=\"Path to the build directory\",\n )\n group.addoption(\n \"--run-xfail\",\n action=\"store_true\",\n help=\"If provided, tests marked as xfail will be run\",\n )\n\n\nexcept ImportError:\n pytest = None # type: ignore\n\n\nclass JavascriptException(Exception):\n def __init__(self, msg, stack):\n self.msg = msg\n self.stack = stack\n # In chrome the stack contains the message\n if self.stack and self.stack.startswith(self.msg):\n self.msg = \"\"\n\n def __str__(self):\n return \"\\n\\n\".join(x for x in [self.msg, self.stack] if x)\n\n\nclass SeleniumWrapper:\n JavascriptException = JavascriptException\n\n def __init__(\n self, server_port, server_hostname=\"127.0.0.1\", server_log=None, build_dir=None\n ):\n if build_dir is None:\n build_dir = BUILD_PATH\n\n self.driver = self.get_driver()\n self.server_port = server_port\n self.server_hostname = server_hostname\n self.server_log = server_log\n\n if not (pathlib.Path(build_dir) / \"test.html\").exists():\n # selenium does not expose HTTP response codes\n raise ValueError(\n f\"{(build_dir / 'test.html').resolve()} \" f\"does not exist!\"\n )\n self.driver.get(f\"http://{server_hostname}:{server_port}/test.html\")\n self.run_js(\"Error.stackTraceLimit = Infinity\")\n self.run_js(\"await languagePluginLoader\")\n\n @property\n def logs(self):\n logs = self.driver.execute_script(\"return window.logs\")\n if logs is not None:\n return \"\\n\".join(str(x) for x in logs)\n else:\n return \"\"\n\n def clean_logs(self):\n self.driver.execute_script(\"window.logs = []\")\n\n def run(self, code):\n return self.run_js(\n f\"\"\"\n let result = pyodide.runPython({code!r});\n if(result && result.toJs){{\n let converted_result = result.toJs();\n result.destroy();\n return converted_result;\n }}\n return result;\n \"\"\"\n )\n\n def run_async(self, code):\n return self.run_js(\n f\"\"\"\n let result = await pyodide.runPythonAsync({code!r});\n if(result && result.toJs){{\n let converted_result = result.toJs();\n result.destroy();\n return converted_result;\n }}\n return result;\n \"\"\"\n )\n\n def run_js(self, code):\n if isinstance(code, str) and code.startswith(\"\\n\"):\n # we have a multiline string, fix indentation\n code = textwrap.dedent(code)\n\n wrapper = \"\"\"\n let cb = arguments[arguments.length - 1];\n let run = async () => { %s }\n (async () => {\n try {\n let result = await run();\n if(pyodide && pyodide._module && pyodide._module._PyErr_Occurred()){\n try {\n pyodide._module._pythonexc2js();\n } catch(e){\n console.error(`Python exited with error flag set! Error was:\\n{e.message}`);\n // Don't put original error message in new one: we want\n // \"pytest.raises(xxx, match=msg)\" to fail\n throw new Error(`Python exited with error flag set!`);\n }\n }\n cb([0, result]);\n } catch (e) {\n cb([1, e.toString(), e.stack]);\n }\n })()\n \"\"\"\n\n retval = self.driver.execute_async_script(wrapper % code)\n\n if retval[0] == 0:\n return retval[1]\n else:\n raise JavascriptException(retval[1], retval[2])\n\n def run_webworker(self, code):\n if isinstance(code, str) and code.startswith(\"\\n\"):\n # we have a multiline string, fix indentation\n code = textwrap.dedent(code)\n\n return self.run_js(\n \"\"\"\n let worker = new Worker( '{}' );\n worker.postMessage({{ python: {!r} }});\n return new Promise((res, rej) => {{\n worker.onerror = e => rej(e);\n worker.onmessage = e => {{\n if (e.data.results) {{\n res(e.data.results);\n }} else {{\n rej(e.data.error);\n }}\n }};\n }})\n \"\"\".format(\n f\"http://{self.server_hostname}:{self.server_port}/webworker_dev.js\",\n code,\n )\n )\n\n def load_package(self, packages):\n self.run_js(\"await pyodide.loadPackage({!r})\".format(packages))\n\n @property\n def urls(self):\n for handle in self.driver.window_handles:\n self.driver.switch_to.window(handle)\n yield self.driver.current_url\n\n\nclass FirefoxWrapper(SeleniumWrapper):\n\n browser = \"firefox\"\n\n def get_driver(self):\n from selenium.webdriver import Firefox\n from selenium.webdriver.firefox.options import Options\n\n options = Options()\n options.add_argument(\"-headless\")\n\n return Firefox(executable_path=\"geckodriver\", options=options)\n\n\nclass ChromeWrapper(SeleniumWrapper):\n\n browser = \"chrome\"\n\n def get_driver(self):\n from selenium.webdriver import Chrome\n from selenium.webdriver.chrome.options import Options\n\n options = Options()\n options.add_argument(\"--headless\")\n options.add_argument(\"--no-sandbox\")\n\n return Chrome(options=options)\n\n\nif pytest is not None:\n\n @pytest.fixture(params=[\"firefox\", \"chrome\"])\n def selenium_standalone(request, web_server_main):\n server_hostname, server_port, server_log = web_server_main\n if request.param == \"firefox\":\n cls = FirefoxWrapper\n elif request.param == \"chrome\":\n cls = ChromeWrapper\n selenium = cls(\n build_dir=request.config.option.build_dir,\n server_port=server_port,\n server_hostname=server_hostname,\n server_log=server_log,\n )\n try:\n yield selenium\n finally:\n print(selenium.logs)\n selenium.driver.quit()\n\n @pytest.fixture(params=[\"firefox\", \"chrome\"], scope=\"module\")\n def _selenium_cached(request, web_server_main):\n # Cached selenium instance. This is a copy-paste of\n # selenium_standalone to avoid fixture scope issues\n server_hostname, server_port, server_log = web_server_main\n if request.param == \"firefox\":\n cls = FirefoxWrapper\n elif request.param == \"chrome\":\n cls = ChromeWrapper\n selenium = cls(\n build_dir=request.config.option.build_dir,\n server_port=server_port,\n server_hostname=server_hostname,\n server_log=server_log,\n )\n try:\n yield selenium\n finally:\n selenium.driver.quit()\n\n @pytest.fixture\n def selenium(_selenium_cached):\n # selenium instance cached at the module level\n try:\n _selenium_cached.clean_logs()\n yield _selenium_cached\n finally:\n print(_selenium_cached.logs)\n\n\[email protected](scope=\"session\")\ndef web_server_main(request):\n \"\"\"Web server that serves files in the build/ directory\"\"\"\n with spawn_web_server(request.config.option.build_dir) as output:\n yield output\n\n\[email protected](scope=\"session\")\ndef web_server_secondary(request):\n \"\"\"Secondary web server that serves files build/ directory\"\"\"\n with spawn_web_server(request.config.option.build_dir) as output:\n yield output\n\n\[email protected](scope=\"session\")\ndef web_server_tst_data(request):\n \"\"\"Web server that serves files in the src/tests/data/ directory\"\"\"\n with spawn_web_server(TEST_PATH / \"data\") as output:\n yield output\n\n\[email protected]\ndef spawn_web_server(build_dir=None):\n\n if build_dir is None:\n build_dir = BUILD_PATH\n\n tmp_dir = tempfile.mkdtemp()\n log_path = pathlib.Path(tmp_dir) / \"http-server.log\"\n q = multiprocessing.Queue()\n p = multiprocessing.Process(target=run_web_server, args=(q, log_path, build_dir))\n\n try:\n p.start()\n port = q.get()\n hostname = \"127.0.0.1\"\n\n print(\n f\"Spawning webserver at http://{hostname}:{port} \"\n f\"(see logs in {log_path})\"\n )\n yield hostname, port, log_path\n finally:\n q.put(\"TERMINATE\")\n p.join()\n shutil.rmtree(tmp_dir)\n\n\ndef run_web_server(q, log_filepath, build_dir):\n \"\"\"Start the HTTP web server\n\n Parameters\n ----------\n q : Queue\n communication queue\n log_path : pathlib.Path\n path to the file where to store the logs\n \"\"\"\n import http.server\n import socketserver\n\n os.chdir(build_dir)\n\n log_fh = log_filepath.open(\"w\", buffering=1)\n sys.stdout = log_fh\n sys.stderr = log_fh\n\n test_prefix = \"/src/tests/\"\n\n class Handler(http.server.SimpleHTTPRequestHandler):\n def log_message(self, format_, *args):\n print(\n \"[%s] source: %s:%s - %s\"\n % (self.log_date_time_string(), *self.client_address, format_ % args)\n )\n\n def end_headers(self):\n # Enable Cross-Origin Resource Sharing (CORS)\n self.send_header(\"Access-Control-Allow-Origin\", \"*\")\n super().end_headers()\n\n with socketserver.TCPServer((\"\", 0), Handler) as httpd:\n host, port = httpd.server_address\n print(f\"Starting webserver at http://{host}:{port}\")\n httpd.server_name = \"test-server\"\n httpd.server_port = port\n q.put(port)\n\n def service_actions():\n try:\n if q.get(False) == \"TERMINATE\":\n print(\"Stopping server...\")\n sys.exit(0)\n except queue.Empty:\n pass\n\n httpd.service_actions = service_actions\n httpd.serve_forever()\n\n\nif (\n __name__ == \"__main__\"\n and multiprocessing.current_process().name == \"MainProcess\"\n and not hasattr(sys, \"_pytest_session\")\n):\n with spawn_web_server():\n # run forever\n while True:\n time.sleep(1)\n", "path": "conftest.py"}]}
| 3,731 | 212 |
gh_patches_debug_19727
|
rasdani/github-patches
|
git_diff
|
facebookresearch__hydra-1424
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Upgrade to OmegaConf 2.1
OmegaConf 2.1 is adding many important new features.
For example:
* Powerful interpolation grammar supporting nested interpolations
* Relative interpolations
* And many many bug fixes
Release notes: [omegaconf==2.1.0.rc1](https://github.com/omry/omegaconf/releases/tag/v2.1.0.rc1).
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py`
Content:
```
1 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
2 from dataclasses import dataclass
3 from typing import Optional
4
5 from hydra.core.config_store import ConfigStore
6 from omegaconf import II
7
8
9 @dataclass
10 class RedisConf:
11 # host address via REDIS_HOST environment variable, default: localhost
12 host: str = II("env:REDIS_HOST,localhost")
13 # port via REDIS_PORT environment variable, default: 6379
14 port: int = II("env:REDIS_PORT,6379")
15 # database via REDIS_DB environment variable, default: 0
16 db: Optional[str] = II("env:REDIS_DB,0")
17 # password via REDIS_PASSWORD environment variable, default: no password
18 password: str = II("env:REDIS_PASSWORD,")
19 # switch to run without redis server in single thread, for testing purposes only
20 mock: bool = II("env:REDIS_MOCK,False")
21
22
23 @dataclass
24 class EnqueueConf:
25 # maximum runtime of the job before it's killed (e.g. "1d" for 1 day, units: d/h/m/s), default: no limit
26 job_timeout: Optional[str] = None
27 # maximum queued time before the job before is discarded (e.g. "1d" for 1 day, units: d/h/m/s), default: no limit
28 ttl: Optional[str] = None
29 # how long successful jobs and their results are kept (e.g. "1d" for 1 day, units: d/h/m/s), default: no limit
30 result_ttl: Optional[str] = None
31 # specifies how long failed jobs are kept (e.g. "1d" for 1 day, units: d/h/m/s), default: no limit
32 failure_ttl: Optional[str] = None
33 # place job at the front of the queue, instead of the back
34 at_front: bool = False
35 # job id, will be overidden automatically by a uuid unless specified explicitly
36 job_id: Optional[str] = None
37 # description, will be overidden automatically unless specified explicitly
38 description: Optional[str] = None
39
40
41 @dataclass
42 class RQLauncherConf:
43 _target_: str = "hydra_plugins.hydra_rq_launcher.rq_launcher.RQLauncher"
44 # enqueue configuration
45 enqueue: EnqueueConf = EnqueueConf()
46 # queue name
47 queue: str = "default"
48 # redis configuration
49 redis: RedisConf = RedisConf()
50 # stop after enqueueing by raising custom exception
51 stop_after_enqueue: bool = False
52 # wait time in seconds when polling results
53 wait_polling: float = 1.0
54
55
56 ConfigStore.instance().store(
57 group="hydra/launcher", name="rq", node=RQLauncherConf, provider="rq_launcher"
58 )
59
```
Path: `plugins/hydra_ax_sweeper/setup.py`
Content:
```
1 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
2 # type: ignore
3 from setuptools import find_namespace_packages, setup
4
5 with open("README.md", "r") as fh:
6 LONG_DESC = fh.read()
7 setup(
8 name="hydra-ax-sweeper",
9 version="1.1.0rc1",
10 author="Omry Yadan, Shagun Sodhani",
11 author_email="[email protected], [email protected]",
12 description="Hydra Ax Sweeper plugin",
13 long_description=LONG_DESC,
14 long_description_content_type="text/markdown",
15 url="https://github.com/facebookresearch/hydra/",
16 packages=find_namespace_packages(include=["hydra_plugins.*"]),
17 classifiers=[
18 "License :: OSI Approved :: MIT License",
19 "Programming Language :: Python :: 3.7",
20 "Programming Language :: Python :: 3.8",
21 "Programming Language :: Python :: 3.9",
22 "Operating System :: POSIX :: Linux",
23 "Operating System :: MacOS",
24 "Development Status :: 4 - Beta",
25 ],
26 install_requires=[
27 "hydra-core>=1.0.0",
28 "ax-platform>=0.1.13",
29 "numpy<1.20.0", # remove once ax is upgraded to support numpy 1.20
30 ],
31 include_package_data=True,
32 )
33
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/plugins/hydra_ax_sweeper/setup.py b/plugins/hydra_ax_sweeper/setup.py
--- a/plugins/hydra_ax_sweeper/setup.py
+++ b/plugins/hydra_ax_sweeper/setup.py
@@ -25,8 +25,7 @@
],
install_requires=[
"hydra-core>=1.0.0",
- "ax-platform>=0.1.13",
- "numpy<1.20.0", # remove once ax is upgraded to support numpy 1.20
+ "ax-platform>=0.1.20",
],
include_package_data=True,
)
diff --git a/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py b/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py
--- a/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py
+++ b/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py
@@ -15,7 +15,7 @@
# database via REDIS_DB environment variable, default: 0
db: Optional[str] = II("env:REDIS_DB,0")
# password via REDIS_PASSWORD environment variable, default: no password
- password: str = II("env:REDIS_PASSWORD,")
+ password: str = II("env:REDIS_PASSWORD")
# switch to run without redis server in single thread, for testing purposes only
mock: bool = II("env:REDIS_MOCK,False")
|
{"golden_diff": "diff --git a/plugins/hydra_ax_sweeper/setup.py b/plugins/hydra_ax_sweeper/setup.py\n--- a/plugins/hydra_ax_sweeper/setup.py\n+++ b/plugins/hydra_ax_sweeper/setup.py\n@@ -25,8 +25,7 @@\n ],\n install_requires=[\n \"hydra-core>=1.0.0\",\n- \"ax-platform>=0.1.13\",\n- \"numpy<1.20.0\", # remove once ax is upgraded to support numpy 1.20\n+ \"ax-platform>=0.1.20\",\n ],\n include_package_data=True,\n )\ndiff --git a/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py b/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py\n--- a/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py\n+++ b/plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py\n@@ -15,7 +15,7 @@\n # database via REDIS_DB environment variable, default: 0\n db: Optional[str] = II(\"env:REDIS_DB,0\")\n # password via REDIS_PASSWORD environment variable, default: no password\n- password: str = II(\"env:REDIS_PASSWORD,\")\n+ password: str = II(\"env:REDIS_PASSWORD\")\n # switch to run without redis server in single thread, for testing purposes only\n mock: bool = II(\"env:REDIS_MOCK,False\")\n", "issue": "Upgrade to OmegaConf 2.1\nOmegaConf 2.1 is adding many important new features.\r\nFor example:\r\n* Powerful interpolation grammar supporting nested interpolations\r\n* Relative interpolations\r\n* And many many bug fixes\r\n\r\nRelease notes: [omegaconf==2.1.0.rc1](https://github.com/omry/omegaconf/releases/tag/v2.1.0.rc1).\n", "before_files": [{"content": "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved\nfrom dataclasses import dataclass\nfrom typing import Optional\n\nfrom hydra.core.config_store import ConfigStore\nfrom omegaconf import II\n\n\n@dataclass\nclass RedisConf:\n # host address via REDIS_HOST environment variable, default: localhost\n host: str = II(\"env:REDIS_HOST,localhost\")\n # port via REDIS_PORT environment variable, default: 6379\n port: int = II(\"env:REDIS_PORT,6379\")\n # database via REDIS_DB environment variable, default: 0\n db: Optional[str] = II(\"env:REDIS_DB,0\")\n # password via REDIS_PASSWORD environment variable, default: no password\n password: str = II(\"env:REDIS_PASSWORD,\")\n # switch to run without redis server in single thread, for testing purposes only\n mock: bool = II(\"env:REDIS_MOCK,False\")\n\n\n@dataclass\nclass EnqueueConf:\n # maximum runtime of the job before it's killed (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n job_timeout: Optional[str] = None\n # maximum queued time before the job before is discarded (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n ttl: Optional[str] = None\n # how long successful jobs and their results are kept (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n result_ttl: Optional[str] = None\n # specifies how long failed jobs are kept (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n failure_ttl: Optional[str] = None\n # place job at the front of the queue, instead of the back\n at_front: bool = False\n # job id, will be overidden automatically by a uuid unless specified explicitly\n job_id: Optional[str] = None\n # description, will be overidden automatically unless specified explicitly\n description: Optional[str] = None\n\n\n@dataclass\nclass RQLauncherConf:\n _target_: str = \"hydra_plugins.hydra_rq_launcher.rq_launcher.RQLauncher\"\n # enqueue configuration\n enqueue: EnqueueConf = EnqueueConf()\n # queue name\n queue: str = \"default\"\n # redis configuration\n redis: RedisConf = RedisConf()\n # stop after enqueueing by raising custom exception\n stop_after_enqueue: bool = False\n # wait time in seconds when polling results\n wait_polling: float = 1.0\n\n\nConfigStore.instance().store(\n group=\"hydra/launcher\", name=\"rq\", node=RQLauncherConf, provider=\"rq_launcher\"\n)\n", "path": "plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py"}, {"content": "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved\n# type: ignore\nfrom setuptools import find_namespace_packages, setup\n\nwith open(\"README.md\", \"r\") as fh:\n LONG_DESC = fh.read()\n setup(\n name=\"hydra-ax-sweeper\",\n version=\"1.1.0rc1\",\n author=\"Omry Yadan, Shagun Sodhani\",\n author_email=\"[email protected], [email protected]\",\n description=\"Hydra Ax Sweeper plugin\",\n long_description=LONG_DESC,\n long_description_content_type=\"text/markdown\",\n url=\"https://github.com/facebookresearch/hydra/\",\n packages=find_namespace_packages(include=[\"hydra_plugins.*\"]),\n classifiers=[\n \"License :: OSI Approved :: MIT License\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n \"Programming Language :: Python :: 3.9\",\n \"Operating System :: POSIX :: Linux\",\n \"Operating System :: MacOS\",\n \"Development Status :: 4 - Beta\",\n ],\n install_requires=[\n \"hydra-core>=1.0.0\",\n \"ax-platform>=0.1.13\",\n \"numpy<1.20.0\", # remove once ax is upgraded to support numpy 1.20\n ],\n include_package_data=True,\n )\n", "path": "plugins/hydra_ax_sweeper/setup.py"}], "after_files": [{"content": "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved\nfrom dataclasses import dataclass\nfrom typing import Optional\n\nfrom hydra.core.config_store import ConfigStore\nfrom omegaconf import II\n\n\n@dataclass\nclass RedisConf:\n # host address via REDIS_HOST environment variable, default: localhost\n host: str = II(\"env:REDIS_HOST,localhost\")\n # port via REDIS_PORT environment variable, default: 6379\n port: int = II(\"env:REDIS_PORT,6379\")\n # database via REDIS_DB environment variable, default: 0\n db: Optional[str] = II(\"env:REDIS_DB,0\")\n # password via REDIS_PASSWORD environment variable, default: no password\n password: str = II(\"env:REDIS_PASSWORD\")\n # switch to run without redis server in single thread, for testing purposes only\n mock: bool = II(\"env:REDIS_MOCK,False\")\n\n\n@dataclass\nclass EnqueueConf:\n # maximum runtime of the job before it's killed (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n job_timeout: Optional[str] = None\n # maximum queued time before the job before is discarded (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n ttl: Optional[str] = None\n # how long successful jobs and their results are kept (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n result_ttl: Optional[str] = None\n # specifies how long failed jobs are kept (e.g. \"1d\" for 1 day, units: d/h/m/s), default: no limit\n failure_ttl: Optional[str] = None\n # place job at the front of the queue, instead of the back\n at_front: bool = False\n # job id, will be overidden automatically by a uuid unless specified explicitly\n job_id: Optional[str] = None\n # description, will be overidden automatically unless specified explicitly\n description: Optional[str] = None\n\n\n@dataclass\nclass RQLauncherConf:\n _target_: str = \"hydra_plugins.hydra_rq_launcher.rq_launcher.RQLauncher\"\n # enqueue configuration\n enqueue: EnqueueConf = EnqueueConf()\n # queue name\n queue: str = \"default\"\n # redis configuration\n redis: RedisConf = RedisConf()\n # stop after enqueueing by raising custom exception\n stop_after_enqueue: bool = False\n # wait time in seconds when polling results\n wait_polling: float = 1.0\n\n\nConfigStore.instance().store(\n group=\"hydra/launcher\", name=\"rq\", node=RQLauncherConf, provider=\"rq_launcher\"\n)\n", "path": "plugins/hydra_rq_launcher/hydra_plugins/hydra_rq_launcher/config.py"}, {"content": "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved\n# type: ignore\nfrom setuptools import find_namespace_packages, setup\n\nwith open(\"README.md\", \"r\") as fh:\n LONG_DESC = fh.read()\n setup(\n name=\"hydra-ax-sweeper\",\n version=\"1.1.0rc1\",\n author=\"Omry Yadan, Shagun Sodhani\",\n author_email=\"[email protected], [email protected]\",\n description=\"Hydra Ax Sweeper plugin\",\n long_description=LONG_DESC,\n long_description_content_type=\"text/markdown\",\n url=\"https://github.com/facebookresearch/hydra/\",\n packages=find_namespace_packages(include=[\"hydra_plugins.*\"]),\n classifiers=[\n \"License :: OSI Approved :: MIT License\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n \"Programming Language :: Python :: 3.9\",\n \"Operating System :: POSIX :: Linux\",\n \"Operating System :: MacOS\",\n \"Development Status :: 4 - Beta\",\n ],\n install_requires=[\n \"hydra-core>=1.0.0\",\n \"ax-platform>=0.1.20\",\n ],\n include_package_data=True,\n )\n", "path": "plugins/hydra_ax_sweeper/setup.py"}]}
| 1,471 | 342 |
gh_patches_debug_31077
|
rasdani/github-patches
|
git_diff
|
sopel-irc__sopel-1441
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
imdb module not working anymore
I just noticed that anytime you make a call to imdb now the bot responds:
> [MOVIE] No API key provided.
I know it used to work, not sure how recently. Maybe it can be switched to a different database that doesn't require an API key?
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `sopel/modules/movie.py`
Content:
```
1 # coding=utf-8
2 """
3 imdb.py - Sopel Movie Information Module
4 Copyright © 2012-2013, Elad Alfassa, <[email protected]>
5 Licensed under the Eiffel Forum License 2.
6
7 This module relies on omdbapi.com
8 """
9 from __future__ import unicode_literals, absolute_import, print_function, division
10
11 import requests
12 import sopel.module
13 from sopel.logger import get_logger
14
15 LOGGER = get_logger(__name__)
16
17
18 @sopel.module.commands('movie', 'imdb')
19 @sopel.module.example('.movie ThisTitleDoesNotExist', '[MOVIE] Movie not found!')
20 @sopel.module.example('.movie Citizen Kane', '[MOVIE] Title: Citizen Kane | Year: 1941 | Rating: 8.4 | Genre: Drama, Mystery | IMDB Link: http://imdb.com/title/tt0033467')
21 def movie(bot, trigger):
22 """
23 Returns some information about a movie, like Title, Year, Rating, Genre and IMDB Link.
24 """
25 if not trigger.group(2):
26 return
27 word = trigger.group(2).rstrip()
28 uri = "http://www.omdbapi.com/"
29 data = requests.get(uri, params={'t': word}, timeout=30,
30 verify=bot.config.core.verify_ssl).json()
31 if data['Response'] == 'False':
32 if 'Error' in data:
33 message = '[MOVIE] %s' % data['Error']
34 else:
35 LOGGER.warning(
36 'Got an error from the OMDb api, search phrase was %s; data was %s',
37 word, str(data))
38 message = '[MOVIE] Got an error from OMDbapi'
39 else:
40 message = '[MOVIE] Title: ' + data['Title'] + \
41 ' | Year: ' + data['Year'] + \
42 ' | Rating: ' + data['imdbRating'] + \
43 ' | Genre: ' + data['Genre'] + \
44 ' | IMDB Link: http://imdb.com/title/' + data['imdbID']
45 bot.say(message)
46
47
48 if __name__ == "__main__":
49 from sopel.test_tools import run_example_tests
50 run_example_tests(__file__)
51
```
Path: `conftest.py`
Content:
```
1 # This file lists files which should be ignored by pytest
2 collect_ignore = ["setup.py", "sopel.py", "sopel/modules/ipython.py", "sopel/modules/movie.py"]
3
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/conftest.py b/conftest.py
--- a/conftest.py
+++ b/conftest.py
@@ -1,2 +1,2 @@
# This file lists files which should be ignored by pytest
-collect_ignore = ["setup.py", "sopel.py", "sopel/modules/ipython.py", "sopel/modules/movie.py"]
+collect_ignore = ["setup.py", "sopel.py", "sopel/modules/ipython.py"]
diff --git a/sopel/modules/movie.py b/sopel/modules/movie.py
deleted file mode 100644
--- a/sopel/modules/movie.py
+++ /dev/null
@@ -1,50 +0,0 @@
-# coding=utf-8
-"""
-imdb.py - Sopel Movie Information Module
-Copyright © 2012-2013, Elad Alfassa, <[email protected]>
-Licensed under the Eiffel Forum License 2.
-
-This module relies on omdbapi.com
-"""
-from __future__ import unicode_literals, absolute_import, print_function, division
-
-import requests
-import sopel.module
-from sopel.logger import get_logger
-
-LOGGER = get_logger(__name__)
-
-
[email protected]('movie', 'imdb')
[email protected]('.movie ThisTitleDoesNotExist', '[MOVIE] Movie not found!')
[email protected]('.movie Citizen Kane', '[MOVIE] Title: Citizen Kane | Year: 1941 | Rating: 8.4 | Genre: Drama, Mystery | IMDB Link: http://imdb.com/title/tt0033467')
-def movie(bot, trigger):
- """
- Returns some information about a movie, like Title, Year, Rating, Genre and IMDB Link.
- """
- if not trigger.group(2):
- return
- word = trigger.group(2).rstrip()
- uri = "http://www.omdbapi.com/"
- data = requests.get(uri, params={'t': word}, timeout=30,
- verify=bot.config.core.verify_ssl).json()
- if data['Response'] == 'False':
- if 'Error' in data:
- message = '[MOVIE] %s' % data['Error']
- else:
- LOGGER.warning(
- 'Got an error from the OMDb api, search phrase was %s; data was %s',
- word, str(data))
- message = '[MOVIE] Got an error from OMDbapi'
- else:
- message = '[MOVIE] Title: ' + data['Title'] + \
- ' | Year: ' + data['Year'] + \
- ' | Rating: ' + data['imdbRating'] + \
- ' | Genre: ' + data['Genre'] + \
- ' | IMDB Link: http://imdb.com/title/' + data['imdbID']
- bot.say(message)
-
-
-if __name__ == "__main__":
- from sopel.test_tools import run_example_tests
- run_example_tests(__file__)
|
{"golden_diff": "diff --git a/conftest.py b/conftest.py\n--- a/conftest.py\n+++ b/conftest.py\n@@ -1,2 +1,2 @@\n # This file lists files which should be ignored by pytest\n-collect_ignore = [\"setup.py\", \"sopel.py\", \"sopel/modules/ipython.py\", \"sopel/modules/movie.py\"]\n+collect_ignore = [\"setup.py\", \"sopel.py\", \"sopel/modules/ipython.py\"]\ndiff --git a/sopel/modules/movie.py b/sopel/modules/movie.py\ndeleted file mode 100644\n--- a/sopel/modules/movie.py\n+++ /dev/null\n@@ -1,50 +0,0 @@\n-# coding=utf-8\n-\"\"\"\n-imdb.py - Sopel Movie Information Module\n-Copyright \u00a9 2012-2013, Elad Alfassa, <[email protected]>\n-Licensed under the Eiffel Forum License 2.\n-\n-This module relies on omdbapi.com\n-\"\"\"\n-from __future__ import unicode_literals, absolute_import, print_function, division\n-\n-import requests\n-import sopel.module\n-from sopel.logger import get_logger\n-\n-LOGGER = get_logger(__name__)\n-\n-\[email protected]('movie', 'imdb')\[email protected]('.movie ThisTitleDoesNotExist', '[MOVIE] Movie not found!')\[email protected]('.movie Citizen Kane', '[MOVIE] Title: Citizen Kane | Year: 1941 | Rating: 8.4 | Genre: Drama, Mystery | IMDB Link: http://imdb.com/title/tt0033467')\n-def movie(bot, trigger):\n- \"\"\"\n- Returns some information about a movie, like Title, Year, Rating, Genre and IMDB Link.\n- \"\"\"\n- if not trigger.group(2):\n- return\n- word = trigger.group(2).rstrip()\n- uri = \"http://www.omdbapi.com/\"\n- data = requests.get(uri, params={'t': word}, timeout=30,\n- verify=bot.config.core.verify_ssl).json()\n- if data['Response'] == 'False':\n- if 'Error' in data:\n- message = '[MOVIE] %s' % data['Error']\n- else:\n- LOGGER.warning(\n- 'Got an error from the OMDb api, search phrase was %s; data was %s',\n- word, str(data))\n- message = '[MOVIE] Got an error from OMDbapi'\n- else:\n- message = '[MOVIE] Title: ' + data['Title'] + \\\n- ' | Year: ' + data['Year'] + \\\n- ' | Rating: ' + data['imdbRating'] + \\\n- ' | Genre: ' + data['Genre'] + \\\n- ' | IMDB Link: http://imdb.com/title/' + data['imdbID']\n- bot.say(message)\n-\n-\n-if __name__ == \"__main__\":\n- from sopel.test_tools import run_example_tests\n- run_example_tests(__file__)\n", "issue": "imdb module not working anymore\nI just noticed that anytime you make a call to imdb now the bot responds: \r\n\r\n> [MOVIE] No API key provided.\r\n\r\nI know it used to work, not sure how recently. Maybe it can be switched to a different database that doesn't require an API key?\n", "before_files": [{"content": "# coding=utf-8\n\"\"\"\nimdb.py - Sopel Movie Information Module\nCopyright \u00a9 2012-2013, Elad Alfassa, <[email protected]>\nLicensed under the Eiffel Forum License 2.\n\nThis module relies on omdbapi.com\n\"\"\"\nfrom __future__ import unicode_literals, absolute_import, print_function, division\n\nimport requests\nimport sopel.module\nfrom sopel.logger import get_logger\n\nLOGGER = get_logger(__name__)\n\n\[email protected]('movie', 'imdb')\[email protected]('.movie ThisTitleDoesNotExist', '[MOVIE] Movie not found!')\[email protected]('.movie Citizen Kane', '[MOVIE] Title: Citizen Kane | Year: 1941 | Rating: 8.4 | Genre: Drama, Mystery | IMDB Link: http://imdb.com/title/tt0033467')\ndef movie(bot, trigger):\n \"\"\"\n Returns some information about a movie, like Title, Year, Rating, Genre and IMDB Link.\n \"\"\"\n if not trigger.group(2):\n return\n word = trigger.group(2).rstrip()\n uri = \"http://www.omdbapi.com/\"\n data = requests.get(uri, params={'t': word}, timeout=30,\n verify=bot.config.core.verify_ssl).json()\n if data['Response'] == 'False':\n if 'Error' in data:\n message = '[MOVIE] %s' % data['Error']\n else:\n LOGGER.warning(\n 'Got an error from the OMDb api, search phrase was %s; data was %s',\n word, str(data))\n message = '[MOVIE] Got an error from OMDbapi'\n else:\n message = '[MOVIE] Title: ' + data['Title'] + \\\n ' | Year: ' + data['Year'] + \\\n ' | Rating: ' + data['imdbRating'] + \\\n ' | Genre: ' + data['Genre'] + \\\n ' | IMDB Link: http://imdb.com/title/' + data['imdbID']\n bot.say(message)\n\n\nif __name__ == \"__main__\":\n from sopel.test_tools import run_example_tests\n run_example_tests(__file__)\n", "path": "sopel/modules/movie.py"}, {"content": "# This file lists files which should be ignored by pytest\ncollect_ignore = [\"setup.py\", \"sopel.py\", \"sopel/modules/ipython.py\", \"sopel/modules/movie.py\"]\n", "path": "conftest.py"}], "after_files": [{"content": null, "path": "sopel/modules/movie.py"}, {"content": "# This file lists files which should be ignored by pytest\ncollect_ignore = [\"setup.py\", \"sopel.py\", \"sopel/modules/ipython.py\"]\n", "path": "conftest.py"}]}
| 975 | 695 |
gh_patches_debug_19487
|
rasdani/github-patches
|
git_diff
|
Lightning-AI__torchmetrics-1011
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Compatibility with future PT 1.12
## 🐛 Bug
```
> distance = x @ y.T
E RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'
```
### To Reproduce
https://github.com/PyTorchLightning/metrics/runs/6275393755?check_suite_focus=true
#### Code sample
```py
distance = x @ y.T
```
### Expected behavior
<!-- A clear and concise description of what you expected to happen. -->
### Environment
- OS (e.g., Linux): linux
- Python & PyTorch Version (e.g., 1.0): py3.8 & pt1.12
### Additional context
context see https://github.com/pytorch/pytorch/pull/75647
slack: https://pytorch.slack.com/archives/C3PDTEV8E/p1651742487294399
tl;dr: We don't have correct and fast linalg algorithms for half in CPU as none of the backend libraries that we use support them so it's better not to support these via half-baked implementations, and simply make the users cast their inputs if they want to use these methods
> but for GPU it shall be supported, correct? >> Yes
note as well that this just applies to Half on CPU and for linalg functios (think matmul and conv). Pointwise functions on Half on CPU will still be available, and Half on CUDA will still have full support
> it was implemented up till 1.11 but there was no real speed-up, correct?
Not only it was slower, but it was not numerically stable, so it was pretty much a bug (hence the removal without deprecation)
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `torchmetrics/functional/pairwise/cosine.py`
Content:
```
1 # Copyright The PyTorch Lightning team.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 from typing import Optional
15
16 import torch
17 from torch import Tensor
18 from typing_extensions import Literal
19
20 from torchmetrics.functional.pairwise.helpers import _check_input, _reduce_distance_matrix
21
22
23 def _pairwise_cosine_similarity_update(
24 x: Tensor, y: Optional[Tensor] = None, zero_diagonal: Optional[bool] = None
25 ) -> Tensor:
26 """Calculates the pairwise cosine similarity matrix.
27
28 Args:
29 x: tensor of shape ``[N,d]``
30 y: tensor of shape ``[M,d]``
31 zero_diagonal: determines if the diagonal of the distance matrix should be set to zero
32 """
33 x, y, zero_diagonal = _check_input(x, y, zero_diagonal)
34
35 norm = torch.norm(x, p=2, dim=1)
36 x /= norm.unsqueeze(1)
37 norm = torch.norm(y, p=2, dim=1)
38 y /= norm.unsqueeze(1)
39
40 distance = x @ y.T
41 if zero_diagonal:
42 distance.fill_diagonal_(0)
43 return distance
44
45
46 def pairwise_cosine_similarity(
47 x: Tensor,
48 y: Optional[Tensor] = None,
49 reduction: Literal["mean", "sum", "none", None] = None,
50 zero_diagonal: Optional[bool] = None,
51 ) -> Tensor:
52 r"""Calculates pairwise cosine similarity:
53
54 .. math::
55 s_{cos}(x,y) = \frac{<x,y>}{||x|| \cdot ||y||}
56 = \frac{\sum_{d=1}^D x_d \cdot y_d }{\sqrt{\sum_{d=1}^D x_i^2} \cdot \sqrt{\sum_{d=1}^D x_i^2}}
57
58 If both :math:`x` and :math:`y` are passed in, the calculation will be performed pairwise
59 between the rows of :math:`x` and :math:`y`.
60 If only :math:`x` is passed in, the calculation will be performed between the rows of :math:`x`.
61
62 Args:
63 x: Tensor with shape ``[N, d]``
64 y: Tensor with shape ``[M, d]``, optional
65 reduction: reduction to apply along the last dimension. Choose between `'mean'`, `'sum'`
66 (applied along column dimension) or `'none'`, `None` for no reduction
67 zero_diagonal: if the diagonal of the distance matrix should be set to 0. If only :math:`x` is given
68 this defaults to ``True`` else if :math:`y` is also given it defaults to ``False``
69
70 Returns:
71 A ``[N,N]`` matrix of distances if only ``x`` is given, else a ``[N,M]`` matrix
72
73 Example:
74 >>> import torch
75 >>> from torchmetrics.functional import pairwise_cosine_similarity
76 >>> x = torch.tensor([[2, 3], [3, 5], [5, 8]], dtype=torch.float32)
77 >>> y = torch.tensor([[1, 0], [2, 1]], dtype=torch.float32)
78 >>> pairwise_cosine_similarity(x, y)
79 tensor([[0.5547, 0.8682],
80 [0.5145, 0.8437],
81 [0.5300, 0.8533]])
82 >>> pairwise_cosine_similarity(x)
83 tensor([[0.0000, 0.9989, 0.9996],
84 [0.9989, 0.0000, 0.9998],
85 [0.9996, 0.9998, 0.0000]])
86
87 """
88 distance = _pairwise_cosine_similarity_update(x, y, zero_diagonal)
89 return _reduce_distance_matrix(distance, reduction)
90
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/torchmetrics/functional/pairwise/cosine.py b/torchmetrics/functional/pairwise/cosine.py
--- a/torchmetrics/functional/pairwise/cosine.py
+++ b/torchmetrics/functional/pairwise/cosine.py
@@ -20,6 +20,16 @@
from torchmetrics.functional.pairwise.helpers import _check_input, _reduce_distance_matrix
+def _safe_matmul(x: Tensor, y: Tensor) -> Tensor:
+ """Safe calculation of matrix multiplication.
+
+ If input is float16, will cast to float32 for computation and back again.
+ """
+ if x.dtype == torch.float16 or y.dtype == torch.float16:
+ return (x.float() @ y.T.float()).half()
+ return x @ y.T
+
+
def _pairwise_cosine_similarity_update(
x: Tensor, y: Optional[Tensor] = None, zero_diagonal: Optional[bool] = None
) -> Tensor:
@@ -37,7 +47,7 @@
norm = torch.norm(y, p=2, dim=1)
y /= norm.unsqueeze(1)
- distance = x @ y.T
+ distance = _safe_matmul(x, y)
if zero_diagonal:
distance.fill_diagonal_(0)
return distance
|
{"golden_diff": "diff --git a/torchmetrics/functional/pairwise/cosine.py b/torchmetrics/functional/pairwise/cosine.py\n--- a/torchmetrics/functional/pairwise/cosine.py\n+++ b/torchmetrics/functional/pairwise/cosine.py\n@@ -20,6 +20,16 @@\n from torchmetrics.functional.pairwise.helpers import _check_input, _reduce_distance_matrix\n \n \n+def _safe_matmul(x: Tensor, y: Tensor) -> Tensor:\n+ \"\"\"Safe calculation of matrix multiplication.\n+\n+ If input is float16, will cast to float32 for computation and back again.\n+ \"\"\"\n+ if x.dtype == torch.float16 or y.dtype == torch.float16:\n+ return (x.float() @ y.T.float()).half()\n+ return x @ y.T\n+\n+\n def _pairwise_cosine_similarity_update(\n x: Tensor, y: Optional[Tensor] = None, zero_diagonal: Optional[bool] = None\n ) -> Tensor:\n@@ -37,7 +47,7 @@\n norm = torch.norm(y, p=2, dim=1)\n y /= norm.unsqueeze(1)\n \n- distance = x @ y.T\n+ distance = _safe_matmul(x, y)\n if zero_diagonal:\n distance.fill_diagonal_(0)\n return distance\n", "issue": "Compatibility with future PT 1.12\n## \ud83d\udc1b Bug\r\n\r\n```\r\n> distance = x @ y.T\r\nE RuntimeError: \"addmm_impl_cpu_\" not implemented for 'Half'\r\n```\r\n\r\n### To Reproduce\r\n\r\nhttps://github.com/PyTorchLightning/metrics/runs/6275393755?check_suite_focus=true\r\n\r\n#### Code sample\r\n\r\n```py\r\ndistance = x @ y.T\r\n```\r\n\r\n### Expected behavior\r\n\r\n<!-- A clear and concise description of what you expected to happen. -->\r\n\r\n### Environment\r\n\r\n- OS (e.g., Linux): linux\r\n- Python & PyTorch Version (e.g., 1.0): py3.8 & pt1.12\r\n\r\n### Additional context\r\n\r\ncontext see https://github.com/pytorch/pytorch/pull/75647\r\nslack: https://pytorch.slack.com/archives/C3PDTEV8E/p1651742487294399\r\n\r\ntl;dr: We don't have correct and fast linalg algorithms for half in CPU as none of the backend libraries that we use support them so it's better not to support these via half-baked implementations, and simply make the users cast their inputs if they want to use these methods\r\n\r\n> but for GPU it shall be supported, correct? >> Yes\r\n\r\nnote as well that this just applies to Half on CPU and for linalg functios (think matmul and conv). Pointwise functions on Half on CPU will still be available, and Half on CUDA will still have full support\r\n\r\n> it was implemented up till 1.11 but there was no real speed-up, correct?\r\n\r\nNot only it was slower, but it was not numerically stable, so it was pretty much a bug (hence the removal without deprecation)\n", "before_files": [{"content": "# Copyright The PyTorch Lightning team.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nfrom typing import Optional\n\nimport torch\nfrom torch import Tensor\nfrom typing_extensions import Literal\n\nfrom torchmetrics.functional.pairwise.helpers import _check_input, _reduce_distance_matrix\n\n\ndef _pairwise_cosine_similarity_update(\n x: Tensor, y: Optional[Tensor] = None, zero_diagonal: Optional[bool] = None\n) -> Tensor:\n \"\"\"Calculates the pairwise cosine similarity matrix.\n\n Args:\n x: tensor of shape ``[N,d]``\n y: tensor of shape ``[M,d]``\n zero_diagonal: determines if the diagonal of the distance matrix should be set to zero\n \"\"\"\n x, y, zero_diagonal = _check_input(x, y, zero_diagonal)\n\n norm = torch.norm(x, p=2, dim=1)\n x /= norm.unsqueeze(1)\n norm = torch.norm(y, p=2, dim=1)\n y /= norm.unsqueeze(1)\n\n distance = x @ y.T\n if zero_diagonal:\n distance.fill_diagonal_(0)\n return distance\n\n\ndef pairwise_cosine_similarity(\n x: Tensor,\n y: Optional[Tensor] = None,\n reduction: Literal[\"mean\", \"sum\", \"none\", None] = None,\n zero_diagonal: Optional[bool] = None,\n) -> Tensor:\n r\"\"\"Calculates pairwise cosine similarity:\n\n .. math::\n s_{cos}(x,y) = \\frac{<x,y>}{||x|| \\cdot ||y||}\n = \\frac{\\sum_{d=1}^D x_d \\cdot y_d }{\\sqrt{\\sum_{d=1}^D x_i^2} \\cdot \\sqrt{\\sum_{d=1}^D x_i^2}}\n\n If both :math:`x` and :math:`y` are passed in, the calculation will be performed pairwise\n between the rows of :math:`x` and :math:`y`.\n If only :math:`x` is passed in, the calculation will be performed between the rows of :math:`x`.\n\n Args:\n x: Tensor with shape ``[N, d]``\n y: Tensor with shape ``[M, d]``, optional\n reduction: reduction to apply along the last dimension. Choose between `'mean'`, `'sum'`\n (applied along column dimension) or `'none'`, `None` for no reduction\n zero_diagonal: if the diagonal of the distance matrix should be set to 0. If only :math:`x` is given\n this defaults to ``True`` else if :math:`y` is also given it defaults to ``False``\n\n Returns:\n A ``[N,N]`` matrix of distances if only ``x`` is given, else a ``[N,M]`` matrix\n\n Example:\n >>> import torch\n >>> from torchmetrics.functional import pairwise_cosine_similarity\n >>> x = torch.tensor([[2, 3], [3, 5], [5, 8]], dtype=torch.float32)\n >>> y = torch.tensor([[1, 0], [2, 1]], dtype=torch.float32)\n >>> pairwise_cosine_similarity(x, y)\n tensor([[0.5547, 0.8682],\n [0.5145, 0.8437],\n [0.5300, 0.8533]])\n >>> pairwise_cosine_similarity(x)\n tensor([[0.0000, 0.9989, 0.9996],\n [0.9989, 0.0000, 0.9998],\n [0.9996, 0.9998, 0.0000]])\n\n \"\"\"\n distance = _pairwise_cosine_similarity_update(x, y, zero_diagonal)\n return _reduce_distance_matrix(distance, reduction)\n", "path": "torchmetrics/functional/pairwise/cosine.py"}], "after_files": [{"content": "# Copyright The PyTorch Lightning team.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nfrom typing import Optional\n\nimport torch\nfrom torch import Tensor\nfrom typing_extensions import Literal\n\nfrom torchmetrics.functional.pairwise.helpers import _check_input, _reduce_distance_matrix\n\n\ndef _safe_matmul(x: Tensor, y: Tensor) -> Tensor:\n \"\"\"Safe calculation of matrix multiplication.\n\n If input is float16, will cast to float32 for computation and back again.\n \"\"\"\n if x.dtype == torch.float16 or y.dtype == torch.float16:\n return (x.float() @ y.T.float()).half()\n return x @ y.T\n\n\ndef _pairwise_cosine_similarity_update(\n x: Tensor, y: Optional[Tensor] = None, zero_diagonal: Optional[bool] = None\n) -> Tensor:\n \"\"\"Calculates the pairwise cosine similarity matrix.\n\n Args:\n x: tensor of shape ``[N,d]``\n y: tensor of shape ``[M,d]``\n zero_diagonal: determines if the diagonal of the distance matrix should be set to zero\n \"\"\"\n x, y, zero_diagonal = _check_input(x, y, zero_diagonal)\n\n norm = torch.norm(x, p=2, dim=1)\n x /= norm.unsqueeze(1)\n norm = torch.norm(y, p=2, dim=1)\n y /= norm.unsqueeze(1)\n\n distance = _safe_matmul(x, y)\n if zero_diagonal:\n distance.fill_diagonal_(0)\n return distance\n\n\ndef pairwise_cosine_similarity(\n x: Tensor,\n y: Optional[Tensor] = None,\n reduction: Literal[\"mean\", \"sum\", \"none\", None] = None,\n zero_diagonal: Optional[bool] = None,\n) -> Tensor:\n r\"\"\"Calculates pairwise cosine similarity:\n\n .. math::\n s_{cos}(x,y) = \\frac{<x,y>}{||x|| \\cdot ||y||}\n = \\frac{\\sum_{d=1}^D x_d \\cdot y_d }{\\sqrt{\\sum_{d=1}^D x_i^2} \\cdot \\sqrt{\\sum_{d=1}^D x_i^2}}\n\n If both :math:`x` and :math:`y` are passed in, the calculation will be performed pairwise\n between the rows of :math:`x` and :math:`y`.\n If only :math:`x` is passed in, the calculation will be performed between the rows of :math:`x`.\n\n Args:\n x: Tensor with shape ``[N, d]``\n y: Tensor with shape ``[M, d]``, optional\n reduction: reduction to apply along the last dimension. Choose between `'mean'`, `'sum'`\n (applied along column dimension) or `'none'`, `None` for no reduction\n zero_diagonal: if the diagonal of the distance matrix should be set to 0. If only :math:`x` is given\n this defaults to ``True`` else if :math:`y` is also given it defaults to ``False``\n\n Returns:\n A ``[N,N]`` matrix of distances if only ``x`` is given, else a ``[N,M]`` matrix\n\n Example:\n >>> import torch\n >>> from torchmetrics.functional import pairwise_cosine_similarity\n >>> x = torch.tensor([[2, 3], [3, 5], [5, 8]], dtype=torch.float32)\n >>> y = torch.tensor([[1, 0], [2, 1]], dtype=torch.float32)\n >>> pairwise_cosine_similarity(x, y)\n tensor([[0.5547, 0.8682],\n [0.5145, 0.8437],\n [0.5300, 0.8533]])\n >>> pairwise_cosine_similarity(x)\n tensor([[0.0000, 0.9989, 0.9996],\n [0.9989, 0.0000, 0.9998],\n [0.9996, 0.9998, 0.0000]])\n\n \"\"\"\n distance = _pairwise_cosine_similarity_update(x, y, zero_diagonal)\n return _reduce_distance_matrix(distance, reduction)\n", "path": "torchmetrics/functional/pairwise/cosine.py"}]}
| 1,811 | 298 |
gh_patches_debug_38729
|
rasdani/github-patches
|
git_diff
|
kivy__kivy-1348
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Kivy 1.8.0 dev: touch.is_double_tap is set allways to true on Windows
Hello,
On MS Windows with Kivy 1.8.0 dev: If you press a button twice, even after a greater time gap between the touches, you always get touch.is_double_tap == True on the second tap.
Does not appear with 1.7.1 on Android.
Greetings
Carsten
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `kivy/input/postproc/doubletap.py`
Content:
```
1 '''
2 Double Tap
3 ==========
4
5 Search touch for a double tap
6 '''
7
8 __all__ = ('InputPostprocDoubleTap', )
9
10 from kivy.config import Config
11 from kivy.vector import Vector
12 from kivy.clock import Clock
13
14
15 class InputPostprocDoubleTap(object):
16 '''
17 InputPostProcDoubleTap is a post-processor to check if
18 a touch is a double tap or not.
19 Double tap can be configured in the Kivy config file::
20
21 [postproc]
22 double_tap_time = 250
23 double_tap_distance = 20
24
25 Distance parameter is in 0-1000, and time is in millisecond.
26 '''
27
28 def __init__(self):
29 dist = Config.getint('postproc', 'double_tap_distance')
30 self.double_tap_distance = dist / 1000.0
31 time = Config.getint('postproc', 'double_tap_time')
32 self.double_tap_time = time / 1000.0
33 self.touches = {}
34
35 def find_double_tap(self, ref):
36 '''Find a double tap touch within self.touches.
37 The touch must be not a previous double tap, and the distance
38 must be ok, also, the touch profile must be compared so the kind
39 of touch is the same
40 '''
41 ref_button = None
42 if 'button' in ref.profile:
43 ref_button = ref.button
44
45 for touchid in self.touches:
46 if ref.uid == touchid:
47 continue
48 etype, touch = self.touches[touchid]
49 if etype != 'end':
50 continue
51 if touch.is_double_tap:
52 continue
53 distance = Vector.distance(
54 Vector(ref.sx, ref.sy),
55 Vector(touch.osx, touch.osy))
56 if distance > self.double_tap_distance:
57 continue
58 if touch.is_mouse_scrolling or ref.is_mouse_scrolling:
59 continue
60 touch_button = None
61 if 'button' in touch.profile:
62 touch_button = touch.button
63 if touch_button != ref_button:
64 continue
65 touch.double_tap_distance = distance
66 return touch
67 return None
68
69 def process(self, events):
70 if self.double_tap_distance == 0 or self.double_tap_time == 0:
71 return events
72 # first, check if a touch down have a double tap
73 for etype, touch in events:
74 if not touch.is_touch:
75 continue
76 if etype == 'begin':
77 double_tap = self.find_double_tap(touch)
78 if double_tap:
79 touch.is_double_tap = True
80 time = touch.time_start - double_tap.time_start
81 touch.double_tap_time = time
82 distance = double_tap.double_tap_distance
83 touch.double_tap_distance = distance
84
85 # add the touch internaly
86 self.touches[touch.uid] = (etype, touch)
87
88 # second, check if up-touch is timeout for double tap
89 time_current = Clock.get_time()
90 to_delete = []
91 for touchid in self.touches.keys():
92 etype, touch = self.touches[touchid]
93 if etype != 'end':
94 continue
95 if time_current - touch.time_start < self.double_tap_time:
96 continue
97 to_delete.append(touchid)
98
99 for touchid in to_delete:
100 del self.touches[touchid]
101
102 return events
103
```
Path: `kivy/input/postproc/tripletap.py`
Content:
```
1 '''
2 Triple Tap
3 ==========
4
5 .. versionadded:: 1.7.0
6
7 Search touch for a triple tap
8 '''
9
10 __all__ = ('InputPostprocTripleTap', )
11
12 from kivy.config import Config
13 from kivy.vector import Vector
14 from kivy.clock import Clock
15
16
17 class InputPostprocTripleTap(object):
18 '''
19 InputPostProcTripleTap is a post-processor to check if
20 a touch is a triple tap or not.
21 Triple tap can be configured in the Kivy config file::
22
23 [postproc]
24 triple_tap_time = 250
25 triple_tap_distance = 20
26
27 Distance parameter is in 0-1000, and time is in millisecond.
28 '''
29
30 def __init__(self):
31 dist = Config.getint('postproc', 'triple_tap_distance')
32 self.triple_tap_distance = dist / 1000.0
33 time = Config.getint('postproc', 'triple_tap_time')
34 self.triple_tap_time = time / 1000.0
35 self.touches = {}
36
37 def find_triple_tap(self, ref):
38 '''Find a triple tap touch within self.touches.
39 The touch must be not a previous triple tap, and the distance
40 must be ok, also, the touch profile must be compared so the kind
41 of touch is the same
42 '''
43 ref_button = None
44 if 'button' in ref.profile:
45 ref_button = ref.button
46
47 for touchid in self.touches:
48 if ref.uid == touchid:
49 continue
50 etype, touch = self.touches[touchid]
51 if not touch.is_double_tap:
52 continue
53 if etype != 'end':
54 continue
55 if touch.is_triple_tap:
56 continue
57 distance = Vector.distance(
58 Vector(ref.sx, ref.sy),
59 Vector(touch.osx, touch.osy))
60 if distance > self.triple_tap_distance:
61 continue
62 if touch.is_mouse_scrolling or ref.is_mouse_scrolling:
63 continue
64 touch_button = None
65 if 'button' in touch.profile:
66 touch_button = touch.button
67 if touch_button != ref_button:
68 continue
69 touch.triple_tap_distance = distance
70 return touch
71 return None
72
73 def process(self, events):
74 if self.triple_tap_distance == 0 or self.triple_tap_time == 0:
75 return events
76 # first, check if a touch down have a triple tap
77 for etype, touch in events:
78 if not touch.is_touch:
79 continue
80 if etype == 'begin':
81 triple_tap = self.find_triple_tap(touch)
82 if triple_tap:
83 touch.is_double_tap = False
84 touch.is_triple_tap = True
85 time = touch.time_start - triple_tap.time_start
86 touch.triple_tap_time = time
87 distance = triple_tap.triple_tap_distance
88 touch.triple_tap_distance = distance
89
90 # add the touch internaly
91 self.touches[touch.uid] = (etype, touch)
92
93 # second, check if up-touch is timeout for triple tap
94 time_current = Clock.get_time()
95 to_delete = []
96 for touchid in self.touches.keys():
97 etype, touch = self.touches[touchid]
98 if etype != 'end':
99 continue
100 if time_current - touch.time_start < self.triple_tap_time:
101 continue
102 to_delete.append(touchid)
103
104 for touchid in to_delete:
105 del self.touches[touchid]
106
107 return events
108
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/kivy/input/postproc/doubletap.py b/kivy/input/postproc/doubletap.py
--- a/kivy/input/postproc/doubletap.py
+++ b/kivy/input/postproc/doubletap.py
@@ -7,6 +7,7 @@
__all__ = ('InputPostprocDoubleTap', )
+from time import time
from kivy.config import Config
from kivy.vector import Vector
from kivy.clock import Clock
@@ -77,8 +78,8 @@
double_tap = self.find_double_tap(touch)
if double_tap:
touch.is_double_tap = True
- time = touch.time_start - double_tap.time_start
- touch.double_tap_time = time
+ tap_time = touch.time_start - double_tap.time_start
+ touch.double_tap_time = tap_time
distance = double_tap.double_tap_distance
touch.double_tap_distance = distance
@@ -86,7 +87,7 @@
self.touches[touch.uid] = (etype, touch)
# second, check if up-touch is timeout for double tap
- time_current = Clock.get_time()
+ time_current = time()
to_delete = []
for touchid in self.touches.keys():
etype, touch = self.touches[touchid]
diff --git a/kivy/input/postproc/tripletap.py b/kivy/input/postproc/tripletap.py
--- a/kivy/input/postproc/tripletap.py
+++ b/kivy/input/postproc/tripletap.py
@@ -9,6 +9,7 @@
__all__ = ('InputPostprocTripleTap', )
+from time import time
from kivy.config import Config
from kivy.vector import Vector
from kivy.clock import Clock
@@ -82,8 +83,8 @@
if triple_tap:
touch.is_double_tap = False
touch.is_triple_tap = True
- time = touch.time_start - triple_tap.time_start
- touch.triple_tap_time = time
+ tap_time = touch.time_start - triple_tap.time_start
+ touch.triple_tap_time = tap_time
distance = triple_tap.triple_tap_distance
touch.triple_tap_distance = distance
@@ -91,7 +92,7 @@
self.touches[touch.uid] = (etype, touch)
# second, check if up-touch is timeout for triple tap
- time_current = Clock.get_time()
+ time_current = time()
to_delete = []
for touchid in self.touches.keys():
etype, touch = self.touches[touchid]
|
{"golden_diff": "diff --git a/kivy/input/postproc/doubletap.py b/kivy/input/postproc/doubletap.py\n--- a/kivy/input/postproc/doubletap.py\n+++ b/kivy/input/postproc/doubletap.py\n@@ -7,6 +7,7 @@\n \n __all__ = ('InputPostprocDoubleTap', )\n \n+from time import time\n from kivy.config import Config\n from kivy.vector import Vector\n from kivy.clock import Clock\n@@ -77,8 +78,8 @@\n double_tap = self.find_double_tap(touch)\n if double_tap:\n touch.is_double_tap = True\n- time = touch.time_start - double_tap.time_start\n- touch.double_tap_time = time\n+ tap_time = touch.time_start - double_tap.time_start\n+ touch.double_tap_time = tap_time\n distance = double_tap.double_tap_distance\n touch.double_tap_distance = distance\n \n@@ -86,7 +87,7 @@\n self.touches[touch.uid] = (etype, touch)\n \n # second, check if up-touch is timeout for double tap\n- time_current = Clock.get_time()\n+ time_current = time()\n to_delete = []\n for touchid in self.touches.keys():\n etype, touch = self.touches[touchid]\ndiff --git a/kivy/input/postproc/tripletap.py b/kivy/input/postproc/tripletap.py\n--- a/kivy/input/postproc/tripletap.py\n+++ b/kivy/input/postproc/tripletap.py\n@@ -9,6 +9,7 @@\n \n __all__ = ('InputPostprocTripleTap', )\n \n+from time import time\n from kivy.config import Config\n from kivy.vector import Vector\n from kivy.clock import Clock\n@@ -82,8 +83,8 @@\n if triple_tap:\n touch.is_double_tap = False\n touch.is_triple_tap = True\n- time = touch.time_start - triple_tap.time_start\n- touch.triple_tap_time = time\n+ tap_time = touch.time_start - triple_tap.time_start\n+ touch.triple_tap_time = tap_time\n distance = triple_tap.triple_tap_distance\n touch.triple_tap_distance = distance\n \n@@ -91,7 +92,7 @@\n self.touches[touch.uid] = (etype, touch)\n \n # second, check if up-touch is timeout for triple tap\n- time_current = Clock.get_time()\n+ time_current = time()\n to_delete = []\n for touchid in self.touches.keys():\n etype, touch = self.touches[touchid]\n", "issue": "Kivy 1.8.0 dev: touch.is_double_tap is set allways to true on Windows\nHello,\nOn MS Windows with Kivy 1.8.0 dev: If you press a button twice, even after a greater time gap between the touches, you always get touch.is_double_tap == True on the second tap. \n\nDoes not appear with 1.7.1 on Android.\n\nGreetings\n\nCarsten\n\n", "before_files": [{"content": "'''\nDouble Tap\n==========\n\nSearch touch for a double tap\n'''\n\n__all__ = ('InputPostprocDoubleTap', )\n\nfrom kivy.config import Config\nfrom kivy.vector import Vector\nfrom kivy.clock import Clock\n\n\nclass InputPostprocDoubleTap(object):\n '''\n InputPostProcDoubleTap is a post-processor to check if\n a touch is a double tap or not.\n Double tap can be configured in the Kivy config file::\n\n [postproc]\n double_tap_time = 250\n double_tap_distance = 20\n\n Distance parameter is in 0-1000, and time is in millisecond.\n '''\n\n def __init__(self):\n dist = Config.getint('postproc', 'double_tap_distance')\n self.double_tap_distance = dist / 1000.0\n time = Config.getint('postproc', 'double_tap_time')\n self.double_tap_time = time / 1000.0\n self.touches = {}\n\n def find_double_tap(self, ref):\n '''Find a double tap touch within self.touches.\n The touch must be not a previous double tap, and the distance\n must be ok, also, the touch profile must be compared so the kind\n of touch is the same\n '''\n ref_button = None\n if 'button' in ref.profile:\n ref_button = ref.button\n\n for touchid in self.touches:\n if ref.uid == touchid:\n continue\n etype, touch = self.touches[touchid]\n if etype != 'end':\n continue\n if touch.is_double_tap:\n continue\n distance = Vector.distance(\n Vector(ref.sx, ref.sy),\n Vector(touch.osx, touch.osy))\n if distance > self.double_tap_distance:\n continue\n if touch.is_mouse_scrolling or ref.is_mouse_scrolling:\n continue\n touch_button = None\n if 'button' in touch.profile:\n touch_button = touch.button\n if touch_button != ref_button:\n continue\n touch.double_tap_distance = distance\n return touch\n return None\n\n def process(self, events):\n if self.double_tap_distance == 0 or self.double_tap_time == 0:\n return events\n # first, check if a touch down have a double tap\n for etype, touch in events:\n if not touch.is_touch:\n continue\n if etype == 'begin':\n double_tap = self.find_double_tap(touch)\n if double_tap:\n touch.is_double_tap = True\n time = touch.time_start - double_tap.time_start\n touch.double_tap_time = time\n distance = double_tap.double_tap_distance\n touch.double_tap_distance = distance\n\n # add the touch internaly\n self.touches[touch.uid] = (etype, touch)\n\n # second, check if up-touch is timeout for double tap\n time_current = Clock.get_time()\n to_delete = []\n for touchid in self.touches.keys():\n etype, touch = self.touches[touchid]\n if etype != 'end':\n continue\n if time_current - touch.time_start < self.double_tap_time:\n continue\n to_delete.append(touchid)\n\n for touchid in to_delete:\n del self.touches[touchid]\n\n return events\n", "path": "kivy/input/postproc/doubletap.py"}, {"content": "'''\nTriple Tap\n==========\n\n.. versionadded:: 1.7.0\n\nSearch touch for a triple tap\n'''\n\n__all__ = ('InputPostprocTripleTap', )\n\nfrom kivy.config import Config\nfrom kivy.vector import Vector\nfrom kivy.clock import Clock\n\n\nclass InputPostprocTripleTap(object):\n '''\n InputPostProcTripleTap is a post-processor to check if\n a touch is a triple tap or not.\n Triple tap can be configured in the Kivy config file::\n\n [postproc]\n triple_tap_time = 250\n triple_tap_distance = 20\n\n Distance parameter is in 0-1000, and time is in millisecond.\n '''\n\n def __init__(self):\n dist = Config.getint('postproc', 'triple_tap_distance')\n self.triple_tap_distance = dist / 1000.0\n time = Config.getint('postproc', 'triple_tap_time')\n self.triple_tap_time = time / 1000.0\n self.touches = {}\n\n def find_triple_tap(self, ref):\n '''Find a triple tap touch within self.touches.\n The touch must be not a previous triple tap, and the distance\n must be ok, also, the touch profile must be compared so the kind\n of touch is the same\n '''\n ref_button = None\n if 'button' in ref.profile:\n ref_button = ref.button\n\n for touchid in self.touches:\n if ref.uid == touchid:\n continue\n etype, touch = self.touches[touchid]\n if not touch.is_double_tap:\n continue\n if etype != 'end':\n continue\n if touch.is_triple_tap:\n continue\n distance = Vector.distance(\n Vector(ref.sx, ref.sy),\n Vector(touch.osx, touch.osy))\n if distance > self.triple_tap_distance:\n continue\n if touch.is_mouse_scrolling or ref.is_mouse_scrolling:\n continue\n touch_button = None\n if 'button' in touch.profile:\n touch_button = touch.button\n if touch_button != ref_button:\n continue\n touch.triple_tap_distance = distance\n return touch\n return None\n\n def process(self, events):\n if self.triple_tap_distance == 0 or self.triple_tap_time == 0:\n return events\n # first, check if a touch down have a triple tap\n for etype, touch in events:\n if not touch.is_touch:\n continue\n if etype == 'begin':\n triple_tap = self.find_triple_tap(touch)\n if triple_tap:\n touch.is_double_tap = False\n touch.is_triple_tap = True\n time = touch.time_start - triple_tap.time_start\n touch.triple_tap_time = time\n distance = triple_tap.triple_tap_distance\n touch.triple_tap_distance = distance\n\n # add the touch internaly\n self.touches[touch.uid] = (etype, touch)\n\n # second, check if up-touch is timeout for triple tap\n time_current = Clock.get_time()\n to_delete = []\n for touchid in self.touches.keys():\n etype, touch = self.touches[touchid]\n if etype != 'end':\n continue\n if time_current - touch.time_start < self.triple_tap_time:\n continue\n to_delete.append(touchid)\n\n for touchid in to_delete:\n del self.touches[touchid]\n\n return events\n", "path": "kivy/input/postproc/tripletap.py"}], "after_files": [{"content": "'''\nDouble Tap\n==========\n\nSearch touch for a double tap\n'''\n\n__all__ = ('InputPostprocDoubleTap', )\n\nfrom time import time\nfrom kivy.config import Config\nfrom kivy.vector import Vector\nfrom kivy.clock import Clock\n\n\nclass InputPostprocDoubleTap(object):\n '''\n InputPostProcDoubleTap is a post-processor to check if\n a touch is a double tap or not.\n Double tap can be configured in the Kivy config file::\n\n [postproc]\n double_tap_time = 250\n double_tap_distance = 20\n\n Distance parameter is in 0-1000, and time is in millisecond.\n '''\n\n def __init__(self):\n dist = Config.getint('postproc', 'double_tap_distance')\n self.double_tap_distance = dist / 1000.0\n time = Config.getint('postproc', 'double_tap_time')\n self.double_tap_time = time / 1000.0\n self.touches = {}\n\n def find_double_tap(self, ref):\n '''Find a double tap touch within self.touches.\n The touch must be not a previous double tap, and the distance\n must be ok, also, the touch profile must be compared so the kind\n of touch is the same\n '''\n ref_button = None\n if 'button' in ref.profile:\n ref_button = ref.button\n\n for touchid in self.touches:\n if ref.uid == touchid:\n continue\n etype, touch = self.touches[touchid]\n if etype != 'end':\n continue\n if touch.is_double_tap:\n continue\n distance = Vector.distance(\n Vector(ref.sx, ref.sy),\n Vector(touch.osx, touch.osy))\n if distance > self.double_tap_distance:\n continue\n if touch.is_mouse_scrolling or ref.is_mouse_scrolling:\n continue\n touch_button = None\n if 'button' in touch.profile:\n touch_button = touch.button\n if touch_button != ref_button:\n continue\n touch.double_tap_distance = distance\n return touch\n return None\n\n def process(self, events):\n if self.double_tap_distance == 0 or self.double_tap_time == 0:\n return events\n # first, check if a touch down have a double tap\n for etype, touch in events:\n if not touch.is_touch:\n continue\n if etype == 'begin':\n double_tap = self.find_double_tap(touch)\n if double_tap:\n touch.is_double_tap = True\n tap_time = touch.time_start - double_tap.time_start\n touch.double_tap_time = tap_time\n distance = double_tap.double_tap_distance\n touch.double_tap_distance = distance\n\n # add the touch internaly\n self.touches[touch.uid] = (etype, touch)\n\n # second, check if up-touch is timeout for double tap\n time_current = time()\n to_delete = []\n for touchid in self.touches.keys():\n etype, touch = self.touches[touchid]\n if etype != 'end':\n continue\n if time_current - touch.time_start < self.double_tap_time:\n continue\n to_delete.append(touchid)\n\n for touchid in to_delete:\n del self.touches[touchid]\n\n return events\n", "path": "kivy/input/postproc/doubletap.py"}, {"content": "'''\nTriple Tap\n==========\n\n.. versionadded:: 1.7.0\n\nSearch touch for a triple tap\n'''\n\n__all__ = ('InputPostprocTripleTap', )\n\nfrom time import time\nfrom kivy.config import Config\nfrom kivy.vector import Vector\nfrom kivy.clock import Clock\n\n\nclass InputPostprocTripleTap(object):\n '''\n InputPostProcTripleTap is a post-processor to check if\n a touch is a triple tap or not.\n Triple tap can be configured in the Kivy config file::\n\n [postproc]\n triple_tap_time = 250\n triple_tap_distance = 20\n\n Distance parameter is in 0-1000, and time is in millisecond.\n '''\n\n def __init__(self):\n dist = Config.getint('postproc', 'triple_tap_distance')\n self.triple_tap_distance = dist / 1000.0\n time = Config.getint('postproc', 'triple_tap_time')\n self.triple_tap_time = time / 1000.0\n self.touches = {}\n\n def find_triple_tap(self, ref):\n '''Find a triple tap touch within self.touches.\n The touch must be not a previous triple tap, and the distance\n must be ok, also, the touch profile must be compared so the kind\n of touch is the same\n '''\n ref_button = None\n if 'button' in ref.profile:\n ref_button = ref.button\n\n for touchid in self.touches:\n if ref.uid == touchid:\n continue\n etype, touch = self.touches[touchid]\n if not touch.is_double_tap:\n continue\n if etype != 'end':\n continue\n if touch.is_triple_tap:\n continue\n distance = Vector.distance(\n Vector(ref.sx, ref.sy),\n Vector(touch.osx, touch.osy))\n if distance > self.triple_tap_distance:\n continue\n if touch.is_mouse_scrolling or ref.is_mouse_scrolling:\n continue\n touch_button = None\n if 'button' in touch.profile:\n touch_button = touch.button\n if touch_button != ref_button:\n continue\n touch.triple_tap_distance = distance\n return touch\n return None\n\n def process(self, events):\n if self.triple_tap_distance == 0 or self.triple_tap_time == 0:\n return events\n # first, check if a touch down have a triple tap\n for etype, touch in events:\n if not touch.is_touch:\n continue\n if etype == 'begin':\n triple_tap = self.find_triple_tap(touch)\n if triple_tap:\n touch.is_double_tap = False\n touch.is_triple_tap = True\n tap_time = touch.time_start - triple_tap.time_start\n touch.triple_tap_time = tap_time\n distance = triple_tap.triple_tap_distance\n touch.triple_tap_distance = distance\n\n # add the touch internaly\n self.touches[touch.uid] = (etype, touch)\n\n # second, check if up-touch is timeout for triple tap\n time_current = time()\n to_delete = []\n for touchid in self.touches.keys():\n etype, touch = self.touches[touchid]\n if etype != 'end':\n continue\n if time_current - touch.time_start < self.triple_tap_time:\n continue\n to_delete.append(touchid)\n\n for touchid in to_delete:\n del self.touches[touchid]\n\n return events\n", "path": "kivy/input/postproc/tripletap.py"}]}
| 2,329 | 586 |
gh_patches_debug_37251
|
rasdani/github-patches
|
git_diff
|
databricks__koalas-189
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Document all the methods in Metadata
There are a bunch of methods like index_info, index_fields. It's pretty difficult to figure out what they do. We should just add some basic docstring comments.
@ueshin you are probably the best person to take this since you created the file.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `databricks/koalas/metadata.py`
Content:
```
1 #
2 # Copyright (C) 2019 Databricks, Inc.
3 #
4 # Licensed under the Apache License, Version 2.0 (the "License");
5 # you may not use this file except in compliance with the License.
6 # You may obtain a copy of the License at
7 #
8 # http://www.apache.org/licenses/LICENSE-2.0
9 #
10 # Unless required by applicable law or agreed to in writing, software
11 # distributed under the License is distributed on an "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 # See the License for the specific language governing permissions and
14 # limitations under the License.
15 #
16
17 """
18 A metadata to manage indexes.
19 """
20 import pandas as pd
21
22 from databricks.koalas.dask.compatibility import string_types
23
24
25 class Metadata(object):
26 """
27 Manages column names and index information
28 """
29
30 def __init__(self, column_fields, index_info=None):
31 """ Create a new metadata to manage column fields and index fields and names.
32
33 :param column_fields: list of string
34 Field names to appear as columns.
35 :param index_info: list of string pair
36 Each pair holds the index field name which exists in Spark fields,
37 and the index name.
38 """
39 assert all(isinstance(col, string_types) for col in column_fields)
40 assert index_info is None \
41 or all(isinstance(index_field, string_types)
42 and (index_name is None or isinstance(index_name, string_types))
43 for index_field, index_name in index_info)
44 self._column_fields = column_fields
45 self._index_info = index_info or []
46
47 @property
48 def column_fields(self):
49 return self._column_fields
50
51 @property
52 def index_info(self):
53 return self._index_info
54
55 @property
56 def index_fields(self):
57 return [index_field for index_field, _ in self._index_info]
58
59 @property
60 def index_names(self):
61 return [name for _, name in self._index_info]
62
63 @property
64 def all_fields(self):
65 index_fields = self.index_fields
66 return index_fields + [field for field in self._column_fields
67 if field not in index_fields]
68
69 def copy(self, column_fields=None, index_info=None):
70 if column_fields is None:
71 column_fields = self._column_fields
72 if index_info is None:
73 index_info = self._index_info
74 return Metadata(column_fields=column_fields.copy(), index_info=index_info.copy())
75
76 @staticmethod
77 def from_pandas(pdf):
78 column_fields = [str(col) for col in pdf.columns]
79 index = pdf.index
80 if isinstance(index, pd.MultiIndex):
81 if index.names is None:
82 index_info = [('__index_level_{}__'.format(i), None)
83 for i in range(len(index.levels))]
84 else:
85 index_info = [('__index_level_{}__'.format(i) if name is None else name, name)
86 for i, name in enumerate(index.names)]
87 else:
88 index_info = [(index.name
89 if index.name is not None else '__index_level_0__', index.name)]
90
91 return Metadata(column_fields=column_fields, index_info=index_info)
92
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/databricks/koalas/metadata.py b/databricks/koalas/metadata.py
--- a/databricks/koalas/metadata.py
+++ b/databricks/koalas/metadata.py
@@ -24,7 +24,11 @@
class Metadata(object):
"""
- Manages column names and index information
+ Manages column names and index information.
+
+ :ivar _column_fields: list of the Spark field names to be seen as columns in Koalas DataFrame.
+ :ivar _index_info: list of pair holding the Spark field names for indexes,
+ and the index name to be seen in Koalas DataFrame.
"""
def __init__(self, column_fields, index_info=None):
@@ -46,27 +50,38 @@
@property
def column_fields(self):
+ """ Returns the managed column field names. """
return self._column_fields
@property
def index_info(self):
+ """ Return the managed index information. """
return self._index_info
@property
def index_fields(self):
+ """ Returns the managed index field names. """
return [index_field for index_field, _ in self._index_info]
@property
def index_names(self):
+ """ Return the managed index names. """
return [name for _, name in self._index_info]
@property
def all_fields(self):
+ """ Return all the field names including index field names. """
index_fields = self.index_fields
return index_fields + [field for field in self._column_fields
if field not in index_fields]
def copy(self, column_fields=None, index_info=None):
+ """ Copy the metadata.
+
+ :param column_fields: the new column field names. If None, then the original ones are used.
+ :param index_info: the new index information. If None, then the original one is used.
+ :return: the copied metadata.
+ """
if column_fields is None:
column_fields = self._column_fields
if index_info is None:
@@ -75,6 +90,11 @@
@staticmethod
def from_pandas(pdf):
+ """ Create a metadata from pandas DataFrame.
+
+ :param pdf: :class:`pd.DataFrame`
+ :return: the created metadata
+ """
column_fields = [str(col) for col in pdf.columns]
index = pdf.index
if isinstance(index, pd.MultiIndex):
|
{"golden_diff": "diff --git a/databricks/koalas/metadata.py b/databricks/koalas/metadata.py\n--- a/databricks/koalas/metadata.py\n+++ b/databricks/koalas/metadata.py\n@@ -24,7 +24,11 @@\n \n class Metadata(object):\n \"\"\"\n- Manages column names and index information\n+ Manages column names and index information.\n+\n+ :ivar _column_fields: list of the Spark field names to be seen as columns in Koalas DataFrame.\n+ :ivar _index_info: list of pair holding the Spark field names for indexes,\n+ and the index name to be seen in Koalas DataFrame.\n \"\"\"\n \n def __init__(self, column_fields, index_info=None):\n@@ -46,27 +50,38 @@\n \n @property\n def column_fields(self):\n+ \"\"\" Returns the managed column field names. \"\"\"\n return self._column_fields\n \n @property\n def index_info(self):\n+ \"\"\" Return the managed index information. \"\"\"\n return self._index_info\n \n @property\n def index_fields(self):\n+ \"\"\" Returns the managed index field names. \"\"\"\n return [index_field for index_field, _ in self._index_info]\n \n @property\n def index_names(self):\n+ \"\"\" Return the managed index names. \"\"\"\n return [name for _, name in self._index_info]\n \n @property\n def all_fields(self):\n+ \"\"\" Return all the field names including index field names. \"\"\"\n index_fields = self.index_fields\n return index_fields + [field for field in self._column_fields\n if field not in index_fields]\n \n def copy(self, column_fields=None, index_info=None):\n+ \"\"\" Copy the metadata.\n+\n+ :param column_fields: the new column field names. If None, then the original ones are used.\n+ :param index_info: the new index information. If None, then the original one is used.\n+ :return: the copied metadata.\n+ \"\"\"\n if column_fields is None:\n column_fields = self._column_fields\n if index_info is None:\n@@ -75,6 +90,11 @@\n \n @staticmethod\n def from_pandas(pdf):\n+ \"\"\" Create a metadata from pandas DataFrame.\n+\n+ :param pdf: :class:`pd.DataFrame`\n+ :return: the created metadata\n+ \"\"\"\n column_fields = [str(col) for col in pdf.columns]\n index = pdf.index\n if isinstance(index, pd.MultiIndex):\n", "issue": "Document all the methods in Metadata\nThere are a bunch of methods like index_info, index_fields. It's pretty difficult to figure out what they do. We should just add some basic docstring comments.\r\n\r\n@ueshin you are probably the best person to take this since you created the file.\r\n\n", "before_files": [{"content": "#\n# Copyright (C) 2019 Databricks, Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\n\n\"\"\"\nA metadata to manage indexes.\n\"\"\"\nimport pandas as pd\n\nfrom databricks.koalas.dask.compatibility import string_types\n\n\nclass Metadata(object):\n \"\"\"\n Manages column names and index information\n \"\"\"\n\n def __init__(self, column_fields, index_info=None):\n \"\"\" Create a new metadata to manage column fields and index fields and names.\n\n :param column_fields: list of string\n Field names to appear as columns.\n :param index_info: list of string pair\n Each pair holds the index field name which exists in Spark fields,\n and the index name.\n \"\"\"\n assert all(isinstance(col, string_types) for col in column_fields)\n assert index_info is None \\\n or all(isinstance(index_field, string_types)\n and (index_name is None or isinstance(index_name, string_types))\n for index_field, index_name in index_info)\n self._column_fields = column_fields\n self._index_info = index_info or []\n\n @property\n def column_fields(self):\n return self._column_fields\n\n @property\n def index_info(self):\n return self._index_info\n\n @property\n def index_fields(self):\n return [index_field for index_field, _ in self._index_info]\n\n @property\n def index_names(self):\n return [name for _, name in self._index_info]\n\n @property\n def all_fields(self):\n index_fields = self.index_fields\n return index_fields + [field for field in self._column_fields\n if field not in index_fields]\n\n def copy(self, column_fields=None, index_info=None):\n if column_fields is None:\n column_fields = self._column_fields\n if index_info is None:\n index_info = self._index_info\n return Metadata(column_fields=column_fields.copy(), index_info=index_info.copy())\n\n @staticmethod\n def from_pandas(pdf):\n column_fields = [str(col) for col in pdf.columns]\n index = pdf.index\n if isinstance(index, pd.MultiIndex):\n if index.names is None:\n index_info = [('__index_level_{}__'.format(i), None)\n for i in range(len(index.levels))]\n else:\n index_info = [('__index_level_{}__'.format(i) if name is None else name, name)\n for i, name in enumerate(index.names)]\n else:\n index_info = [(index.name\n if index.name is not None else '__index_level_0__', index.name)]\n\n return Metadata(column_fields=column_fields, index_info=index_info)\n", "path": "databricks/koalas/metadata.py"}], "after_files": [{"content": "#\n# Copyright (C) 2019 Databricks, Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\n\n\"\"\"\nA metadata to manage indexes.\n\"\"\"\nimport pandas as pd\n\nfrom databricks.koalas.dask.compatibility import string_types\n\n\nclass Metadata(object):\n \"\"\"\n Manages column names and index information.\n\n :ivar _column_fields: list of the Spark field names to be seen as columns in Koalas DataFrame.\n :ivar _index_info: list of pair holding the Spark field names for indexes,\n and the index name to be seen in Koalas DataFrame.\n \"\"\"\n\n def __init__(self, column_fields, index_info=None):\n \"\"\" Create a new metadata to manage column fields and index fields and names.\n\n :param column_fields: list of string\n Field names to appear as columns.\n :param index_info: list of string pair\n Each pair holds the index field name which exists in Spark fields,\n and the index name.\n \"\"\"\n assert all(isinstance(col, string_types) for col in column_fields)\n assert index_info is None \\\n or all(isinstance(index_field, string_types)\n and (index_name is None or isinstance(index_name, string_types))\n for index_field, index_name in index_info)\n self._column_fields = column_fields\n self._index_info = index_info or []\n\n @property\n def column_fields(self):\n \"\"\" Returns the managed column field names. \"\"\"\n return self._column_fields\n\n @property\n def index_info(self):\n \"\"\" Return the managed index information. \"\"\"\n return self._index_info\n\n @property\n def index_fields(self):\n \"\"\" Returns the managed index field names. \"\"\"\n return [index_field for index_field, _ in self._index_info]\n\n @property\n def index_names(self):\n \"\"\" Return the managed index names. \"\"\"\n return [name for _, name in self._index_info]\n\n @property\n def all_fields(self):\n \"\"\" Return all the field names including index field names. \"\"\"\n index_fields = self.index_fields\n return index_fields + [field for field in self._column_fields\n if field not in index_fields]\n\n def copy(self, column_fields=None, index_info=None):\n \"\"\" Copy the metadata.\n\n :param column_fields: the new column field names. If None, then the original ones are used.\n :param index_info: the new index information. If None, then the original one is used.\n :return: the copied metadata.\n \"\"\"\n if column_fields is None:\n column_fields = self._column_fields\n if index_info is None:\n index_info = self._index_info\n return Metadata(column_fields=column_fields.copy(), index_info=index_info.copy())\n\n @staticmethod\n def from_pandas(pdf):\n \"\"\" Create a metadata from pandas DataFrame.\n\n :param pdf: :class:`pd.DataFrame`\n :return: the created metadata\n \"\"\"\n column_fields = [str(col) for col in pdf.columns]\n index = pdf.index\n if isinstance(index, pd.MultiIndex):\n if index.names is None:\n index_info = [('__index_level_{}__'.format(i), None)\n for i in range(len(index.levels))]\n else:\n index_info = [('__index_level_{}__'.format(i) if name is None else name, name)\n for i, name in enumerate(index.names)]\n else:\n index_info = [(index.name\n if index.name is not None else '__index_level_0__', index.name)]\n\n return Metadata(column_fields=column_fields, index_info=index_info)\n", "path": "databricks/koalas/metadata.py"}]}
| 1,192 | 557 |
gh_patches_debug_5870
|
rasdani/github-patches
|
git_diff
|
mitmproxy__mitmproxy-1513
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Wait for new cryptography release
For the next mitmproxy release, we want to recommend Python 3.5 by default. This requires a cryptography release which includes https://github.com/pyca/cryptography/pull/3063.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 from setuptools import setup, find_packages
2 from codecs import open
3 import os
4
5 from netlib import version
6
7 # Based on https://github.com/pypa/sampleproject/blob/master/setup.py
8 # and https://python-packaging-user-guide.readthedocs.org/
9
10 here = os.path.abspath(os.path.dirname(__file__))
11
12 with open(os.path.join(here, 'README.rst'), encoding='utf-8') as f:
13 long_description = f.read()
14
15 setup(
16 name="mitmproxy",
17 version=version.VERSION,
18 description="An interactive, SSL-capable, man-in-the-middle HTTP proxy for penetration testers and software developers.",
19 long_description=long_description,
20 url="http://mitmproxy.org",
21 author="Aldo Cortesi",
22 author_email="[email protected]",
23 license="MIT",
24 classifiers=[
25 "License :: OSI Approved :: MIT License",
26 "Development Status :: 5 - Production/Stable",
27 "Environment :: Console",
28 "Environment :: Console :: Curses",
29 "Operating System :: MacOS :: MacOS X",
30 "Operating System :: POSIX",
31 "Operating System :: Microsoft :: Windows",
32 "Programming Language :: Python",
33 "Programming Language :: Python :: 2",
34 "Programming Language :: Python :: 2.7",
35 "Programming Language :: Python :: 3",
36 "Programming Language :: Python :: 3.5",
37 "Programming Language :: Python :: Implementation :: CPython",
38 "Programming Language :: Python :: Implementation :: PyPy",
39 "Topic :: Security",
40 "Topic :: Internet",
41 "Topic :: Internet :: WWW/HTTP",
42 "Topic :: Internet :: Proxy Servers",
43 "Topic :: Software Development :: Testing"
44 ],
45 packages=find_packages(include=[
46 "mitmproxy", "mitmproxy.*",
47 "pathod", "pathod.*",
48 "netlib", "netlib.*"
49 ]),
50 include_package_data=True,
51 entry_points={
52 'console_scripts': [
53 "mitmproxy = mitmproxy.main:mitmproxy",
54 "mitmdump = mitmproxy.main:mitmdump",
55 "mitmweb = mitmproxy.main:mitmweb",
56 "pathod = pathod.pathod_cmdline:go_pathod",
57 "pathoc = pathod.pathoc_cmdline:go_pathoc"
58 ]
59 },
60 # https://packaging.python.org/en/latest/requirements/#install-requires
61 # It is not considered best practice to use install_requires to pin dependencies to specific versions.
62 install_requires=[
63 "backports.ssl_match_hostname>=3.5.0.1, <3.6",
64 "blinker>=1.4, <1.5",
65 "click>=6.2, <7.0",
66 "certifi>=2015.11.20.1", # no semver here - this should always be on the last release!
67 "configargparse>=0.10, <0.11",
68 "construct>=2.5.2, <2.6",
69 "cryptography>=1.3, <1.5",
70 "cssutils>=1.0.1, <1.1",
71 "Flask>=0.10.1, <0.12",
72 "h2>=2.4.1, <3",
73 "html2text>=2016.1.8, <=2016.5.29",
74 "hyperframe>=4.0.1, <5",
75 "jsbeautifier>=1.6.3, <1.7",
76 "lxml>=3.5.0, <=3.6.0", # no wheels for 3.6.1 yet.
77 "Pillow>=3.2, <3.4",
78 "passlib>=1.6.5, <1.7",
79 "pyasn1>=0.1.9, <0.2",
80 "pyOpenSSL>=16.0, <17.0",
81 "pyparsing>=2.1.3, <2.2",
82 "pyperclip>=1.5.22, <1.6",
83 "requests>=2.9.1, <2.12",
84 "six>=1.10, <1.11",
85 "tornado>=4.3, <4.5",
86 "urwid>=1.3.1, <1.4",
87 "watchdog>=0.8.3, <0.9",
88 "brotlipy>=0.3.0, <0.5",
89 ],
90 extras_require={
91 ':sys_platform == "win32"': [
92 "pydivert>=0.0.7, <0.1",
93 ],
94 ':sys_platform != "win32"': [
95 ],
96 # Do not use a range operator here: https://bitbucket.org/pypa/setuptools/issues/380
97 # Ubuntu Trusty and other still ship with setuptools < 17.1
98 ':python_version == "2.7"': [
99 "enum34>=1.0.4, <2",
100 "ipaddress>=1.0.15, <1.1",
101 "typing==3.5.2.2",
102 ],
103 'dev': [
104 "tox>=2.3, <3",
105 "mock>=2.0, <2.1",
106 "pytest>=2.8.7, <3",
107 "pytest-cov>=2.2.1, <3",
108 "pytest-timeout>=1.0.0, <2",
109 "pytest-xdist>=1.14, <2",
110 "sphinx>=1.3.5, <1.5",
111 "sphinx-autobuild>=0.5.2, <0.7",
112 "sphinxcontrib-documentedlist>=0.4.0, <0.5",
113 "sphinx_rtd_theme>=0.1.9, <0.2",
114 ],
115 'contentviews': [
116 # TODO: Find Python 3 replacements
117 # "protobuf>=2.6.1, <2.7",
118 # "pyamf>=0.8.0, <0.9",
119 ],
120 'examples': [
121 "beautifulsoup4>=4.4.1, <4.6",
122 "pytz>=2015.07.0, <=2016.6.1",
123 ]
124 }
125 )
126
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -66,7 +66,7 @@
"certifi>=2015.11.20.1", # no semver here - this should always be on the last release!
"configargparse>=0.10, <0.11",
"construct>=2.5.2, <2.6",
- "cryptography>=1.3, <1.5",
+ "cryptography>=1.3, <1.6",
"cssutils>=1.0.1, <1.1",
"Flask>=0.10.1, <0.12",
"h2>=2.4.1, <3",
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -66,7 +66,7 @@\n \"certifi>=2015.11.20.1\", # no semver here - this should always be on the last release!\n \"configargparse>=0.10, <0.11\",\n \"construct>=2.5.2, <2.6\",\n- \"cryptography>=1.3, <1.5\",\n+ \"cryptography>=1.3, <1.6\",\n \"cssutils>=1.0.1, <1.1\",\n \"Flask>=0.10.1, <0.12\",\n \"h2>=2.4.1, <3\",\n", "issue": "Wait for new cryptography release\nFor the next mitmproxy release, we want to recommend Python 3.5 by default. This requires a cryptography release which includes https://github.com/pyca/cryptography/pull/3063.\n\n", "before_files": [{"content": "from setuptools import setup, find_packages\nfrom codecs import open\nimport os\n\nfrom netlib import version\n\n# Based on https://github.com/pypa/sampleproject/blob/master/setup.py\n# and https://python-packaging-user-guide.readthedocs.org/\n\nhere = os.path.abspath(os.path.dirname(__file__))\n\nwith open(os.path.join(here, 'README.rst'), encoding='utf-8') as f:\n long_description = f.read()\n\nsetup(\n name=\"mitmproxy\",\n version=version.VERSION,\n description=\"An interactive, SSL-capable, man-in-the-middle HTTP proxy for penetration testers and software developers.\",\n long_description=long_description,\n url=\"http://mitmproxy.org\",\n author=\"Aldo Cortesi\",\n author_email=\"[email protected]\",\n license=\"MIT\",\n classifiers=[\n \"License :: OSI Approved :: MIT License\",\n \"Development Status :: 5 - Production/Stable\",\n \"Environment :: Console\",\n \"Environment :: Console :: Curses\",\n \"Operating System :: MacOS :: MacOS X\",\n \"Operating System :: POSIX\",\n \"Operating System :: Microsoft :: Windows\",\n \"Programming Language :: Python\",\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.5\",\n \"Programming Language :: Python :: Implementation :: CPython\",\n \"Programming Language :: Python :: Implementation :: PyPy\",\n \"Topic :: Security\",\n \"Topic :: Internet\",\n \"Topic :: Internet :: WWW/HTTP\",\n \"Topic :: Internet :: Proxy Servers\",\n \"Topic :: Software Development :: Testing\"\n ],\n packages=find_packages(include=[\n \"mitmproxy\", \"mitmproxy.*\",\n \"pathod\", \"pathod.*\",\n \"netlib\", \"netlib.*\"\n ]),\n include_package_data=True,\n entry_points={\n 'console_scripts': [\n \"mitmproxy = mitmproxy.main:mitmproxy\",\n \"mitmdump = mitmproxy.main:mitmdump\",\n \"mitmweb = mitmproxy.main:mitmweb\",\n \"pathod = pathod.pathod_cmdline:go_pathod\",\n \"pathoc = pathod.pathoc_cmdline:go_pathoc\"\n ]\n },\n # https://packaging.python.org/en/latest/requirements/#install-requires\n # It is not considered best practice to use install_requires to pin dependencies to specific versions.\n install_requires=[\n \"backports.ssl_match_hostname>=3.5.0.1, <3.6\",\n \"blinker>=1.4, <1.5\",\n \"click>=6.2, <7.0\",\n \"certifi>=2015.11.20.1\", # no semver here - this should always be on the last release!\n \"configargparse>=0.10, <0.11\",\n \"construct>=2.5.2, <2.6\",\n \"cryptography>=1.3, <1.5\",\n \"cssutils>=1.0.1, <1.1\",\n \"Flask>=0.10.1, <0.12\",\n \"h2>=2.4.1, <3\",\n \"html2text>=2016.1.8, <=2016.5.29\",\n \"hyperframe>=4.0.1, <5\",\n \"jsbeautifier>=1.6.3, <1.7\",\n \"lxml>=3.5.0, <=3.6.0\", # no wheels for 3.6.1 yet.\n \"Pillow>=3.2, <3.4\",\n \"passlib>=1.6.5, <1.7\",\n \"pyasn1>=0.1.9, <0.2\",\n \"pyOpenSSL>=16.0, <17.0\",\n \"pyparsing>=2.1.3, <2.2\",\n \"pyperclip>=1.5.22, <1.6\",\n \"requests>=2.9.1, <2.12\",\n \"six>=1.10, <1.11\",\n \"tornado>=4.3, <4.5\",\n \"urwid>=1.3.1, <1.4\",\n \"watchdog>=0.8.3, <0.9\",\n \"brotlipy>=0.3.0, <0.5\",\n ],\n extras_require={\n ':sys_platform == \"win32\"': [\n \"pydivert>=0.0.7, <0.1\",\n ],\n ':sys_platform != \"win32\"': [\n ],\n # Do not use a range operator here: https://bitbucket.org/pypa/setuptools/issues/380\n # Ubuntu Trusty and other still ship with setuptools < 17.1\n ':python_version == \"2.7\"': [\n \"enum34>=1.0.4, <2\",\n \"ipaddress>=1.0.15, <1.1\",\n \"typing==3.5.2.2\",\n ],\n 'dev': [\n \"tox>=2.3, <3\",\n \"mock>=2.0, <2.1\",\n \"pytest>=2.8.7, <3\",\n \"pytest-cov>=2.2.1, <3\",\n \"pytest-timeout>=1.0.0, <2\",\n \"pytest-xdist>=1.14, <2\",\n \"sphinx>=1.3.5, <1.5\",\n \"sphinx-autobuild>=0.5.2, <0.7\",\n \"sphinxcontrib-documentedlist>=0.4.0, <0.5\",\n \"sphinx_rtd_theme>=0.1.9, <0.2\",\n ],\n 'contentviews': [\n # TODO: Find Python 3 replacements\n # \"protobuf>=2.6.1, <2.7\",\n # \"pyamf>=0.8.0, <0.9\",\n ],\n 'examples': [\n \"beautifulsoup4>=4.4.1, <4.6\",\n \"pytz>=2015.07.0, <=2016.6.1\",\n ]\n }\n)\n", "path": "setup.py"}], "after_files": [{"content": "from setuptools import setup, find_packages\nfrom codecs import open\nimport os\n\nfrom netlib import version\n\n# Based on https://github.com/pypa/sampleproject/blob/master/setup.py\n# and https://python-packaging-user-guide.readthedocs.org/\n\nhere = os.path.abspath(os.path.dirname(__file__))\n\nwith open(os.path.join(here, 'README.rst'), encoding='utf-8') as f:\n long_description = f.read()\n\nsetup(\n name=\"mitmproxy\",\n version=version.VERSION,\n description=\"An interactive, SSL-capable, man-in-the-middle HTTP proxy for penetration testers and software developers.\",\n long_description=long_description,\n url=\"http://mitmproxy.org\",\n author=\"Aldo Cortesi\",\n author_email=\"[email protected]\",\n license=\"MIT\",\n classifiers=[\n \"License :: OSI Approved :: MIT License\",\n \"Development Status :: 5 - Production/Stable\",\n \"Environment :: Console\",\n \"Environment :: Console :: Curses\",\n \"Operating System :: MacOS :: MacOS X\",\n \"Operating System :: POSIX\",\n \"Operating System :: Microsoft :: Windows\",\n \"Programming Language :: Python\",\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.5\",\n \"Programming Language :: Python :: Implementation :: CPython\",\n \"Programming Language :: Python :: Implementation :: PyPy\",\n \"Topic :: Security\",\n \"Topic :: Internet\",\n \"Topic :: Internet :: WWW/HTTP\",\n \"Topic :: Internet :: Proxy Servers\",\n \"Topic :: Software Development :: Testing\"\n ],\n packages=find_packages(include=[\n \"mitmproxy\", \"mitmproxy.*\",\n \"pathod\", \"pathod.*\",\n \"netlib\", \"netlib.*\"\n ]),\n include_package_data=True,\n entry_points={\n 'console_scripts': [\n \"mitmproxy = mitmproxy.main:mitmproxy\",\n \"mitmdump = mitmproxy.main:mitmdump\",\n \"mitmweb = mitmproxy.main:mitmweb\",\n \"pathod = pathod.pathod_cmdline:go_pathod\",\n \"pathoc = pathod.pathoc_cmdline:go_pathoc\"\n ]\n },\n # https://packaging.python.org/en/latest/requirements/#install-requires\n # It is not considered best practice to use install_requires to pin dependencies to specific versions.\n install_requires=[\n \"backports.ssl_match_hostname>=3.5.0.1, <3.6\",\n \"blinker>=1.4, <1.5\",\n \"click>=6.2, <7.0\",\n \"certifi>=2015.11.20.1\", # no semver here - this should always be on the last release!\n \"configargparse>=0.10, <0.11\",\n \"construct>=2.5.2, <2.6\",\n \"cryptography>=1.3, <1.6\",\n \"cssutils>=1.0.1, <1.1\",\n \"Flask>=0.10.1, <0.12\",\n \"h2>=2.4.1, <3\",\n \"html2text>=2016.1.8, <=2016.5.29\",\n \"hyperframe>=4.0.1, <5\",\n \"jsbeautifier>=1.6.3, <1.7\",\n \"lxml>=3.5.0, <=3.6.0\", # no wheels for 3.6.1 yet.\n \"Pillow>=3.2, <3.4\",\n \"passlib>=1.6.5, <1.7\",\n \"pyasn1>=0.1.9, <0.2\",\n \"pyOpenSSL>=16.0, <17.0\",\n \"pyparsing>=2.1.3, <2.2\",\n \"pyperclip>=1.5.22, <1.6\",\n \"requests>=2.9.1, <2.12\",\n \"six>=1.10, <1.11\",\n \"tornado>=4.3, <4.5\",\n \"urwid>=1.3.1, <1.4\",\n \"watchdog>=0.8.3, <0.9\",\n \"brotlipy>=0.3.0, <0.5\",\n ],\n extras_require={\n ':sys_platform == \"win32\"': [\n \"pydivert>=0.0.7, <0.1\",\n ],\n ':sys_platform != \"win32\"': [\n ],\n # Do not use a range operator here: https://bitbucket.org/pypa/setuptools/issues/380\n # Ubuntu Trusty and other still ship with setuptools < 17.1\n ':python_version == \"2.7\"': [\n \"enum34>=1.0.4, <2\",\n \"ipaddress>=1.0.15, <1.1\",\n \"typing==3.5.2.2\",\n ],\n 'dev': [\n \"tox>=2.3, <3\",\n \"mock>=2.0, <2.1\",\n \"pytest>=2.8.7, <3\",\n \"pytest-cov>=2.2.1, <3\",\n \"pytest-timeout>=1.0.0, <2\",\n \"pytest-xdist>=1.14, <2\",\n \"sphinx>=1.3.5, <1.5\",\n \"sphinx-autobuild>=0.5.2, <0.7\",\n \"sphinxcontrib-documentedlist>=0.4.0, <0.5\",\n \"sphinx_rtd_theme>=0.1.9, <0.2\",\n ],\n 'contentviews': [\n # TODO: Find Python 3 replacements\n # \"protobuf>=2.6.1, <2.7\",\n # \"pyamf>=0.8.0, <0.9\",\n ],\n 'examples': [\n \"beautifulsoup4>=4.4.1, <4.6\",\n \"pytz>=2015.07.0, <=2016.6.1\",\n ]\n }\n)\n", "path": "setup.py"}]}
| 1,990 | 176 |
gh_patches_debug_63301
|
rasdani/github-patches
|
git_diff
|
scikit-hep__pyhf-372
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Update tensorflow-probability to the next release that includes continuous approximations
# Description
This is a follow up to #302. As the bug is fixed in upstream tensorflow-probability, we just need to wait for a new release to be shipped.
This bug was because of a change in the API to get rid of the continuous approximation to the Poisson pmf which broke our tests.
### Describe the solution you'd like
Unfix tensorflow-probability to `0.3.0` and bump to the next available release post-0.4.0.
Update Tensorflow to TensorFlow 1.12.0 release
# Description
[TensorFlow 1.12.0 has been released](https://github.com/tensorflow/tensorflow/releases/tag/v1.12.0) and it has breaking changes. Most notably
> Remove `tf.contrib.linalg`. `tf.linalg` should be used instead.
Once there is a new release of TensorFlow probability (`v0.5.0` — c.f. Issue #360 and #330) that upgrades to `v1.12.0` then we can follow them in upgrading.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 #!/usr/bin/env python
2
3 from setuptools import setup, find_packages
4 from os import path
5 import sys
6
7 this_directory = path.abspath(path.dirname(__file__))
8 if sys.version_info.major < 3:
9 from io import open
10 with open(path.join(this_directory, 'README.md'), encoding='utf-8') as readme_md:
11 long_description = readme_md.read()
12
13 extras_require = {
14 'tensorflow': [
15 'tensorflow<1.12.0,>=1.10.0',
16 'tensorflow-probability==0.3.0',
17 'numpy<=1.14.5,>=1.14.0', # Lower of 1.14.0 instead of 1.13.3 to ensure doctest pass
18 'setuptools<=39.1.0',
19 ],
20 'torch': ['torch>=0.4.0'],
21 'mxnet': [
22 'mxnet>=1.0.0',
23 'requests<2.19.0,>=2.18.4',
24 'numpy<1.15.0,>=1.8.2',
25 'requests<2.19.0,>=2.18.4',
26 ],
27 # 'dask': [
28 # 'dask[array]'
29 # ],
30 'xmlimport': ['uproot'],
31 'minuit': ['iminuit'],
32 'develop': [
33 'pyflakes',
34 'pytest<4.0.0,>=3.5.1',
35 'pytest-cov>=2.5.1',
36 'pytest-mock',
37 'pytest-benchmark[histogram]',
38 'pytest-console-scripts',
39 'python-coveralls',
40 'coverage>=4.0', # coveralls
41 'matplotlib',
42 'jupyter',
43 'nbdime',
44 'uproot>=3.0.0',
45 'papermill>=0.16.0',
46 'graphviz',
47 'bumpversion',
48 'sphinx',
49 'sphinxcontrib-bibtex',
50 'sphinxcontrib-napoleon',
51 'sphinx_rtd_theme',
52 'nbsphinx',
53 'sphinx-issues',
54 'm2r',
55 'jsonpatch',
56 'ipython<7', # jupyter_console and ipython clash in dependency requirement -- downgrade ipython for now
57 'pre-commit',
58 'black;python_version>="3.6"', # Black is Python3 only
59 'twine',
60 ],
61 }
62 extras_require['complete'] = sorted(set(sum(extras_require.values(), [])))
63
64 setup(
65 name='pyhf',
66 version='0.0.15',
67 description='(partial) pure python histfactory implementation',
68 long_description=long_description,
69 long_description_content_type='text/markdown',
70 url='https://github.com/diana-hep/pyhf',
71 author='Lukas Heinrich',
72 author_email='[email protected]',
73 license='Apache',
74 keywords='physics fitting numpy scipy tensorflow pytorch mxnet dask',
75 classifiers=[
76 "Programming Language :: Python :: 2",
77 "Programming Language :: Python :: 2.7",
78 "Programming Language :: Python :: 3",
79 "Programming Language :: Python :: 3.6",
80 ],
81 packages=find_packages(),
82 include_package_data=True,
83 python_requires=">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*",
84 install_requires=[
85 'scipy', # requires numpy, which is required by pyhf, tensorflow, and mxnet
86 'click>=6.0', # for console scripts,
87 'tqdm', # for readxml
88 'six', # for modifiers
89 'jsonschema>=v3.0.0a2', # for utils, alpha-release for draft 6
90 'jsonpatch',
91 ],
92 extras_require=extras_require,
93 entry_points={'console_scripts': ['pyhf=pyhf.commandline:pyhf']},
94 dependency_links=[],
95 )
96
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -12,8 +12,8 @@
extras_require = {
'tensorflow': [
- 'tensorflow<1.12.0,>=1.10.0',
- 'tensorflow-probability==0.3.0',
+ 'tensorflow>=1.12.0',
+ 'tensorflow-probability>=0.5.0',
'numpy<=1.14.5,>=1.14.0', # Lower of 1.14.0 instead of 1.13.3 to ensure doctest pass
'setuptools<=39.1.0',
],
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -12,8 +12,8 @@\n \n extras_require = {\n 'tensorflow': [\n- 'tensorflow<1.12.0,>=1.10.0',\n- 'tensorflow-probability==0.3.0',\n+ 'tensorflow>=1.12.0',\n+ 'tensorflow-probability>=0.5.0',\n 'numpy<=1.14.5,>=1.14.0', # Lower of 1.14.0 instead of 1.13.3 to ensure doctest pass\n 'setuptools<=39.1.0',\n ],\n", "issue": "Update tensorflow-probability to the next release that includes continuous approximations\n# Description\r\n\r\nThis is a follow up to #302. As the bug is fixed in upstream tensorflow-probability, we just need to wait for a new release to be shipped.\r\n\r\nThis bug was because of a change in the API to get rid of the continuous approximation to the Poisson pmf which broke our tests.\r\n\r\n### Describe the solution you'd like\r\n\r\nUnfix tensorflow-probability to `0.3.0` and bump to the next available release post-0.4.0.\nUpdate Tensorflow to TensorFlow 1.12.0 release\n# Description\r\n\r\n[TensorFlow 1.12.0 has been released](https://github.com/tensorflow/tensorflow/releases/tag/v1.12.0) and it has breaking changes. Most notably\r\n\r\n> Remove `tf.contrib.linalg`. `tf.linalg` should be used instead. \r\n\r\nOnce there is a new release of TensorFlow probability (`v0.5.0` — c.f. Issue #360 and #330) that upgrades to `v1.12.0` then we can follow them in upgrading.\r\n\n", "before_files": [{"content": "#!/usr/bin/env python\n\nfrom setuptools import setup, find_packages\nfrom os import path\nimport sys\n\nthis_directory = path.abspath(path.dirname(__file__))\nif sys.version_info.major < 3:\n from io import open\nwith open(path.join(this_directory, 'README.md'), encoding='utf-8') as readme_md:\n long_description = readme_md.read()\n\nextras_require = {\n 'tensorflow': [\n 'tensorflow<1.12.0,>=1.10.0',\n 'tensorflow-probability==0.3.0',\n 'numpy<=1.14.5,>=1.14.0', # Lower of 1.14.0 instead of 1.13.3 to ensure doctest pass\n 'setuptools<=39.1.0',\n ],\n 'torch': ['torch>=0.4.0'],\n 'mxnet': [\n 'mxnet>=1.0.0',\n 'requests<2.19.0,>=2.18.4',\n 'numpy<1.15.0,>=1.8.2',\n 'requests<2.19.0,>=2.18.4',\n ],\n # 'dask': [\n # 'dask[array]'\n # ],\n 'xmlimport': ['uproot'],\n 'minuit': ['iminuit'],\n 'develop': [\n 'pyflakes',\n 'pytest<4.0.0,>=3.5.1',\n 'pytest-cov>=2.5.1',\n 'pytest-mock',\n 'pytest-benchmark[histogram]',\n 'pytest-console-scripts',\n 'python-coveralls',\n 'coverage>=4.0', # coveralls\n 'matplotlib',\n 'jupyter',\n 'nbdime',\n 'uproot>=3.0.0',\n 'papermill>=0.16.0',\n 'graphviz',\n 'bumpversion',\n 'sphinx',\n 'sphinxcontrib-bibtex',\n 'sphinxcontrib-napoleon',\n 'sphinx_rtd_theme',\n 'nbsphinx',\n 'sphinx-issues',\n 'm2r',\n 'jsonpatch',\n 'ipython<7', # jupyter_console and ipython clash in dependency requirement -- downgrade ipython for now\n 'pre-commit',\n 'black;python_version>=\"3.6\"', # Black is Python3 only\n 'twine',\n ],\n}\nextras_require['complete'] = sorted(set(sum(extras_require.values(), [])))\n\nsetup(\n name='pyhf',\n version='0.0.15',\n description='(partial) pure python histfactory implementation',\n long_description=long_description,\n long_description_content_type='text/markdown',\n url='https://github.com/diana-hep/pyhf',\n author='Lukas Heinrich',\n author_email='[email protected]',\n license='Apache',\n keywords='physics fitting numpy scipy tensorflow pytorch mxnet dask',\n classifiers=[\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.6\",\n ],\n packages=find_packages(),\n include_package_data=True,\n python_requires=\">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*\",\n install_requires=[\n 'scipy', # requires numpy, which is required by pyhf, tensorflow, and mxnet\n 'click>=6.0', # for console scripts,\n 'tqdm', # for readxml\n 'six', # for modifiers\n 'jsonschema>=v3.0.0a2', # for utils, alpha-release for draft 6\n 'jsonpatch',\n ],\n extras_require=extras_require,\n entry_points={'console_scripts': ['pyhf=pyhf.commandline:pyhf']},\n dependency_links=[],\n)\n", "path": "setup.py"}], "after_files": [{"content": "#!/usr/bin/env python\n\nfrom setuptools import setup, find_packages\nfrom os import path\nimport sys\n\nthis_directory = path.abspath(path.dirname(__file__))\nif sys.version_info.major < 3:\n from io import open\nwith open(path.join(this_directory, 'README.md'), encoding='utf-8') as readme_md:\n long_description = readme_md.read()\n\nextras_require = {\n 'tensorflow': [\n 'tensorflow>=1.12.0',\n 'tensorflow-probability>=0.5.0',\n 'numpy<=1.14.5,>=1.14.0', # Lower of 1.14.0 instead of 1.13.3 to ensure doctest pass\n 'setuptools<=39.1.0',\n ],\n 'torch': ['torch>=0.4.0'],\n 'mxnet': [\n 'mxnet>=1.0.0',\n 'requests<2.19.0,>=2.18.4',\n 'numpy<1.15.0,>=1.8.2',\n 'requests<2.19.0,>=2.18.4',\n ],\n # 'dask': [\n # 'dask[array]'\n # ],\n 'xmlimport': ['uproot'],\n 'minuit': ['iminuit'],\n 'develop': [\n 'pyflakes',\n 'pytest<4.0.0,>=3.5.1',\n 'pytest-cov>=2.5.1',\n 'pytest-mock',\n 'pytest-benchmark[histogram]',\n 'pytest-console-scripts',\n 'python-coveralls',\n 'coverage>=4.0', # coveralls\n 'matplotlib',\n 'jupyter',\n 'nbdime',\n 'uproot>=3.0.0',\n 'papermill>=0.16.0',\n 'graphviz',\n 'bumpversion',\n 'sphinx',\n 'sphinxcontrib-bibtex',\n 'sphinxcontrib-napoleon',\n 'sphinx_rtd_theme',\n 'nbsphinx',\n 'sphinx-issues',\n 'm2r',\n 'jsonpatch',\n 'ipython<7', # jupyter_console and ipython clash in dependency requirement -- downgrade ipython for now\n 'pre-commit',\n 'black;python_version>=\"3.6\"', # Black is Python3 only\n 'twine',\n ],\n}\nextras_require['complete'] = sorted(set(sum(extras_require.values(), [])))\n\nsetup(\n name='pyhf',\n version='0.0.15',\n description='(partial) pure python histfactory implementation',\n long_description=long_description,\n long_description_content_type='text/markdown',\n url='https://github.com/diana-hep/pyhf',\n author='Lukas Heinrich',\n author_email='[email protected]',\n license='Apache',\n keywords='physics fitting numpy scipy tensorflow pytorch mxnet dask',\n classifiers=[\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.6\",\n ],\n packages=find_packages(),\n include_package_data=True,\n python_requires=\">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*\",\n install_requires=[\n 'scipy', # requires numpy, which is required by pyhf, tensorflow, and mxnet\n 'click>=6.0', # for console scripts,\n 'tqdm', # for readxml\n 'six', # for modifiers\n 'jsonschema>=v3.0.0a2', # for utils, alpha-release for draft 6\n 'jsonpatch',\n ],\n extras_require=extras_require,\n entry_points={'console_scripts': ['pyhf=pyhf.commandline:pyhf']},\n dependency_links=[],\n)\n", "path": "setup.py"}]}
| 1,587 | 161 |
gh_patches_debug_33301
|
rasdani/github-patches
|
git_diff
|
ansible__ansible-lint-1747
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
command-instead-of-module "yum clean" revisited
<!--- Verify first that your issue is not already reported on GitHub -->
<!--- Also test if the latest release and main branch are affected too -->
##### Summary
<!--- Explain the problem briefly below -->
The lint error `command-instead-of-module` is raised for command `yum clean`. As the `yum` module documentation states there is no support for doing `yum clean` operation in the module. So the only option is to run a command.
This issue has been raised in the past as #369 and `warn: false` was recommended. But that is now deprecated in 2.11.
So shouldn't ansible-lint detect if `yum clean` is being run and not raise `command-instead-of-module`?
If there is positive feedback and nobody else wants to do it then I can volunteer to make the patch - it should be a simple change, no?
##### Issue Type
- Bug Report
##### Ansible and Ansible Lint details
<!--- Paste verbatim output between triple backticks -->
```console (paste below)
ansible --version
ansible [core 2.11.5]
config file = /etc/ansible/ansible.cfg
configured module search path = ['/usr/share/ansible/plugins/modules']
ansible python module location = /opt/ansible/lib64/python3.6/site-packages/ansible
ansible collection location = /usr/share/ansible/collections
executable location = /opt/ansible/bin/ansible
python version = 3.6.8 (default, Nov 16 2020, 16:55:22) [GCC 4.8.5 20150623 (Red Hat 4.8.5-44)]
jinja version = 3.0.2
libyaml = True
ansible-lint --version
ansible-lint 5.2.0 using ansible 2.11.5
```
- ansible installation method: pip
- ansible-lint installation method: pip
##### OS / ENVIRONMENT
<!--- Provide all relevant information below, e.g. target OS versions, network device firmware, etc. -->
EL7
##### STEPS TO REPRODUCE
<!--- Describe exactly how to reproduce the problem, using a minimal test-case -->
Have a command that runs `yum clean`.
<!--- Paste example playbooks or commands between triple backticks below -->
```yaml
command:
cmd: yum clean all
```
<!--- HINT: You can paste gist.github.com links for larger files -->
##### Desired Behaviour
<!--- Describe what you expected to happen when running the steps above -->
`command-instead-of-module` should not be raised for `yum clean` which cannot be done using the `yum` module.
Possible security bugs should be reported via email to `[email protected]`
##### Actual Behaviour
<!--- Describe what actually happened. If possible run with extra verbosity (-vvvv) -->
`command-instead-of-module` is raised even though the module cannot do this action.
<!--- Paste verbatim command output between triple backticks -->
```paste below
```
[minimum complete verifiable example]: http://stackoverflow.com/help/mcve
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/ansiblelint/rules/CommandsInsteadOfModulesRule.py`
Content:
```
1 # Copyright (c) 2013-2014 Will Thames <[email protected]>
2 #
3 # Permission is hereby granted, free of charge, to any person obtaining a copy
4 # of this software and associated documentation files (the "Software"), to deal
5 # in the Software without restriction, including without limitation the rights
6 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7 # copies of the Software, and to permit persons to whom the Software is
8 # furnished to do so, subject to the following conditions:
9 #
10 # The above copyright notice and this permission notice shall be included in
11 # all copies or substantial portions of the Software.
12 #
13 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19 # THE SOFTWARE.
20
21 import os
22 import sys
23 from typing import TYPE_CHECKING, Any, Dict, Union
24
25 from ansiblelint.rules import AnsibleLintRule
26 from ansiblelint.utils import convert_to_boolean, get_first_cmd_arg, get_second_cmd_arg
27
28 if TYPE_CHECKING:
29 from typing import Optional
30
31 from ansiblelint.file_utils import Lintable
32
33
34 class CommandsInsteadOfModulesRule(AnsibleLintRule):
35 id = 'command-instead-of-module'
36 shortdesc = 'Using command rather than module'
37 description = (
38 'Executing a command when there is an Ansible module is generally a bad idea'
39 )
40 severity = 'HIGH'
41 tags = ['command-shell', 'idiom']
42 version_added = 'historic'
43
44 _commands = ['command', 'shell']
45 _modules = {
46 'apt-get': 'apt-get',
47 'chkconfig': 'service',
48 'curl': 'get_url or uri',
49 'git': 'git',
50 'hg': 'hg',
51 'letsencrypt': 'acme_certificate',
52 'mktemp': 'tempfile',
53 'mount': 'mount',
54 'patch': 'patch',
55 'rpm': 'yum or rpm_key',
56 'rsync': 'synchronize',
57 'sed': 'template, replace or lineinfile',
58 'service': 'service',
59 'supervisorctl': 'supervisorctl',
60 'svn': 'subversion',
61 'systemctl': 'systemd',
62 'tar': 'unarchive',
63 'unzip': 'unarchive',
64 'wget': 'get_url or uri',
65 'yum': 'yum',
66 }
67
68 _executable_options = {
69 'git': ['branch', 'log'],
70 'systemctl': ['set-default', 'show-environment', 'status'],
71 }
72
73 def matchtask(
74 self, task: Dict[str, Any], file: 'Optional[Lintable]' = None
75 ) -> Union[bool, str]:
76
77 if task['action']['__ansible_module__'] not in self._commands:
78 return False
79
80 first_cmd_arg = get_first_cmd_arg(task)
81 second_cmd_arg = get_second_cmd_arg(task)
82
83 if not first_cmd_arg:
84 return False
85
86 executable = os.path.basename(first_cmd_arg)
87
88 if (
89 second_cmd_arg
90 and executable in self._executable_options
91 and second_cmd_arg in self._executable_options[executable]
92 ):
93 return False
94
95 if executable in self._modules and convert_to_boolean(
96 task['action'].get('warn', True)
97 ):
98 message = '{0} used in place of {1} module'
99 return message.format(executable, self._modules[executable])
100 return False
101
102
103 if "pytest" in sys.modules:
104 import pytest
105
106 from ansiblelint.testing import RunFromText # pylint: disable=ungrouped-imports
107
108 APT_GET = '''
109 - hosts: all
110 tasks:
111 - name: run apt-get update
112 command: apt-get update
113 '''
114
115 GIT_BRANCH = '''
116 - hosts: all
117 tasks:
118 - name: print current git branch
119 command: git branch
120 '''
121
122 GIT_LOG = '''
123 - hosts: all
124 tasks:
125 - name: print git log
126 command: git log
127 '''
128
129 RESTART_SSHD = '''
130 - hosts: all
131 tasks:
132 - name: restart sshd
133 command: systemctl restart sshd
134 '''
135
136 SYSTEMCTL_STATUS = '''
137 - hosts: all
138 tasks:
139 - name: show systemctl service status
140 command: systemctl status systemd-timesyncd
141 '''
142
143 SYSTEMD_ENVIRONMENT = '''
144 - hosts: all
145 tasks:
146 - name: show systemd environment
147 command: systemctl show-environment
148 '''
149
150 SYSTEMD_RUNLEVEL = '''
151 - hosts: all
152 tasks:
153 - name: set systemd runlevel
154 command: systemctl set-default multi-user.target
155 '''
156
157 @pytest.mark.parametrize(
158 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
159 )
160 def test_apt_get(rule_runner: RunFromText) -> None:
161 """The apt module supports update."""
162 results = rule_runner.run_playbook(APT_GET)
163 assert len(results) == 1
164
165 @pytest.mark.parametrize(
166 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
167 )
168 def test_restart_sshd(rule_runner: RunFromText) -> None:
169 """Restarting services is supported by the systemd module."""
170 results = rule_runner.run_playbook(RESTART_SSHD)
171 assert len(results) == 1
172
173 @pytest.mark.parametrize(
174 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
175 )
176 def test_git_log(rule_runner: RunFromText) -> None:
177 """The git log command is not supported by the git module."""
178 results = rule_runner.run_playbook(GIT_LOG)
179 assert len(results) == 0
180
181 @pytest.mark.parametrize(
182 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
183 )
184 def test_git_branch(rule_runner: RunFromText) -> None:
185 """The git branch command is not supported by the git module."""
186 results = rule_runner.run_playbook(GIT_BRANCH)
187 assert len(results) == 0
188
189 @pytest.mark.parametrize(
190 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
191 )
192 def test_systemd_status(rule_runner: RunFromText) -> None:
193 """Set-default is not supported by the systemd module."""
194 results = rule_runner.run_playbook(SYSTEMCTL_STATUS)
195 assert len(results) == 0
196
197 @pytest.mark.parametrize(
198 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
199 )
200 def test_systemd_environment(rule_runner: RunFromText) -> None:
201 """Showing the environment is not supported by the systemd module."""
202 results = rule_runner.run_playbook(SYSTEMD_ENVIRONMENT)
203 assert len(results) == 0
204
205 @pytest.mark.parametrize(
206 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
207 )
208 def test_systemd_runlevel(rule_runner: RunFromText) -> None:
209 """Set-default is not supported by the systemd module."""
210 results = rule_runner.run_playbook(SYSTEMD_RUNLEVEL)
211 assert len(results) == 0
212
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py b/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py
--- a/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py
+++ b/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py
@@ -68,6 +68,7 @@
_executable_options = {
'git': ['branch', 'log'],
'systemctl': ['set-default', 'show-environment', 'status'],
+ 'yum': ['clean'],
}
def matchtask(
@@ -100,7 +101,7 @@
return False
-if "pytest" in sys.modules:
+if "pytest" in sys.modules: # noqa: C901
import pytest
from ansiblelint.testing import RunFromText # pylint: disable=ungrouped-imports
@@ -154,6 +155,20 @@
command: systemctl set-default multi-user.target
'''
+ YUM_UPDATE = '''
+- hosts: all
+ tasks:
+ - name: run yum update
+ command: yum update
+'''
+
+ YUM_CLEAN = '''
+- hosts: all
+ tasks:
+ - name: clear yum cache
+ command: yum clean all
+'''
+
@pytest.mark.parametrize(
'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
)
@@ -209,3 +224,19 @@
"""Set-default is not supported by the systemd module."""
results = rule_runner.run_playbook(SYSTEMD_RUNLEVEL)
assert len(results) == 0
+
+ @pytest.mark.parametrize(
+ 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
+ )
+ def test_yum_update(rule_runner: RunFromText) -> None:
+ """Using yum update should fail."""
+ results = rule_runner.run_playbook(YUM_UPDATE)
+ assert len(results) == 1
+
+ @pytest.mark.parametrize(
+ 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']
+ )
+ def test_yum_clean(rule_runner: RunFromText) -> None:
+ """The yum module does not support clearing yum cache."""
+ results = rule_runner.run_playbook(YUM_CLEAN)
+ assert len(results) == 0
|
{"golden_diff": "diff --git a/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py b/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py\n--- a/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py\n+++ b/src/ansiblelint/rules/CommandsInsteadOfModulesRule.py\n@@ -68,6 +68,7 @@\n _executable_options = {\n 'git': ['branch', 'log'],\n 'systemctl': ['set-default', 'show-environment', 'status'],\n+ 'yum': ['clean'],\n }\n \n def matchtask(\n@@ -100,7 +101,7 @@\n return False\n \n \n-if \"pytest\" in sys.modules:\n+if \"pytest\" in sys.modules: # noqa: C901\n import pytest\n \n from ansiblelint.testing import RunFromText # pylint: disable=ungrouped-imports\n@@ -154,6 +155,20 @@\n command: systemctl set-default multi-user.target\n '''\n \n+ YUM_UPDATE = '''\n+- hosts: all\n+ tasks:\n+ - name: run yum update\n+ command: yum update\n+'''\n+\n+ YUM_CLEAN = '''\n+- hosts: all\n+ tasks:\n+ - name: clear yum cache\n+ command: yum clean all\n+'''\n+\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n@@ -209,3 +224,19 @@\n \"\"\"Set-default is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMD_RUNLEVEL)\n assert len(results) == 0\n+\n+ @pytest.mark.parametrize(\n+ 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n+ )\n+ def test_yum_update(rule_runner: RunFromText) -> None:\n+ \"\"\"Using yum update should fail.\"\"\"\n+ results = rule_runner.run_playbook(YUM_UPDATE)\n+ assert len(results) == 1\n+\n+ @pytest.mark.parametrize(\n+ 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n+ )\n+ def test_yum_clean(rule_runner: RunFromText) -> None:\n+ \"\"\"The yum module does not support clearing yum cache.\"\"\"\n+ results = rule_runner.run_playbook(YUM_CLEAN)\n+ assert len(results) == 0\n", "issue": "command-instead-of-module \"yum clean\" revisited\n<!--- Verify first that your issue is not already reported on GitHub -->\r\n<!--- Also test if the latest release and main branch are affected too -->\r\n\r\n##### Summary\r\n<!--- Explain the problem briefly below -->\r\nThe lint error `command-instead-of-module` is raised for command `yum clean`. As the `yum` module documentation states there is no support for doing `yum clean` operation in the module. So the only option is to run a command.\r\n\r\nThis issue has been raised in the past as #369 and `warn: false` was recommended. But that is now deprecated in 2.11.\r\n\r\nSo shouldn't ansible-lint detect if `yum clean` is being run and not raise `command-instead-of-module`?\r\n\r\nIf there is positive feedback and nobody else wants to do it then I can volunteer to make the patch - it should be a simple change, no?\r\n\r\n##### Issue Type\r\n\r\n- Bug Report\r\n\r\n##### Ansible and Ansible Lint details\r\n<!--- Paste verbatim output between triple backticks -->\r\n```console (paste below)\r\nansible --version\r\nansible [core 2.11.5]\r\n config file = /etc/ansible/ansible.cfg\r\n configured module search path = ['/usr/share/ansible/plugins/modules']\r\n ansible python module location = /opt/ansible/lib64/python3.6/site-packages/ansible\r\n ansible collection location = /usr/share/ansible/collections\r\n executable location = /opt/ansible/bin/ansible\r\n python version = 3.6.8 (default, Nov 16 2020, 16:55:22) [GCC 4.8.5 20150623 (Red Hat 4.8.5-44)]\r\n jinja version = 3.0.2\r\n libyaml = True\r\n\r\nansible-lint --version\r\nansible-lint 5.2.0 using ansible 2.11.5\r\n\r\n```\r\n\r\n- ansible installation method: pip\r\n- ansible-lint installation method: pip\r\n\r\n##### OS / ENVIRONMENT\r\n<!--- Provide all relevant information below, e.g. target OS versions, network device firmware, etc. -->\r\nEL7\r\n\r\n##### STEPS TO REPRODUCE\r\n<!--- Describe exactly how to reproduce the problem, using a minimal test-case -->\r\nHave a command that runs `yum clean`.\r\n\r\n<!--- Paste example playbooks or commands between triple backticks below -->\r\n```yaml\r\n command:\r\n cmd: yum clean all\r\n```\r\n\r\n<!--- HINT: You can paste gist.github.com links for larger files -->\r\n\r\n##### Desired Behaviour\r\n<!--- Describe what you expected to happen when running the steps above -->\r\n`command-instead-of-module` should not be raised for `yum clean` which cannot be done using the `yum` module.\r\n\r\nPossible security bugs should be reported via email to `[email protected]`\r\n\r\n##### Actual Behaviour\r\n<!--- Describe what actually happened. If possible run with extra verbosity (-vvvv) -->\r\n`command-instead-of-module` is raised even though the module cannot do this action.\r\n\r\n<!--- Paste verbatim command output between triple backticks -->\r\n```paste below\r\n\r\n```\r\n\r\n\r\n[minimum complete verifiable example]: http://stackoverflow.com/help/mcve\r\n\n", "before_files": [{"content": "# Copyright (c) 2013-2014 Will Thames <[email protected]>\n#\n# Permission is hereby granted, free of charge, to any person obtaining a copy\n# of this software and associated documentation files (the \"Software\"), to deal\n# in the Software without restriction, including without limitation the rights\n# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\n# copies of the Software, and to permit persons to whom the Software is\n# furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice shall be included in\n# all copies or substantial portions of the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\n# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\n# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN\n# THE SOFTWARE.\n\nimport os\nimport sys\nfrom typing import TYPE_CHECKING, Any, Dict, Union\n\nfrom ansiblelint.rules import AnsibleLintRule\nfrom ansiblelint.utils import convert_to_boolean, get_first_cmd_arg, get_second_cmd_arg\n\nif TYPE_CHECKING:\n from typing import Optional\n\n from ansiblelint.file_utils import Lintable\n\n\nclass CommandsInsteadOfModulesRule(AnsibleLintRule):\n id = 'command-instead-of-module'\n shortdesc = 'Using command rather than module'\n description = (\n 'Executing a command when there is an Ansible module is generally a bad idea'\n )\n severity = 'HIGH'\n tags = ['command-shell', 'idiom']\n version_added = 'historic'\n\n _commands = ['command', 'shell']\n _modules = {\n 'apt-get': 'apt-get',\n 'chkconfig': 'service',\n 'curl': 'get_url or uri',\n 'git': 'git',\n 'hg': 'hg',\n 'letsencrypt': 'acme_certificate',\n 'mktemp': 'tempfile',\n 'mount': 'mount',\n 'patch': 'patch',\n 'rpm': 'yum or rpm_key',\n 'rsync': 'synchronize',\n 'sed': 'template, replace or lineinfile',\n 'service': 'service',\n 'supervisorctl': 'supervisorctl',\n 'svn': 'subversion',\n 'systemctl': 'systemd',\n 'tar': 'unarchive',\n 'unzip': 'unarchive',\n 'wget': 'get_url or uri',\n 'yum': 'yum',\n }\n\n _executable_options = {\n 'git': ['branch', 'log'],\n 'systemctl': ['set-default', 'show-environment', 'status'],\n }\n\n def matchtask(\n self, task: Dict[str, Any], file: 'Optional[Lintable]' = None\n ) -> Union[bool, str]:\n\n if task['action']['__ansible_module__'] not in self._commands:\n return False\n\n first_cmd_arg = get_first_cmd_arg(task)\n second_cmd_arg = get_second_cmd_arg(task)\n\n if not first_cmd_arg:\n return False\n\n executable = os.path.basename(first_cmd_arg)\n\n if (\n second_cmd_arg\n and executable in self._executable_options\n and second_cmd_arg in self._executable_options[executable]\n ):\n return False\n\n if executable in self._modules and convert_to_boolean(\n task['action'].get('warn', True)\n ):\n message = '{0} used in place of {1} module'\n return message.format(executable, self._modules[executable])\n return False\n\n\nif \"pytest\" in sys.modules:\n import pytest\n\n from ansiblelint.testing import RunFromText # pylint: disable=ungrouped-imports\n\n APT_GET = '''\n- hosts: all\n tasks:\n - name: run apt-get update\n command: apt-get update\n'''\n\n GIT_BRANCH = '''\n- hosts: all\n tasks:\n - name: print current git branch\n command: git branch\n'''\n\n GIT_LOG = '''\n- hosts: all\n tasks:\n - name: print git log\n command: git log\n'''\n\n RESTART_SSHD = '''\n- hosts: all\n tasks:\n - name: restart sshd\n command: systemctl restart sshd\n'''\n\n SYSTEMCTL_STATUS = '''\n- hosts: all\n tasks:\n - name: show systemctl service status\n command: systemctl status systemd-timesyncd\n'''\n\n SYSTEMD_ENVIRONMENT = '''\n- hosts: all\n tasks:\n - name: show systemd environment\n command: systemctl show-environment\n'''\n\n SYSTEMD_RUNLEVEL = '''\n- hosts: all\n tasks:\n - name: set systemd runlevel\n command: systemctl set-default multi-user.target\n'''\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_apt_get(rule_runner: RunFromText) -> None:\n \"\"\"The apt module supports update.\"\"\"\n results = rule_runner.run_playbook(APT_GET)\n assert len(results) == 1\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_restart_sshd(rule_runner: RunFromText) -> None:\n \"\"\"Restarting services is supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(RESTART_SSHD)\n assert len(results) == 1\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_git_log(rule_runner: RunFromText) -> None:\n \"\"\"The git log command is not supported by the git module.\"\"\"\n results = rule_runner.run_playbook(GIT_LOG)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_git_branch(rule_runner: RunFromText) -> None:\n \"\"\"The git branch command is not supported by the git module.\"\"\"\n results = rule_runner.run_playbook(GIT_BRANCH)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_systemd_status(rule_runner: RunFromText) -> None:\n \"\"\"Set-default is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMCTL_STATUS)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_systemd_environment(rule_runner: RunFromText) -> None:\n \"\"\"Showing the environment is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMD_ENVIRONMENT)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_systemd_runlevel(rule_runner: RunFromText) -> None:\n \"\"\"Set-default is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMD_RUNLEVEL)\n assert len(results) == 0\n", "path": "src/ansiblelint/rules/CommandsInsteadOfModulesRule.py"}], "after_files": [{"content": "# Copyright (c) 2013-2014 Will Thames <[email protected]>\n#\n# Permission is hereby granted, free of charge, to any person obtaining a copy\n# of this software and associated documentation files (the \"Software\"), to deal\n# in the Software without restriction, including without limitation the rights\n# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\n# copies of the Software, and to permit persons to whom the Software is\n# furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice shall be included in\n# all copies or substantial portions of the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\n# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\n# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN\n# THE SOFTWARE.\n\nimport os\nimport sys\nfrom typing import TYPE_CHECKING, Any, Dict, Union\n\nfrom ansiblelint.rules import AnsibleLintRule\nfrom ansiblelint.utils import convert_to_boolean, get_first_cmd_arg, get_second_cmd_arg\n\nif TYPE_CHECKING:\n from typing import Optional\n\n from ansiblelint.file_utils import Lintable\n\n\nclass CommandsInsteadOfModulesRule(AnsibleLintRule):\n id = 'command-instead-of-module'\n shortdesc = 'Using command rather than module'\n description = (\n 'Executing a command when there is an Ansible module is generally a bad idea'\n )\n severity = 'HIGH'\n tags = ['command-shell', 'idiom']\n version_added = 'historic'\n\n _commands = ['command', 'shell']\n _modules = {\n 'apt-get': 'apt-get',\n 'chkconfig': 'service',\n 'curl': 'get_url or uri',\n 'git': 'git',\n 'hg': 'hg',\n 'letsencrypt': 'acme_certificate',\n 'mktemp': 'tempfile',\n 'mount': 'mount',\n 'patch': 'patch',\n 'rpm': 'yum or rpm_key',\n 'rsync': 'synchronize',\n 'sed': 'template, replace or lineinfile',\n 'service': 'service',\n 'supervisorctl': 'supervisorctl',\n 'svn': 'subversion',\n 'systemctl': 'systemd',\n 'tar': 'unarchive',\n 'unzip': 'unarchive',\n 'wget': 'get_url or uri',\n 'yum': 'yum',\n }\n\n _executable_options = {\n 'git': ['branch', 'log'],\n 'systemctl': ['set-default', 'show-environment', 'status'],\n 'yum': ['clean'],\n }\n\n def matchtask(\n self, task: Dict[str, Any], file: 'Optional[Lintable]' = None\n ) -> Union[bool, str]:\n\n if task['action']['__ansible_module__'] not in self._commands:\n return False\n\n first_cmd_arg = get_first_cmd_arg(task)\n second_cmd_arg = get_second_cmd_arg(task)\n\n if not first_cmd_arg:\n return False\n\n executable = os.path.basename(first_cmd_arg)\n\n if (\n second_cmd_arg\n and executable in self._executable_options\n and second_cmd_arg in self._executable_options[executable]\n ):\n return False\n\n if executable in self._modules and convert_to_boolean(\n task['action'].get('warn', True)\n ):\n message = '{0} used in place of {1} module'\n return message.format(executable, self._modules[executable])\n return False\n\n\nif \"pytest\" in sys.modules: # noqa: C901\n import pytest\n\n from ansiblelint.testing import RunFromText # pylint: disable=ungrouped-imports\n\n APT_GET = '''\n- hosts: all\n tasks:\n - name: run apt-get update\n command: apt-get update\n'''\n\n GIT_BRANCH = '''\n- hosts: all\n tasks:\n - name: print current git branch\n command: git branch\n'''\n\n GIT_LOG = '''\n- hosts: all\n tasks:\n - name: print git log\n command: git log\n'''\n\n RESTART_SSHD = '''\n- hosts: all\n tasks:\n - name: restart sshd\n command: systemctl restart sshd\n'''\n\n SYSTEMCTL_STATUS = '''\n- hosts: all\n tasks:\n - name: show systemctl service status\n command: systemctl status systemd-timesyncd\n'''\n\n SYSTEMD_ENVIRONMENT = '''\n- hosts: all\n tasks:\n - name: show systemd environment\n command: systemctl show-environment\n'''\n\n SYSTEMD_RUNLEVEL = '''\n- hosts: all\n tasks:\n - name: set systemd runlevel\n command: systemctl set-default multi-user.target\n'''\n\n YUM_UPDATE = '''\n- hosts: all\n tasks:\n - name: run yum update\n command: yum update\n'''\n\n YUM_CLEAN = '''\n- hosts: all\n tasks:\n - name: clear yum cache\n command: yum clean all\n'''\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_apt_get(rule_runner: RunFromText) -> None:\n \"\"\"The apt module supports update.\"\"\"\n results = rule_runner.run_playbook(APT_GET)\n assert len(results) == 1\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_restart_sshd(rule_runner: RunFromText) -> None:\n \"\"\"Restarting services is supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(RESTART_SSHD)\n assert len(results) == 1\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_git_log(rule_runner: RunFromText) -> None:\n \"\"\"The git log command is not supported by the git module.\"\"\"\n results = rule_runner.run_playbook(GIT_LOG)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_git_branch(rule_runner: RunFromText) -> None:\n \"\"\"The git branch command is not supported by the git module.\"\"\"\n results = rule_runner.run_playbook(GIT_BRANCH)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_systemd_status(rule_runner: RunFromText) -> None:\n \"\"\"Set-default is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMCTL_STATUS)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_systemd_environment(rule_runner: RunFromText) -> None:\n \"\"\"Showing the environment is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMD_ENVIRONMENT)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_systemd_runlevel(rule_runner: RunFromText) -> None:\n \"\"\"Set-default is not supported by the systemd module.\"\"\"\n results = rule_runner.run_playbook(SYSTEMD_RUNLEVEL)\n assert len(results) == 0\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_yum_update(rule_runner: RunFromText) -> None:\n \"\"\"Using yum update should fail.\"\"\"\n results = rule_runner.run_playbook(YUM_UPDATE)\n assert len(results) == 1\n\n @pytest.mark.parametrize(\n 'rule_runner', (CommandsInsteadOfModulesRule,), indirect=['rule_runner']\n )\n def test_yum_clean(rule_runner: RunFromText) -> None:\n \"\"\"The yum module does not support clearing yum cache.\"\"\"\n results = rule_runner.run_playbook(YUM_CLEAN)\n assert len(results) == 0\n", "path": "src/ansiblelint/rules/CommandsInsteadOfModulesRule.py"}]}
| 3,109 | 524 |
gh_patches_debug_2778
|
rasdani/github-patches
|
git_diff
|
pytorch__ignite-1324
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Create a logo for Ignite
### 🚀 Feature
@vfdev-5 asked me to work on a logo to represent Ignite and its relation to main PyTorch, so I’m opening this issue to post iterations and provide a place for discussion.
All feedback is welcome! I'm looking forward to hearing the community's thoughts.
These first iterations use the same orange as PyTorch (`#ee4c2c`)and maintain similar line weight (and sometimes the small circle) in order to show a visual relationship between the projects. The potential directions for Ignite’s logomark are meant to highlight Ignite’s strengths of simplicity and speed as well as the kick starting nature of some of its “out-of-the-box” features.
### Option 1-1
Compared to the current PyTorch logo, Option 1 is meant to be more a energetic spark than a steady, symmetrical flame.
<img width="502" alt="1-1" src="https://user-images.githubusercontent.com/50221806/88605197-19e91480-d02e-11ea-9d97-5fc07286dc95.png">
<img width="502" alt="1-1color" src="https://user-images.githubusercontent.com/50221806/88605198-1a81ab00-d02e-11ea-8771-2f2713077df9.png">
### Option 2-1
Option 2 is the furthest from the current PyTorch logo and revolves around the idea of a matchstick. The flame shape is closest to the current PyTorch logo of the different options.
<img width="502" alt="2-1" src="https://user-images.githubusercontent.com/50221806/88605212-22d9e600-d02e-11ea-8678-eb0785fcd140.png">
<img width="502" alt="2-1color" src="https://user-images.githubusercontent.com/50221806/88605215-23727c80-d02e-11ea-89cf-b5ac451839ac.png">
### Option 3-1
Another idea around a spark originating from a single point. Different flame shape and direction.
<img width="502" alt="3-1" src="https://user-images.githubusercontent.com/50221806/88605221-2a998a80-d02e-11ea-85d0-8e9ac7b711c3.png">
<img width="502" alt="3-1color" src="https://user-images.githubusercontent.com/50221806/88605222-2a998a80-d02e-11ea-8372-87e1aa4eaca7.png">
### Option 4-1
This developed as a variation of Option 3. While it is my least favorite, I wanted to provide an option that feels sharper and more explosive.
<img width="502" alt="4-1" src="https://user-images.githubusercontent.com/50221806/88605232-2ff6d500-d02e-11ea-8078-e4d25c48d10b.png">
<img width="502" alt="4-1color" src="https://user-images.githubusercontent.com/50221806/88605234-308f6b80-d02e-11ea-99c9-8ba077afe688.png">
Update Circle CI docker image to pytorch 1.6
## 🚀 Feature
Following the release of 1.6 version of PyTorch, let's update Circle CI docker image :
- https://github.com/pytorch/ignite/blob/master/.circleci/config.yml
and add 1.5.1 version to pytorch compatibilty versions checking :
- https://github.com/pytorch/ignite/blob/master/.github/workflows/pytorch-version-tests.yml
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `docs/source/conf.py`
Content:
```
1 # -*- coding: utf-8 -*-
2 #
3 # Configuration file for the Sphinx documentation builder.
4 #
5 # This file does only contain a selection of the most common options. For a
6 # full list see the documentation:
7 # http://www.sphinx-doc.org/en/stable/config
8
9 # -- Path setup --------------------------------------------------------------
10
11 # If extensions (or modules to document with autodoc) are in another directory,
12 # add these directories to sys.path here. If the directory is relative to the
13 # documentation root, use os.path.abspath to make it absolute, like shown here.
14 #
15 import os
16 import sys
17
18 sys.path.insert(0, os.path.abspath("../.."))
19 import ignite
20 import pytorch_sphinx_theme
21
22 # -- Project information -----------------------------------------------------
23
24 project = "ignite"
25 copyright = "2020, PyTorch-Ignite Contributors"
26 author = "PyTorch-Ignite Contributors"
27
28 # The short X.Y version
29 try:
30 version = os.environ["code_version"]
31 if "master" in version:
32 version = "master (" + ignite.__version__ + ")"
33 else:
34 version = version.replace("v", "")
35 except KeyError:
36 version = ignite.__version__
37
38 # The full version, including alpha/beta/rc tags
39 release = "master"
40
41
42 # -- General configuration ---------------------------------------------------
43
44 # If your documentation needs a minimal Sphinx version, state it here.
45 #
46 # needs_sphinx = '1.0'
47
48 # Add any Sphinx extension module names here, as strings. They can be
49 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
50 # ones.
51 extensions = [
52 "sphinx.ext.autosummary",
53 "sphinx.ext.doctest",
54 "sphinx.ext.intersphinx",
55 "sphinx.ext.todo",
56 "sphinx.ext.coverage",
57 "sphinx.ext.mathjax",
58 "sphinx.ext.napoleon",
59 "sphinx.ext.viewcode",
60 "sphinx.ext.autosectionlabel",
61 ]
62
63 # Add any paths that contain templates here, relative to this directory.
64 templates_path = ["_templates"]
65
66 # The suffix(es) of source filenames.
67 # You can specify multiple suffix as a list of string:
68 #
69 # source_suffix = ['.rst', '.md']
70 source_suffix = ".rst"
71
72 # The master toctree document.
73 master_doc = "index"
74
75 # The language for content autogenerated by Sphinx. Refer to documentation
76 # for a list of supported languages.
77 #
78 # This is also used if you do content translation via gettext catalogs.
79 # Usually you set "language" from the command line for these cases.
80 language = None
81
82 # List of patterns, relative to source directory, that match files and
83 # directories to ignore when looking for source files.
84 # This pattern also affects html_static_path and html_extra_path .
85 exclude_patterns = []
86
87 # The name of the Pygments (syntax highlighting) style to use.
88 pygments_style = "sphinx"
89
90
91 # -- Options for HTML output -------------------------------------------------
92
93 # The theme to use for HTML and HTML Help pages. See the documentation for
94 # a list of builtin themes.
95 #
96 html_theme = "pytorch_sphinx_theme"
97 html_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]
98
99 html_theme_options = {
100 "canonical_url": "https://pytorch.org/ignite/index.html",
101 "collapse_navigation": False,
102 "display_version": True,
103 "logo_only": True,
104 }
105
106 html_logo = "_static/img/ignite-logo-dark.svg"
107
108 # Theme options are theme-specific and customize the look and feel of a theme
109 # further. For a list of options available for each theme, see the
110 # documentation.
111 #
112 # html_theme_options = {}
113
114 # Add any paths that contain custom static files (such as style sheets) here,
115 # relative to this directory. They are copied after the builtin static files,
116 # so a file named "default.css" will overwrite the builtin "default.css".
117 html_static_path = ["_static", "_templates/_static"]
118
119 html_context = {
120 "css_files": [
121 # 'https://fonts.googleapis.com/css?family=Lato',
122 # '_static/css/pytorch_theme.css'
123 "_static/css/ignite_theme.css"
124 ],
125 }
126
127
128 # -- Options for HTMLHelp output ---------------------------------------------
129
130 # Output file base name for HTML help builder.
131 htmlhelp_basename = "ignitedoc"
132
133
134 # -- Options for LaTeX output ------------------------------------------------
135
136 latex_elements = {
137 # The paper size ('letterpaper' or 'a4paper').
138 #
139 # 'papersize': 'letterpaper',
140 # The font size ('10pt', '11pt' or '12pt').
141 #
142 # 'pointsize': '10pt',
143 # Additional stuff for the LaTeX preamble.
144 #
145 # 'preamble': '',
146 # Latex figure (float) alignment
147 #
148 # 'figure_align': 'htbp',
149 }
150
151 # Grouping the document tree into LaTeX files. List of tuples
152 # (source start file, target name, title,
153 # author, documentclass [howto, manual, or own class]).
154 latex_documents = [
155 (master_doc, "ignite.tex", "ignite Documentation", "Torch Contributors", "manual"),
156 ]
157
158
159 # -- Options for manual page output ------------------------------------------
160
161 # One entry per manual page. List of tuples
162 # (source start file, name, description, authors, manual section).
163 man_pages = [(master_doc, "ignite", "ignite Documentation", [author], 1)]
164
165
166 # -- Options for Texinfo output ----------------------------------------------
167
168 # Grouping the document tree into Texinfo files. List of tuples
169 # (source start file, target name, title, author,
170 # dir menu entry, description, category)
171 texinfo_documents = [
172 (
173 master_doc,
174 "ignite",
175 "ignite Documentation",
176 author,
177 "ignite",
178 "One line description of project.",
179 "Miscellaneous",
180 ),
181 ]
182
183
184 # -- Extension configuration -------------------------------------------------
185
186 # -- Options for intersphinx extension ---------------------------------------
187
188 # Example configuration for intersphinx: refer to the Python standard library.
189 intersphinx_mapping = {"https://docs.python.org/": None}
190
191 # -- Options for todo extension ----------------------------------------------
192
193 # If true, `todo` and `todoList` produce output, else they produce nothing.
194 todo_include_todos = True
195
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/docs/source/conf.py b/docs/source/conf.py
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -103,7 +103,7 @@
"logo_only": True,
}
-html_logo = "_static/img/ignite-logo-dark.svg"
+html_logo = "_static/img/ignite_logo.svg"
# Theme options are theme-specific and customize the look and feel of a theme
# further. For a list of options available for each theme, see the
|
{"golden_diff": "diff --git a/docs/source/conf.py b/docs/source/conf.py\n--- a/docs/source/conf.py\n+++ b/docs/source/conf.py\n@@ -103,7 +103,7 @@\n \"logo_only\": True,\n }\n \n-html_logo = \"_static/img/ignite-logo-dark.svg\"\n+html_logo = \"_static/img/ignite_logo.svg\"\n \n # Theme options are theme-specific and customize the look and feel of a theme\n # further. For a list of options available for each theme, see the\n", "issue": "Create a logo for Ignite\n### \ud83d\ude80 Feature\r\n\r\n@vfdev-5 asked me to work on a logo to represent Ignite and its relation to main PyTorch, so I\u2019m opening this issue to post iterations and provide a place for discussion. \r\n\r\nAll feedback is welcome! I'm looking forward to hearing the community's thoughts.\r\n\r\nThese first iterations use the same orange as PyTorch (`#ee4c2c`)and maintain similar line weight (and sometimes the small circle) in order to show a visual relationship between the projects. The potential directions for Ignite\u2019s logomark are meant to highlight Ignite\u2019s strengths of simplicity and speed as well as the kick starting nature of some of its \u201cout-of-the-box\u201d features.\r\n\r\n### Option 1-1\r\nCompared to the current PyTorch logo, Option 1 is meant to be more a energetic spark than a steady, symmetrical flame.\r\n<img width=\"502\" alt=\"1-1\" src=\"https://user-images.githubusercontent.com/50221806/88605197-19e91480-d02e-11ea-9d97-5fc07286dc95.png\">\r\n<img width=\"502\" alt=\"1-1color\" src=\"https://user-images.githubusercontent.com/50221806/88605198-1a81ab00-d02e-11ea-8771-2f2713077df9.png\">\r\n\r\n### Option 2-1\r\nOption 2 is the furthest from the current PyTorch logo and revolves around the idea of a matchstick. The flame shape is closest to the current PyTorch logo of the different options.\r\n<img width=\"502\" alt=\"2-1\" src=\"https://user-images.githubusercontent.com/50221806/88605212-22d9e600-d02e-11ea-8678-eb0785fcd140.png\">\r\n<img width=\"502\" alt=\"2-1color\" src=\"https://user-images.githubusercontent.com/50221806/88605215-23727c80-d02e-11ea-89cf-b5ac451839ac.png\">\r\n\r\n### Option 3-1\r\nAnother idea around a spark originating from a single point. Different flame shape and direction.\r\n<img width=\"502\" alt=\"3-1\" src=\"https://user-images.githubusercontent.com/50221806/88605221-2a998a80-d02e-11ea-85d0-8e9ac7b711c3.png\">\r\n<img width=\"502\" alt=\"3-1color\" src=\"https://user-images.githubusercontent.com/50221806/88605222-2a998a80-d02e-11ea-8372-87e1aa4eaca7.png\">\r\n\r\n### Option 4-1\r\nThis developed as a variation of Option 3. While it is my least favorite, I wanted to provide an option that feels sharper and more explosive.\r\n<img width=\"502\" alt=\"4-1\" src=\"https://user-images.githubusercontent.com/50221806/88605232-2ff6d500-d02e-11ea-8078-e4d25c48d10b.png\">\r\n<img width=\"502\" alt=\"4-1color\" src=\"https://user-images.githubusercontent.com/50221806/88605234-308f6b80-d02e-11ea-99c9-8ba077afe688.png\">\nUpdate Circle CI docker image to pytorch 1.6\n## \ud83d\ude80 Feature\r\n\r\nFollowing the release of 1.6 version of PyTorch, let's update Circle CI docker image :\r\n- https://github.com/pytorch/ignite/blob/master/.circleci/config.yml\r\nand add 1.5.1 version to pytorch compatibilty versions checking :\r\n- https://github.com/pytorch/ignite/blob/master/.github/workflows/pytorch-version-tests.yml\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n#\n# Configuration file for the Sphinx documentation builder.\n#\n# This file does only contain a selection of the most common options. For a\n# full list see the documentation:\n# http://www.sphinx-doc.org/en/stable/config\n\n# -- Path setup --------------------------------------------------------------\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\n#\nimport os\nimport sys\n\nsys.path.insert(0, os.path.abspath(\"../..\"))\nimport ignite\nimport pytorch_sphinx_theme\n\n# -- Project information -----------------------------------------------------\n\nproject = \"ignite\"\ncopyright = \"2020, PyTorch-Ignite Contributors\"\nauthor = \"PyTorch-Ignite Contributors\"\n\n# The short X.Y version\ntry:\n version = os.environ[\"code_version\"]\n if \"master\" in version:\n version = \"master (\" + ignite.__version__ + \")\"\n else:\n version = version.replace(\"v\", \"\")\nexcept KeyError:\n version = ignite.__version__\n\n# The full version, including alpha/beta/rc tags\nrelease = \"master\"\n\n\n# -- General configuration ---------------------------------------------------\n\n# If your documentation needs a minimal Sphinx version, state it here.\n#\n# needs_sphinx = '1.0'\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom\n# ones.\nextensions = [\n \"sphinx.ext.autosummary\",\n \"sphinx.ext.doctest\",\n \"sphinx.ext.intersphinx\",\n \"sphinx.ext.todo\",\n \"sphinx.ext.coverage\",\n \"sphinx.ext.mathjax\",\n \"sphinx.ext.napoleon\",\n \"sphinx.ext.viewcode\",\n \"sphinx.ext.autosectionlabel\",\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = [\"_templates\"]\n\n# The suffix(es) of source filenames.\n# You can specify multiple suffix as a list of string:\n#\n# source_suffix = ['.rst', '.md']\nsource_suffix = \".rst\"\n\n# The master toctree document.\nmaster_doc = \"index\"\n\n# The language for content autogenerated by Sphinx. Refer to documentation\n# for a list of supported languages.\n#\n# This is also used if you do content translation via gettext catalogs.\n# Usually you set \"language\" from the command line for these cases.\nlanguage = None\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This pattern also affects html_static_path and html_extra_path .\nexclude_patterns = []\n\n# The name of the Pygments (syntax highlighting) style to use.\npygments_style = \"sphinx\"\n\n\n# -- Options for HTML output -------------------------------------------------\n\n# The theme to use for HTML and HTML Help pages. See the documentation for\n# a list of builtin themes.\n#\nhtml_theme = \"pytorch_sphinx_theme\"\nhtml_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]\n\nhtml_theme_options = {\n \"canonical_url\": \"https://pytorch.org/ignite/index.html\",\n \"collapse_navigation\": False,\n \"display_version\": True,\n \"logo_only\": True,\n}\n\nhtml_logo = \"_static/img/ignite-logo-dark.svg\"\n\n# Theme options are theme-specific and customize the look and feel of a theme\n# further. For a list of options available for each theme, see the\n# documentation.\n#\n# html_theme_options = {}\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = [\"_static\", \"_templates/_static\"]\n\nhtml_context = {\n \"css_files\": [\n # 'https://fonts.googleapis.com/css?family=Lato',\n # '_static/css/pytorch_theme.css'\n \"_static/css/ignite_theme.css\"\n ],\n}\n\n\n# -- Options for HTMLHelp output ---------------------------------------------\n\n# Output file base name for HTML help builder.\nhtmlhelp_basename = \"ignitedoc\"\n\n\n# -- Options for LaTeX output ------------------------------------------------\n\nlatex_elements = {\n # The paper size ('letterpaper' or 'a4paper').\n #\n # 'papersize': 'letterpaper',\n # The font size ('10pt', '11pt' or '12pt').\n #\n # 'pointsize': '10pt',\n # Additional stuff for the LaTeX preamble.\n #\n # 'preamble': '',\n # Latex figure (float) alignment\n #\n # 'figure_align': 'htbp',\n}\n\n# Grouping the document tree into LaTeX files. List of tuples\n# (source start file, target name, title,\n# author, documentclass [howto, manual, or own class]).\nlatex_documents = [\n (master_doc, \"ignite.tex\", \"ignite Documentation\", \"Torch Contributors\", \"manual\"),\n]\n\n\n# -- Options for manual page output ------------------------------------------\n\n# One entry per manual page. List of tuples\n# (source start file, name, description, authors, manual section).\nman_pages = [(master_doc, \"ignite\", \"ignite Documentation\", [author], 1)]\n\n\n# -- Options for Texinfo output ----------------------------------------------\n\n# Grouping the document tree into Texinfo files. List of tuples\n# (source start file, target name, title, author,\n# dir menu entry, description, category)\ntexinfo_documents = [\n (\n master_doc,\n \"ignite\",\n \"ignite Documentation\",\n author,\n \"ignite\",\n \"One line description of project.\",\n \"Miscellaneous\",\n ),\n]\n\n\n# -- Extension configuration -------------------------------------------------\n\n# -- Options for intersphinx extension ---------------------------------------\n\n# Example configuration for intersphinx: refer to the Python standard library.\nintersphinx_mapping = {\"https://docs.python.org/\": None}\n\n# -- Options for todo extension ----------------------------------------------\n\n# If true, `todo` and `todoList` produce output, else they produce nothing.\ntodo_include_todos = True\n", "path": "docs/source/conf.py"}], "after_files": [{"content": "# -*- coding: utf-8 -*-\n#\n# Configuration file for the Sphinx documentation builder.\n#\n# This file does only contain a selection of the most common options. For a\n# full list see the documentation:\n# http://www.sphinx-doc.org/en/stable/config\n\n# -- Path setup --------------------------------------------------------------\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\n#\nimport os\nimport sys\n\nsys.path.insert(0, os.path.abspath(\"../..\"))\nimport ignite\nimport pytorch_sphinx_theme\n\n# -- Project information -----------------------------------------------------\n\nproject = \"ignite\"\ncopyright = \"2020, PyTorch-Ignite Contributors\"\nauthor = \"PyTorch-Ignite Contributors\"\n\n# The short X.Y version\ntry:\n version = os.environ[\"code_version\"]\n if \"master\" in version:\n version = \"master (\" + ignite.__version__ + \")\"\n else:\n version = version.replace(\"v\", \"\")\nexcept KeyError:\n version = ignite.__version__\n\n# The full version, including alpha/beta/rc tags\nrelease = \"master\"\n\n\n# -- General configuration ---------------------------------------------------\n\n# If your documentation needs a minimal Sphinx version, state it here.\n#\n# needs_sphinx = '1.0'\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom\n# ones.\nextensions = [\n \"sphinx.ext.autosummary\",\n \"sphinx.ext.doctest\",\n \"sphinx.ext.intersphinx\",\n \"sphinx.ext.todo\",\n \"sphinx.ext.coverage\",\n \"sphinx.ext.mathjax\",\n \"sphinx.ext.napoleon\",\n \"sphinx.ext.viewcode\",\n \"sphinx.ext.autosectionlabel\",\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = [\"_templates\"]\n\n# The suffix(es) of source filenames.\n# You can specify multiple suffix as a list of string:\n#\n# source_suffix = ['.rst', '.md']\nsource_suffix = \".rst\"\n\n# The master toctree document.\nmaster_doc = \"index\"\n\n# The language for content autogenerated by Sphinx. Refer to documentation\n# for a list of supported languages.\n#\n# This is also used if you do content translation via gettext catalogs.\n# Usually you set \"language\" from the command line for these cases.\nlanguage = None\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This pattern also affects html_static_path and html_extra_path .\nexclude_patterns = []\n\n# The name of the Pygments (syntax highlighting) style to use.\npygments_style = \"sphinx\"\n\n\n# -- Options for HTML output -------------------------------------------------\n\n# The theme to use for HTML and HTML Help pages. See the documentation for\n# a list of builtin themes.\n#\nhtml_theme = \"pytorch_sphinx_theme\"\nhtml_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]\n\nhtml_theme_options = {\n \"canonical_url\": \"https://pytorch.org/ignite/index.html\",\n \"collapse_navigation\": False,\n \"display_version\": True,\n \"logo_only\": True,\n}\n\nhtml_logo = \"_static/img/ignite_logo.svg\"\n\n# Theme options are theme-specific and customize the look and feel of a theme\n# further. For a list of options available for each theme, see the\n# documentation.\n#\n# html_theme_options = {}\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = [\"_static\", \"_templates/_static\"]\n\nhtml_context = {\n \"css_files\": [\n # 'https://fonts.googleapis.com/css?family=Lato',\n # '_static/css/pytorch_theme.css'\n \"_static/css/ignite_theme.css\"\n ],\n}\n\n\n# -- Options for HTMLHelp output ---------------------------------------------\n\n# Output file base name for HTML help builder.\nhtmlhelp_basename = \"ignitedoc\"\n\n\n# -- Options for LaTeX output ------------------------------------------------\n\nlatex_elements = {\n # The paper size ('letterpaper' or 'a4paper').\n #\n # 'papersize': 'letterpaper',\n # The font size ('10pt', '11pt' or '12pt').\n #\n # 'pointsize': '10pt',\n # Additional stuff for the LaTeX preamble.\n #\n # 'preamble': '',\n # Latex figure (float) alignment\n #\n # 'figure_align': 'htbp',\n}\n\n# Grouping the document tree into LaTeX files. List of tuples\n# (source start file, target name, title,\n# author, documentclass [howto, manual, or own class]).\nlatex_documents = [\n (master_doc, \"ignite.tex\", \"ignite Documentation\", \"Torch Contributors\", \"manual\"),\n]\n\n\n# -- Options for manual page output ------------------------------------------\n\n# One entry per manual page. List of tuples\n# (source start file, name, description, authors, manual section).\nman_pages = [(master_doc, \"ignite\", \"ignite Documentation\", [author], 1)]\n\n\n# -- Options for Texinfo output ----------------------------------------------\n\n# Grouping the document tree into Texinfo files. List of tuples\n# (source start file, target name, title, author,\n# dir menu entry, description, category)\ntexinfo_documents = [\n (\n master_doc,\n \"ignite\",\n \"ignite Documentation\",\n author,\n \"ignite\",\n \"One line description of project.\",\n \"Miscellaneous\",\n ),\n]\n\n\n# -- Extension configuration -------------------------------------------------\n\n# -- Options for intersphinx extension ---------------------------------------\n\n# Example configuration for intersphinx: refer to the Python standard library.\nintersphinx_mapping = {\"https://docs.python.org/\": None}\n\n# -- Options for todo extension ----------------------------------------------\n\n# If true, `todo` and `todoList` produce output, else they produce nothing.\ntodo_include_todos = True\n", "path": "docs/source/conf.py"}]}
| 3,065 | 109 |
gh_patches_debug_947
|
rasdani/github-patches
|
git_diff
|
databricks__koalas-105
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
How to call dev/_make_missing_functions.py?
```
rxin @ C02XT0W6JGH5 : ~/workspace/spark-pandas (master)
> dev/_make_missing_functions.py
Traceback (most recent call last):
File "dev/_make_missing_functions.py", line 22, in <module>
from databricks.koala.frame import PandasLikeDataFrame
ImportError: No module named databricks.koala.frame
```
Do I need to install koala first? We should add documentation to CONTRIBUTING.md. It'd also be best if this runs against the existing code base, rather than a system-wide installed Koala.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `dev/_make_missing_functions.py`
Content:
```
1 #!/usr/bin/env python
2 #
3 # Copyright (C) 2019 Databricks, Inc.
4 #
5 # Licensed under the Apache License, Version 2.0 (the "License");
6 # you may not use this file except in compliance with the License.
7 # You may obtain a copy of the License at
8 #
9 # http://www.apache.org/licenses/LICENSE-2.0
10 #
11 # Unless required by applicable law or agreed to in writing, software
12 # distributed under the License is distributed on an "AS IS" BASIS,
13 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 # See the License for the specific language governing permissions and
15 # limitations under the License.
16 #
17
18 import inspect
19
20 import pandas as pd
21
22 from databricks.koalas.frame import PandasLikeDataFrame
23 from databricks.koalas.missing.frame import _MissingPandasLikeDataFrame
24 from databricks.koalas.missing.series import _MissingPandasLikeSeries
25 from databricks.koalas.series import PandasLikeSeries
26
27
28 INDENT_LEN = 4
29 LINE_LEN_LIMIT = 100
30
31
32 def inspect_missing_functions(original_type, target_type, missing_type):
33 """
34 Find functions which exist in original_type but not in target_type,
35 or the signature is modified.
36
37 :return: the tuple of the missing function name and its signature,
38 and the name of the functions the signature of which is different
39 and its original and modified signature.
40 """
41 missing = []
42 modified = []
43
44 already_in_missing = set([(name, inspect.signature(func)) for name, func
45 in inspect.getmembers(missing_type, inspect.isfunction)])
46 for name, func in inspect.getmembers(original_type, inspect.isfunction):
47 # Skip the private attributes
48 if name.startswith('_'):
49 continue
50
51 original_signature = inspect.signature(func, follow_wrapped=True)
52
53 if hasattr(target_type, name):
54 f = getattr(target_type, name)
55 if inspect.isfunction(f):
56 target_signature = inspect.signature(f)
57 if (name, target_signature) in already_in_missing:
58 missing.append((name, original_signature))
59 elif str(original_signature) != str(target_signature):
60 modified.append((name, original_signature, target_signature))
61 continue
62
63 missing.append((name, original_signature))
64
65 return missing, modified
66
67
68 def format_arguments(arguments, prefix_len, suffix_len):
69 """Format arguments not to break pydocstyle.
70
71 :param arguments: the argument list
72 :param prefix_len: the prefix length when the argument string needs line break
73 :param suffix_len: the suffix length to check the line length exceeds the limit
74 :return: the formatted argument string
75 """
76 lines = ['']
77
78 def append_arg(arg):
79 if prefix_len + len(lines[-1]) + len(', ') + len(arg) + suffix_len > LINE_LEN_LIMIT:
80 lines.append('')
81 append_arg(arg)
82 else:
83 if len(lines[-1]) > 0:
84 arg = ', {}'.format(arg)
85 lines[-1] += arg
86
87 for arg in arguments:
88 append_arg(arg)
89
90 return (',\n' + (' ' * prefix_len)).join(lines)
91
92
93 def format_method_arguments(name, signature):
94 """Format the method arguments from its name and signature.
95
96 :return: the formatted argument string
97 """
98 arguments = []
99
100 for param in signature.parameters.values():
101 if param.default is not inspect.Signature.empty and isinstance(param.default, type):
102 arguments.append('{}={}'.format(param.name, param.default.__name__))
103 elif param.default is not inspect.Signature.empty and repr(param.default) == 'nan':
104 arguments.append('{}={}'.format(param.name, 'np.nan'))
105 else:
106 arguments.append(str(param))
107
108 prefix_len = INDENT_LEN + len('def {}('.format(name))
109 suffix_len = len('):')
110 return format_arguments(arguments, prefix_len, suffix_len)
111
112
113 def format_derived_from(original_type, unavailable_arguments, signature):
114 """Format `@derived_from` decorator.
115
116 :param original_type: the original type to be derived
117 :param unavailable_arguments: the arguments Koalas does not support yet
118 :param signature: the method signature
119 :return: the formatted `@derived_from` decorator
120 """
121 if len(unavailable_arguments) == 0:
122 return '@derived_from(pd.{})'.format(original_type.__name__)
123
124 arguments = []
125
126 for arg in unavailable_arguments:
127 param = signature.parameters[arg]
128 if param.default == inspect.Parameter.empty or \
129 param.kind == inspect.Parameter.VAR_POSITIONAL or \
130 param.kind == inspect.Parameter.VAR_KEYWORD:
131 continue
132 arguments.append(repr(arg))
133
134 prefix = '@derived_from(pd.{}, ua_args=['.format(original_type.__name__)
135 suffix = '])'
136 prefix_len = INDENT_LEN + len(prefix)
137 suffix_len = len(suffix)
138 return '{}{}{}'.format(prefix, format_arguments(arguments, prefix_len, suffix_len), suffix)
139
140
141 def format_raise_errors(original_type, name, unavailable_arguments, signature):
142 """
143 Format raise error statements for unavailable arguments when specified the different value
144 from the default value.
145
146 :return: the formatted raise error statements
147 """
148 raise_errors = ''
149
150 for arg in unavailable_arguments:
151 param = signature.parameters[arg]
152 if param.default == inspect.Parameter.empty or \
153 param.kind == inspect.Parameter.VAR_POSITIONAL or \
154 param.kind == inspect.Parameter.VAR_KEYWORD:
155 continue
156 if repr(param.default) == 'nan':
157 not_equal = 'not np.isnan({})'.format(arg)
158 elif isinstance(param.default, type):
159 not_equal = '{} is not {}'.format(arg, param.default.__name__)
160 elif param.default is None or \
161 param.default is True or param.default is False:
162 not_equal = '{} is not {}'.format(arg, repr(param.default))
163 else:
164 not_equal = '{} != {}'.format(arg, repr(param.default))
165
166 raise_error_prefix = 'raise PandasNotImplementedError('
167 raise_error_suffix = ')'
168 arguments = format_arguments(
169 arguments=["class_name='pd.{}'".format(original_type.__name__),
170 "method_name='{}'".format(name),
171 "arg_name='{}'".format(arg)],
172 prefix_len=(INDENT_LEN * 3 + len(raise_error_prefix)),
173 suffix_len=len(raise_error_suffix))
174 raise_errors += ("""
175 if {0}:
176 {1}{2}{3}""".format(not_equal, raise_error_prefix, arguments, raise_error_suffix))
177
178 return raise_errors
179
180
181 def make_misssing_function(original_type, name, signature):
182 """Make a missing functions stub.
183
184 :return: the stub definition for the missing function
185 """
186 arguments = format_method_arguments(name, signature)
187 error_argument = format_arguments(
188 arguments=["class_name='pd.{}'".format(original_type.__name__),
189 "method_name='{}'".format(name)],
190 prefix_len=(8 + len('raise PandasNotImplementedError(')),
191 suffix_len=len(')'))
192
193 return ("""
194 def {0}({1}):
195 \"""A stub for the equivalent method to `pd.{2}.{0}()`.
196
197 The method `pd.{2}.{0}()` is not implemented yet.
198 \"""
199 raise PandasNotImplementedError({3})"""
200 .format(name, arguments, original_type.__name__, error_argument))
201
202
203 def make_modified_function_def(original_type, name, original, target):
204 """Make the modified function definition.
205
206 :return: the definition for the modified function
207 """
208 arguments = format_method_arguments(name, original)
209 argument_names = set(target.parameters)
210 unavailable_arguments = [p for p in original.parameters if p not in argument_names]
211 derived_from = format_derived_from(original_type, unavailable_arguments, original)
212 raise_error = format_raise_errors(original_type, name, unavailable_arguments, original)
213 return ("""
214 {0}
215 def {1}({2}):{3}""".format(derived_from, name, arguments, raise_error))
216
217
218 def _main():
219 for original_type, target_type, missing_type in \
220 [(pd.DataFrame, PandasLikeDataFrame, _MissingPandasLikeDataFrame),
221 (pd.Series, PandasLikeSeries, _MissingPandasLikeSeries)]:
222 missing, modified = inspect_missing_functions(original_type, target_type, missing_type)
223
224 print('MISSING functions for {}'.format(original_type.__name__))
225 for name, signature in missing:
226 # print(make_misssing_function(original_type, name, signature))
227 print(""" {0} = unsupported_function('{0}')""".format(name))
228
229 print()
230 print('MODIFIED functions for {}'.format(original_type.__name__))
231 for name, original, target in modified:
232 print(make_modified_function_def(original_type, name, original, target))
233
234
235 if __name__ == '__main__':
236 _main()
237
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/dev/_make_missing_functions.py b/dev/_make_missing_functions.py
--- a/dev/_make_missing_functions.py
+++ b/dev/_make_missing_functions.py
@@ -15,6 +15,12 @@
# limitations under the License.
#
+"""
+A script to generate the missing function stubs. Before running this,
+make sure you install koalas from the current checkout by running:
+pip install -e .
+"""
+
import inspect
import pandas as pd
|
{"golden_diff": "diff --git a/dev/_make_missing_functions.py b/dev/_make_missing_functions.py\n--- a/dev/_make_missing_functions.py\n+++ b/dev/_make_missing_functions.py\n@@ -15,6 +15,12 @@\n # limitations under the License.\n #\n \n+\"\"\"\n+A script to generate the missing function stubs. Before running this,\n+make sure you install koalas from the current checkout by running:\n+pip install -e .\n+\"\"\"\n+\n import inspect\n \n import pandas as pd\n", "issue": "How to call dev/_make_missing_functions.py?\n```\r\nrxin @ C02XT0W6JGH5 : ~/workspace/spark-pandas (master) \r\n> dev/_make_missing_functions.py \r\nTraceback (most recent call last):\r\n File \"dev/_make_missing_functions.py\", line 22, in <module>\r\n from databricks.koala.frame import PandasLikeDataFrame\r\nImportError: No module named databricks.koala.frame\r\n```\r\n\r\nDo I need to install koala first? We should add documentation to CONTRIBUTING.md. It'd also be best if this runs against the existing code base, rather than a system-wide installed Koala.\r\n\n", "before_files": [{"content": "#!/usr/bin/env python\n#\n# Copyright (C) 2019 Databricks, Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\n\nimport inspect\n\nimport pandas as pd\n\nfrom databricks.koalas.frame import PandasLikeDataFrame\nfrom databricks.koalas.missing.frame import _MissingPandasLikeDataFrame\nfrom databricks.koalas.missing.series import _MissingPandasLikeSeries\nfrom databricks.koalas.series import PandasLikeSeries\n\n\nINDENT_LEN = 4\nLINE_LEN_LIMIT = 100\n\n\ndef inspect_missing_functions(original_type, target_type, missing_type):\n \"\"\"\n Find functions which exist in original_type but not in target_type,\n or the signature is modified.\n\n :return: the tuple of the missing function name and its signature,\n and the name of the functions the signature of which is different\n and its original and modified signature.\n \"\"\"\n missing = []\n modified = []\n\n already_in_missing = set([(name, inspect.signature(func)) for name, func\n in inspect.getmembers(missing_type, inspect.isfunction)])\n for name, func in inspect.getmembers(original_type, inspect.isfunction):\n # Skip the private attributes\n if name.startswith('_'):\n continue\n\n original_signature = inspect.signature(func, follow_wrapped=True)\n\n if hasattr(target_type, name):\n f = getattr(target_type, name)\n if inspect.isfunction(f):\n target_signature = inspect.signature(f)\n if (name, target_signature) in already_in_missing:\n missing.append((name, original_signature))\n elif str(original_signature) != str(target_signature):\n modified.append((name, original_signature, target_signature))\n continue\n\n missing.append((name, original_signature))\n\n return missing, modified\n\n\ndef format_arguments(arguments, prefix_len, suffix_len):\n \"\"\"Format arguments not to break pydocstyle.\n\n :param arguments: the argument list\n :param prefix_len: the prefix length when the argument string needs line break\n :param suffix_len: the suffix length to check the line length exceeds the limit\n :return: the formatted argument string\n \"\"\"\n lines = ['']\n\n def append_arg(arg):\n if prefix_len + len(lines[-1]) + len(', ') + len(arg) + suffix_len > LINE_LEN_LIMIT:\n lines.append('')\n append_arg(arg)\n else:\n if len(lines[-1]) > 0:\n arg = ', {}'.format(arg)\n lines[-1] += arg\n\n for arg in arguments:\n append_arg(arg)\n\n return (',\\n' + (' ' * prefix_len)).join(lines)\n\n\ndef format_method_arguments(name, signature):\n \"\"\"Format the method arguments from its name and signature.\n\n :return: the formatted argument string\n \"\"\"\n arguments = []\n\n for param in signature.parameters.values():\n if param.default is not inspect.Signature.empty and isinstance(param.default, type):\n arguments.append('{}={}'.format(param.name, param.default.__name__))\n elif param.default is not inspect.Signature.empty and repr(param.default) == 'nan':\n arguments.append('{}={}'.format(param.name, 'np.nan'))\n else:\n arguments.append(str(param))\n\n prefix_len = INDENT_LEN + len('def {}('.format(name))\n suffix_len = len('):')\n return format_arguments(arguments, prefix_len, suffix_len)\n\n\ndef format_derived_from(original_type, unavailable_arguments, signature):\n \"\"\"Format `@derived_from` decorator.\n\n :param original_type: the original type to be derived\n :param unavailable_arguments: the arguments Koalas does not support yet\n :param signature: the method signature\n :return: the formatted `@derived_from` decorator\n \"\"\"\n if len(unavailable_arguments) == 0:\n return '@derived_from(pd.{})'.format(original_type.__name__)\n\n arguments = []\n\n for arg in unavailable_arguments:\n param = signature.parameters[arg]\n if param.default == inspect.Parameter.empty or \\\n param.kind == inspect.Parameter.VAR_POSITIONAL or \\\n param.kind == inspect.Parameter.VAR_KEYWORD:\n continue\n arguments.append(repr(arg))\n\n prefix = '@derived_from(pd.{}, ua_args=['.format(original_type.__name__)\n suffix = '])'\n prefix_len = INDENT_LEN + len(prefix)\n suffix_len = len(suffix)\n return '{}{}{}'.format(prefix, format_arguments(arguments, prefix_len, suffix_len), suffix)\n\n\ndef format_raise_errors(original_type, name, unavailable_arguments, signature):\n \"\"\"\n Format raise error statements for unavailable arguments when specified the different value\n from the default value.\n\n :return: the formatted raise error statements\n \"\"\"\n raise_errors = ''\n\n for arg in unavailable_arguments:\n param = signature.parameters[arg]\n if param.default == inspect.Parameter.empty or \\\n param.kind == inspect.Parameter.VAR_POSITIONAL or \\\n param.kind == inspect.Parameter.VAR_KEYWORD:\n continue\n if repr(param.default) == 'nan':\n not_equal = 'not np.isnan({})'.format(arg)\n elif isinstance(param.default, type):\n not_equal = '{} is not {}'.format(arg, param.default.__name__)\n elif param.default is None or \\\n param.default is True or param.default is False:\n not_equal = '{} is not {}'.format(arg, repr(param.default))\n else:\n not_equal = '{} != {}'.format(arg, repr(param.default))\n\n raise_error_prefix = 'raise PandasNotImplementedError('\n raise_error_suffix = ')'\n arguments = format_arguments(\n arguments=[\"class_name='pd.{}'\".format(original_type.__name__),\n \"method_name='{}'\".format(name),\n \"arg_name='{}'\".format(arg)],\n prefix_len=(INDENT_LEN * 3 + len(raise_error_prefix)),\n suffix_len=len(raise_error_suffix))\n raise_errors += (\"\"\"\n if {0}:\n {1}{2}{3}\"\"\".format(not_equal, raise_error_prefix, arguments, raise_error_suffix))\n\n return raise_errors\n\n\ndef make_misssing_function(original_type, name, signature):\n \"\"\"Make a missing functions stub.\n\n :return: the stub definition for the missing function\n \"\"\"\n arguments = format_method_arguments(name, signature)\n error_argument = format_arguments(\n arguments=[\"class_name='pd.{}'\".format(original_type.__name__),\n \"method_name='{}'\".format(name)],\n prefix_len=(8 + len('raise PandasNotImplementedError(')),\n suffix_len=len(')'))\n\n return (\"\"\"\n def {0}({1}):\n \\\"\"\"A stub for the equivalent method to `pd.{2}.{0}()`.\n\n The method `pd.{2}.{0}()` is not implemented yet.\n \\\"\"\"\n raise PandasNotImplementedError({3})\"\"\"\n .format(name, arguments, original_type.__name__, error_argument))\n\n\ndef make_modified_function_def(original_type, name, original, target):\n \"\"\"Make the modified function definition.\n\n :return: the definition for the modified function\n \"\"\"\n arguments = format_method_arguments(name, original)\n argument_names = set(target.parameters)\n unavailable_arguments = [p for p in original.parameters if p not in argument_names]\n derived_from = format_derived_from(original_type, unavailable_arguments, original)\n raise_error = format_raise_errors(original_type, name, unavailable_arguments, original)\n return (\"\"\"\n {0}\n def {1}({2}):{3}\"\"\".format(derived_from, name, arguments, raise_error))\n\n\ndef _main():\n for original_type, target_type, missing_type in \\\n [(pd.DataFrame, PandasLikeDataFrame, _MissingPandasLikeDataFrame),\n (pd.Series, PandasLikeSeries, _MissingPandasLikeSeries)]:\n missing, modified = inspect_missing_functions(original_type, target_type, missing_type)\n\n print('MISSING functions for {}'.format(original_type.__name__))\n for name, signature in missing:\n # print(make_misssing_function(original_type, name, signature))\n print(\"\"\" {0} = unsupported_function('{0}')\"\"\".format(name))\n\n print()\n print('MODIFIED functions for {}'.format(original_type.__name__))\n for name, original, target in modified:\n print(make_modified_function_def(original_type, name, original, target))\n\n\nif __name__ == '__main__':\n _main()\n", "path": "dev/_make_missing_functions.py"}], "after_files": [{"content": "#!/usr/bin/env python\n#\n# Copyright (C) 2019 Databricks, Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\n\n\"\"\"\nA script to generate the missing function stubs. Before running this,\nmake sure you install koalas from the current checkout by running:\npip install -e .\n\"\"\"\n\nimport inspect\n\nimport pandas as pd\n\nfrom databricks.koalas.frame import PandasLikeDataFrame\nfrom databricks.koalas.missing.frame import _MissingPandasLikeDataFrame\nfrom databricks.koalas.missing.series import _MissingPandasLikeSeries\nfrom databricks.koalas.series import PandasLikeSeries\n\n\nINDENT_LEN = 4\nLINE_LEN_LIMIT = 100\n\n\ndef inspect_missing_functions(original_type, target_type, missing_type):\n \"\"\"\n Find functions which exist in original_type but not in target_type,\n or the signature is modified.\n\n :return: the tuple of the missing function name and its signature,\n and the name of the functions the signature of which is different\n and its original and modified signature.\n \"\"\"\n missing = []\n modified = []\n\n already_in_missing = set([(name, inspect.signature(func)) for name, func\n in inspect.getmembers(missing_type, inspect.isfunction)])\n for name, func in inspect.getmembers(original_type, inspect.isfunction):\n # Skip the private attributes\n if name.startswith('_'):\n continue\n\n original_signature = inspect.signature(func, follow_wrapped=True)\n\n if hasattr(target_type, name):\n f = getattr(target_type, name)\n if inspect.isfunction(f):\n target_signature = inspect.signature(f)\n if (name, target_signature) in already_in_missing:\n missing.append((name, original_signature))\n elif str(original_signature) != str(target_signature):\n modified.append((name, original_signature, target_signature))\n continue\n\n missing.append((name, original_signature))\n\n return missing, modified\n\n\ndef format_arguments(arguments, prefix_len, suffix_len):\n \"\"\"Format arguments not to break pydocstyle.\n\n :param arguments: the argument list\n :param prefix_len: the prefix length when the argument string needs line break\n :param suffix_len: the suffix length to check the line length exceeds the limit\n :return: the formatted argument string\n \"\"\"\n lines = ['']\n\n def append_arg(arg):\n if prefix_len + len(lines[-1]) + len(', ') + len(arg) + suffix_len > LINE_LEN_LIMIT:\n lines.append('')\n append_arg(arg)\n else:\n if len(lines[-1]) > 0:\n arg = ', {}'.format(arg)\n lines[-1] += arg\n\n for arg in arguments:\n append_arg(arg)\n\n return (',\\n' + (' ' * prefix_len)).join(lines)\n\n\ndef format_method_arguments(name, signature):\n \"\"\"Format the method arguments from its name and signature.\n\n :return: the formatted argument string\n \"\"\"\n arguments = []\n\n for param in signature.parameters.values():\n if param.default is not inspect.Signature.empty and isinstance(param.default, type):\n arguments.append('{}={}'.format(param.name, param.default.__name__))\n elif param.default is not inspect.Signature.empty and repr(param.default) == 'nan':\n arguments.append('{}={}'.format(param.name, 'np.nan'))\n else:\n arguments.append(str(param))\n\n prefix_len = INDENT_LEN + len('def {}('.format(name))\n suffix_len = len('):')\n return format_arguments(arguments, prefix_len, suffix_len)\n\n\ndef format_derived_from(original_type, unavailable_arguments, signature):\n \"\"\"Format `@derived_from` decorator.\n\n :param original_type: the original type to be derived\n :param unavailable_arguments: the arguments Koalas does not support yet\n :param signature: the method signature\n :return: the formatted `@derived_from` decorator\n \"\"\"\n if len(unavailable_arguments) == 0:\n return '@derived_from(pd.{})'.format(original_type.__name__)\n\n arguments = []\n\n for arg in unavailable_arguments:\n param = signature.parameters[arg]\n if param.default == inspect.Parameter.empty or \\\n param.kind == inspect.Parameter.VAR_POSITIONAL or \\\n param.kind == inspect.Parameter.VAR_KEYWORD:\n continue\n arguments.append(repr(arg))\n\n prefix = '@derived_from(pd.{}, ua_args=['.format(original_type.__name__)\n suffix = '])'\n prefix_len = INDENT_LEN + len(prefix)\n suffix_len = len(suffix)\n return '{}{}{}'.format(prefix, format_arguments(arguments, prefix_len, suffix_len), suffix)\n\n\ndef format_raise_errors(original_type, name, unavailable_arguments, signature):\n \"\"\"\n Format raise error statements for unavailable arguments when specified the different value\n from the default value.\n\n :return: the formatted raise error statements\n \"\"\"\n raise_errors = ''\n\n for arg in unavailable_arguments:\n param = signature.parameters[arg]\n if param.default == inspect.Parameter.empty or \\\n param.kind == inspect.Parameter.VAR_POSITIONAL or \\\n param.kind == inspect.Parameter.VAR_KEYWORD:\n continue\n if repr(param.default) == 'nan':\n not_equal = 'not np.isnan({})'.format(arg)\n elif isinstance(param.default, type):\n not_equal = '{} is not {}'.format(arg, param.default.__name__)\n elif param.default is None or \\\n param.default is True or param.default is False:\n not_equal = '{} is not {}'.format(arg, repr(param.default))\n else:\n not_equal = '{} != {}'.format(arg, repr(param.default))\n\n raise_error_prefix = 'raise PandasNotImplementedError('\n raise_error_suffix = ')'\n arguments = format_arguments(\n arguments=[\"class_name='pd.{}'\".format(original_type.__name__),\n \"method_name='{}'\".format(name),\n \"arg_name='{}'\".format(arg)],\n prefix_len=(INDENT_LEN * 3 + len(raise_error_prefix)),\n suffix_len=len(raise_error_suffix))\n raise_errors += (\"\"\"\n if {0}:\n {1}{2}{3}\"\"\".format(not_equal, raise_error_prefix, arguments, raise_error_suffix))\n\n return raise_errors\n\n\ndef make_misssing_function(original_type, name, signature):\n \"\"\"Make a missing functions stub.\n\n :return: the stub definition for the missing function\n \"\"\"\n arguments = format_method_arguments(name, signature)\n error_argument = format_arguments(\n arguments=[\"class_name='pd.{}'\".format(original_type.__name__),\n \"method_name='{}'\".format(name)],\n prefix_len=(8 + len('raise PandasNotImplementedError(')),\n suffix_len=len(')'))\n\n return (\"\"\"\n def {0}({1}):\n \\\"\"\"A stub for the equivalent method to `pd.{2}.{0}()`.\n\n The method `pd.{2}.{0}()` is not implemented yet.\n \\\"\"\"\n raise PandasNotImplementedError({3})\"\"\"\n .format(name, arguments, original_type.__name__, error_argument))\n\n\ndef make_modified_function_def(original_type, name, original, target):\n \"\"\"Make the modified function definition.\n\n :return: the definition for the modified function\n \"\"\"\n arguments = format_method_arguments(name, original)\n argument_names = set(target.parameters)\n unavailable_arguments = [p for p in original.parameters if p not in argument_names]\n derived_from = format_derived_from(original_type, unavailable_arguments, original)\n raise_error = format_raise_errors(original_type, name, unavailable_arguments, original)\n return (\"\"\"\n {0}\n def {1}({2}):{3}\"\"\".format(derived_from, name, arguments, raise_error))\n\n\ndef _main():\n for original_type, target_type, missing_type in \\\n [(pd.DataFrame, PandasLikeDataFrame, _MissingPandasLikeDataFrame),\n (pd.Series, PandasLikeSeries, _MissingPandasLikeSeries)]:\n missing, modified = inspect_missing_functions(original_type, target_type, missing_type)\n\n print('MISSING functions for {}'.format(original_type.__name__))\n for name, signature in missing:\n # print(make_misssing_function(original_type, name, signature))\n print(\"\"\" {0} = unsupported_function('{0}')\"\"\".format(name))\n\n print()\n print('MODIFIED functions for {}'.format(original_type.__name__))\n for name, original, target in modified:\n print(make_modified_function_def(original_type, name, original, target))\n\n\nif __name__ == '__main__':\n _main()\n", "path": "dev/_make_missing_functions.py"}]}
| 2,931 | 105 |
gh_patches_debug_14775
|
rasdani/github-patches
|
git_diff
|
hylang__hy-1122
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Hy sets are really broken.
``` Hy
(env-hy) C:\Users\ME\Code>hy
hy 0.11.0 using CPython(v3.4.3:9b73f1c3e601) 3.4.3 on Windows
=> #{:a 'a}
Traceback (most recent call last):
File "C:\Python34\Scripts\env-hy\Scripts\hy-script.py", line 9, in <module>
load_entry_point('hy==0.11.0', 'console_scripts', 'hy')()
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\cmdline.py", line 341, in hy_main
sys.exit(cmdline_handler("hy", sys.argv))
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\cmdline.py", line 336, in cmdline_handler
return run_repl(spy=options.spy)
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\cmdline.py", line 234, in run_repl
os=platform.system()
File "C:\Python34\Lib\code.py", line 234, in interact
more = self.push(line)
File "C:\Python34\Lib\code.py", line 256, in push
more = self.runsource(source, self.filename)
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\cmdline.py", line 93, in runsource
tokens = tokenize(source)
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\lex\__init__.py", line 33, in tokenize
return parser.parse(lexer.lex(buf))
File "C:\Python34\Scripts\env-hy\lib\site-packages\rply\parser.py", line 23, in parse
t, symstack, statestack, state
File "C:\Python34\Scripts\env-hy\lib\site-packages\rply\parser.py", line 80, in _reduce_production
value = p.func(targ)
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\lex\parser.py", line 69, in wrapped
ret = fun(p)
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\lex\parser.py", line 214, in t_set
return HySet(p[1])
File "C:\Python34\Scripts\env-hy\lib\site-packages\hy\models\set.py", line 31, in __init__
items = sorted(items)
TypeError: unorderable types: HyExpression() < HyKeyword()
(env-hy) C:\Users\ME\Code>
```
That is NOT supposed to happen.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `hy/models/set.py`
Content:
```
1 # Copyright (c) 2013 Paul Tagliamonte <[email protected]>
2 #
3 # Permission is hereby granted, free of charge, to any person obtaining a
4 # copy of this software and associated documentation files (the "Software"),
5 # to deal in the Software without restriction, including without limitation
6 # the rights to use, copy, modify, merge, publish, distribute, sublicense,
7 # and/or sell copies of the Software, and to permit persons to whom the
8 # Software is furnished to do so, subject to the following conditions:
9 #
10 # The above copyright notice and this permission notice shall be included in
11 # all copies or substantial portions of the Software.
12 #
13 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
16 # THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
18 # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
19 # DEALINGS IN THE SOFTWARE.
20
21 from hy.models.list import HyList
22 from functools import reduce
23
24
25 class HySet(HyList):
26 """
27 Hy set (actually a list that pretends to be a set)
28 """
29
30 def __init__(self, items):
31 items = sorted(items)
32 items = list(reduce(lambda r, v: v in r and r or r+[v], items, []))
33 super(HySet, self).__init__(items)
34
35 def __repr__(self):
36 return "#{%s}" % (" ".join([repr(x) for x in self]))
37
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/hy/models/set.py b/hy/models/set.py
--- a/hy/models/set.py
+++ b/hy/models/set.py
@@ -18,19 +18,16 @@
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
+from hy.models import _wrappers, wrap_value
from hy.models.list import HyList
-from functools import reduce
class HySet(HyList):
"""
- Hy set (actually a list that pretends to be a set)
+ Hy set (just a representation of a set)
"""
- def __init__(self, items):
- items = sorted(items)
- items = list(reduce(lambda r, v: v in r and r or r+[v], items, []))
- super(HySet, self).__init__(items)
-
def __repr__(self):
return "#{%s}" % (" ".join([repr(x) for x in self]))
+
+_wrappers[set] = lambda s: HySet(wrap_value(x) for x in s)
|
{"golden_diff": "diff --git a/hy/models/set.py b/hy/models/set.py\n--- a/hy/models/set.py\n+++ b/hy/models/set.py\n@@ -18,19 +18,16 @@\n # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\n # DEALINGS IN THE SOFTWARE.\n \n+from hy.models import _wrappers, wrap_value\n from hy.models.list import HyList\n-from functools import reduce\n \n \n class HySet(HyList):\n \"\"\"\n- Hy set (actually a list that pretends to be a set)\n+ Hy set (just a representation of a set)\n \"\"\"\n \n- def __init__(self, items):\n- items = sorted(items)\n- items = list(reduce(lambda r, v: v in r and r or r+[v], items, []))\n- super(HySet, self).__init__(items)\n-\n def __repr__(self):\n return \"#{%s}\" % (\" \".join([repr(x) for x in self]))\n+\n+_wrappers[set] = lambda s: HySet(wrap_value(x) for x in s)\n", "issue": "Hy sets are really broken.\n``` Hy\n(env-hy) C:\\Users\\ME\\Code>hy\nhy 0.11.0 using CPython(v3.4.3:9b73f1c3e601) 3.4.3 on Windows\n=> #{:a 'a}\nTraceback (most recent call last):\n File \"C:\\Python34\\Scripts\\env-hy\\Scripts\\hy-script.py\", line 9, in <module>\n load_entry_point('hy==0.11.0', 'console_scripts', 'hy')()\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\cmdline.py\", line 341, in hy_main\n sys.exit(cmdline_handler(\"hy\", sys.argv))\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\cmdline.py\", line 336, in cmdline_handler\n return run_repl(spy=options.spy)\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\cmdline.py\", line 234, in run_repl\n os=platform.system()\n File \"C:\\Python34\\Lib\\code.py\", line 234, in interact\n more = self.push(line)\n File \"C:\\Python34\\Lib\\code.py\", line 256, in push\n more = self.runsource(source, self.filename)\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\cmdline.py\", line 93, in runsource\n tokens = tokenize(source)\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\lex\\__init__.py\", line 33, in tokenize\n return parser.parse(lexer.lex(buf))\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\rply\\parser.py\", line 23, in parse\n t, symstack, statestack, state\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\rply\\parser.py\", line 80, in _reduce_production\n value = p.func(targ)\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\lex\\parser.py\", line 69, in wrapped\n ret = fun(p)\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\lex\\parser.py\", line 214, in t_set\n return HySet(p[1])\n File \"C:\\Python34\\Scripts\\env-hy\\lib\\site-packages\\hy\\models\\set.py\", line 31, in __init__\n items = sorted(items)\nTypeError: unorderable types: HyExpression() < HyKeyword()\n\n(env-hy) C:\\Users\\ME\\Code>\n```\n\nThat is NOT supposed to happen.\n\n", "before_files": [{"content": "# Copyright (c) 2013 Paul Tagliamonte <[email protected]>\n#\n# Permission is hereby granted, free of charge, to any person obtaining a\n# copy of this software and associated documentation files (the \"Software\"),\n# to deal in the Software without restriction, including without limitation\n# the rights to use, copy, modify, merge, publish, distribute, sublicense,\n# and/or sell copies of the Software, and to permit persons to whom the\n# Software is furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice shall be included in\n# all copies or substantial portions of the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL\n# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING\n# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\n# DEALINGS IN THE SOFTWARE.\n\nfrom hy.models.list import HyList\nfrom functools import reduce\n\n\nclass HySet(HyList):\n \"\"\"\n Hy set (actually a list that pretends to be a set)\n \"\"\"\n\n def __init__(self, items):\n items = sorted(items)\n items = list(reduce(lambda r, v: v in r and r or r+[v], items, []))\n super(HySet, self).__init__(items)\n\n def __repr__(self):\n return \"#{%s}\" % (\" \".join([repr(x) for x in self]))\n", "path": "hy/models/set.py"}], "after_files": [{"content": "# Copyright (c) 2013 Paul Tagliamonte <[email protected]>\n#\n# Permission is hereby granted, free of charge, to any person obtaining a\n# copy of this software and associated documentation files (the \"Software\"),\n# to deal in the Software without restriction, including without limitation\n# the rights to use, copy, modify, merge, publish, distribute, sublicense,\n# and/or sell copies of the Software, and to permit persons to whom the\n# Software is furnished to do so, subject to the following conditions:\n#\n# The above copyright notice and this permission notice shall be included in\n# all copies or substantial portions of the Software.\n#\n# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL\n# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING\n# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\n# DEALINGS IN THE SOFTWARE.\n\nfrom hy.models import _wrappers, wrap_value\nfrom hy.models.list import HyList\n\n\nclass HySet(HyList):\n \"\"\"\n Hy set (just a representation of a set)\n \"\"\"\n\n def __repr__(self):\n return \"#{%s}\" % (\" \".join([repr(x) for x in self]))\n\n_wrappers[set] = lambda s: HySet(wrap_value(x) for x in s)\n", "path": "hy/models/set.py"}]}
| 1,352 | 242 |
gh_patches_debug_28579
|
rasdani/github-patches
|
git_diff
|
davanstrien__flyswot-115
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
update default for ensure_model to get latest model
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/flyswot/inference.py`
Content:
```
1 """Inference functionality"""
2 import csv
3 import mimetypes
4 import time
5 from abc import ABC
6 from abc import abstractmethod
7 from dataclasses import asdict
8 from dataclasses import dataclass
9 from datetime import datetime
10 from datetime import timedelta
11 from pathlib import Path
12 from typing import Iterable
13 from typing import Iterator
14 from typing import List
15 from typing import Union
16
17 import numpy as np
18 import onnxruntime as rt # type: ignore
19 import typer
20 from PIL import Image # type: ignore
21 from rich.table import Table
22 from toolz import itertoolz # type: ignore
23
24 from flyswot import core
25 from flyswot import models
26 from flyswot.console import console
27
28 app = typer.Typer()
29
30
31 @dataclass()
32 class ImagePredictionItem:
33 """Prediction for an image.
34
35 Attributes:
36 path: The Path to the image
37 predicted_label: The predicted label i.e. the argmax value for the prediction tensor
38 condidence: The confidence for `predicted_label` i.e. the max value for prediction tensor
39 """
40
41 path: Path
42 predicted_label: str
43 confidence: float
44
45 def __post_init__(self) -> Union[Path, None]:
46 """attempt to get absolute path"""
47 try:
48 self.path: Path = self.path.absolute()
49 except AttributeError:
50 pass
51
52
53 @dataclass
54 class PredictionBatch:
55 """Container for ImagePredictionItems"""
56
57 batch: List[ImagePredictionItem]
58
59 def __post_init__(self):
60 """Returns a list of all predicted labels in batch"""
61 self.batch_labels: Iterator[str] = (item.predicted_label for item in self.batch)
62
63
64 image_extensions = {k for k, v in mimetypes.types_map.items() if v.startswith("image/")}
65
66
67 @app.command()
68 def predict_image(
69 image: Path = typer.Argument(..., readable=True, resolve_path=True)
70 ) -> None:
71 """Predict a single image"""
72 pass # pragma: no cover
73
74
75 @app.command(name="directory")
76 def predict_directory(
77 directory: Path = typer.Argument(
78 ...,
79 readable=True,
80 resolve_path=True,
81 help="Directory to start searching for images from",
82 ),
83 csv_save_dir: Path = typer.Argument(
84 ...,
85 writable=True,
86 resolve_path=True,
87 help="Directory used to store the csv report",
88 ),
89 pattern: str = typer.Option("fse", help="Pattern used to filter image filenames"),
90 bs: int = typer.Option(16, help="Batch Size"),
91 image_format: str = typer.Option(
92 ".tif",
93 help="Image format for flyswot to use for predictions",
94 ),
95 ):
96 """Predicts against all images stored under DIRECTORY which match PATTERN in the filename.
97
98 By default searches for filenames containing 'fse'.
99
100 Creates a CSV report saved to `csv_save_dir`
101 """
102 start_time = time.perf_counter()
103 model_dir = models.ensure_model_dir()
104 # TODO add load learner function that can be passed a model name
105 model_parts = models.ensure_model(model_dir)
106 model = model_parts.model
107 vocab = models.load_vocab(model_parts.vocab)
108 onnxinference = OnnxInferenceSession(model, vocab)
109 files = core.get_image_files_from_pattern(directory, pattern, image_format)
110 files = list(files)
111 typer.echo(f"Found {len(files)} files matching {pattern} in {directory}")
112 csv_fname = create_csv_fname(csv_save_dir)
113 create_csv_header(csv_fname)
114 with typer.progressbar(length=len(files)) as progress:
115 all_preds = []
116 predictions = []
117 for batch in itertoolz.partition_all(bs, files):
118 batch_predictions = onnxinference.predict_batch(batch, bs)
119 all_preds.append(batch_predictions.batch_labels)
120 predictions.append(batch_predictions)
121 progress.update(len(batch))
122 write_batch_preds_to_csv(csv_fname, batch_predictions)
123 all_preds = list(itertoolz.concat(all_preds))
124 typer.echo(f"CSV report stored in {csv_fname}")
125 delta = timedelta(seconds=time.perf_counter() - start_time)
126 typer.echo(f"Time taken to run: {str(delta)}")
127 print_table(all_preds)
128
129
130 def print_table(decoded) -> None:
131 """Prints table summary of predicted labels"""
132 table = Table(show_header=True, title="Prediction summary")
133 table.add_column(
134 "Class",
135 )
136 table.add_column("Count")
137 table.add_column("Percentage")
138 total = len(decoded)
139 frequencies = itertoolz.frequencies(decoded)
140 for is_last_element, var in core.signal_last(frequencies.items()):
141 key, value = var
142 count = value
143 percentage = round((count / total) * 100, 2)
144 if is_last_element:
145 table.add_row(key, str(count), f"{percentage}", end_section=True)
146 table.add_row("Total", str(total), "")
147 else:
148 table.add_row(key, str(count), f"{percentage}")
149 console.print(table)
150
151
152 def create_csv_fname(csv_directory: Path) -> Path:
153 """Creates a csv filename"""
154 date_now = datetime.now()
155 date_now = date_now.strftime("%Y_%m_%d_%H_%M")
156 fname = Path(date_now + ".csv")
157 return Path(csv_directory / fname)
158
159
160 def create_csv_header(csv_path: Path) -> None:
161 """Creates a header for csv `csv_path`"""
162 with open(csv_path, mode="w", newline="") as csv_file:
163 field_names = ["path", "directory", "predicted_label", "confidence"]
164 writer = csv.DictWriter(csv_file, fieldnames=field_names)
165 writer.writeheader()
166
167
168 def write_batch_preds_to_csv(csv_fpath: Path, predictions: PredictionBatch) -> None:
169 """Appends `predictions` batch to `csv_path`"""
170 with open(csv_fpath, mode="a", newline="") as csv_file:
171 field_names = ["path", "directory", "predicted_label", "confidence"]
172 writer = csv.DictWriter(csv_file, fieldnames=field_names)
173 for pred in predictions.batch:
174 row = asdict(pred)
175 row["directory"] = pred.path.parent
176 writer.writerow(row)
177
178
179 class InferenceSession(ABC):
180 """Abstract class for inference sessions"""
181
182 @abstractmethod
183 def __init__(self, model: Path, vocab: List):
184 """Inference Sessions should init from a model file and vocab"""
185 self.model = model
186 self.vocab = vocab
187
188 @abstractmethod
189 def predict_image(self, image: Path):
190 """Predict a single image"""
191 pass
192
193 @abstractmethod
194 def predict_batch(self, model: Path, batch: Iterable[Path], bs: int):
195 """Predict a batch"""
196 pass
197
198
199 def softmax(x):
200 """return softmax of `x`"""
201 x = x.reshape(-1)
202 e_x = np.exp(x - np.max(x))
203 return e_x / e_x.sum(axis=0)
204
205
206 # class FastaiInferenceModel(InferenceSession):
207 # def __init__(self, model):
208 # self.model = model
209 # self.learn = load_learner(model)
210
211 # def predict_image(self, image: Path) -> Any:
212 # return self.learn.predict(image)
213
214 # def predict_batch(self, batch: Iterable[Path], bs: int) -> PredictionBatch:
215 # test_dl = self.learn.dls.test_dl(batch, bs=bs)
216 # vocab = dict(enumerate(self.learn.dls.vocab))
217 # with self.learn.no_bar():
218 # fastai_preds: Any = self.learn.get_preds(dl=test_dl, with_decoded=True)
219 # prediction_tensors: Iterable[Any] = fastai_preds[0]
220 # prediction_items = []
221 # for file, pred in zip(batch, prediction_tensors):
222 # arg_max = int(np.array(pred).argmax())
223 # predicted_label = vocab[int(arg_max)]
224 # confidence = float(np.array(pred).max())
225 # prediction_items.append(
226 # ImagePredictionItem(file, predicted_label, confidence)
227 # )
228 # return PredictionBatch(prediction_items)
229
230
231 class OnnxInferenceSession(InferenceSession):
232 """onnx inference session"""
233
234 def __init__(self, model: Path, vocab: Path):
235 """Create onnx session"""
236 self.model = model
237 self.session = rt.InferenceSession(str(model))
238
239 self.vocab = vocab
240 self.vocab_mapping = dict(enumerate(self.vocab))
241
242 def _load_vocab(self, vocab: Path) -> List:
243 with open(vocab, "r") as f:
244 return [item.strip("\n") for item in f.readlines()]
245
246 def predict_image(self, image: Path):
247 """Predict a single image"""
248 img = self._load_image(image)
249 raw_result = self.session.run(["output"], {"image": img})
250 pred = self._postprocess(raw_result)
251 arg_max = int(np.array(pred).argmax())
252 predicted_label = self.vocab_mapping[int(arg_max)]
253 confidence = float(np.array(pred).max())
254 return ImagePredictionItem(image, predicted_label, confidence)
255
256 def _preprocess(self, input_data: np.ndarray) -> np.ndarray:
257 # converts the input data into the float32 input for onnx
258 img_data = input_data.astype("float32")
259
260 # normalize
261 mean_vec = np.array([0.485, 0.456, 0.406])
262 stddev_vec = np.array([0.229, 0.224, 0.225])
263 norm_img_data = np.zeros(img_data.shape).astype("float32")
264 for i in range(img_data.shape[0]):
265 norm_img_data[i, :, :] = (
266 img_data[i, :, :] / 255 - mean_vec[i]
267 ) / stddev_vec[i]
268
269 # add batch channel
270 norm_img_data = norm_img_data.reshape(1, 3, 512, 512).astype("float32")
271 return norm_img_data
272
273 def _load_image(self, file: Path) -> np.ndarray:
274 """loads image and carries out preprocessing for inference"""
275 image = Image.open(file, mode="r")
276 image = image.resize((512, 512), Image.BILINEAR)
277 image_data = np.array(image).transpose(2, 0, 1)
278 return self._preprocess(image_data)
279
280 def _postprocess(self, result: List):
281 """process results from onnx session"""
282 return softmax(np.array(result)).tolist()
283
284 def predict_batch(self, batch: Iterable[Path], bs: int):
285 """predicts a batch of images"""
286 prediction_items = [self.predict_image(file) for file in batch]
287 return PredictionBatch(prediction_items)
288
289
290 if __name__ == "__main__":
291 app()
292
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/flyswot/inference.py b/src/flyswot/inference.py
--- a/src/flyswot/inference.py
+++ b/src/flyswot/inference.py
@@ -19,7 +19,7 @@
import typer
from PIL import Image # type: ignore
from rich.table import Table
-from toolz import itertoolz # type: ignore
+from toolz import itertoolz
from flyswot import core
from flyswot import models
@@ -89,9 +89,9 @@
pattern: str = typer.Option("fse", help="Pattern used to filter image filenames"),
bs: int = typer.Option(16, help="Batch Size"),
image_format: str = typer.Option(
- ".tif",
- help="Image format for flyswot to use for predictions",
+ ".tif", help="Image format for flyswot to use for predictions"
),
+ check_latest: bool = typer.Option(True, help="Use latest available model"),
):
"""Predicts against all images stored under DIRECTORY which match PATTERN in the filename.
@@ -102,7 +102,7 @@
start_time = time.perf_counter()
model_dir = models.ensure_model_dir()
# TODO add load learner function that can be passed a model name
- model_parts = models.ensure_model(model_dir)
+ model_parts = models.ensure_model(model_dir, check_latest)
model = model_parts.model
vocab = models.load_vocab(model_parts.vocab)
onnxinference = OnnxInferenceSession(model, vocab)
|
{"golden_diff": "diff --git a/src/flyswot/inference.py b/src/flyswot/inference.py\n--- a/src/flyswot/inference.py\n+++ b/src/flyswot/inference.py\n@@ -19,7 +19,7 @@\n import typer\n from PIL import Image # type: ignore\n from rich.table import Table\n-from toolz import itertoolz # type: ignore\n+from toolz import itertoolz\n \n from flyswot import core\n from flyswot import models\n@@ -89,9 +89,9 @@\n pattern: str = typer.Option(\"fse\", help=\"Pattern used to filter image filenames\"),\n bs: int = typer.Option(16, help=\"Batch Size\"),\n image_format: str = typer.Option(\n- \".tif\",\n- help=\"Image format for flyswot to use for predictions\",\n+ \".tif\", help=\"Image format for flyswot to use for predictions\"\n ),\n+ check_latest: bool = typer.Option(True, help=\"Use latest available model\"),\n ):\n \"\"\"Predicts against all images stored under DIRECTORY which match PATTERN in the filename.\n \n@@ -102,7 +102,7 @@\n start_time = time.perf_counter()\n model_dir = models.ensure_model_dir()\n # TODO add load learner function that can be passed a model name\n- model_parts = models.ensure_model(model_dir)\n+ model_parts = models.ensure_model(model_dir, check_latest)\n model = model_parts.model\n vocab = models.load_vocab(model_parts.vocab)\n onnxinference = OnnxInferenceSession(model, vocab)\n", "issue": "update default for ensure_model to get latest model \n\n", "before_files": [{"content": "\"\"\"Inference functionality\"\"\"\nimport csv\nimport mimetypes\nimport time\nfrom abc import ABC\nfrom abc import abstractmethod\nfrom dataclasses import asdict\nfrom dataclasses import dataclass\nfrom datetime import datetime\nfrom datetime import timedelta\nfrom pathlib import Path\nfrom typing import Iterable\nfrom typing import Iterator\nfrom typing import List\nfrom typing import Union\n\nimport numpy as np\nimport onnxruntime as rt # type: ignore\nimport typer\nfrom PIL import Image # type: ignore\nfrom rich.table import Table\nfrom toolz import itertoolz # type: ignore\n\nfrom flyswot import core\nfrom flyswot import models\nfrom flyswot.console import console\n\napp = typer.Typer()\n\n\n@dataclass()\nclass ImagePredictionItem:\n \"\"\"Prediction for an image.\n\n Attributes:\n path: The Path to the image\n predicted_label: The predicted label i.e. the argmax value for the prediction tensor\n condidence: The confidence for `predicted_label` i.e. the max value for prediction tensor\n \"\"\"\n\n path: Path\n predicted_label: str\n confidence: float\n\n def __post_init__(self) -> Union[Path, None]:\n \"\"\"attempt to get absolute path\"\"\"\n try:\n self.path: Path = self.path.absolute()\n except AttributeError:\n pass\n\n\n@dataclass\nclass PredictionBatch:\n \"\"\"Container for ImagePredictionItems\"\"\"\n\n batch: List[ImagePredictionItem]\n\n def __post_init__(self):\n \"\"\"Returns a list of all predicted labels in batch\"\"\"\n self.batch_labels: Iterator[str] = (item.predicted_label for item in self.batch)\n\n\nimage_extensions = {k for k, v in mimetypes.types_map.items() if v.startswith(\"image/\")}\n\n\[email protected]()\ndef predict_image(\n image: Path = typer.Argument(..., readable=True, resolve_path=True)\n) -> None:\n \"\"\"Predict a single image\"\"\"\n pass # pragma: no cover\n\n\[email protected](name=\"directory\")\ndef predict_directory(\n directory: Path = typer.Argument(\n ...,\n readable=True,\n resolve_path=True,\n help=\"Directory to start searching for images from\",\n ),\n csv_save_dir: Path = typer.Argument(\n ...,\n writable=True,\n resolve_path=True,\n help=\"Directory used to store the csv report\",\n ),\n pattern: str = typer.Option(\"fse\", help=\"Pattern used to filter image filenames\"),\n bs: int = typer.Option(16, help=\"Batch Size\"),\n image_format: str = typer.Option(\n \".tif\",\n help=\"Image format for flyswot to use for predictions\",\n ),\n):\n \"\"\"Predicts against all images stored under DIRECTORY which match PATTERN in the filename.\n\n By default searches for filenames containing 'fse'.\n\n Creates a CSV report saved to `csv_save_dir`\n \"\"\"\n start_time = time.perf_counter()\n model_dir = models.ensure_model_dir()\n # TODO add load learner function that can be passed a model name\n model_parts = models.ensure_model(model_dir)\n model = model_parts.model\n vocab = models.load_vocab(model_parts.vocab)\n onnxinference = OnnxInferenceSession(model, vocab)\n files = core.get_image_files_from_pattern(directory, pattern, image_format)\n files = list(files)\n typer.echo(f\"Found {len(files)} files matching {pattern} in {directory}\")\n csv_fname = create_csv_fname(csv_save_dir)\n create_csv_header(csv_fname)\n with typer.progressbar(length=len(files)) as progress:\n all_preds = []\n predictions = []\n for batch in itertoolz.partition_all(bs, files):\n batch_predictions = onnxinference.predict_batch(batch, bs)\n all_preds.append(batch_predictions.batch_labels)\n predictions.append(batch_predictions)\n progress.update(len(batch))\n write_batch_preds_to_csv(csv_fname, batch_predictions)\n all_preds = list(itertoolz.concat(all_preds))\n typer.echo(f\"CSV report stored in {csv_fname}\")\n delta = timedelta(seconds=time.perf_counter() - start_time)\n typer.echo(f\"Time taken to run: {str(delta)}\")\n print_table(all_preds)\n\n\ndef print_table(decoded) -> None:\n \"\"\"Prints table summary of predicted labels\"\"\"\n table = Table(show_header=True, title=\"Prediction summary\")\n table.add_column(\n \"Class\",\n )\n table.add_column(\"Count\")\n table.add_column(\"Percentage\")\n total = len(decoded)\n frequencies = itertoolz.frequencies(decoded)\n for is_last_element, var in core.signal_last(frequencies.items()):\n key, value = var\n count = value\n percentage = round((count / total) * 100, 2)\n if is_last_element:\n table.add_row(key, str(count), f\"{percentage}\", end_section=True)\n table.add_row(\"Total\", str(total), \"\")\n else:\n table.add_row(key, str(count), f\"{percentage}\")\n console.print(table)\n\n\ndef create_csv_fname(csv_directory: Path) -> Path:\n \"\"\"Creates a csv filename\"\"\"\n date_now = datetime.now()\n date_now = date_now.strftime(\"%Y_%m_%d_%H_%M\")\n fname = Path(date_now + \".csv\")\n return Path(csv_directory / fname)\n\n\ndef create_csv_header(csv_path: Path) -> None:\n \"\"\"Creates a header for csv `csv_path`\"\"\"\n with open(csv_path, mode=\"w\", newline=\"\") as csv_file:\n field_names = [\"path\", \"directory\", \"predicted_label\", \"confidence\"]\n writer = csv.DictWriter(csv_file, fieldnames=field_names)\n writer.writeheader()\n\n\ndef write_batch_preds_to_csv(csv_fpath: Path, predictions: PredictionBatch) -> None:\n \"\"\"Appends `predictions` batch to `csv_path`\"\"\"\n with open(csv_fpath, mode=\"a\", newline=\"\") as csv_file:\n field_names = [\"path\", \"directory\", \"predicted_label\", \"confidence\"]\n writer = csv.DictWriter(csv_file, fieldnames=field_names)\n for pred in predictions.batch:\n row = asdict(pred)\n row[\"directory\"] = pred.path.parent\n writer.writerow(row)\n\n\nclass InferenceSession(ABC):\n \"\"\"Abstract class for inference sessions\"\"\"\n\n @abstractmethod\n def __init__(self, model: Path, vocab: List):\n \"\"\"Inference Sessions should init from a model file and vocab\"\"\"\n self.model = model\n self.vocab = vocab\n\n @abstractmethod\n def predict_image(self, image: Path):\n \"\"\"Predict a single image\"\"\"\n pass\n\n @abstractmethod\n def predict_batch(self, model: Path, batch: Iterable[Path], bs: int):\n \"\"\"Predict a batch\"\"\"\n pass\n\n\ndef softmax(x):\n \"\"\"return softmax of `x`\"\"\"\n x = x.reshape(-1)\n e_x = np.exp(x - np.max(x))\n return e_x / e_x.sum(axis=0)\n\n\n# class FastaiInferenceModel(InferenceSession):\n# def __init__(self, model):\n# self.model = model\n# self.learn = load_learner(model)\n\n# def predict_image(self, image: Path) -> Any:\n# return self.learn.predict(image)\n\n# def predict_batch(self, batch: Iterable[Path], bs: int) -> PredictionBatch:\n# test_dl = self.learn.dls.test_dl(batch, bs=bs)\n# vocab = dict(enumerate(self.learn.dls.vocab))\n# with self.learn.no_bar():\n# fastai_preds: Any = self.learn.get_preds(dl=test_dl, with_decoded=True)\n# prediction_tensors: Iterable[Any] = fastai_preds[0]\n# prediction_items = []\n# for file, pred in zip(batch, prediction_tensors):\n# arg_max = int(np.array(pred).argmax())\n# predicted_label = vocab[int(arg_max)]\n# confidence = float(np.array(pred).max())\n# prediction_items.append(\n# ImagePredictionItem(file, predicted_label, confidence)\n# )\n# return PredictionBatch(prediction_items)\n\n\nclass OnnxInferenceSession(InferenceSession):\n \"\"\"onnx inference session\"\"\"\n\n def __init__(self, model: Path, vocab: Path):\n \"\"\"Create onnx session\"\"\"\n self.model = model\n self.session = rt.InferenceSession(str(model))\n\n self.vocab = vocab\n self.vocab_mapping = dict(enumerate(self.vocab))\n\n def _load_vocab(self, vocab: Path) -> List:\n with open(vocab, \"r\") as f:\n return [item.strip(\"\\n\") for item in f.readlines()]\n\n def predict_image(self, image: Path):\n \"\"\"Predict a single image\"\"\"\n img = self._load_image(image)\n raw_result = self.session.run([\"output\"], {\"image\": img})\n pred = self._postprocess(raw_result)\n arg_max = int(np.array(pred).argmax())\n predicted_label = self.vocab_mapping[int(arg_max)]\n confidence = float(np.array(pred).max())\n return ImagePredictionItem(image, predicted_label, confidence)\n\n def _preprocess(self, input_data: np.ndarray) -> np.ndarray:\n # converts the input data into the float32 input for onnx\n img_data = input_data.astype(\"float32\")\n\n # normalize\n mean_vec = np.array([0.485, 0.456, 0.406])\n stddev_vec = np.array([0.229, 0.224, 0.225])\n norm_img_data = np.zeros(img_data.shape).astype(\"float32\")\n for i in range(img_data.shape[0]):\n norm_img_data[i, :, :] = (\n img_data[i, :, :] / 255 - mean_vec[i]\n ) / stddev_vec[i]\n\n # add batch channel\n norm_img_data = norm_img_data.reshape(1, 3, 512, 512).astype(\"float32\")\n return norm_img_data\n\n def _load_image(self, file: Path) -> np.ndarray:\n \"\"\"loads image and carries out preprocessing for inference\"\"\"\n image = Image.open(file, mode=\"r\")\n image = image.resize((512, 512), Image.BILINEAR)\n image_data = np.array(image).transpose(2, 0, 1)\n return self._preprocess(image_data)\n\n def _postprocess(self, result: List):\n \"\"\"process results from onnx session\"\"\"\n return softmax(np.array(result)).tolist()\n\n def predict_batch(self, batch: Iterable[Path], bs: int):\n \"\"\"predicts a batch of images\"\"\"\n prediction_items = [self.predict_image(file) for file in batch]\n return PredictionBatch(prediction_items)\n\n\nif __name__ == \"__main__\":\n app()\n", "path": "src/flyswot/inference.py"}], "after_files": [{"content": "\"\"\"Inference functionality\"\"\"\nimport csv\nimport mimetypes\nimport time\nfrom abc import ABC\nfrom abc import abstractmethod\nfrom dataclasses import asdict\nfrom dataclasses import dataclass\nfrom datetime import datetime\nfrom datetime import timedelta\nfrom pathlib import Path\nfrom typing import Iterable\nfrom typing import Iterator\nfrom typing import List\nfrom typing import Union\n\nimport numpy as np\nimport onnxruntime as rt # type: ignore\nimport typer\nfrom PIL import Image # type: ignore\nfrom rich.table import Table\nfrom toolz import itertoolz\n\nfrom flyswot import core\nfrom flyswot import models\nfrom flyswot.console import console\n\napp = typer.Typer()\n\n\n@dataclass()\nclass ImagePredictionItem:\n \"\"\"Prediction for an image.\n\n Attributes:\n path: The Path to the image\n predicted_label: The predicted label i.e. the argmax value for the prediction tensor\n condidence: The confidence for `predicted_label` i.e. the max value for prediction tensor\n \"\"\"\n\n path: Path\n predicted_label: str\n confidence: float\n\n def __post_init__(self) -> Union[Path, None]:\n \"\"\"attempt to get absolute path\"\"\"\n try:\n self.path: Path = self.path.absolute()\n except AttributeError:\n pass\n\n\n@dataclass\nclass PredictionBatch:\n \"\"\"Container for ImagePredictionItems\"\"\"\n\n batch: List[ImagePredictionItem]\n\n def __post_init__(self):\n \"\"\"Returns a list of all predicted labels in batch\"\"\"\n self.batch_labels: Iterator[str] = (item.predicted_label for item in self.batch)\n\n\nimage_extensions = {k for k, v in mimetypes.types_map.items() if v.startswith(\"image/\")}\n\n\[email protected]()\ndef predict_image(\n image: Path = typer.Argument(..., readable=True, resolve_path=True)\n) -> None:\n \"\"\"Predict a single image\"\"\"\n pass # pragma: no cover\n\n\[email protected](name=\"directory\")\ndef predict_directory(\n directory: Path = typer.Argument(\n ...,\n readable=True,\n resolve_path=True,\n help=\"Directory to start searching for images from\",\n ),\n csv_save_dir: Path = typer.Argument(\n ...,\n writable=True,\n resolve_path=True,\n help=\"Directory used to store the csv report\",\n ),\n pattern: str = typer.Option(\"fse\", help=\"Pattern used to filter image filenames\"),\n bs: int = typer.Option(16, help=\"Batch Size\"),\n image_format: str = typer.Option(\n \".tif\", help=\"Image format for flyswot to use for predictions\"\n ),\n check_latest: bool = typer.Option(True, help=\"Use latest available model\"),\n):\n \"\"\"Predicts against all images stored under DIRECTORY which match PATTERN in the filename.\n\n By default searches for filenames containing 'fse'.\n\n Creates a CSV report saved to `csv_save_dir`\n \"\"\"\n start_time = time.perf_counter()\n model_dir = models.ensure_model_dir()\n # TODO add load learner function that can be passed a model name\n model_parts = models.ensure_model(model_dir, check_latest)\n model = model_parts.model\n vocab = models.load_vocab(model_parts.vocab)\n onnxinference = OnnxInferenceSession(model, vocab)\n files = core.get_image_files_from_pattern(directory, pattern, image_format)\n files = list(files)\n typer.echo(f\"Found {len(files)} files matching {pattern} in {directory}\")\n csv_fname = create_csv_fname(csv_save_dir)\n create_csv_header(csv_fname)\n with typer.progressbar(length=len(files)) as progress:\n all_preds = []\n predictions = []\n for batch in itertoolz.partition_all(bs, files):\n batch_predictions = onnxinference.predict_batch(batch, bs)\n all_preds.append(batch_predictions.batch_labels)\n predictions.append(batch_predictions)\n progress.update(len(batch))\n write_batch_preds_to_csv(csv_fname, batch_predictions)\n all_preds = list(itertoolz.concat(all_preds))\n typer.echo(f\"CSV report stored in {csv_fname}\")\n delta = timedelta(seconds=time.perf_counter() - start_time)\n typer.echo(f\"Time taken to run: {str(delta)}\")\n print_table(all_preds)\n\n\ndef print_table(decoded) -> None:\n \"\"\"Prints table summary of predicted labels\"\"\"\n table = Table(show_header=True, title=\"Prediction summary\")\n table.add_column(\n \"Class\",\n )\n table.add_column(\"Count\")\n table.add_column(\"Percentage\")\n total = len(decoded)\n frequencies = itertoolz.frequencies(decoded)\n for is_last_element, var in core.signal_last(frequencies.items()):\n key, value = var\n count = value\n percentage = round((count / total) * 100, 2)\n if is_last_element:\n table.add_row(key, str(count), f\"{percentage}\", end_section=True)\n table.add_row(\"Total\", str(total), \"\")\n else:\n table.add_row(key, str(count), f\"{percentage}\")\n console.print(table)\n\n\ndef create_csv_fname(csv_directory: Path) -> Path:\n \"\"\"Creates a csv filename\"\"\"\n date_now = datetime.now()\n date_now = date_now.strftime(\"%Y_%m_%d_%H_%M\")\n fname = Path(date_now + \".csv\")\n return Path(csv_directory / fname)\n\n\ndef create_csv_header(csv_path: Path) -> None:\n \"\"\"Creates a header for csv `csv_path`\"\"\"\n with open(csv_path, mode=\"w\", newline=\"\") as csv_file:\n field_names = [\"path\", \"directory\", \"predicted_label\", \"confidence\"]\n writer = csv.DictWriter(csv_file, fieldnames=field_names)\n writer.writeheader()\n\n\ndef write_batch_preds_to_csv(csv_fpath: Path, predictions: PredictionBatch) -> None:\n \"\"\"Appends `predictions` batch to `csv_path`\"\"\"\n with open(csv_fpath, mode=\"a\", newline=\"\") as csv_file:\n field_names = [\"path\", \"directory\", \"predicted_label\", \"confidence\"]\n writer = csv.DictWriter(csv_file, fieldnames=field_names)\n for pred in predictions.batch:\n row = asdict(pred)\n row[\"directory\"] = pred.path.parent\n writer.writerow(row)\n\n\nclass InferenceSession(ABC):\n \"\"\"Abstract class for inference sessions\"\"\"\n\n @abstractmethod\n def __init__(self, model: Path, vocab: List):\n \"\"\"Inference Sessions should init from a model file and vocab\"\"\"\n self.model = model\n self.vocab = vocab\n\n @abstractmethod\n def predict_image(self, image: Path):\n \"\"\"Predict a single image\"\"\"\n pass\n\n @abstractmethod\n def predict_batch(self, model: Path, batch: Iterable[Path], bs: int):\n \"\"\"Predict a batch\"\"\"\n pass\n\n\ndef softmax(x):\n \"\"\"return softmax of `x`\"\"\"\n x = x.reshape(-1)\n e_x = np.exp(x - np.max(x))\n return e_x / e_x.sum(axis=0)\n\n\n# class FastaiInferenceModel(InferenceSession):\n# def __init__(self, model):\n# self.model = model\n# self.learn = load_learner(model)\n\n# def predict_image(self, image: Path) -> Any:\n# return self.learn.predict(image)\n\n# def predict_batch(self, batch: Iterable[Path], bs: int) -> PredictionBatch:\n# test_dl = self.learn.dls.test_dl(batch, bs=bs)\n# vocab = dict(enumerate(self.learn.dls.vocab))\n# with self.learn.no_bar():\n# fastai_preds: Any = self.learn.get_preds(dl=test_dl, with_decoded=True)\n# prediction_tensors: Iterable[Any] = fastai_preds[0]\n# prediction_items = []\n# for file, pred in zip(batch, prediction_tensors):\n# arg_max = int(np.array(pred).argmax())\n# predicted_label = vocab[int(arg_max)]\n# confidence = float(np.array(pred).max())\n# prediction_items.append(\n# ImagePredictionItem(file, predicted_label, confidence)\n# )\n# return PredictionBatch(prediction_items)\n\n\nclass OnnxInferenceSession(InferenceSession):\n \"\"\"onnx inference session\"\"\"\n\n def __init__(self, model: Path, vocab: Path):\n \"\"\"Create onnx session\"\"\"\n self.model = model\n self.session = rt.InferenceSession(str(model))\n\n self.vocab = vocab\n self.vocab_mapping = dict(enumerate(self.vocab))\n\n def _load_vocab(self, vocab: Path) -> List:\n with open(vocab, \"r\") as f:\n return [item.strip(\"\\n\") for item in f.readlines()]\n\n def predict_image(self, image: Path):\n \"\"\"Predict a single image\"\"\"\n img = self._load_image(image)\n raw_result = self.session.run([\"output\"], {\"image\": img})\n pred = self._postprocess(raw_result)\n arg_max = int(np.array(pred).argmax())\n predicted_label = self.vocab_mapping[int(arg_max)]\n confidence = float(np.array(pred).max())\n return ImagePredictionItem(image, predicted_label, confidence)\n\n def _preprocess(self, input_data: np.ndarray) -> np.ndarray:\n # converts the input data into the float32 input for onnx\n img_data = input_data.astype(\"float32\")\n\n # normalize\n mean_vec = np.array([0.485, 0.456, 0.406])\n stddev_vec = np.array([0.229, 0.224, 0.225])\n norm_img_data = np.zeros(img_data.shape).astype(\"float32\")\n for i in range(img_data.shape[0]):\n norm_img_data[i, :, :] = (\n img_data[i, :, :] / 255 - mean_vec[i]\n ) / stddev_vec[i]\n\n # add batch channel\n norm_img_data = norm_img_data.reshape(1, 3, 512, 512).astype(\"float32\")\n return norm_img_data\n\n def _load_image(self, file: Path) -> np.ndarray:\n \"\"\"loads image and carries out preprocessing for inference\"\"\"\n image = Image.open(file, mode=\"r\")\n image = image.resize((512, 512), Image.BILINEAR)\n image_data = np.array(image).transpose(2, 0, 1)\n return self._preprocess(image_data)\n\n def _postprocess(self, result: List):\n \"\"\"process results from onnx session\"\"\"\n return softmax(np.array(result)).tolist()\n\n def predict_batch(self, batch: Iterable[Path], bs: int):\n \"\"\"predicts a batch of images\"\"\"\n prediction_items = [self.predict_image(file) for file in batch]\n return PredictionBatch(prediction_items)\n\n\nif __name__ == \"__main__\":\n app()\n", "path": "src/flyswot/inference.py"}]}
| 3,398 | 357 |
gh_patches_debug_1429
|
rasdani/github-patches
|
git_diff
|
google__turbinia-785
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
import TurbiniaException to partitions.py
```
Traceback (most recent call last):
File "PATH/v2/lib/python3.8/site-packages/turbinia/workers/__init__.py", line 916, in run_wrapper
self.result = self.run(evidence, self.result)
File "PATH/v2/lib/python3.8/site-packages/turbinia/workers/partitions.py", line 144, in run
path_specs = partitions.Enumerate(evidence)
File "/PATH/v2/lib/python3.8/site-packages/turbinia/processors/partitions.py", line 49, in Enumerate
raise TurbiniaException(
NameError: name 'TurbiniaException' is not defined
2021-03-05 18:45:56 [ERROR] PartitionEnumerationTask Task failed with exception: [name 'TurbiniaException' is not defined]
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `turbinia/processors/partitions.py`
Content:
```
1 # -*- coding: utf-8 -*-
2 # Copyright 2021 Google LLC
3 #
4 # Licensed under the Apache License, Version 2.0 (the "License");
5 # you may not use this file except in compliance with the License.
6 # You may obtain a copy of the License at
7 #
8 # https://www.apache.org/licenses/LICENSE-2.0
9 #
10 # Unless required by applicable law or agreed to in writing, software
11 # distributed under the License is distributed on an "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 # See the License for the specific language governing permissions and
14 # limitations under the License.
15 """Evidence processor to enumerate partitions."""
16
17 import logging
18
19 from dfvfs.helpers import volume_scanner
20 from dfvfs.lib import definitions as dfvfs_definitions
21 from dfvfs.lib import errors as dfvfs_errors
22
23 from turbinia.lib.dfvfs_classes import UnattendedVolumeScannerMediator
24
25 log = logging.getLogger('turbinia')
26
27
28 def Enumerate(evidence):
29 """Uses dfVFS to enumerate partitions in a disk / image.
30
31 Args:
32 evidence: Evidence object to be scanned.
33
34 Raises:
35 TurbiniaException if source evidence can't be scanned.
36
37 Returns:
38 list[dfVFS.path_spec]: path specs for identified partitions
39 """
40 dfvfs_definitions.PREFERRED_GPT_BACK_END = (
41 dfvfs_definitions.TYPE_INDICATOR_GPT)
42 mediator = UnattendedVolumeScannerMediator()
43 mediator.credentials = evidence.credentials
44 path_specs = []
45 try:
46 scanner = volume_scanner.VolumeScanner(mediator=mediator)
47 path_specs = scanner.GetBasePathSpecs(evidence.local_path)
48 except dfvfs_errors.ScannerError as e:
49 raise TurbiniaException(
50 'Could not enumerate partitions [{0!s}]: {1!s}'.format(
51 evidence.local_path, e))
52
53 return path_specs
54
55
56 def GetPartitionEncryptionType(path_spec):
57 """Checks a partition for encryption.
58
59 Args:
60 path_spec (dfVFS.path_spec): Partition path_spec.
61
62 Returns:
63 String representing the type of encryption, or None.
64 """
65 encryption_type = None
66 if path_spec.parent.type_indicator == dfvfs_definitions.TYPE_INDICATOR_BDE:
67 encryption_type = 'BDE'
68 return encryption_type
69
70
71 def GetPathSpecByLocation(path_specs, location):
72 """Finds a path_spec from a list of path_specs for a given location.
73
74 Args:
75 path_specs (list[dfVFS.path_spec]): List of path_specs from volume scanner.
76 location (str): dfVFS location to search for.
77
78 Returns:
79 dfVFS.path_spec for the given location or None if not found.
80 """
81 for path_spec in path_specs:
82 child_path_spec = path_spec
83 fs_location = getattr(path_spec, 'location', None)
84 while path_spec.HasParent():
85 type_indicator = path_spec.type_indicator
86 if type_indicator in (dfvfs_definitions.TYPE_INDICATOR_TSK_PARTITION,
87 dfvfs_definitions.TYPE_INDICATOR_GPT):
88 if fs_location in ('\\', '/'):
89 fs_location = getattr(path_spec, 'location', None)
90 break
91 path_spec = path_spec.parent
92 if fs_location == location:
93 return child_path_spec
94 return None
95
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/turbinia/processors/partitions.py b/turbinia/processors/partitions.py
--- a/turbinia/processors/partitions.py
+++ b/turbinia/processors/partitions.py
@@ -21,6 +21,7 @@
from dfvfs.lib import errors as dfvfs_errors
from turbinia.lib.dfvfs_classes import UnattendedVolumeScannerMediator
+from turbinia import TurbiniaException
log = logging.getLogger('turbinia')
|
{"golden_diff": "diff --git a/turbinia/processors/partitions.py b/turbinia/processors/partitions.py\n--- a/turbinia/processors/partitions.py\n+++ b/turbinia/processors/partitions.py\n@@ -21,6 +21,7 @@\n from dfvfs.lib import errors as dfvfs_errors\n \n from turbinia.lib.dfvfs_classes import UnattendedVolumeScannerMediator\n+from turbinia import TurbiniaException\n \n log = logging.getLogger('turbinia')\n", "issue": "import TurbiniaException to partitions.py\n```\r\nTraceback (most recent call last):\r\n File \"PATH/v2/lib/python3.8/site-packages/turbinia/workers/__init__.py\", line 916, in run_wrapper\r\n self.result = self.run(evidence, self.result)\r\n File \"PATH/v2/lib/python3.8/site-packages/turbinia/workers/partitions.py\", line 144, in run\r\n path_specs = partitions.Enumerate(evidence)\r\n File \"/PATH/v2/lib/python3.8/site-packages/turbinia/processors/partitions.py\", line 49, in Enumerate\r\n raise TurbiniaException(\r\nNameError: name 'TurbiniaException' is not defined\r\n\r\n2021-03-05 18:45:56 [ERROR] PartitionEnumerationTask Task failed with exception: [name 'TurbiniaException' is not defined]\r\n```\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n# Copyright 2021 Google LLC\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# https://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\"\"\"Evidence processor to enumerate partitions.\"\"\"\n\nimport logging\n\nfrom dfvfs.helpers import volume_scanner\nfrom dfvfs.lib import definitions as dfvfs_definitions\nfrom dfvfs.lib import errors as dfvfs_errors\n\nfrom turbinia.lib.dfvfs_classes import UnattendedVolumeScannerMediator\n\nlog = logging.getLogger('turbinia')\n\n\ndef Enumerate(evidence):\n \"\"\"Uses dfVFS to enumerate partitions in a disk / image.\n\n Args:\n evidence: Evidence object to be scanned.\n\n Raises:\n TurbiniaException if source evidence can't be scanned.\n\n Returns:\n list[dfVFS.path_spec]: path specs for identified partitions\n \"\"\"\n dfvfs_definitions.PREFERRED_GPT_BACK_END = (\n dfvfs_definitions.TYPE_INDICATOR_GPT)\n mediator = UnattendedVolumeScannerMediator()\n mediator.credentials = evidence.credentials\n path_specs = []\n try:\n scanner = volume_scanner.VolumeScanner(mediator=mediator)\n path_specs = scanner.GetBasePathSpecs(evidence.local_path)\n except dfvfs_errors.ScannerError as e:\n raise TurbiniaException(\n 'Could not enumerate partitions [{0!s}]: {1!s}'.format(\n evidence.local_path, e))\n\n return path_specs\n\n\ndef GetPartitionEncryptionType(path_spec):\n \"\"\"Checks a partition for encryption.\n\n Args:\n path_spec (dfVFS.path_spec): Partition path_spec.\n\n Returns:\n String representing the type of encryption, or None.\n \"\"\"\n encryption_type = None\n if path_spec.parent.type_indicator == dfvfs_definitions.TYPE_INDICATOR_BDE:\n encryption_type = 'BDE'\n return encryption_type\n\n\ndef GetPathSpecByLocation(path_specs, location):\n \"\"\"Finds a path_spec from a list of path_specs for a given location.\n\n Args:\n path_specs (list[dfVFS.path_spec]): List of path_specs from volume scanner.\n location (str): dfVFS location to search for.\n\n Returns:\n dfVFS.path_spec for the given location or None if not found.\n \"\"\"\n for path_spec in path_specs:\n child_path_spec = path_spec\n fs_location = getattr(path_spec, 'location', None)\n while path_spec.HasParent():\n type_indicator = path_spec.type_indicator\n if type_indicator in (dfvfs_definitions.TYPE_INDICATOR_TSK_PARTITION,\n dfvfs_definitions.TYPE_INDICATOR_GPT):\n if fs_location in ('\\\\', '/'):\n fs_location = getattr(path_spec, 'location', None)\n break\n path_spec = path_spec.parent\n if fs_location == location:\n return child_path_spec\n return None\n", "path": "turbinia/processors/partitions.py"}], "after_files": [{"content": "# -*- coding: utf-8 -*-\n# Copyright 2021 Google LLC\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# https://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\"\"\"Evidence processor to enumerate partitions.\"\"\"\n\nimport logging\n\nfrom dfvfs.helpers import volume_scanner\nfrom dfvfs.lib import definitions as dfvfs_definitions\nfrom dfvfs.lib import errors as dfvfs_errors\n\nfrom turbinia.lib.dfvfs_classes import UnattendedVolumeScannerMediator\nfrom turbinia import TurbiniaException\n\nlog = logging.getLogger('turbinia')\n\n\ndef Enumerate(evidence):\n \"\"\"Uses dfVFS to enumerate partitions in a disk / image.\n\n Args:\n evidence: Evidence object to be scanned.\n\n Raises:\n TurbiniaException if source evidence can't be scanned.\n\n Returns:\n list[dfVFS.path_spec]: path specs for identified partitions\n \"\"\"\n dfvfs_definitions.PREFERRED_GPT_BACK_END = (\n dfvfs_definitions.TYPE_INDICATOR_GPT)\n mediator = UnattendedVolumeScannerMediator()\n mediator.credentials = evidence.credentials\n path_specs = []\n try:\n scanner = volume_scanner.VolumeScanner(mediator=mediator)\n path_specs = scanner.GetBasePathSpecs(evidence.local_path)\n except dfvfs_errors.ScannerError as e:\n raise TurbiniaException(\n 'Could not enumerate partitions [{0!s}]: {1!s}'.format(\n evidence.local_path, e))\n\n return path_specs\n\n\ndef GetPartitionEncryptionType(path_spec):\n \"\"\"Checks a partition for encryption.\n\n Args:\n path_spec (dfVFS.path_spec): Partition path_spec.\n\n Returns:\n String representing the type of encryption, or None.\n \"\"\"\n encryption_type = None\n if path_spec.parent.type_indicator == dfvfs_definitions.TYPE_INDICATOR_BDE:\n encryption_type = 'BDE'\n return encryption_type\n\n\ndef GetPathSpecByLocation(path_specs, location):\n \"\"\"Finds a path_spec from a list of path_specs for a given location.\n\n Args:\n path_specs (list[dfVFS.path_spec]): List of path_specs from volume scanner.\n location (str): dfVFS location to search for.\n\n Returns:\n dfVFS.path_spec for the given location or None if not found.\n \"\"\"\n for path_spec in path_specs:\n child_path_spec = path_spec\n fs_location = getattr(path_spec, 'location', None)\n while path_spec.HasParent():\n type_indicator = path_spec.type_indicator\n if type_indicator in (dfvfs_definitions.TYPE_INDICATOR_TSK_PARTITION,\n dfvfs_definitions.TYPE_INDICATOR_GPT):\n if fs_location in ('\\\\', '/'):\n fs_location = getattr(path_spec, 'location', None)\n break\n path_spec = path_spec.parent\n if fs_location == location:\n return child_path_spec\n return None\n", "path": "turbinia/processors/partitions.py"}]}
| 1,357 | 108 |
gh_patches_debug_21968
|
rasdani/github-patches
|
git_diff
|
pypa__pip-4429
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
support git refs in @ syntax
We'd like to be able to put paths to gerrit reviews in requirements files.
Given a gerrit like https://review.openstack.org/#/c/345601/6, the path given for a git pull looks like:
git pull https://git.openstack.org/openstack/oslo.db refs/changes/01/345601/6
pip syntax we'd expect would be:
```
.venv/bin/pip install -e git+https://git.openstack.org/openstack/oslo.db@refs/changes/01/345601/6#egg=oslo.db
```
current output:
```
Obtaining oslo.db from git+https://git.openstack.org/openstack/oslo.db@refs/changes/01/345601/6#egg=oslo.db
Cloning https://git.openstack.org/openstack/oslo.db (to refs/changes/01/345601/6) to ./.venv/src/oslo.db
Could not find a tag or branch 'refs/changes/01/345601/6', assuming commit.
error: pathspec 'refs/changes/01/345601/6' did not match any file(s) known to git.
Command "git checkout -q refs/changes/01/345601/6" failed with error code 1 in /home/classic/.venv/src/oslo.db
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `pip/vcs/git.py`
Content:
```
1 from __future__ import absolute_import
2
3 import logging
4 import tempfile
5 import os.path
6
7 from pip.compat import samefile
8 from pip.exceptions import BadCommand
9 from pip._vendor.six.moves.urllib import parse as urllib_parse
10 from pip._vendor.six.moves.urllib import request as urllib_request
11 from pip._vendor.packaging.version import parse as parse_version
12
13 from pip.utils import display_path, rmtree
14 from pip.vcs import vcs, VersionControl
15
16
17 urlsplit = urllib_parse.urlsplit
18 urlunsplit = urllib_parse.urlunsplit
19
20
21 logger = logging.getLogger(__name__)
22
23
24 class Git(VersionControl):
25 name = 'git'
26 dirname = '.git'
27 repo_name = 'clone'
28 schemes = (
29 'git', 'git+http', 'git+https', 'git+ssh', 'git+git', 'git+file',
30 )
31
32 def __init__(self, url=None, *args, **kwargs):
33
34 # Works around an apparent Git bug
35 # (see http://article.gmane.org/gmane.comp.version-control.git/146500)
36 if url:
37 scheme, netloc, path, query, fragment = urlsplit(url)
38 if scheme.endswith('file'):
39 initial_slashes = path[:-len(path.lstrip('/'))]
40 newpath = (
41 initial_slashes +
42 urllib_request.url2pathname(path)
43 .replace('\\', '/').lstrip('/')
44 )
45 url = urlunsplit((scheme, netloc, newpath, query, fragment))
46 after_plus = scheme.find('+') + 1
47 url = scheme[:after_plus] + urlunsplit(
48 (scheme[after_plus:], netloc, newpath, query, fragment),
49 )
50
51 super(Git, self).__init__(url, *args, **kwargs)
52
53 def get_git_version(self):
54 VERSION_PFX = 'git version '
55 version = self.run_command(['version'], show_stdout=False)
56 if version.startswith(VERSION_PFX):
57 version = version[len(VERSION_PFX):].split()[0]
58 else:
59 version = ''
60 # get first 3 positions of the git version becasue
61 # on windows it is x.y.z.windows.t, and this parses as
62 # LegacyVersion which always smaller than a Version.
63 version = '.'.join(version.split('.')[:3])
64 return parse_version(version)
65
66 def export(self, location):
67 """Export the Git repository at the url to the destination location"""
68 temp_dir = tempfile.mkdtemp('-export', 'pip-')
69 self.unpack(temp_dir)
70 try:
71 if not location.endswith('/'):
72 location = location + '/'
73 self.run_command(
74 ['checkout-index', '-a', '-f', '--prefix', location],
75 show_stdout=False, cwd=temp_dir)
76 finally:
77 rmtree(temp_dir)
78
79 def check_rev_options(self, rev, dest, rev_options):
80 """Check the revision options before checkout to compensate that tags
81 and branches may need origin/ as a prefix.
82 Returns the SHA1 of the branch or tag if found.
83 """
84 revisions = self.get_short_refs(dest)
85
86 origin_rev = 'origin/%s' % rev
87 if origin_rev in revisions:
88 # remote branch
89 return [revisions[origin_rev]]
90 elif rev in revisions:
91 # a local tag or branch name
92 return [revisions[rev]]
93 else:
94 logger.warning(
95 "Could not find a tag or branch '%s', assuming commit.", rev,
96 )
97 return rev_options
98
99 def check_version(self, dest, rev_options):
100 """
101 Compare the current sha to the ref. ref may be a branch or tag name,
102 but current rev will always point to a sha. This means that a branch
103 or tag will never compare as True. So this ultimately only matches
104 against exact shas.
105 """
106 return self.get_revision(dest).startswith(rev_options[0])
107
108 def switch(self, dest, url, rev_options):
109 self.run_command(['config', 'remote.origin.url', url], cwd=dest)
110 self.run_command(['checkout', '-q'] + rev_options, cwd=dest)
111
112 self.update_submodules(dest)
113
114 def update(self, dest, rev_options):
115 # First fetch changes from the default remote
116 if self.get_git_version() >= parse_version('1.9.0'):
117 # fetch tags in addition to everything else
118 self.run_command(['fetch', '-q', '--tags'], cwd=dest)
119 else:
120 self.run_command(['fetch', '-q'], cwd=dest)
121 # Then reset to wanted revision (maybe even origin/master)
122 if rev_options:
123 rev_options = self.check_rev_options(
124 rev_options[0], dest, rev_options,
125 )
126 self.run_command(['reset', '--hard', '-q'] + rev_options, cwd=dest)
127 #: update submodules
128 self.update_submodules(dest)
129
130 def obtain(self, dest):
131 url, rev = self.get_url_rev()
132 if rev:
133 rev_options = [rev]
134 rev_display = ' (to %s)' % rev
135 else:
136 rev_options = ['origin/master']
137 rev_display = ''
138 if self.check_destination(dest, url, rev_options, rev_display):
139 logger.info(
140 'Cloning %s%s to %s', url, rev_display, display_path(dest),
141 )
142 self.run_command(['clone', '-q', url, dest])
143
144 if rev:
145 rev_options = self.check_rev_options(rev, dest, rev_options)
146 # Only do a checkout if rev_options differs from HEAD
147 if not self.check_version(dest, rev_options):
148 self.run_command(
149 ['checkout', '-q'] + rev_options,
150 cwd=dest,
151 )
152 #: repo may contain submodules
153 self.update_submodules(dest)
154
155 def get_url(self, location):
156 """Return URL of the first remote encountered."""
157 remotes = self.run_command(
158 ['config', '--get-regexp', r'remote\..*\.url'],
159 show_stdout=False, cwd=location)
160 remotes = remotes.splitlines()
161 found_remote = remotes[0]
162 for remote in remotes:
163 if remote.startswith('remote.origin.url '):
164 found_remote = remote
165 break
166 url = found_remote.split(' ')[1]
167 return url.strip()
168
169 def get_revision(self, location):
170 current_rev = self.run_command(
171 ['rev-parse', 'HEAD'], show_stdout=False, cwd=location)
172 return current_rev.strip()
173
174 def get_full_refs(self, location):
175 """Yields tuples of (commit, ref) for branches and tags"""
176 output = self.run_command(['show-ref'],
177 show_stdout=False, cwd=location)
178 for line in output.strip().splitlines():
179 commit, ref = line.split(' ', 1)
180 yield commit.strip(), ref.strip()
181
182 def is_ref_remote(self, ref):
183 return ref.startswith('refs/remotes/')
184
185 def is_ref_branch(self, ref):
186 return ref.startswith('refs/heads/')
187
188 def is_ref_tag(self, ref):
189 return ref.startswith('refs/tags/')
190
191 def is_ref_commit(self, ref):
192 """A ref is a commit sha if it is not anything else"""
193 return not any((
194 self.is_ref_remote(ref),
195 self.is_ref_branch(ref),
196 self.is_ref_tag(ref),
197 ))
198
199 # Should deprecate `get_refs` since it's ambiguous
200 def get_refs(self, location):
201 return self.get_short_refs(location)
202
203 def get_short_refs(self, location):
204 """Return map of named refs (branches or tags) to commit hashes."""
205 rv = {}
206 for commit, ref in self.get_full_refs(location):
207 ref_name = None
208 if self.is_ref_remote(ref):
209 ref_name = ref[len('refs/remotes/'):]
210 elif self.is_ref_branch(ref):
211 ref_name = ref[len('refs/heads/'):]
212 elif self.is_ref_tag(ref):
213 ref_name = ref[len('refs/tags/'):]
214 if ref_name is not None:
215 rv[ref_name] = commit
216 return rv
217
218 def _get_subdirectory(self, location):
219 """Return the relative path of setup.py to the git repo root."""
220 # find the repo root
221 git_dir = self.run_command(['rev-parse', '--git-dir'],
222 show_stdout=False, cwd=location).strip()
223 if not os.path.isabs(git_dir):
224 git_dir = os.path.join(location, git_dir)
225 root_dir = os.path.join(git_dir, '..')
226 # find setup.py
227 orig_location = location
228 while not os.path.exists(os.path.join(location, 'setup.py')):
229 last_location = location
230 location = os.path.dirname(location)
231 if location == last_location:
232 # We've traversed up to the root of the filesystem without
233 # finding setup.py
234 logger.warning(
235 "Could not find setup.py for directory %s (tried all "
236 "parent directories)",
237 orig_location,
238 )
239 return None
240 # relative path of setup.py to repo root
241 if samefile(root_dir, location):
242 return None
243 return os.path.relpath(location, root_dir)
244
245 def get_src_requirement(self, dist, location):
246 repo = self.get_url(location)
247 if not repo.lower().startswith('git:'):
248 repo = 'git+' + repo
249 egg_project_name = dist.egg_name().split('-', 1)[0]
250 if not repo:
251 return None
252 current_rev = self.get_revision(location)
253 req = '%s@%s#egg=%s' % (repo, current_rev, egg_project_name)
254 subdirectory = self._get_subdirectory(location)
255 if subdirectory:
256 req += '&subdirectory=' + subdirectory
257 return req
258
259 def get_url_rev(self):
260 """
261 Prefixes stub URLs like 'user@hostname:user/repo.git' with 'ssh://'.
262 That's required because although they use SSH they sometimes doesn't
263 work with a ssh:// scheme (e.g. Github). But we need a scheme for
264 parsing. Hence we remove it again afterwards and return it as a stub.
265 """
266 if '://' not in self.url:
267 assert 'file:' not in self.url
268 self.url = self.url.replace('git+', 'git+ssh://')
269 url, rev = super(Git, self).get_url_rev()
270 url = url.replace('ssh://', '')
271 else:
272 url, rev = super(Git, self).get_url_rev()
273
274 return url, rev
275
276 def update_submodules(self, location):
277 if not os.path.exists(os.path.join(location, '.gitmodules')):
278 return
279 self.run_command(
280 ['submodule', 'update', '--init', '--recursive', '-q'],
281 cwd=location,
282 )
283
284 @classmethod
285 def controls_location(cls, location):
286 if super(Git, cls).controls_location(location):
287 return True
288 try:
289 r = cls().run_command(['rev-parse'],
290 cwd=location,
291 show_stdout=False,
292 on_returncode='ignore')
293 return not r
294 except BadCommand:
295 logger.debug("could not determine if %s is under git control "
296 "because git is not available", location)
297 return False
298
299
300 vcs.register(Git)
301
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/pip/vcs/git.py b/pip/vcs/git.py
--- a/pip/vcs/git.py
+++ b/pip/vcs/git.py
@@ -92,7 +92,8 @@
return [revisions[rev]]
else:
logger.warning(
- "Could not find a tag or branch '%s', assuming commit.", rev,
+ "Could not find a tag or branch '%s', assuming commit or ref",
+ rev,
)
return rev_options
@@ -146,9 +147,14 @@
# Only do a checkout if rev_options differs from HEAD
if not self.check_version(dest, rev_options):
self.run_command(
- ['checkout', '-q'] + rev_options,
+ ['fetch', '-q', url] + rev_options,
cwd=dest,
)
+ self.run_command(
+ ['checkout', '-q', 'FETCH_HEAD'],
+ cwd=dest,
+ )
+
#: repo may contain submodules
self.update_submodules(dest)
|
{"golden_diff": "diff --git a/pip/vcs/git.py b/pip/vcs/git.py\n--- a/pip/vcs/git.py\n+++ b/pip/vcs/git.py\n@@ -92,7 +92,8 @@\n return [revisions[rev]]\n else:\n logger.warning(\n- \"Could not find a tag or branch '%s', assuming commit.\", rev,\n+ \"Could not find a tag or branch '%s', assuming commit or ref\",\n+ rev,\n )\n return rev_options\n \n@@ -146,9 +147,14 @@\n # Only do a checkout if rev_options differs from HEAD\n if not self.check_version(dest, rev_options):\n self.run_command(\n- ['checkout', '-q'] + rev_options,\n+ ['fetch', '-q', url] + rev_options,\n cwd=dest,\n )\n+ self.run_command(\n+ ['checkout', '-q', 'FETCH_HEAD'],\n+ cwd=dest,\n+ )\n+\n #: repo may contain submodules\n self.update_submodules(dest)\n", "issue": "support git refs in @ syntax\nWe'd like to be able to put paths to gerrit reviews in requirements files.\n\nGiven a gerrit like https://review.openstack.org/#/c/345601/6, the path given for a git pull looks like:\n\n git pull https://git.openstack.org/openstack/oslo.db refs/changes/01/345601/6\n\npip syntax we'd expect would be:\n\n```\n.venv/bin/pip install -e git+https://git.openstack.org/openstack/oslo.db@refs/changes/01/345601/6#egg=oslo.db\n```\n\ncurrent output:\n\n```\n\nObtaining oslo.db from git+https://git.openstack.org/openstack/oslo.db@refs/changes/01/345601/6#egg=oslo.db\n Cloning https://git.openstack.org/openstack/oslo.db (to refs/changes/01/345601/6) to ./.venv/src/oslo.db\n Could not find a tag or branch 'refs/changes/01/345601/6', assuming commit.\nerror: pathspec 'refs/changes/01/345601/6' did not match any file(s) known to git.\nCommand \"git checkout -q refs/changes/01/345601/6\" failed with error code 1 in /home/classic/.venv/src/oslo.db\n```\n\n", "before_files": [{"content": "from __future__ import absolute_import\n\nimport logging\nimport tempfile\nimport os.path\n\nfrom pip.compat import samefile\nfrom pip.exceptions import BadCommand\nfrom pip._vendor.six.moves.urllib import parse as urllib_parse\nfrom pip._vendor.six.moves.urllib import request as urllib_request\nfrom pip._vendor.packaging.version import parse as parse_version\n\nfrom pip.utils import display_path, rmtree\nfrom pip.vcs import vcs, VersionControl\n\n\nurlsplit = urllib_parse.urlsplit\nurlunsplit = urllib_parse.urlunsplit\n\n\nlogger = logging.getLogger(__name__)\n\n\nclass Git(VersionControl):\n name = 'git'\n dirname = '.git'\n repo_name = 'clone'\n schemes = (\n 'git', 'git+http', 'git+https', 'git+ssh', 'git+git', 'git+file',\n )\n\n def __init__(self, url=None, *args, **kwargs):\n\n # Works around an apparent Git bug\n # (see http://article.gmane.org/gmane.comp.version-control.git/146500)\n if url:\n scheme, netloc, path, query, fragment = urlsplit(url)\n if scheme.endswith('file'):\n initial_slashes = path[:-len(path.lstrip('/'))]\n newpath = (\n initial_slashes +\n urllib_request.url2pathname(path)\n .replace('\\\\', '/').lstrip('/')\n )\n url = urlunsplit((scheme, netloc, newpath, query, fragment))\n after_plus = scheme.find('+') + 1\n url = scheme[:after_plus] + urlunsplit(\n (scheme[after_plus:], netloc, newpath, query, fragment),\n )\n\n super(Git, self).__init__(url, *args, **kwargs)\n\n def get_git_version(self):\n VERSION_PFX = 'git version '\n version = self.run_command(['version'], show_stdout=False)\n if version.startswith(VERSION_PFX):\n version = version[len(VERSION_PFX):].split()[0]\n else:\n version = ''\n # get first 3 positions of the git version becasue\n # on windows it is x.y.z.windows.t, and this parses as\n # LegacyVersion which always smaller than a Version.\n version = '.'.join(version.split('.')[:3])\n return parse_version(version)\n\n def export(self, location):\n \"\"\"Export the Git repository at the url to the destination location\"\"\"\n temp_dir = tempfile.mkdtemp('-export', 'pip-')\n self.unpack(temp_dir)\n try:\n if not location.endswith('/'):\n location = location + '/'\n self.run_command(\n ['checkout-index', '-a', '-f', '--prefix', location],\n show_stdout=False, cwd=temp_dir)\n finally:\n rmtree(temp_dir)\n\n def check_rev_options(self, rev, dest, rev_options):\n \"\"\"Check the revision options before checkout to compensate that tags\n and branches may need origin/ as a prefix.\n Returns the SHA1 of the branch or tag if found.\n \"\"\"\n revisions = self.get_short_refs(dest)\n\n origin_rev = 'origin/%s' % rev\n if origin_rev in revisions:\n # remote branch\n return [revisions[origin_rev]]\n elif rev in revisions:\n # a local tag or branch name\n return [revisions[rev]]\n else:\n logger.warning(\n \"Could not find a tag or branch '%s', assuming commit.\", rev,\n )\n return rev_options\n\n def check_version(self, dest, rev_options):\n \"\"\"\n Compare the current sha to the ref. ref may be a branch or tag name,\n but current rev will always point to a sha. This means that a branch\n or tag will never compare as True. So this ultimately only matches\n against exact shas.\n \"\"\"\n return self.get_revision(dest).startswith(rev_options[0])\n\n def switch(self, dest, url, rev_options):\n self.run_command(['config', 'remote.origin.url', url], cwd=dest)\n self.run_command(['checkout', '-q'] + rev_options, cwd=dest)\n\n self.update_submodules(dest)\n\n def update(self, dest, rev_options):\n # First fetch changes from the default remote\n if self.get_git_version() >= parse_version('1.9.0'):\n # fetch tags in addition to everything else\n self.run_command(['fetch', '-q', '--tags'], cwd=dest)\n else:\n self.run_command(['fetch', '-q'], cwd=dest)\n # Then reset to wanted revision (maybe even origin/master)\n if rev_options:\n rev_options = self.check_rev_options(\n rev_options[0], dest, rev_options,\n )\n self.run_command(['reset', '--hard', '-q'] + rev_options, cwd=dest)\n #: update submodules\n self.update_submodules(dest)\n\n def obtain(self, dest):\n url, rev = self.get_url_rev()\n if rev:\n rev_options = [rev]\n rev_display = ' (to %s)' % rev\n else:\n rev_options = ['origin/master']\n rev_display = ''\n if self.check_destination(dest, url, rev_options, rev_display):\n logger.info(\n 'Cloning %s%s to %s', url, rev_display, display_path(dest),\n )\n self.run_command(['clone', '-q', url, dest])\n\n if rev:\n rev_options = self.check_rev_options(rev, dest, rev_options)\n # Only do a checkout if rev_options differs from HEAD\n if not self.check_version(dest, rev_options):\n self.run_command(\n ['checkout', '-q'] + rev_options,\n cwd=dest,\n )\n #: repo may contain submodules\n self.update_submodules(dest)\n\n def get_url(self, location):\n \"\"\"Return URL of the first remote encountered.\"\"\"\n remotes = self.run_command(\n ['config', '--get-regexp', r'remote\\..*\\.url'],\n show_stdout=False, cwd=location)\n remotes = remotes.splitlines()\n found_remote = remotes[0]\n for remote in remotes:\n if remote.startswith('remote.origin.url '):\n found_remote = remote\n break\n url = found_remote.split(' ')[1]\n return url.strip()\n\n def get_revision(self, location):\n current_rev = self.run_command(\n ['rev-parse', 'HEAD'], show_stdout=False, cwd=location)\n return current_rev.strip()\n\n def get_full_refs(self, location):\n \"\"\"Yields tuples of (commit, ref) for branches and tags\"\"\"\n output = self.run_command(['show-ref'],\n show_stdout=False, cwd=location)\n for line in output.strip().splitlines():\n commit, ref = line.split(' ', 1)\n yield commit.strip(), ref.strip()\n\n def is_ref_remote(self, ref):\n return ref.startswith('refs/remotes/')\n\n def is_ref_branch(self, ref):\n return ref.startswith('refs/heads/')\n\n def is_ref_tag(self, ref):\n return ref.startswith('refs/tags/')\n\n def is_ref_commit(self, ref):\n \"\"\"A ref is a commit sha if it is not anything else\"\"\"\n return not any((\n self.is_ref_remote(ref),\n self.is_ref_branch(ref),\n self.is_ref_tag(ref),\n ))\n\n # Should deprecate `get_refs` since it's ambiguous\n def get_refs(self, location):\n return self.get_short_refs(location)\n\n def get_short_refs(self, location):\n \"\"\"Return map of named refs (branches or tags) to commit hashes.\"\"\"\n rv = {}\n for commit, ref in self.get_full_refs(location):\n ref_name = None\n if self.is_ref_remote(ref):\n ref_name = ref[len('refs/remotes/'):]\n elif self.is_ref_branch(ref):\n ref_name = ref[len('refs/heads/'):]\n elif self.is_ref_tag(ref):\n ref_name = ref[len('refs/tags/'):]\n if ref_name is not None:\n rv[ref_name] = commit\n return rv\n\n def _get_subdirectory(self, location):\n \"\"\"Return the relative path of setup.py to the git repo root.\"\"\"\n # find the repo root\n git_dir = self.run_command(['rev-parse', '--git-dir'],\n show_stdout=False, cwd=location).strip()\n if not os.path.isabs(git_dir):\n git_dir = os.path.join(location, git_dir)\n root_dir = os.path.join(git_dir, '..')\n # find setup.py\n orig_location = location\n while not os.path.exists(os.path.join(location, 'setup.py')):\n last_location = location\n location = os.path.dirname(location)\n if location == last_location:\n # We've traversed up to the root of the filesystem without\n # finding setup.py\n logger.warning(\n \"Could not find setup.py for directory %s (tried all \"\n \"parent directories)\",\n orig_location,\n )\n return None\n # relative path of setup.py to repo root\n if samefile(root_dir, location):\n return None\n return os.path.relpath(location, root_dir)\n\n def get_src_requirement(self, dist, location):\n repo = self.get_url(location)\n if not repo.lower().startswith('git:'):\n repo = 'git+' + repo\n egg_project_name = dist.egg_name().split('-', 1)[0]\n if not repo:\n return None\n current_rev = self.get_revision(location)\n req = '%s@%s#egg=%s' % (repo, current_rev, egg_project_name)\n subdirectory = self._get_subdirectory(location)\n if subdirectory:\n req += '&subdirectory=' + subdirectory\n return req\n\n def get_url_rev(self):\n \"\"\"\n Prefixes stub URLs like 'user@hostname:user/repo.git' with 'ssh://'.\n That's required because although they use SSH they sometimes doesn't\n work with a ssh:// scheme (e.g. Github). But we need a scheme for\n parsing. Hence we remove it again afterwards and return it as a stub.\n \"\"\"\n if '://' not in self.url:\n assert 'file:' not in self.url\n self.url = self.url.replace('git+', 'git+ssh://')\n url, rev = super(Git, self).get_url_rev()\n url = url.replace('ssh://', '')\n else:\n url, rev = super(Git, self).get_url_rev()\n\n return url, rev\n\n def update_submodules(self, location):\n if not os.path.exists(os.path.join(location, '.gitmodules')):\n return\n self.run_command(\n ['submodule', 'update', '--init', '--recursive', '-q'],\n cwd=location,\n )\n\n @classmethod\n def controls_location(cls, location):\n if super(Git, cls).controls_location(location):\n return True\n try:\n r = cls().run_command(['rev-parse'],\n cwd=location,\n show_stdout=False,\n on_returncode='ignore')\n return not r\n except BadCommand:\n logger.debug(\"could not determine if %s is under git control \"\n \"because git is not available\", location)\n return False\n\n\nvcs.register(Git)\n", "path": "pip/vcs/git.py"}], "after_files": [{"content": "from __future__ import absolute_import\n\nimport logging\nimport tempfile\nimport os.path\n\nfrom pip.compat import samefile\nfrom pip.exceptions import BadCommand\nfrom pip._vendor.six.moves.urllib import parse as urllib_parse\nfrom pip._vendor.six.moves.urllib import request as urllib_request\nfrom pip._vendor.packaging.version import parse as parse_version\n\nfrom pip.utils import display_path, rmtree\nfrom pip.vcs import vcs, VersionControl\n\n\nurlsplit = urllib_parse.urlsplit\nurlunsplit = urllib_parse.urlunsplit\n\n\nlogger = logging.getLogger(__name__)\n\n\nclass Git(VersionControl):\n name = 'git'\n dirname = '.git'\n repo_name = 'clone'\n schemes = (\n 'git', 'git+http', 'git+https', 'git+ssh', 'git+git', 'git+file',\n )\n\n def __init__(self, url=None, *args, **kwargs):\n\n # Works around an apparent Git bug\n # (see http://article.gmane.org/gmane.comp.version-control.git/146500)\n if url:\n scheme, netloc, path, query, fragment = urlsplit(url)\n if scheme.endswith('file'):\n initial_slashes = path[:-len(path.lstrip('/'))]\n newpath = (\n initial_slashes +\n urllib_request.url2pathname(path)\n .replace('\\\\', '/').lstrip('/')\n )\n url = urlunsplit((scheme, netloc, newpath, query, fragment))\n after_plus = scheme.find('+') + 1\n url = scheme[:after_plus] + urlunsplit(\n (scheme[after_plus:], netloc, newpath, query, fragment),\n )\n\n super(Git, self).__init__(url, *args, **kwargs)\n\n def get_git_version(self):\n VERSION_PFX = 'git version '\n version = self.run_command(['version'], show_stdout=False)\n if version.startswith(VERSION_PFX):\n version = version[len(VERSION_PFX):].split()[0]\n else:\n version = ''\n # get first 3 positions of the git version becasue\n # on windows it is x.y.z.windows.t, and this parses as\n # LegacyVersion which always smaller than a Version.\n version = '.'.join(version.split('.')[:3])\n return parse_version(version)\n\n def export(self, location):\n \"\"\"Export the Git repository at the url to the destination location\"\"\"\n temp_dir = tempfile.mkdtemp('-export', 'pip-')\n self.unpack(temp_dir)\n try:\n if not location.endswith('/'):\n location = location + '/'\n self.run_command(\n ['checkout-index', '-a', '-f', '--prefix', location],\n show_stdout=False, cwd=temp_dir)\n finally:\n rmtree(temp_dir)\n\n def check_rev_options(self, rev, dest, rev_options):\n \"\"\"Check the revision options before checkout to compensate that tags\n and branches may need origin/ as a prefix.\n Returns the SHA1 of the branch or tag if found.\n \"\"\"\n revisions = self.get_short_refs(dest)\n\n origin_rev = 'origin/%s' % rev\n if origin_rev in revisions:\n # remote branch\n return [revisions[origin_rev]]\n elif rev in revisions:\n # a local tag or branch name\n return [revisions[rev]]\n else:\n logger.warning(\n \"Could not find a tag or branch '%s', assuming commit or ref\",\n rev,\n )\n return rev_options\n\n def check_version(self, dest, rev_options):\n \"\"\"\n Compare the current sha to the ref. ref may be a branch or tag name,\n but current rev will always point to a sha. This means that a branch\n or tag will never compare as True. So this ultimately only matches\n against exact shas.\n \"\"\"\n return self.get_revision(dest).startswith(rev_options[0])\n\n def switch(self, dest, url, rev_options):\n self.run_command(['config', 'remote.origin.url', url], cwd=dest)\n self.run_command(['checkout', '-q'] + rev_options, cwd=dest)\n\n self.update_submodules(dest)\n\n def update(self, dest, rev_options):\n # First fetch changes from the default remote\n if self.get_git_version() >= parse_version('1.9.0'):\n # fetch tags in addition to everything else\n self.run_command(['fetch', '-q', '--tags'], cwd=dest)\n else:\n self.run_command(['fetch', '-q'], cwd=dest)\n # Then reset to wanted revision (maybe even origin/master)\n if rev_options:\n rev_options = self.check_rev_options(\n rev_options[0], dest, rev_options,\n )\n self.run_command(['reset', '--hard', '-q'] + rev_options, cwd=dest)\n #: update submodules\n self.update_submodules(dest)\n\n def obtain(self, dest):\n url, rev = self.get_url_rev()\n if rev:\n rev_options = [rev]\n rev_display = ' (to %s)' % rev\n else:\n rev_options = ['origin/master']\n rev_display = ''\n if self.check_destination(dest, url, rev_options, rev_display):\n logger.info(\n 'Cloning %s%s to %s', url, rev_display, display_path(dest),\n )\n self.run_command(['clone', '-q', url, dest])\n\n if rev:\n rev_options = self.check_rev_options(rev, dest, rev_options)\n # Only do a checkout if rev_options differs from HEAD\n if not self.check_version(dest, rev_options):\n self.run_command(\n ['fetch', '-q', url] + rev_options,\n cwd=dest,\n )\n self.run_command(\n ['checkout', '-q', 'FETCH_HEAD'],\n cwd=dest,\n )\n\n #: repo may contain submodules\n self.update_submodules(dest)\n\n def get_url(self, location):\n \"\"\"Return URL of the first remote encountered.\"\"\"\n remotes = self.run_command(\n ['config', '--get-regexp', r'remote\\..*\\.url'],\n show_stdout=False, cwd=location)\n remotes = remotes.splitlines()\n found_remote = remotes[0]\n for remote in remotes:\n if remote.startswith('remote.origin.url '):\n found_remote = remote\n break\n url = found_remote.split(' ')[1]\n return url.strip()\n\n def get_revision(self, location):\n current_rev = self.run_command(\n ['rev-parse', 'HEAD'], show_stdout=False, cwd=location)\n return current_rev.strip()\n\n def get_full_refs(self, location):\n \"\"\"Yields tuples of (commit, ref) for branches and tags\"\"\"\n output = self.run_command(['show-ref'],\n show_stdout=False, cwd=location)\n for line in output.strip().splitlines():\n commit, ref = line.split(' ', 1)\n yield commit.strip(), ref.strip()\n\n def is_ref_remote(self, ref):\n return ref.startswith('refs/remotes/')\n\n def is_ref_branch(self, ref):\n return ref.startswith('refs/heads/')\n\n def is_ref_tag(self, ref):\n return ref.startswith('refs/tags/')\n\n def is_ref_commit(self, ref):\n \"\"\"A ref is a commit sha if it is not anything else\"\"\"\n return not any((\n self.is_ref_remote(ref),\n self.is_ref_branch(ref),\n self.is_ref_tag(ref),\n ))\n\n # Should deprecate `get_refs` since it's ambiguous\n def get_refs(self, location):\n return self.get_short_refs(location)\n\n def get_short_refs(self, location):\n \"\"\"Return map of named refs (branches or tags) to commit hashes.\"\"\"\n rv = {}\n for commit, ref in self.get_full_refs(location):\n ref_name = None\n if self.is_ref_remote(ref):\n ref_name = ref[len('refs/remotes/'):]\n elif self.is_ref_branch(ref):\n ref_name = ref[len('refs/heads/'):]\n elif self.is_ref_tag(ref):\n ref_name = ref[len('refs/tags/'):]\n if ref_name is not None:\n rv[ref_name] = commit\n return rv\n\n def _get_subdirectory(self, location):\n \"\"\"Return the relative path of setup.py to the git repo root.\"\"\"\n # find the repo root\n git_dir = self.run_command(['rev-parse', '--git-dir'],\n show_stdout=False, cwd=location).strip()\n if not os.path.isabs(git_dir):\n git_dir = os.path.join(location, git_dir)\n root_dir = os.path.join(git_dir, '..')\n # find setup.py\n orig_location = location\n while not os.path.exists(os.path.join(location, 'setup.py')):\n last_location = location\n location = os.path.dirname(location)\n if location == last_location:\n # We've traversed up to the root of the filesystem without\n # finding setup.py\n logger.warning(\n \"Could not find setup.py for directory %s (tried all \"\n \"parent directories)\",\n orig_location,\n )\n return None\n # relative path of setup.py to repo root\n if samefile(root_dir, location):\n return None\n return os.path.relpath(location, root_dir)\n\n def get_src_requirement(self, dist, location):\n repo = self.get_url(location)\n if not repo.lower().startswith('git:'):\n repo = 'git+' + repo\n egg_project_name = dist.egg_name().split('-', 1)[0]\n if not repo:\n return None\n current_rev = self.get_revision(location)\n req = '%s@%s#egg=%s' % (repo, current_rev, egg_project_name)\n subdirectory = self._get_subdirectory(location)\n if subdirectory:\n req += '&subdirectory=' + subdirectory\n return req\n\n def get_url_rev(self):\n \"\"\"\n Prefixes stub URLs like 'user@hostname:user/repo.git' with 'ssh://'.\n That's required because although they use SSH they sometimes doesn't\n work with a ssh:// scheme (e.g. Github). But we need a scheme for\n parsing. Hence we remove it again afterwards and return it as a stub.\n \"\"\"\n if '://' not in self.url:\n assert 'file:' not in self.url\n self.url = self.url.replace('git+', 'git+ssh://')\n url, rev = super(Git, self).get_url_rev()\n url = url.replace('ssh://', '')\n else:\n url, rev = super(Git, self).get_url_rev()\n\n return url, rev\n\n def update_submodules(self, location):\n if not os.path.exists(os.path.join(location, '.gitmodules')):\n return\n self.run_command(\n ['submodule', 'update', '--init', '--recursive', '-q'],\n cwd=location,\n )\n\n @classmethod\n def controls_location(cls, location):\n if super(Git, cls).controls_location(location):\n return True\n try:\n r = cls().run_command(['rev-parse'],\n cwd=location,\n show_stdout=False,\n on_returncode='ignore')\n return not r\n except BadCommand:\n logger.debug(\"could not determine if %s is under git control \"\n \"because git is not available\", location)\n return False\n\n\nvcs.register(Git)\n", "path": "pip/vcs/git.py"}]}
| 3,844 | 230 |
gh_patches_debug_16024
|
rasdani/github-patches
|
git_diff
|
mindsdb__mindsdb-2390
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Error when csv header has empty space
### Discussed in https://github.com/mindsdb/mindsdb/discussions/2343
<div type='discussions-op-text'>
<sup>Originally posted by **Ashok0** June 13, 2022</sup>
Hi,
I have a question regarding usage of imported data with MindsDB. I registered a MindsDB account and selected "Add Data" > "Import File" and uploaded some sample CSV data to a table. I can view the data just fine as shown in the following screencap: https://imgur.com/a/X6mrzHt
If I attempt to select an individual column i.e. 'sensitivity' with the following statement: **SELECT sensitivity FROM files.bedcheck**,
I receive the following error message: **Binder Error: Referenced column "sensitivity" not found in FROM clause! Candidate bindings: "df_table. sensitivity" LINE 1: SELECT sensitivity AS sensitivity**
Any assistance in how I can resolve this error would be greatly appreciated.
Thank you!</div>
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `mindsdb/integrations/handlers/file_handler/file_handler.py`
Content:
```
1 from io import BytesIO, StringIO
2 import os
3 import csv
4 import json
5 import codecs
6 import traceback
7 import tempfile
8 from urllib.parse import urlparse
9
10 import requests
11 import pandas as pd
12
13 from mindsdb_sql import parse_sql
14 from mindsdb_sql.parser.ast.base import ASTNode
15 from mindsdb_sql.parser.ast import DropTables, Select
16
17 from mindsdb.api.mysql.mysql_proxy.utilities.sql import query_df
18 from mindsdb.integrations.libs.base_handler import DatabaseHandler
19 from mindsdb.integrations.libs.response import (
20 HandlerStatusResponse as StatusResponse,
21 HandlerResponse as Response,
22 RESPONSE_TYPE
23 )
24
25
26 def clean_row(row):
27 n_row = []
28 for cell in row:
29 if str(cell) in ['', ' ', ' ', 'NaN', 'nan', 'NA']:
30 n_row.append(None)
31 else:
32 n_row.append(cell)
33
34 return n_row
35
36
37 class FileHandler(DatabaseHandler):
38 """
39 Handler for files
40 """
41 type = 'files'
42
43 def __init__(self, name=None, db_store=None, fs_store=None, connection_data=None, file_controller=None):
44 super().__init__(name)
45 self.parser = parse_sql
46 self.fs_store = fs_store
47 self.custom_parser = connection_data.get('custom_parser')
48 self.clean_rows = connection_data.get('clean_rows', True)
49 self.file_controller = file_controller
50
51 def connect(self, **kwargs):
52 return
53
54 def disconnect(self, **kwargs):
55 return
56
57 def check_connection(self) -> StatusResponse:
58 return StatusResponse(True)
59
60 def query(self, query: ASTNode) -> Response:
61 if type(query) == DropTables:
62 for table_identifier in query.tables:
63 if len(table_identifier.parts) == 2 and table_identifier.parts[0] != self.name:
64 return Response(
65 RESPONSE_TYPE.ERROR,
66 error_message=f"Can't delete table from database '{table_identifier.parts[0]}'"
67 )
68 table_name = table_identifier.parts[-1]
69 try:
70 self.file_controller.delete_file(table_name)
71 except Exception as e:
72 return Response(
73 RESPONSE_TYPE.ERROR,
74 error_message=f"Can't delete table '{table_name}': {e}"
75 )
76 return Response(RESPONSE_TYPE.OK)
77 elif type(query) == Select:
78 table_name = query.from_table.parts[-1]
79 file_path = self.file_controller.get_file_path(table_name, company_id=None)
80 df, _columns = self._handle_source(file_path, self.clean_rows, self.custom_parser)
81 result_df = query_df(df, query)
82 return Response(
83 RESPONSE_TYPE.TABLE,
84 data_frame=result_df
85 )
86 else:
87 return Response(
88 RESPONSE_TYPE.ERROR,
89 error_message="Only 'select' and 'drop' queries allowed for files"
90 )
91
92 def native_query(self, query: str) -> Response:
93 ast = self.parser(query, dialect='mindsdb')
94 return self.query(ast)
95
96 @staticmethod
97 def _handle_source(file_path, clean_rows=True, custom_parser=None):
98 # get file data io, format and dialect
99 data, fmt, dialect = FileHandler._get_data_io(file_path)
100 data.seek(0) # make sure we are at 0 in file pointer
101
102 if custom_parser:
103 header, file_data = custom_parser(data, fmt)
104
105 elif fmt == 'csv':
106 csv_reader = list(csv.reader(data, dialect))
107 header = csv_reader[0]
108 file_data = csv_reader[1:]
109
110 elif fmt in ['xlsx', 'xls']:
111 data.seek(0)
112 df = pd.read_excel(data)
113 header = df.columns.values.tolist()
114 file_data = df.values.tolist()
115
116 elif fmt == 'json':
117 data.seek(0)
118 json_doc = json.loads(data.read())
119 df = pd.json_normalize(json_doc, max_level=0)
120 header = df.columns.values.tolist()
121 file_data = df.values.tolist()
122
123 else:
124 raise ValueError('Could not load file into any format, supported formats are csv, json, xls, xlsx')
125
126 if clean_rows:
127 file_list_data = [clean_row(row) for row in file_data]
128 else:
129 file_list_data = file_data
130
131 col_map = dict((col, col) for col in header)
132 return pd.DataFrame(file_list_data, columns=header), col_map
133
134 @staticmethod
135 def _get_data_io(file_path):
136 """
137 This gets a file either url or local file and defiens what the format is as well as dialect
138 :param file: file path or url
139 :return: data_io, format, dialect
140 """
141
142 ############
143 # get file as io object
144 ############
145
146 # file_path = self._get_file_path()
147
148 data = BytesIO()
149
150 try:
151 with open(file_path, 'rb') as fp:
152 data = BytesIO(fp.read())
153 except Exception as e:
154 error = 'Could not load file, possible exception : {exception}'.format(exception=e)
155 print(error)
156 raise ValueError(error)
157
158 dialect = None
159
160 ############
161 # check for file type
162 ############
163
164 # try to guess if its an excel file
165 xlsx_sig = b'\x50\x4B\x05\06'
166 # xlsx_sig2 = b'\x50\x4B\x03\x04'
167 xls_sig = b'\x09\x08\x10\x00\x00\x06\x05\x00'
168
169 # different whence, offset, size for different types
170 excel_meta = [('xls', 0, 512, 8), ('xlsx', 2, -22, 4)]
171
172 for filename, whence, offset, size in excel_meta:
173
174 try:
175 data.seek(offset, whence) # Seek to the offset.
176 bytes = data.read(size) # Capture the specified number of bytes.
177 data.seek(0)
178 codecs.getencoder('hex')(bytes)
179
180 if bytes == xls_sig:
181 return data, 'xls', dialect
182 elif bytes == xlsx_sig:
183 return data, 'xlsx', dialect
184
185 except Exception:
186 data.seek(0)
187
188 # if not excel it can be a json file or a CSV, convert from binary to stringio
189
190 byte_str = data.read()
191 # Move it to StringIO
192 try:
193 # Handle Microsoft's BOM "special" UTF-8 encoding
194 if byte_str.startswith(codecs.BOM_UTF8):
195 data = StringIO(byte_str.decode('utf-8-sig'))
196 else:
197 data = StringIO(byte_str.decode('utf-8'))
198
199 except Exception:
200 print(traceback.format_exc())
201 print('Could not load into string')
202
203 # see if its JSON
204 buffer = data.read(100)
205 data.seek(0)
206 text = buffer.strip()
207 # analyze first n characters
208 if len(text) > 0:
209 text = text.strip()
210 # it it looks like a json, then try to parse it
211 if text.startswith('{') or text.startswith('['):
212 try:
213 json.loads(data.read())
214 data.seek(0)
215 return data, 'json', dialect
216 except Exception:
217 data.seek(0)
218 return data, None, dialect
219
220 # lets try to figure out if its a csv
221 try:
222 dialect = FileHandler._get_csv_dialect(file_path)
223 if dialect:
224 return data, 'csv', dialect
225 return data, None, dialect
226 except Exception:
227 data.seek(0)
228 print('Could not detect format for this file')
229 print(traceback.format_exc())
230 # No file type identified
231 return data, None, dialect
232
233 @staticmethod
234 def _get_file_path(path) -> str:
235 try:
236 is_url = urlparse(path).scheme in ('http', 'https')
237 except Exception:
238 is_url = False
239 if is_url:
240 path = FileHandler._fetch_url(path)
241 return path
242
243 @staticmethod
244 def _get_csv_dialect(file_path) -> csv.Dialect:
245 with open(file_path, 'rt') as f:
246 try:
247 accepted_csv_delimiters = [',', '\t', ';']
248 dialect = csv.Sniffer().sniff(f.read(128 * 1024), delimiters=accepted_csv_delimiters)
249 except csv.Error:
250 dialect = None
251 return dialect
252
253 @staticmethod
254 def _fetch_url(url: str) -> str:
255 temp_dir = tempfile.mkdtemp(prefix='mindsdb_file_url_')
256 try:
257 r = requests.get(url, stream=True)
258 if r.status_code == 200:
259 with open(os.path.join(temp_dir, 'file'), 'wb') as f:
260 for chunk in r:
261 f.write(chunk)
262 else:
263 raise Exception(f'Responce status code is {r.status_code}')
264 except Exception as e:
265 print(f'Error during getting {url}')
266 print(e)
267 raise
268 return os.path.join(temp_dir, 'file')
269
270 def get_tables(self) -> Response:
271 """
272 List all files
273 """
274 files_meta = self.file_controller.get_files()
275 data = [{
276 'TABLE_NAME': x['name'],
277 'TABLE_ROWS': x['row_count']
278 } for x in files_meta]
279 return Response(
280 RESPONSE_TYPE.TABLE,
281 data_frame=pd.DataFrame(data)
282 )
283
284 def get_columns(self, table_name) -> Response:
285 file_meta = self.file_controller.get_file_meta(table_name)
286 result = Response(
287 RESPONSE_TYPE.TABLE,
288 data_frame=pd.DataFrame([
289 {
290 'Field': x,
291 'Type': 'str'
292 } for x in file_meta['columns']
293 ])
294 )
295 return result
296
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/mindsdb/integrations/handlers/file_handler/file_handler.py b/mindsdb/integrations/handlers/file_handler/file_handler.py
--- a/mindsdb/integrations/handlers/file_handler/file_handler.py
+++ b/mindsdb/integrations/handlers/file_handler/file_handler.py
@@ -128,6 +128,7 @@
else:
file_list_data = file_data
+ header = [x.strip() for x in header]
col_map = dict((col, col) for col in header)
return pd.DataFrame(file_list_data, columns=header), col_map
@@ -287,7 +288,7 @@
RESPONSE_TYPE.TABLE,
data_frame=pd.DataFrame([
{
- 'Field': x,
+ 'Field': x.strip(),
'Type': 'str'
} for x in file_meta['columns']
])
|
{"golden_diff": "diff --git a/mindsdb/integrations/handlers/file_handler/file_handler.py b/mindsdb/integrations/handlers/file_handler/file_handler.py\n--- a/mindsdb/integrations/handlers/file_handler/file_handler.py\n+++ b/mindsdb/integrations/handlers/file_handler/file_handler.py\n@@ -128,6 +128,7 @@\n else:\n file_list_data = file_data\n \n+ header = [x.strip() for x in header]\n col_map = dict((col, col) for col in header)\n return pd.DataFrame(file_list_data, columns=header), col_map\n \n@@ -287,7 +288,7 @@\n RESPONSE_TYPE.TABLE,\n data_frame=pd.DataFrame([\n {\n- 'Field': x,\n+ 'Field': x.strip(),\n 'Type': 'str'\n } for x in file_meta['columns']\n ])\n", "issue": "Error when csv header has empty space\n### Discussed in https://github.com/mindsdb/mindsdb/discussions/2343\r\n\r\n<div type='discussions-op-text'>\r\n\r\n<sup>Originally posted by **Ashok0** June 13, 2022</sup>\r\nHi,\r\n\r\nI have a question regarding usage of imported data with MindsDB. I registered a MindsDB account and selected \"Add Data\" > \"Import File\" and uploaded some sample CSV data to a table. I can view the data just fine as shown in the following screencap: https://imgur.com/a/X6mrzHt\r\n\r\nIf I attempt to select an individual column i.e. 'sensitivity' with the following statement: **SELECT sensitivity FROM files.bedcheck**, \r\nI receive the following error message: **Binder Error: Referenced column \"sensitivity\" not found in FROM clause! Candidate bindings: \"df_table. sensitivity\" LINE 1: SELECT sensitivity AS sensitivity**\r\n\r\nAny assistance in how I can resolve this error would be greatly appreciated. \r\n\r\nThank you!</div>\n", "before_files": [{"content": "from io import BytesIO, StringIO\nimport os\nimport csv\nimport json\nimport codecs\nimport traceback\nimport tempfile\nfrom urllib.parse import urlparse\n\nimport requests\nimport pandas as pd\n\nfrom mindsdb_sql import parse_sql\nfrom mindsdb_sql.parser.ast.base import ASTNode\nfrom mindsdb_sql.parser.ast import DropTables, Select\n\nfrom mindsdb.api.mysql.mysql_proxy.utilities.sql import query_df\nfrom mindsdb.integrations.libs.base_handler import DatabaseHandler\nfrom mindsdb.integrations.libs.response import (\n HandlerStatusResponse as StatusResponse,\n HandlerResponse as Response,\n RESPONSE_TYPE\n)\n\n\ndef clean_row(row):\n n_row = []\n for cell in row:\n if str(cell) in ['', ' ', ' ', 'NaN', 'nan', 'NA']:\n n_row.append(None)\n else:\n n_row.append(cell)\n\n return n_row\n\n\nclass FileHandler(DatabaseHandler):\n \"\"\"\n Handler for files\n \"\"\"\n type = 'files'\n\n def __init__(self, name=None, db_store=None, fs_store=None, connection_data=None, file_controller=None):\n super().__init__(name)\n self.parser = parse_sql\n self.fs_store = fs_store\n self.custom_parser = connection_data.get('custom_parser')\n self.clean_rows = connection_data.get('clean_rows', True)\n self.file_controller = file_controller\n\n def connect(self, **kwargs):\n return\n\n def disconnect(self, **kwargs):\n return\n\n def check_connection(self) -> StatusResponse:\n return StatusResponse(True)\n\n def query(self, query: ASTNode) -> Response:\n if type(query) == DropTables:\n for table_identifier in query.tables:\n if len(table_identifier.parts) == 2 and table_identifier.parts[0] != self.name:\n return Response(\n RESPONSE_TYPE.ERROR,\n error_message=f\"Can't delete table from database '{table_identifier.parts[0]}'\"\n )\n table_name = table_identifier.parts[-1]\n try:\n self.file_controller.delete_file(table_name)\n except Exception as e:\n return Response(\n RESPONSE_TYPE.ERROR,\n error_message=f\"Can't delete table '{table_name}': {e}\"\n )\n return Response(RESPONSE_TYPE.OK)\n elif type(query) == Select:\n table_name = query.from_table.parts[-1]\n file_path = self.file_controller.get_file_path(table_name, company_id=None)\n df, _columns = self._handle_source(file_path, self.clean_rows, self.custom_parser)\n result_df = query_df(df, query)\n return Response(\n RESPONSE_TYPE.TABLE,\n data_frame=result_df\n )\n else:\n return Response(\n RESPONSE_TYPE.ERROR,\n error_message=\"Only 'select' and 'drop' queries allowed for files\"\n )\n\n def native_query(self, query: str) -> Response:\n ast = self.parser(query, dialect='mindsdb')\n return self.query(ast)\n\n @staticmethod\n def _handle_source(file_path, clean_rows=True, custom_parser=None):\n # get file data io, format and dialect\n data, fmt, dialect = FileHandler._get_data_io(file_path)\n data.seek(0) # make sure we are at 0 in file pointer\n\n if custom_parser:\n header, file_data = custom_parser(data, fmt)\n\n elif fmt == 'csv':\n csv_reader = list(csv.reader(data, dialect))\n header = csv_reader[0]\n file_data = csv_reader[1:]\n\n elif fmt in ['xlsx', 'xls']:\n data.seek(0)\n df = pd.read_excel(data)\n header = df.columns.values.tolist()\n file_data = df.values.tolist()\n\n elif fmt == 'json':\n data.seek(0)\n json_doc = json.loads(data.read())\n df = pd.json_normalize(json_doc, max_level=0)\n header = df.columns.values.tolist()\n file_data = df.values.tolist()\n\n else:\n raise ValueError('Could not load file into any format, supported formats are csv, json, xls, xlsx')\n\n if clean_rows:\n file_list_data = [clean_row(row) for row in file_data]\n else:\n file_list_data = file_data\n\n col_map = dict((col, col) for col in header)\n return pd.DataFrame(file_list_data, columns=header), col_map\n\n @staticmethod\n def _get_data_io(file_path):\n \"\"\"\n This gets a file either url or local file and defiens what the format is as well as dialect\n :param file: file path or url\n :return: data_io, format, dialect\n \"\"\"\n\n ############\n # get file as io object\n ############\n\n # file_path = self._get_file_path()\n\n data = BytesIO()\n\n try:\n with open(file_path, 'rb') as fp:\n data = BytesIO(fp.read())\n except Exception as e:\n error = 'Could not load file, possible exception : {exception}'.format(exception=e)\n print(error)\n raise ValueError(error)\n\n dialect = None\n\n ############\n # check for file type\n ############\n\n # try to guess if its an excel file\n xlsx_sig = b'\\x50\\x4B\\x05\\06'\n # xlsx_sig2 = b'\\x50\\x4B\\x03\\x04'\n xls_sig = b'\\x09\\x08\\x10\\x00\\x00\\x06\\x05\\x00'\n\n # different whence, offset, size for different types\n excel_meta = [('xls', 0, 512, 8), ('xlsx', 2, -22, 4)]\n\n for filename, whence, offset, size in excel_meta:\n\n try:\n data.seek(offset, whence) # Seek to the offset.\n bytes = data.read(size) # Capture the specified number of bytes.\n data.seek(0)\n codecs.getencoder('hex')(bytes)\n\n if bytes == xls_sig:\n return data, 'xls', dialect\n elif bytes == xlsx_sig:\n return data, 'xlsx', dialect\n\n except Exception:\n data.seek(0)\n\n # if not excel it can be a json file or a CSV, convert from binary to stringio\n\n byte_str = data.read()\n # Move it to StringIO\n try:\n # Handle Microsoft's BOM \"special\" UTF-8 encoding\n if byte_str.startswith(codecs.BOM_UTF8):\n data = StringIO(byte_str.decode('utf-8-sig'))\n else:\n data = StringIO(byte_str.decode('utf-8'))\n\n except Exception:\n print(traceback.format_exc())\n print('Could not load into string')\n\n # see if its JSON\n buffer = data.read(100)\n data.seek(0)\n text = buffer.strip()\n # analyze first n characters\n if len(text) > 0:\n text = text.strip()\n # it it looks like a json, then try to parse it\n if text.startswith('{') or text.startswith('['):\n try:\n json.loads(data.read())\n data.seek(0)\n return data, 'json', dialect\n except Exception:\n data.seek(0)\n return data, None, dialect\n\n # lets try to figure out if its a csv\n try:\n dialect = FileHandler._get_csv_dialect(file_path)\n if dialect:\n return data, 'csv', dialect\n return data, None, dialect\n except Exception:\n data.seek(0)\n print('Could not detect format for this file')\n print(traceback.format_exc())\n # No file type identified\n return data, None, dialect\n\n @staticmethod\n def _get_file_path(path) -> str:\n try:\n is_url = urlparse(path).scheme in ('http', 'https')\n except Exception:\n is_url = False\n if is_url:\n path = FileHandler._fetch_url(path)\n return path\n\n @staticmethod\n def _get_csv_dialect(file_path) -> csv.Dialect:\n with open(file_path, 'rt') as f:\n try:\n accepted_csv_delimiters = [',', '\\t', ';']\n dialect = csv.Sniffer().sniff(f.read(128 * 1024), delimiters=accepted_csv_delimiters)\n except csv.Error:\n dialect = None\n return dialect\n\n @staticmethod\n def _fetch_url(url: str) -> str:\n temp_dir = tempfile.mkdtemp(prefix='mindsdb_file_url_')\n try:\n r = requests.get(url, stream=True)\n if r.status_code == 200:\n with open(os.path.join(temp_dir, 'file'), 'wb') as f:\n for chunk in r:\n f.write(chunk)\n else:\n raise Exception(f'Responce status code is {r.status_code}')\n except Exception as e:\n print(f'Error during getting {url}')\n print(e)\n raise\n return os.path.join(temp_dir, 'file')\n\n def get_tables(self) -> Response:\n \"\"\"\n List all files\n \"\"\"\n files_meta = self.file_controller.get_files()\n data = [{\n 'TABLE_NAME': x['name'],\n 'TABLE_ROWS': x['row_count']\n } for x in files_meta]\n return Response(\n RESPONSE_TYPE.TABLE,\n data_frame=pd.DataFrame(data)\n )\n\n def get_columns(self, table_name) -> Response:\n file_meta = self.file_controller.get_file_meta(table_name)\n result = Response(\n RESPONSE_TYPE.TABLE,\n data_frame=pd.DataFrame([\n {\n 'Field': x,\n 'Type': 'str'\n } for x in file_meta['columns']\n ])\n )\n return result\n", "path": "mindsdb/integrations/handlers/file_handler/file_handler.py"}], "after_files": [{"content": "from io import BytesIO, StringIO\nimport os\nimport csv\nimport json\nimport codecs\nimport traceback\nimport tempfile\nfrom urllib.parse import urlparse\n\nimport requests\nimport pandas as pd\n\nfrom mindsdb_sql import parse_sql\nfrom mindsdb_sql.parser.ast.base import ASTNode\nfrom mindsdb_sql.parser.ast import DropTables, Select\n\nfrom mindsdb.api.mysql.mysql_proxy.utilities.sql import query_df\nfrom mindsdb.integrations.libs.base_handler import DatabaseHandler\nfrom mindsdb.integrations.libs.response import (\n HandlerStatusResponse as StatusResponse,\n HandlerResponse as Response,\n RESPONSE_TYPE\n)\n\n\ndef clean_row(row):\n n_row = []\n for cell in row:\n if str(cell) in ['', ' ', ' ', 'NaN', 'nan', 'NA']:\n n_row.append(None)\n else:\n n_row.append(cell)\n\n return n_row\n\n\nclass FileHandler(DatabaseHandler):\n \"\"\"\n Handler for files\n \"\"\"\n type = 'files'\n\n def __init__(self, name=None, db_store=None, fs_store=None, connection_data=None, file_controller=None):\n super().__init__(name)\n self.parser = parse_sql\n self.fs_store = fs_store\n self.custom_parser = connection_data.get('custom_parser')\n self.clean_rows = connection_data.get('clean_rows', True)\n self.file_controller = file_controller\n\n def connect(self, **kwargs):\n return\n\n def disconnect(self, **kwargs):\n return\n\n def check_connection(self) -> StatusResponse:\n return StatusResponse(True)\n\n def query(self, query: ASTNode) -> Response:\n if type(query) == DropTables:\n for table_identifier in query.tables:\n if len(table_identifier.parts) == 2 and table_identifier.parts[0] != self.name:\n return Response(\n RESPONSE_TYPE.ERROR,\n error_message=f\"Can't delete table from database '{table_identifier.parts[0]}'\"\n )\n table_name = table_identifier.parts[-1]\n try:\n self.file_controller.delete_file(table_name)\n except Exception as e:\n return Response(\n RESPONSE_TYPE.ERROR,\n error_message=f\"Can't delete table '{table_name}': {e}\"\n )\n return Response(RESPONSE_TYPE.OK)\n elif type(query) == Select:\n table_name = query.from_table.parts[-1]\n file_path = self.file_controller.get_file_path(table_name, company_id=None)\n df, _columns = self._handle_source(file_path, self.clean_rows, self.custom_parser)\n result_df = query_df(df, query)\n return Response(\n RESPONSE_TYPE.TABLE,\n data_frame=result_df\n )\n else:\n return Response(\n RESPONSE_TYPE.ERROR,\n error_message=\"Only 'select' and 'drop' queries allowed for files\"\n )\n\n def native_query(self, query: str) -> Response:\n ast = self.parser(query, dialect='mindsdb')\n return self.query(ast)\n\n @staticmethod\n def _handle_source(file_path, clean_rows=True, custom_parser=None):\n # get file data io, format and dialect\n data, fmt, dialect = FileHandler._get_data_io(file_path)\n data.seek(0) # make sure we are at 0 in file pointer\n\n if custom_parser:\n header, file_data = custom_parser(data, fmt)\n\n elif fmt == 'csv':\n csv_reader = list(csv.reader(data, dialect))\n header = csv_reader[0]\n file_data = csv_reader[1:]\n\n elif fmt in ['xlsx', 'xls']:\n data.seek(0)\n df = pd.read_excel(data)\n header = df.columns.values.tolist()\n file_data = df.values.tolist()\n\n elif fmt == 'json':\n data.seek(0)\n json_doc = json.loads(data.read())\n df = pd.json_normalize(json_doc, max_level=0)\n header = df.columns.values.tolist()\n file_data = df.values.tolist()\n\n else:\n raise ValueError('Could not load file into any format, supported formats are csv, json, xls, xlsx')\n\n if clean_rows:\n file_list_data = [clean_row(row) for row in file_data]\n else:\n file_list_data = file_data\n\n header = [x.strip() for x in header]\n col_map = dict((col, col) for col in header)\n return pd.DataFrame(file_list_data, columns=header), col_map\n\n @staticmethod\n def _get_data_io(file_path):\n \"\"\"\n This gets a file either url or local file and defiens what the format is as well as dialect\n :param file: file path or url\n :return: data_io, format, dialect\n \"\"\"\n\n ############\n # get file as io object\n ############\n\n # file_path = self._get_file_path()\n\n data = BytesIO()\n\n try:\n with open(file_path, 'rb') as fp:\n data = BytesIO(fp.read())\n except Exception as e:\n error = 'Could not load file, possible exception : {exception}'.format(exception=e)\n print(error)\n raise ValueError(error)\n\n dialect = None\n\n ############\n # check for file type\n ############\n\n # try to guess if its an excel file\n xlsx_sig = b'\\x50\\x4B\\x05\\06'\n # xlsx_sig2 = b'\\x50\\x4B\\x03\\x04'\n xls_sig = b'\\x09\\x08\\x10\\x00\\x00\\x06\\x05\\x00'\n\n # different whence, offset, size for different types\n excel_meta = [('xls', 0, 512, 8), ('xlsx', 2, -22, 4)]\n\n for filename, whence, offset, size in excel_meta:\n\n try:\n data.seek(offset, whence) # Seek to the offset.\n bytes = data.read(size) # Capture the specified number of bytes.\n data.seek(0)\n codecs.getencoder('hex')(bytes)\n\n if bytes == xls_sig:\n return data, 'xls', dialect\n elif bytes == xlsx_sig:\n return data, 'xlsx', dialect\n\n except Exception:\n data.seek(0)\n\n # if not excel it can be a json file or a CSV, convert from binary to stringio\n\n byte_str = data.read()\n # Move it to StringIO\n try:\n # Handle Microsoft's BOM \"special\" UTF-8 encoding\n if byte_str.startswith(codecs.BOM_UTF8):\n data = StringIO(byte_str.decode('utf-8-sig'))\n else:\n data = StringIO(byte_str.decode('utf-8'))\n\n except Exception:\n print(traceback.format_exc())\n print('Could not load into string')\n\n # see if its JSON\n buffer = data.read(100)\n data.seek(0)\n text = buffer.strip()\n # analyze first n characters\n if len(text) > 0:\n text = text.strip()\n # it it looks like a json, then try to parse it\n if text.startswith('{') or text.startswith('['):\n try:\n json.loads(data.read())\n data.seek(0)\n return data, 'json', dialect\n except Exception:\n data.seek(0)\n return data, None, dialect\n\n # lets try to figure out if its a csv\n try:\n dialect = FileHandler._get_csv_dialect(file_path)\n if dialect:\n return data, 'csv', dialect\n return data, None, dialect\n except Exception:\n data.seek(0)\n print('Could not detect format for this file')\n print(traceback.format_exc())\n # No file type identified\n return data, None, dialect\n\n @staticmethod\n def _get_file_path(path) -> str:\n try:\n is_url = urlparse(path).scheme in ('http', 'https')\n except Exception:\n is_url = False\n if is_url:\n path = FileHandler._fetch_url(path)\n return path\n\n @staticmethod\n def _get_csv_dialect(file_path) -> csv.Dialect:\n with open(file_path, 'rt') as f:\n try:\n accepted_csv_delimiters = [',', '\\t', ';']\n dialect = csv.Sniffer().sniff(f.read(128 * 1024), delimiters=accepted_csv_delimiters)\n except csv.Error:\n dialect = None\n return dialect\n\n @staticmethod\n def _fetch_url(url: str) -> str:\n temp_dir = tempfile.mkdtemp(prefix='mindsdb_file_url_')\n try:\n r = requests.get(url, stream=True)\n if r.status_code == 200:\n with open(os.path.join(temp_dir, 'file'), 'wb') as f:\n for chunk in r:\n f.write(chunk)\n else:\n raise Exception(f'Responce status code is {r.status_code}')\n except Exception as e:\n print(f'Error during getting {url}')\n print(e)\n raise\n return os.path.join(temp_dir, 'file')\n\n def get_tables(self) -> Response:\n \"\"\"\n List all files\n \"\"\"\n files_meta = self.file_controller.get_files()\n data = [{\n 'TABLE_NAME': x['name'],\n 'TABLE_ROWS': x['row_count']\n } for x in files_meta]\n return Response(\n RESPONSE_TYPE.TABLE,\n data_frame=pd.DataFrame(data)\n )\n\n def get_columns(self, table_name) -> Response:\n file_meta = self.file_controller.get_file_meta(table_name)\n result = Response(\n RESPONSE_TYPE.TABLE,\n data_frame=pd.DataFrame([\n {\n 'Field': x.strip(),\n 'Type': 'str'\n } for x in file_meta['columns']\n ])\n )\n return result\n", "path": "mindsdb/integrations/handlers/file_handler/file_handler.py"}]}
| 3,408 | 197 |
gh_patches_debug_2174
|
rasdani/github-patches
|
git_diff
|
fedora-infra__bodhi-1042
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
GET on /masher/ errors with a 404 response
GET on `/masher` works, but GET on `/masher/` returns an HTTP 404 error code. We should add a route to allow the trailing slash on this URL.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `bodhi/server/__init__.py`
Content:
```
1 # This program is free software; you can redistribute it and/or
2 # modify it under the terms of the GNU General Public License
3 # as published by the Free Software Foundation; either version 2
4 # of the License, or (at your option) any later version.
5 #
6 # This program is distributed in the hope that it will be useful,
7 # but WITHOUT ANY WARRANTY; without even the implied warranty of
8 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
9 # GNU General Public License for more details.
10 #
11 # You should have received a copy of the GNU General Public License
12 # along with this program; if not, write to the Free Software
13 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
14
15 from collections import defaultdict
16 from dogpile.cache import make_region
17 from munch import munchify
18 from sqlalchemy import engine_from_config
19 from sqlalchemy.orm import scoped_session, sessionmaker
20 from zope.sqlalchemy import ZopeTransactionExtension
21
22 from pyramid.settings import asbool
23 from pyramid.security import unauthenticated_userid
24 from pyramid.config import Configurator
25 from pyramid.authentication import AuthTktAuthenticationPolicy
26 from pyramid.authorization import ACLAuthorizationPolicy
27 from pyramid.renderers import JSONP
28 from pyramid.exceptions import HTTPForbidden
29
30 from . import buildsys
31
32 import logging
33
34 log = logging.getLogger(__name__)
35
36
37 # TODO -- someday move this externally to "fedora_flavored_markdown"
38 from bodhi.server import ffmarkdown
39 ffmarkdown.inject()
40
41 #
42 # Request methods
43 #
44
45 def get_dbsession(request):
46 engine = engine_from_config(request.registry.settings, 'sqlalchemy.')
47 Sess = scoped_session(sessionmaker(extension=ZopeTransactionExtension()))
48 Sess.configure(bind=engine)
49 session = Sess()
50
51 def cleanup(request):
52 ## No need to do rollback/commit ourselves. the zope transaction
53 ## manager takes care of that for us...
54 #if request.exception is not None:
55 # session.rollback()
56 #else:
57 # session.commit()
58 ## However, we may still want to explicitly close the session we opened
59 #log.debug("Closing session at the end of a request.")
60 session.close()
61
62 request.add_finished_callback(cleanup)
63
64 return session
65
66
67 def get_cacheregion(request):
68 region = make_region()
69 region.configure_from_config(request.registry.settings, "dogpile.cache.")
70 return region
71
72
73 def get_user(request):
74 from bodhi.server.models import User
75 userid = unauthenticated_userid(request)
76 if userid is not None:
77 user = request.db.query(User).filter_by(name=unicode(userid)).first()
78 # Why munch? https://github.com/fedora-infra/bodhi/issues/473
79 return munchify(user.__json__(request=request))
80
81
82 def groupfinder(userid, request):
83 from bodhi.server.models import User
84 if request.user:
85 user = User.get(request.user.name, request.db)
86 return ['group:' + group.name for group in user.groups]
87
88
89 def get_koji(request):
90 return buildsys.get_session()
91
92
93 def get_buildinfo(request):
94 """
95 A per-request cache populated by the validators and shared with the views
96 to store frequently used package-specific data, like build tags and ACLs.
97 """
98 return defaultdict(dict)
99
100
101 def get_releases(request):
102 from bodhi.server.models import Release
103 return Release.all_releases(request.db)
104
105 #
106 # Cornice filters
107 #
108
109 def exception_filter(response, request):
110 """Log exceptions that get thrown up to cornice"""
111 if isinstance(response, Exception):
112 log.exception('Unhandled exception raised: %r' % response)
113 return response
114
115 from cornice.validators import DEFAULT_FILTERS
116 DEFAULT_FILTERS.insert(0, exception_filter)
117
118
119 #
120 # Bodhi initialization
121 #
122
123 def main(global_config, testing=None, session=None, **settings):
124 """ This function returns a WSGI application """
125 # Setup our buildsystem
126 buildsys.setup_buildsystem(settings)
127
128 # Sessions & Caching
129 from pyramid.session import SignedCookieSessionFactory
130 session_factory = SignedCookieSessionFactory(settings['session.secret'])
131
132 # Construct a list of all groups we're interested in
133 default = ' '.join([settings.get(key, '') for key in [
134 'important_groups',
135 'admin_packager_groups',
136 'mandatory_packager_groups',
137 'admin_groups',
138 ]])
139 # pyramid_fas_openid looks for this setting
140 settings['openid.groups'] = settings.get('openid.groups', default).split()
141
142 config = Configurator(settings=settings, session_factory=session_factory)
143
144 # Plugins
145 config.include('pyramid_mako')
146 config.include('cornice')
147
148 # Lazy-loaded memoized request properties
149 if session:
150 config.add_request_method(lambda _: session, 'db', reify=True)
151 else:
152 config.add_request_method(get_dbsession, 'db', reify=True)
153
154 config.add_request_method(get_user, 'user', reify=True)
155 config.add_request_method(get_koji, 'koji', reify=True)
156 config.add_request_method(get_cacheregion, 'cache', reify=True)
157 config.add_request_method(get_buildinfo, 'buildinfo', reify=True)
158 config.add_request_method(get_releases, 'releases', reify=True)
159
160 # Templating
161 config.add_mako_renderer('.html', settings_prefix='mako.')
162 config.add_static_view('static', 'bodhi:server/static')
163
164 from bodhi.server.renderers import rss, jpeg
165 config.add_renderer('rss', rss)
166 config.add_renderer('jpeg', jpeg)
167 config.add_renderer('jsonp', JSONP(param_name='callback'))
168
169 # i18n
170 config.add_translation_dirs('bodhi:server/locale/')
171
172 # Authentication & Authorization
173 if testing:
174 # use a permissive security policy while running unit tests
175 config.testing_securitypolicy(userid=testing, permissive=True)
176 else:
177 config.set_authentication_policy(AuthTktAuthenticationPolicy(
178 settings['authtkt.secret'],
179 callback=groupfinder,
180 secure=asbool(settings['authtkt.secure']),
181 hashalg='sha512'))
182 config.set_authorization_policy(ACLAuthorizationPolicy())
183
184 # Frontpage
185 config.add_route('home', '/')
186
187 # Views for creating new objects
188 config.add_route('new_update', '/updates/new')
189 config.add_route('new_override', '/overrides/new')
190 config.add_route('new_stack', '/stacks/new')
191
192 # Metrics
193 config.add_route('metrics', '/metrics')
194 config.add_route('masher_status', '/masher')
195
196 # Auto-completion search
197 config.add_route('search_packages', '/search/packages')
198 config.add_route('latest_candidates', '/latest_candidates')
199 config.add_route('latest_builds', '/latest_builds')
200
201 config.add_route('captcha_image', '/captcha/{cipherkey}/')
202
203 # pyramid.openid
204 config.add_route('login', '/login')
205 config.add_view('bodhi.server.security.login', route_name='login')
206 config.add_view('bodhi.server.security.login', context=HTTPForbidden)
207 config.add_route('logout', '/logout')
208 config.add_view('bodhi.server.security.logout', route_name='logout')
209 config.add_route('verify_openid', pattern='/dologin.html')
210 config.add_view('pyramid_fas_openid.verify_openid', route_name='verify_openid')
211
212 config.add_route('api_version', '/api_version')
213
214 # The only user preference we have.
215 config.add_route('popup_toggle', '/popup_toggle')
216
217 config.scan('bodhi.server.views')
218 config.scan('bodhi.server.services')
219 config.scan('bodhi.server.captcha')
220 config.scan('bodhi.server.events')
221
222 return config.make_wsgi_app()
223
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/bodhi/server/__init__.py b/bodhi/server/__init__.py
--- a/bodhi/server/__init__.py
+++ b/bodhi/server/__init__.py
@@ -191,7 +191,7 @@
# Metrics
config.add_route('metrics', '/metrics')
- config.add_route('masher_status', '/masher')
+ config.add_route('masher_status', '/masher/')
# Auto-completion search
config.add_route('search_packages', '/search/packages')
|
{"golden_diff": "diff --git a/bodhi/server/__init__.py b/bodhi/server/__init__.py\n--- a/bodhi/server/__init__.py\n+++ b/bodhi/server/__init__.py\n@@ -191,7 +191,7 @@\n \n # Metrics\n config.add_route('metrics', '/metrics')\n- config.add_route('masher_status', '/masher')\n+ config.add_route('masher_status', '/masher/')\n \n # Auto-completion search\n config.add_route('search_packages', '/search/packages')\n", "issue": "GET on /masher/ errors with a 404 response\nGET on `/masher` works, but GET on `/masher/` returns an HTTP 404 error code. We should add a route to allow the trailing slash on this URL.\n\n", "before_files": [{"content": "# This program is free software; you can redistribute it and/or\n# modify it under the terms of the GNU General Public License\n# as published by the Free Software Foundation; either version 2\n# of the License, or (at your option) any later version.\n#\n# This program is distributed in the hope that it will be useful,\n# but WITHOUT ANY WARRANTY; without even the implied warranty of\n# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n# GNU General Public License for more details.\n#\n# You should have received a copy of the GNU General Public License\n# along with this program; if not, write to the Free Software\n# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.\n\nfrom collections import defaultdict\nfrom dogpile.cache import make_region\nfrom munch import munchify\nfrom sqlalchemy import engine_from_config\nfrom sqlalchemy.orm import scoped_session, sessionmaker\nfrom zope.sqlalchemy import ZopeTransactionExtension\n\nfrom pyramid.settings import asbool\nfrom pyramid.security import unauthenticated_userid\nfrom pyramid.config import Configurator\nfrom pyramid.authentication import AuthTktAuthenticationPolicy\nfrom pyramid.authorization import ACLAuthorizationPolicy\nfrom pyramid.renderers import JSONP\nfrom pyramid.exceptions import HTTPForbidden\n\nfrom . import buildsys\n\nimport logging\n\nlog = logging.getLogger(__name__)\n\n\n# TODO -- someday move this externally to \"fedora_flavored_markdown\"\nfrom bodhi.server import ffmarkdown\nffmarkdown.inject()\n\n#\n# Request methods\n#\n\ndef get_dbsession(request):\n engine = engine_from_config(request.registry.settings, 'sqlalchemy.')\n Sess = scoped_session(sessionmaker(extension=ZopeTransactionExtension()))\n Sess.configure(bind=engine)\n session = Sess()\n\n def cleanup(request):\n ## No need to do rollback/commit ourselves. the zope transaction\n ## manager takes care of that for us...\n #if request.exception is not None:\n # session.rollback()\n #else:\n # session.commit()\n ## However, we may still want to explicitly close the session we opened\n #log.debug(\"Closing session at the end of a request.\")\n session.close()\n\n request.add_finished_callback(cleanup)\n\n return session\n\n\ndef get_cacheregion(request):\n region = make_region()\n region.configure_from_config(request.registry.settings, \"dogpile.cache.\")\n return region\n\n\ndef get_user(request):\n from bodhi.server.models import User\n userid = unauthenticated_userid(request)\n if userid is not None:\n user = request.db.query(User).filter_by(name=unicode(userid)).first()\n # Why munch? https://github.com/fedora-infra/bodhi/issues/473\n return munchify(user.__json__(request=request))\n\n\ndef groupfinder(userid, request):\n from bodhi.server.models import User\n if request.user:\n user = User.get(request.user.name, request.db)\n return ['group:' + group.name for group in user.groups]\n\n\ndef get_koji(request):\n return buildsys.get_session()\n\n\ndef get_buildinfo(request):\n \"\"\"\n A per-request cache populated by the validators and shared with the views\n to store frequently used package-specific data, like build tags and ACLs.\n \"\"\"\n return defaultdict(dict)\n\n\ndef get_releases(request):\n from bodhi.server.models import Release\n return Release.all_releases(request.db)\n\n#\n# Cornice filters\n#\n\ndef exception_filter(response, request):\n \"\"\"Log exceptions that get thrown up to cornice\"\"\"\n if isinstance(response, Exception):\n log.exception('Unhandled exception raised: %r' % response)\n return response\n\nfrom cornice.validators import DEFAULT_FILTERS\nDEFAULT_FILTERS.insert(0, exception_filter)\n\n\n#\n# Bodhi initialization\n#\n\ndef main(global_config, testing=None, session=None, **settings):\n \"\"\" This function returns a WSGI application \"\"\"\n # Setup our buildsystem\n buildsys.setup_buildsystem(settings)\n\n # Sessions & Caching\n from pyramid.session import SignedCookieSessionFactory\n session_factory = SignedCookieSessionFactory(settings['session.secret'])\n\n # Construct a list of all groups we're interested in\n default = ' '.join([settings.get(key, '') for key in [\n 'important_groups',\n 'admin_packager_groups',\n 'mandatory_packager_groups',\n 'admin_groups',\n ]])\n # pyramid_fas_openid looks for this setting\n settings['openid.groups'] = settings.get('openid.groups', default).split()\n\n config = Configurator(settings=settings, session_factory=session_factory)\n\n # Plugins\n config.include('pyramid_mako')\n config.include('cornice')\n\n # Lazy-loaded memoized request properties\n if session:\n config.add_request_method(lambda _: session, 'db', reify=True)\n else:\n config.add_request_method(get_dbsession, 'db', reify=True)\n\n config.add_request_method(get_user, 'user', reify=True)\n config.add_request_method(get_koji, 'koji', reify=True)\n config.add_request_method(get_cacheregion, 'cache', reify=True)\n config.add_request_method(get_buildinfo, 'buildinfo', reify=True)\n config.add_request_method(get_releases, 'releases', reify=True)\n\n # Templating\n config.add_mako_renderer('.html', settings_prefix='mako.')\n config.add_static_view('static', 'bodhi:server/static')\n\n from bodhi.server.renderers import rss, jpeg\n config.add_renderer('rss', rss)\n config.add_renderer('jpeg', jpeg)\n config.add_renderer('jsonp', JSONP(param_name='callback'))\n\n # i18n\n config.add_translation_dirs('bodhi:server/locale/')\n\n # Authentication & Authorization\n if testing:\n # use a permissive security policy while running unit tests\n config.testing_securitypolicy(userid=testing, permissive=True)\n else:\n config.set_authentication_policy(AuthTktAuthenticationPolicy(\n settings['authtkt.secret'],\n callback=groupfinder,\n secure=asbool(settings['authtkt.secure']),\n hashalg='sha512'))\n config.set_authorization_policy(ACLAuthorizationPolicy())\n\n # Frontpage\n config.add_route('home', '/')\n\n # Views for creating new objects\n config.add_route('new_update', '/updates/new')\n config.add_route('new_override', '/overrides/new')\n config.add_route('new_stack', '/stacks/new')\n\n # Metrics\n config.add_route('metrics', '/metrics')\n config.add_route('masher_status', '/masher')\n\n # Auto-completion search\n config.add_route('search_packages', '/search/packages')\n config.add_route('latest_candidates', '/latest_candidates')\n config.add_route('latest_builds', '/latest_builds')\n\n config.add_route('captcha_image', '/captcha/{cipherkey}/')\n\n # pyramid.openid\n config.add_route('login', '/login')\n config.add_view('bodhi.server.security.login', route_name='login')\n config.add_view('bodhi.server.security.login', context=HTTPForbidden)\n config.add_route('logout', '/logout')\n config.add_view('bodhi.server.security.logout', route_name='logout')\n config.add_route('verify_openid', pattern='/dologin.html')\n config.add_view('pyramid_fas_openid.verify_openid', route_name='verify_openid')\n\n config.add_route('api_version', '/api_version')\n\n # The only user preference we have.\n config.add_route('popup_toggle', '/popup_toggle')\n\n config.scan('bodhi.server.views')\n config.scan('bodhi.server.services')\n config.scan('bodhi.server.captcha')\n config.scan('bodhi.server.events')\n\n return config.make_wsgi_app()\n", "path": "bodhi/server/__init__.py"}], "after_files": [{"content": "# This program is free software; you can redistribute it and/or\n# modify it under the terms of the GNU General Public License\n# as published by the Free Software Foundation; either version 2\n# of the License, or (at your option) any later version.\n#\n# This program is distributed in the hope that it will be useful,\n# but WITHOUT ANY WARRANTY; without even the implied warranty of\n# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n# GNU General Public License for more details.\n#\n# You should have received a copy of the GNU General Public License\n# along with this program; if not, write to the Free Software\n# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.\n\nfrom collections import defaultdict\nfrom dogpile.cache import make_region\nfrom munch import munchify\nfrom sqlalchemy import engine_from_config\nfrom sqlalchemy.orm import scoped_session, sessionmaker\nfrom zope.sqlalchemy import ZopeTransactionExtension\n\nfrom pyramid.settings import asbool\nfrom pyramid.security import unauthenticated_userid\nfrom pyramid.config import Configurator\nfrom pyramid.authentication import AuthTktAuthenticationPolicy\nfrom pyramid.authorization import ACLAuthorizationPolicy\nfrom pyramid.renderers import JSONP\nfrom pyramid.exceptions import HTTPForbidden\n\nfrom . import buildsys\n\nimport logging\n\nlog = logging.getLogger(__name__)\n\n\n# TODO -- someday move this externally to \"fedora_flavored_markdown\"\nfrom bodhi.server import ffmarkdown\nffmarkdown.inject()\n\n#\n# Request methods\n#\n\ndef get_dbsession(request):\n engine = engine_from_config(request.registry.settings, 'sqlalchemy.')\n Sess = scoped_session(sessionmaker(extension=ZopeTransactionExtension()))\n Sess.configure(bind=engine)\n session = Sess()\n\n def cleanup(request):\n ## No need to do rollback/commit ourselves. the zope transaction\n ## manager takes care of that for us...\n #if request.exception is not None:\n # session.rollback()\n #else:\n # session.commit()\n ## However, we may still want to explicitly close the session we opened\n #log.debug(\"Closing session at the end of a request.\")\n session.close()\n\n request.add_finished_callback(cleanup)\n\n return session\n\n\ndef get_cacheregion(request):\n region = make_region()\n region.configure_from_config(request.registry.settings, \"dogpile.cache.\")\n return region\n\n\ndef get_user(request):\n from bodhi.server.models import User\n userid = unauthenticated_userid(request)\n if userid is not None:\n user = request.db.query(User).filter_by(name=unicode(userid)).first()\n # Why munch? https://github.com/fedora-infra/bodhi/issues/473\n return munchify(user.__json__(request=request))\n\n\ndef groupfinder(userid, request):\n from bodhi.server.models import User\n if request.user:\n user = User.get(request.user.name, request.db)\n return ['group:' + group.name for group in user.groups]\n\n\ndef get_koji(request):\n return buildsys.get_session()\n\n\ndef get_buildinfo(request):\n \"\"\"\n A per-request cache populated by the validators and shared with the views\n to store frequently used package-specific data, like build tags and ACLs.\n \"\"\"\n return defaultdict(dict)\n\n\ndef get_releases(request):\n from bodhi.server.models import Release\n return Release.all_releases(request.db)\n\n#\n# Cornice filters\n#\n\ndef exception_filter(response, request):\n \"\"\"Log exceptions that get thrown up to cornice\"\"\"\n if isinstance(response, Exception):\n log.exception('Unhandled exception raised: %r' % response)\n return response\n\nfrom cornice.validators import DEFAULT_FILTERS\nDEFAULT_FILTERS.insert(0, exception_filter)\n\n\n#\n# Bodhi initialization\n#\n\ndef main(global_config, testing=None, session=None, **settings):\n \"\"\" This function returns a WSGI application \"\"\"\n # Setup our buildsystem\n buildsys.setup_buildsystem(settings)\n\n # Sessions & Caching\n from pyramid.session import SignedCookieSessionFactory\n session_factory = SignedCookieSessionFactory(settings['session.secret'])\n\n # Construct a list of all groups we're interested in\n default = ' '.join([settings.get(key, '') for key in [\n 'important_groups',\n 'admin_packager_groups',\n 'mandatory_packager_groups',\n 'admin_groups',\n ]])\n # pyramid_fas_openid looks for this setting\n settings['openid.groups'] = settings.get('openid.groups', default).split()\n\n config = Configurator(settings=settings, session_factory=session_factory)\n\n # Plugins\n config.include('pyramid_mako')\n config.include('cornice')\n\n # Lazy-loaded memoized request properties\n if session:\n config.add_request_method(lambda _: session, 'db', reify=True)\n else:\n config.add_request_method(get_dbsession, 'db', reify=True)\n\n config.add_request_method(get_user, 'user', reify=True)\n config.add_request_method(get_koji, 'koji', reify=True)\n config.add_request_method(get_cacheregion, 'cache', reify=True)\n config.add_request_method(get_buildinfo, 'buildinfo', reify=True)\n config.add_request_method(get_releases, 'releases', reify=True)\n\n # Templating\n config.add_mako_renderer('.html', settings_prefix='mako.')\n config.add_static_view('static', 'bodhi:server/static')\n\n from bodhi.server.renderers import rss, jpeg\n config.add_renderer('rss', rss)\n config.add_renderer('jpeg', jpeg)\n config.add_renderer('jsonp', JSONP(param_name='callback'))\n\n # i18n\n config.add_translation_dirs('bodhi:server/locale/')\n\n # Authentication & Authorization\n if testing:\n # use a permissive security policy while running unit tests\n config.testing_securitypolicy(userid=testing, permissive=True)\n else:\n config.set_authentication_policy(AuthTktAuthenticationPolicy(\n settings['authtkt.secret'],\n callback=groupfinder,\n secure=asbool(settings['authtkt.secure']),\n hashalg='sha512'))\n config.set_authorization_policy(ACLAuthorizationPolicy())\n\n # Frontpage\n config.add_route('home', '/')\n\n # Views for creating new objects\n config.add_route('new_update', '/updates/new')\n config.add_route('new_override', '/overrides/new')\n config.add_route('new_stack', '/stacks/new')\n\n # Metrics\n config.add_route('metrics', '/metrics')\n config.add_route('masher_status', '/masher/')\n\n # Auto-completion search\n config.add_route('search_packages', '/search/packages')\n config.add_route('latest_candidates', '/latest_candidates')\n config.add_route('latest_builds', '/latest_builds')\n\n config.add_route('captcha_image', '/captcha/{cipherkey}/')\n\n # pyramid.openid\n config.add_route('login', '/login')\n config.add_view('bodhi.server.security.login', route_name='login')\n config.add_view('bodhi.server.security.login', context=HTTPForbidden)\n config.add_route('logout', '/logout')\n config.add_view('bodhi.server.security.logout', route_name='logout')\n config.add_route('verify_openid', pattern='/dologin.html')\n config.add_view('pyramid_fas_openid.verify_openid', route_name='verify_openid')\n\n config.add_route('api_version', '/api_version')\n\n # The only user preference we have.\n config.add_route('popup_toggle', '/popup_toggle')\n\n config.scan('bodhi.server.views')\n config.scan('bodhi.server.services')\n config.scan('bodhi.server.captcha')\n config.scan('bodhi.server.events')\n\n return config.make_wsgi_app()\n", "path": "bodhi/server/__init__.py"}]}
| 2,580 | 121 |
gh_patches_debug_25484
|
rasdani/github-patches
|
git_diff
|
dj-stripe__dj-stripe-1259
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
DJStripeSubscriptionPermission issue returning bool
This permission is not returning properly the bool.
**Current behaviour**
```python
class DJStripeSubscriptionPermission(BasePermission):
"""
A permission to be used when wanting to permit users with active subscriptions.
"""
def has_permission(self, request, view):
"""
Check if the subscriber has an active subscription.
Returns false if:
* a subscriber isn't passed through the request
See ``utils.subscriber_has_active_subscription`` for more rules.
"""
try:
subscriber_has_active_subscription(subscriber_request_callback(request))
except AttributeError:
return False
```
Here is not returning True or False except if it falls in the exception.
**Expected Behaviour**
```python
class DJStripeSubscriptionPermission(BasePermission):
"""
A permission to be used when wanting to permit users with active subscriptions.
"""
def has_permission(self, request, view):
"""
Check if the subscriber has an active subscription.
Returns false if:
* a subscriber isn't passed through the request
See ``utils.subscriber_has_active_subscription`` for more rules.
"""
try:
return bool(subscriber_has_active_subscription(subscriber_request_callback(request)))
except AttributeError:
return False
```
Just missing a return and it solves the problem. We don't need a bool directly there, I just added just to follow the same patterns as the DRF (also being added to the other project :-))
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `djstripe/contrib/rest_framework/serializers.py`
Content:
```
1 """
2 .. module:: dj-stripe.contrib.rest_framework.serializers.
3
4 :synopsis: dj-stripe - Serializers to be used with the dj-stripe REST API.
5
6 .. moduleauthor:: Philippe Luickx (@philippeluickx)
7
8 """
9
10 from rest_framework import serializers
11 from rest_framework.serializers import ModelSerializer
12
13 from djstripe.models import Subscription
14
15
16 class SubscriptionSerializer(ModelSerializer):
17 """A serializer used for the Subscription model."""
18
19 class Meta:
20 """Model class options."""
21
22 model = Subscription
23 exclude = ["default_tax_rates"]
24
25
26 class CreateSubscriptionSerializer(serializers.Serializer):
27 """A serializer used to create a Subscription."""
28
29 stripe_token = serializers.CharField(max_length=200)
30 plan = serializers.CharField(max_length=50)
31 charge_immediately = serializers.BooleanField(required=False, allow_null=True, default=None)
32 tax_percent = serializers.DecimalField(
33 required=False, max_digits=5, decimal_places=2
34 )
35
```
Path: `djstripe/contrib/rest_framework/permissions.py`
Content:
```
1 """
2 .. module:: dj-stripe.contrib.rest_framework.permissions.
3
4 :synopsis: dj-stripe - Permissions to be used with the dj-stripe REST API.
5
6 .. moduleauthor:: @kavdev, @pydanny
7
8 """
9 from rest_framework.permissions import BasePermission
10
11 from ...settings import subscriber_request_callback
12 from ...utils import subscriber_has_active_subscription
13
14
15 class DJStripeSubscriptionPermission(BasePermission):
16 """
17 A permission to be used when wanting to permit users with active subscriptions.
18 """
19
20 def has_permission(self, request, view):
21 """
22 Check if the subscriber has an active subscription.
23
24 Returns false if:
25 * a subscriber isn't passed through the request
26
27 See ``utils.subscriber_has_active_subscription`` for more rules.
28
29 """
30 try:
31 subscriber_has_active_subscription(subscriber_request_callback(request))
32 except AttributeError:
33 return False
34
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/djstripe/contrib/rest_framework/permissions.py b/djstripe/contrib/rest_framework/permissions.py
--- a/djstripe/contrib/rest_framework/permissions.py
+++ b/djstripe/contrib/rest_framework/permissions.py
@@ -17,7 +17,7 @@
A permission to be used when wanting to permit users with active subscriptions.
"""
- def has_permission(self, request, view):
+ def has_permission(self, request, view) -> bool:
"""
Check if the subscriber has an active subscription.
@@ -28,6 +28,8 @@
"""
try:
- subscriber_has_active_subscription(subscriber_request_callback(request))
+ return subscriber_has_active_subscription(
+ subscriber_request_callback(request)
+ )
except AttributeError:
return False
diff --git a/djstripe/contrib/rest_framework/serializers.py b/djstripe/contrib/rest_framework/serializers.py
--- a/djstripe/contrib/rest_framework/serializers.py
+++ b/djstripe/contrib/rest_framework/serializers.py
@@ -28,7 +28,9 @@
stripe_token = serializers.CharField(max_length=200)
plan = serializers.CharField(max_length=50)
- charge_immediately = serializers.BooleanField(required=False, allow_null=True, default=None)
+ charge_immediately = serializers.BooleanField(
+ required=False, allow_null=True, default=None
+ )
tax_percent = serializers.DecimalField(
required=False, max_digits=5, decimal_places=2
)
|
{"golden_diff": "diff --git a/djstripe/contrib/rest_framework/permissions.py b/djstripe/contrib/rest_framework/permissions.py\n--- a/djstripe/contrib/rest_framework/permissions.py\n+++ b/djstripe/contrib/rest_framework/permissions.py\n@@ -17,7 +17,7 @@\n A permission to be used when wanting to permit users with active subscriptions.\n \"\"\"\n \n- def has_permission(self, request, view):\n+ def has_permission(self, request, view) -> bool:\n \"\"\"\n Check if the subscriber has an active subscription.\n \n@@ -28,6 +28,8 @@\n \n \"\"\"\n try:\n- subscriber_has_active_subscription(subscriber_request_callback(request))\n+ return subscriber_has_active_subscription(\n+ subscriber_request_callback(request)\n+ )\n except AttributeError:\n return False\ndiff --git a/djstripe/contrib/rest_framework/serializers.py b/djstripe/contrib/rest_framework/serializers.py\n--- a/djstripe/contrib/rest_framework/serializers.py\n+++ b/djstripe/contrib/rest_framework/serializers.py\n@@ -28,7 +28,9 @@\n \n stripe_token = serializers.CharField(max_length=200)\n plan = serializers.CharField(max_length=50)\n- charge_immediately = serializers.BooleanField(required=False, allow_null=True, default=None)\n+ charge_immediately = serializers.BooleanField(\n+ required=False, allow_null=True, default=None\n+ )\n tax_percent = serializers.DecimalField(\n required=False, max_digits=5, decimal_places=2\n )\n", "issue": "DJStripeSubscriptionPermission issue returning bool\nThis permission is not returning properly the bool.\r\n\r\n**Current behaviour**\r\n\r\n```python\r\nclass DJStripeSubscriptionPermission(BasePermission):\r\n \"\"\"\r\n A permission to be used when wanting to permit users with active subscriptions.\r\n \"\"\"\r\n\r\n def has_permission(self, request, view):\r\n \"\"\"\r\n Check if the subscriber has an active subscription.\r\n\r\n Returns false if:\r\n * a subscriber isn't passed through the request\r\n\r\n See ``utils.subscriber_has_active_subscription`` for more rules.\r\n\r\n \"\"\"\r\n try:\r\n subscriber_has_active_subscription(subscriber_request_callback(request))\r\n except AttributeError:\r\n return False\r\n```\r\n\r\nHere is not returning True or False except if it falls in the exception.\r\n\r\n\r\n**Expected Behaviour**\r\n\r\n\r\n```python\r\nclass DJStripeSubscriptionPermission(BasePermission):\r\n \"\"\"\r\n A permission to be used when wanting to permit users with active subscriptions.\r\n \"\"\"\r\n\r\n def has_permission(self, request, view):\r\n \"\"\"\r\n Check if the subscriber has an active subscription.\r\n\r\n Returns false if:\r\n * a subscriber isn't passed through the request\r\n\r\n See ``utils.subscriber_has_active_subscription`` for more rules.\r\n\r\n \"\"\"\r\n try:\r\n return bool(subscriber_has_active_subscription(subscriber_request_callback(request)))\r\n except AttributeError:\r\n return False\r\n```\r\n\r\nJust missing a return and it solves the problem. We don't need a bool directly there, I just added just to follow the same patterns as the DRF (also being added to the other project :-))\n", "before_files": [{"content": "\"\"\"\n.. module:: dj-stripe.contrib.rest_framework.serializers.\n\n :synopsis: dj-stripe - Serializers to be used with the dj-stripe REST API.\n\n.. moduleauthor:: Philippe Luickx (@philippeluickx)\n\n\"\"\"\n\nfrom rest_framework import serializers\nfrom rest_framework.serializers import ModelSerializer\n\nfrom djstripe.models import Subscription\n\n\nclass SubscriptionSerializer(ModelSerializer):\n \"\"\"A serializer used for the Subscription model.\"\"\"\n\n class Meta:\n \"\"\"Model class options.\"\"\"\n\n model = Subscription\n exclude = [\"default_tax_rates\"]\n\n\nclass CreateSubscriptionSerializer(serializers.Serializer):\n \"\"\"A serializer used to create a Subscription.\"\"\"\n\n stripe_token = serializers.CharField(max_length=200)\n plan = serializers.CharField(max_length=50)\n charge_immediately = serializers.BooleanField(required=False, allow_null=True, default=None)\n tax_percent = serializers.DecimalField(\n required=False, max_digits=5, decimal_places=2\n )\n", "path": "djstripe/contrib/rest_framework/serializers.py"}, {"content": "\"\"\"\n.. module:: dj-stripe.contrib.rest_framework.permissions.\n\n :synopsis: dj-stripe - Permissions to be used with the dj-stripe REST API.\n\n.. moduleauthor:: @kavdev, @pydanny\n\n\"\"\"\nfrom rest_framework.permissions import BasePermission\n\nfrom ...settings import subscriber_request_callback\nfrom ...utils import subscriber_has_active_subscription\n\n\nclass DJStripeSubscriptionPermission(BasePermission):\n \"\"\"\n A permission to be used when wanting to permit users with active subscriptions.\n \"\"\"\n\n def has_permission(self, request, view):\n \"\"\"\n Check if the subscriber has an active subscription.\n\n Returns false if:\n * a subscriber isn't passed through the request\n\n See ``utils.subscriber_has_active_subscription`` for more rules.\n\n \"\"\"\n try:\n subscriber_has_active_subscription(subscriber_request_callback(request))\n except AttributeError:\n return False\n", "path": "djstripe/contrib/rest_framework/permissions.py"}], "after_files": [{"content": "\"\"\"\n.. module:: dj-stripe.contrib.rest_framework.serializers.\n\n :synopsis: dj-stripe - Serializers to be used with the dj-stripe REST API.\n\n.. moduleauthor:: Philippe Luickx (@philippeluickx)\n\n\"\"\"\n\nfrom rest_framework import serializers\nfrom rest_framework.serializers import ModelSerializer\n\nfrom djstripe.models import Subscription\n\n\nclass SubscriptionSerializer(ModelSerializer):\n \"\"\"A serializer used for the Subscription model.\"\"\"\n\n class Meta:\n \"\"\"Model class options.\"\"\"\n\n model = Subscription\n exclude = [\"default_tax_rates\"]\n\n\nclass CreateSubscriptionSerializer(serializers.Serializer):\n \"\"\"A serializer used to create a Subscription.\"\"\"\n\n stripe_token = serializers.CharField(max_length=200)\n plan = serializers.CharField(max_length=50)\n charge_immediately = serializers.BooleanField(\n required=False, allow_null=True, default=None\n )\n tax_percent = serializers.DecimalField(\n required=False, max_digits=5, decimal_places=2\n )\n", "path": "djstripe/contrib/rest_framework/serializers.py"}, {"content": "\"\"\"\n.. module:: dj-stripe.contrib.rest_framework.permissions.\n\n :synopsis: dj-stripe - Permissions to be used with the dj-stripe REST API.\n\n.. moduleauthor:: @kavdev, @pydanny\n\n\"\"\"\nfrom rest_framework.permissions import BasePermission\n\nfrom ...settings import subscriber_request_callback\nfrom ...utils import subscriber_has_active_subscription\n\n\nclass DJStripeSubscriptionPermission(BasePermission):\n \"\"\"\n A permission to be used when wanting to permit users with active subscriptions.\n \"\"\"\n\n def has_permission(self, request, view) -> bool:\n \"\"\"\n Check if the subscriber has an active subscription.\n\n Returns false if:\n * a subscriber isn't passed through the request\n\n See ``utils.subscriber_has_active_subscription`` for more rules.\n\n \"\"\"\n try:\n return subscriber_has_active_subscription(\n subscriber_request_callback(request)\n )\n except AttributeError:\n return False\n", "path": "djstripe/contrib/rest_framework/permissions.py"}]}
| 1,099 | 334 |
gh_patches_debug_9096
|
rasdani/github-patches
|
git_diff
|
ivy-llc__ivy-26785
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Remove duplicate-keys in `ivy\functional\backends\numpy\__init__.py`
In the file: `ivy\functional\backends\numpy\__init__.py` duplicate keys are present in the following lines
https://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L25
https://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L40
https://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L31
https://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L37
They can be removed.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `ivy/functional/backends/numpy/__init__.py`
Content:
```
1 # global
2 import sys
3 import numpy as np
4
5 # local
6 import ivy
7 from ivy.func_wrapper import _dtype_from_version
8
9 backend_version = {"version": np.__version__}
10
11 # noinspection PyUnresolvedReferences
12 if not ivy.is_local():
13 _module_in_memory = sys.modules[__name__]
14 else:
15 _module_in_memory = sys.modules[ivy.import_module_path].import_cache[__name__]
16
17 use = ivy.utils.backend.ContextManager(_module_in_memory)
18
19 # wrap __array_ufunc__ method of ivy.Array to prioritize Ivy array methods when using numpu backend
20
21
22 def wrap__array_ufunc__(func):
23 def rep_method(self, ufunc, method, *inputs, **kwargs):
24 methods = {
25 "not_equal": "not_equal",
26 "greater": "greater",
27 "less": "less",
28 "greater_equal": "greater_equal",
29 "less_equal": "less_equal",
30 "multiply": "multiply",
31 "divide": "divide",
32 "remainder": "remainder",
33 "equal": "equal",
34 "bitwise_and": "bitwise_and",
35 "matmul": "matmul",
36 "power": "pow",
37 "divide": "divide",
38 "subtract": "subtract",
39 "add": "add",
40 "not_equal": "not_equal",
41 }
42 if ufunc.__name__ in methods.keys():
43 return eval("ivy." + methods[ufunc.__name__] + "(*inputs, **kwargs)")
44 return func(self, ufunc, method, *inputs, **kwargs)
45
46 return rep_method
47
48
49 ivy.Array.__array_ufunc__ = wrap__array_ufunc__(ivy.Array.__array_ufunc__)
50
51 NativeArray = np.ndarray
52 NativeDevice = str
53 NativeDtype = np.dtype
54 NativeShape = tuple
55
56 NativeSparseArray = None
57
58
59 # devices
60 valid_devices = ("cpu",)
61
62 invalid_devices = ("gpu", "tpu")
63
64 # native data types
65 native_int8 = np.dtype("int8")
66 native_int16 = np.dtype("int16")
67 native_int32 = np.dtype("int32")
68 native_int64 = np.dtype("int64")
69 native_uint8 = np.dtype("uint8")
70 native_uint16 = np.dtype("uint16")
71 native_uint32 = np.dtype("uint32")
72 native_uint64 = np.dtype("uint64")
73 native_float16 = np.dtype("float16")
74 native_float32 = np.dtype("float32")
75 native_float64 = np.dtype("float64")
76 native_complex64 = np.dtype("complex64")
77 native_complex128 = np.dtype("complex128")
78 native_double = native_float64
79 native_bool = np.dtype("bool")
80
81 # valid data types
82 # ToDo: Add complex dtypes to valid_dtypes and fix all resulting failures.
83
84 # update these to add new dtypes
85 valid_dtypes = {
86 "1.26.0 and below": (
87 ivy.int8,
88 ivy.int16,
89 ivy.int32,
90 ivy.int64,
91 ivy.uint8,
92 ivy.uint16,
93 ivy.uint32,
94 ivy.uint64,
95 ivy.float16,
96 ivy.float32,
97 ivy.float64,
98 ivy.complex64,
99 ivy.complex128,
100 ivy.bool,
101 )
102 }
103 valid_numeric_dtypes = {
104 "1.26.0 and below": (
105 ivy.int8,
106 ivy.int16,
107 ivy.int32,
108 ivy.int64,
109 ivy.uint8,
110 ivy.uint16,
111 ivy.uint32,
112 ivy.uint64,
113 ivy.float16,
114 ivy.float32,
115 ivy.float64,
116 ivy.complex64,
117 ivy.complex128,
118 )
119 }
120 valid_int_dtypes = {
121 "1.26.0 and below": (
122 ivy.int8,
123 ivy.int16,
124 ivy.int32,
125 ivy.int64,
126 ivy.uint8,
127 ivy.uint16,
128 ivy.uint32,
129 ivy.uint64,
130 )
131 }
132 valid_float_dtypes = {"1.26.0 and below": (ivy.float16, ivy.float32, ivy.float64)}
133 valid_uint_dtypes = {
134 "1.26.0 and below": (ivy.uint8, ivy.uint16, ivy.uint32, ivy.uint64)
135 }
136 valid_complex_dtypes = {"1.26.0 and below": (ivy.complex64, ivy.complex128)}
137
138 # leave these untouched
139 valid_dtypes = _dtype_from_version(valid_dtypes, backend_version)
140 valid_numeric_dtypes = _dtype_from_version(valid_numeric_dtypes, backend_version)
141 valid_int_dtypes = _dtype_from_version(valid_int_dtypes, backend_version)
142 valid_float_dtypes = _dtype_from_version(valid_float_dtypes, backend_version)
143 valid_uint_dtypes = _dtype_from_version(valid_uint_dtypes, backend_version)
144 valid_complex_dtypes = _dtype_from_version(valid_complex_dtypes, backend_version)
145
146 # invalid data types
147 # update these to add new dtypes
148 invalid_dtypes = {"1.26.0 and below": (ivy.bfloat16,)}
149 invalid_numeric_dtypes = {"1.26.0 and below": (ivy.bfloat16,)}
150 invalid_int_dtypes = {"1.26.0 and below": ()}
151 invalid_float_dtypes = {"1.26.0 and below": (ivy.bfloat16,)}
152 invalid_uint_dtypes = {"1.26.0 and below": ()}
153 invalid_complex_dtypes = {"1.26.0 and below": ()}
154
155
156 # leave these untouched
157 invalid_dtypes = _dtype_from_version(invalid_dtypes, backend_version)
158 invalid_numeric_dtypes = _dtype_from_version(invalid_numeric_dtypes, backend_version)
159 invalid_int_dtypes = _dtype_from_version(invalid_int_dtypes, backend_version)
160 invalid_float_dtypes = _dtype_from_version(invalid_float_dtypes, backend_version)
161 invalid_uint_dtypes = _dtype_from_version(invalid_uint_dtypes, backend_version)
162 invalid_complex_dtypes = _dtype_from_version(invalid_complex_dtypes, backend_version)
163
164
165 native_inplace_support = True
166
167 supports_gradients = False
168
169
170 def closest_valid_dtype(type=None, /, as_native=False):
171 if type is None:
172 type = ivy.default_dtype()
173 elif isinstance(type, str) and type in invalid_dtypes:
174 type = {"bfloat16": ivy.float16}[type]
175 return ivy.as_ivy_dtype(type) if not as_native else ivy.as_native_dtype(type)
176
177
178 backend = "numpy"
179
180
181 # local sub-modules
182 from . import activations
183 from .activations import *
184 from . import creation
185 from .creation import *
186 from . import data_type
187 from .data_type import *
188 from . import device
189 from .device import *
190 from . import elementwise
191 from .elementwise import *
192 from . import general
193 from .general import *
194 from . import gradients
195 from .gradients import *
196 from . import layers
197 from .layers import *
198 from . import linear_algebra as linalg
199 from .linear_algebra import *
200 from . import manipulation
201 from .manipulation import *
202 from . import random
203 from .random import *
204 from . import searching
205 from .searching import *
206 from . import set
207 from .set import *
208 from . import sorting
209 from .sorting import *
210 from . import statistical
211 from .statistical import *
212 from . import utility
213 from .utility import *
214 from . import experimental
215 from .experimental import *
216 from . import control_flow_ops
217 from .control_flow_ops import *
218
219
220 # sub-backends
221
222 from . import sub_backends
223 from .sub_backends import *
224
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/ivy/functional/backends/numpy/__init__.py b/ivy/functional/backends/numpy/__init__.py
--- a/ivy/functional/backends/numpy/__init__.py
+++ b/ivy/functional/backends/numpy/__init__.py
@@ -34,10 +34,8 @@
"bitwise_and": "bitwise_and",
"matmul": "matmul",
"power": "pow",
- "divide": "divide",
"subtract": "subtract",
"add": "add",
- "not_equal": "not_equal",
}
if ufunc.__name__ in methods.keys():
return eval("ivy." + methods[ufunc.__name__] + "(*inputs, **kwargs)")
|
{"golden_diff": "diff --git a/ivy/functional/backends/numpy/__init__.py b/ivy/functional/backends/numpy/__init__.py\n--- a/ivy/functional/backends/numpy/__init__.py\n+++ b/ivy/functional/backends/numpy/__init__.py\n@@ -34,10 +34,8 @@\n \"bitwise_and\": \"bitwise_and\",\n \"matmul\": \"matmul\",\n \"power\": \"pow\",\n- \"divide\": \"divide\",\n \"subtract\": \"subtract\",\n \"add\": \"add\",\n- \"not_equal\": \"not_equal\",\n }\n if ufunc.__name__ in methods.keys():\n return eval(\"ivy.\" + methods[ufunc.__name__] + \"(*inputs, **kwargs)\")\n", "issue": "Remove duplicate-keys in `ivy\\functional\\backends\\numpy\\__init__.py`\nIn the file: `ivy\\functional\\backends\\numpy\\__init__.py` duplicate keys are present in the following lines\r\nhttps://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L25\r\nhttps://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L40\r\nhttps://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L31\r\nhttps://github.com/unifyai/ivy/blob/1be0f8c2c8d916b10f06ab538b43fc506a1992a6/ivy/functional/backends/numpy/__init__.py#L37\r\nThey can be removed.\n", "before_files": [{"content": "# global\nimport sys\nimport numpy as np\n\n# local\nimport ivy\nfrom ivy.func_wrapper import _dtype_from_version\n\nbackend_version = {\"version\": np.__version__}\n\n# noinspection PyUnresolvedReferences\nif not ivy.is_local():\n _module_in_memory = sys.modules[__name__]\nelse:\n _module_in_memory = sys.modules[ivy.import_module_path].import_cache[__name__]\n\nuse = ivy.utils.backend.ContextManager(_module_in_memory)\n\n# wrap __array_ufunc__ method of ivy.Array to prioritize Ivy array methods when using numpu backend\n\n\ndef wrap__array_ufunc__(func):\n def rep_method(self, ufunc, method, *inputs, **kwargs):\n methods = {\n \"not_equal\": \"not_equal\",\n \"greater\": \"greater\",\n \"less\": \"less\",\n \"greater_equal\": \"greater_equal\",\n \"less_equal\": \"less_equal\",\n \"multiply\": \"multiply\",\n \"divide\": \"divide\",\n \"remainder\": \"remainder\",\n \"equal\": \"equal\",\n \"bitwise_and\": \"bitwise_and\",\n \"matmul\": \"matmul\",\n \"power\": \"pow\",\n \"divide\": \"divide\",\n \"subtract\": \"subtract\",\n \"add\": \"add\",\n \"not_equal\": \"not_equal\",\n }\n if ufunc.__name__ in methods.keys():\n return eval(\"ivy.\" + methods[ufunc.__name__] + \"(*inputs, **kwargs)\")\n return func(self, ufunc, method, *inputs, **kwargs)\n\n return rep_method\n\n\nivy.Array.__array_ufunc__ = wrap__array_ufunc__(ivy.Array.__array_ufunc__)\n\nNativeArray = np.ndarray\nNativeDevice = str\nNativeDtype = np.dtype\nNativeShape = tuple\n\nNativeSparseArray = None\n\n\n# devices\nvalid_devices = (\"cpu\",)\n\ninvalid_devices = (\"gpu\", \"tpu\")\n\n# native data types\nnative_int8 = np.dtype(\"int8\")\nnative_int16 = np.dtype(\"int16\")\nnative_int32 = np.dtype(\"int32\")\nnative_int64 = np.dtype(\"int64\")\nnative_uint8 = np.dtype(\"uint8\")\nnative_uint16 = np.dtype(\"uint16\")\nnative_uint32 = np.dtype(\"uint32\")\nnative_uint64 = np.dtype(\"uint64\")\nnative_float16 = np.dtype(\"float16\")\nnative_float32 = np.dtype(\"float32\")\nnative_float64 = np.dtype(\"float64\")\nnative_complex64 = np.dtype(\"complex64\")\nnative_complex128 = np.dtype(\"complex128\")\nnative_double = native_float64\nnative_bool = np.dtype(\"bool\")\n\n# valid data types\n# ToDo: Add complex dtypes to valid_dtypes and fix all resulting failures.\n\n# update these to add new dtypes\nvalid_dtypes = {\n \"1.26.0 and below\": (\n ivy.int8,\n ivy.int16,\n ivy.int32,\n ivy.int64,\n ivy.uint8,\n ivy.uint16,\n ivy.uint32,\n ivy.uint64,\n ivy.float16,\n ivy.float32,\n ivy.float64,\n ivy.complex64,\n ivy.complex128,\n ivy.bool,\n )\n}\nvalid_numeric_dtypes = {\n \"1.26.0 and below\": (\n ivy.int8,\n ivy.int16,\n ivy.int32,\n ivy.int64,\n ivy.uint8,\n ivy.uint16,\n ivy.uint32,\n ivy.uint64,\n ivy.float16,\n ivy.float32,\n ivy.float64,\n ivy.complex64,\n ivy.complex128,\n )\n}\nvalid_int_dtypes = {\n \"1.26.0 and below\": (\n ivy.int8,\n ivy.int16,\n ivy.int32,\n ivy.int64,\n ivy.uint8,\n ivy.uint16,\n ivy.uint32,\n ivy.uint64,\n )\n}\nvalid_float_dtypes = {\"1.26.0 and below\": (ivy.float16, ivy.float32, ivy.float64)}\nvalid_uint_dtypes = {\n \"1.26.0 and below\": (ivy.uint8, ivy.uint16, ivy.uint32, ivy.uint64)\n}\nvalid_complex_dtypes = {\"1.26.0 and below\": (ivy.complex64, ivy.complex128)}\n\n# leave these untouched\nvalid_dtypes = _dtype_from_version(valid_dtypes, backend_version)\nvalid_numeric_dtypes = _dtype_from_version(valid_numeric_dtypes, backend_version)\nvalid_int_dtypes = _dtype_from_version(valid_int_dtypes, backend_version)\nvalid_float_dtypes = _dtype_from_version(valid_float_dtypes, backend_version)\nvalid_uint_dtypes = _dtype_from_version(valid_uint_dtypes, backend_version)\nvalid_complex_dtypes = _dtype_from_version(valid_complex_dtypes, backend_version)\n\n# invalid data types\n# update these to add new dtypes\ninvalid_dtypes = {\"1.26.0 and below\": (ivy.bfloat16,)}\ninvalid_numeric_dtypes = {\"1.26.0 and below\": (ivy.bfloat16,)}\ninvalid_int_dtypes = {\"1.26.0 and below\": ()}\ninvalid_float_dtypes = {\"1.26.0 and below\": (ivy.bfloat16,)}\ninvalid_uint_dtypes = {\"1.26.0 and below\": ()}\ninvalid_complex_dtypes = {\"1.26.0 and below\": ()}\n\n\n# leave these untouched\ninvalid_dtypes = _dtype_from_version(invalid_dtypes, backend_version)\ninvalid_numeric_dtypes = _dtype_from_version(invalid_numeric_dtypes, backend_version)\ninvalid_int_dtypes = _dtype_from_version(invalid_int_dtypes, backend_version)\ninvalid_float_dtypes = _dtype_from_version(invalid_float_dtypes, backend_version)\ninvalid_uint_dtypes = _dtype_from_version(invalid_uint_dtypes, backend_version)\ninvalid_complex_dtypes = _dtype_from_version(invalid_complex_dtypes, backend_version)\n\n\nnative_inplace_support = True\n\nsupports_gradients = False\n\n\ndef closest_valid_dtype(type=None, /, as_native=False):\n if type is None:\n type = ivy.default_dtype()\n elif isinstance(type, str) and type in invalid_dtypes:\n type = {\"bfloat16\": ivy.float16}[type]\n return ivy.as_ivy_dtype(type) if not as_native else ivy.as_native_dtype(type)\n\n\nbackend = \"numpy\"\n\n\n# local sub-modules\nfrom . import activations\nfrom .activations import *\nfrom . import creation\nfrom .creation import *\nfrom . import data_type\nfrom .data_type import *\nfrom . import device\nfrom .device import *\nfrom . import elementwise\nfrom .elementwise import *\nfrom . import general\nfrom .general import *\nfrom . import gradients\nfrom .gradients import *\nfrom . import layers\nfrom .layers import *\nfrom . import linear_algebra as linalg\nfrom .linear_algebra import *\nfrom . import manipulation\nfrom .manipulation import *\nfrom . import random\nfrom .random import *\nfrom . import searching\nfrom .searching import *\nfrom . import set\nfrom .set import *\nfrom . import sorting\nfrom .sorting import *\nfrom . import statistical\nfrom .statistical import *\nfrom . import utility\nfrom .utility import *\nfrom . import experimental\nfrom .experimental import *\nfrom . import control_flow_ops\nfrom .control_flow_ops import *\n\n\n# sub-backends\n\nfrom . import sub_backends\nfrom .sub_backends import *\n", "path": "ivy/functional/backends/numpy/__init__.py"}], "after_files": [{"content": "# global\nimport sys\nimport numpy as np\n\n# local\nimport ivy\nfrom ivy.func_wrapper import _dtype_from_version\n\nbackend_version = {\"version\": np.__version__}\n\n# noinspection PyUnresolvedReferences\nif not ivy.is_local():\n _module_in_memory = sys.modules[__name__]\nelse:\n _module_in_memory = sys.modules[ivy.import_module_path].import_cache[__name__]\n\nuse = ivy.utils.backend.ContextManager(_module_in_memory)\n\n# wrap __array_ufunc__ method of ivy.Array to prioritize Ivy array methods when using numpu backend\n\n\ndef wrap__array_ufunc__(func):\n def rep_method(self, ufunc, method, *inputs, **kwargs):\n methods = {\n \"not_equal\": \"not_equal\",\n \"greater\": \"greater\",\n \"less\": \"less\",\n \"greater_equal\": \"greater_equal\",\n \"less_equal\": \"less_equal\",\n \"multiply\": \"multiply\",\n \"divide\": \"divide\",\n \"remainder\": \"remainder\",\n \"equal\": \"equal\",\n \"bitwise_and\": \"bitwise_and\",\n \"matmul\": \"matmul\",\n \"power\": \"pow\",\n \"subtract\": \"subtract\",\n \"add\": \"add\",\n }\n if ufunc.__name__ in methods.keys():\n return eval(\"ivy.\" + methods[ufunc.__name__] + \"(*inputs, **kwargs)\")\n return func(self, ufunc, method, *inputs, **kwargs)\n\n return rep_method\n\n\nivy.Array.__array_ufunc__ = wrap__array_ufunc__(ivy.Array.__array_ufunc__)\n\nNativeArray = np.ndarray\nNativeDevice = str\nNativeDtype = np.dtype\nNativeShape = tuple\n\nNativeSparseArray = None\n\n\n# devices\nvalid_devices = (\"cpu\",)\n\ninvalid_devices = (\"gpu\", \"tpu\")\n\n# native data types\nnative_int8 = np.dtype(\"int8\")\nnative_int16 = np.dtype(\"int16\")\nnative_int32 = np.dtype(\"int32\")\nnative_int64 = np.dtype(\"int64\")\nnative_uint8 = np.dtype(\"uint8\")\nnative_uint16 = np.dtype(\"uint16\")\nnative_uint32 = np.dtype(\"uint32\")\nnative_uint64 = np.dtype(\"uint64\")\nnative_float16 = np.dtype(\"float16\")\nnative_float32 = np.dtype(\"float32\")\nnative_float64 = np.dtype(\"float64\")\nnative_complex64 = np.dtype(\"complex64\")\nnative_complex128 = np.dtype(\"complex128\")\nnative_double = native_float64\nnative_bool = np.dtype(\"bool\")\n\n# valid data types\n# ToDo: Add complex dtypes to valid_dtypes and fix all resulting failures.\n\n# update these to add new dtypes\nvalid_dtypes = {\n \"1.26.0 and below\": (\n ivy.int8,\n ivy.int16,\n ivy.int32,\n ivy.int64,\n ivy.uint8,\n ivy.uint16,\n ivy.uint32,\n ivy.uint64,\n ivy.float16,\n ivy.float32,\n ivy.float64,\n ivy.complex64,\n ivy.complex128,\n ivy.bool,\n )\n}\nvalid_numeric_dtypes = {\n \"1.26.0 and below\": (\n ivy.int8,\n ivy.int16,\n ivy.int32,\n ivy.int64,\n ivy.uint8,\n ivy.uint16,\n ivy.uint32,\n ivy.uint64,\n ivy.float16,\n ivy.float32,\n ivy.float64,\n ivy.complex64,\n ivy.complex128,\n )\n}\nvalid_int_dtypes = {\n \"1.26.0 and below\": (\n ivy.int8,\n ivy.int16,\n ivy.int32,\n ivy.int64,\n ivy.uint8,\n ivy.uint16,\n ivy.uint32,\n ivy.uint64,\n )\n}\nvalid_float_dtypes = {\"1.26.0 and below\": (ivy.float16, ivy.float32, ivy.float64)}\nvalid_uint_dtypes = {\n \"1.26.0 and below\": (ivy.uint8, ivy.uint16, ivy.uint32, ivy.uint64)\n}\nvalid_complex_dtypes = {\"1.26.0 and below\": (ivy.complex64, ivy.complex128)}\n\n# leave these untouched\nvalid_dtypes = _dtype_from_version(valid_dtypes, backend_version)\nvalid_numeric_dtypes = _dtype_from_version(valid_numeric_dtypes, backend_version)\nvalid_int_dtypes = _dtype_from_version(valid_int_dtypes, backend_version)\nvalid_float_dtypes = _dtype_from_version(valid_float_dtypes, backend_version)\nvalid_uint_dtypes = _dtype_from_version(valid_uint_dtypes, backend_version)\nvalid_complex_dtypes = _dtype_from_version(valid_complex_dtypes, backend_version)\n\n# invalid data types\n# update these to add new dtypes\ninvalid_dtypes = {\"1.26.0 and below\": (ivy.bfloat16,)}\ninvalid_numeric_dtypes = {\"1.26.0 and below\": (ivy.bfloat16,)}\ninvalid_int_dtypes = {\"1.26.0 and below\": ()}\ninvalid_float_dtypes = {\"1.26.0 and below\": (ivy.bfloat16,)}\ninvalid_uint_dtypes = {\"1.26.0 and below\": ()}\ninvalid_complex_dtypes = {\"1.26.0 and below\": ()}\n\n\n# leave these untouched\ninvalid_dtypes = _dtype_from_version(invalid_dtypes, backend_version)\ninvalid_numeric_dtypes = _dtype_from_version(invalid_numeric_dtypes, backend_version)\ninvalid_int_dtypes = _dtype_from_version(invalid_int_dtypes, backend_version)\ninvalid_float_dtypes = _dtype_from_version(invalid_float_dtypes, backend_version)\ninvalid_uint_dtypes = _dtype_from_version(invalid_uint_dtypes, backend_version)\ninvalid_complex_dtypes = _dtype_from_version(invalid_complex_dtypes, backend_version)\n\n\nnative_inplace_support = True\n\nsupports_gradients = False\n\n\ndef closest_valid_dtype(type=None, /, as_native=False):\n if type is None:\n type = ivy.default_dtype()\n elif isinstance(type, str) and type in invalid_dtypes:\n type = {\"bfloat16\": ivy.float16}[type]\n return ivy.as_ivy_dtype(type) if not as_native else ivy.as_native_dtype(type)\n\n\nbackend = \"numpy\"\n\n\n# local sub-modules\nfrom . import activations\nfrom .activations import *\nfrom . import creation\nfrom .creation import *\nfrom . import data_type\nfrom .data_type import *\nfrom . import device\nfrom .device import *\nfrom . import elementwise\nfrom .elementwise import *\nfrom . import general\nfrom .general import *\nfrom . import gradients\nfrom .gradients import *\nfrom . import layers\nfrom .layers import *\nfrom . import linear_algebra as linalg\nfrom .linear_algebra import *\nfrom . import manipulation\nfrom .manipulation import *\nfrom . import random\nfrom .random import *\nfrom . import searching\nfrom .searching import *\nfrom . import set\nfrom .set import *\nfrom . import sorting\nfrom .sorting import *\nfrom . import statistical\nfrom .statistical import *\nfrom . import utility\nfrom .utility import *\nfrom . import experimental\nfrom .experimental import *\nfrom . import control_flow_ops\nfrom .control_flow_ops import *\n\n\n# sub-backends\n\nfrom . import sub_backends\nfrom .sub_backends import *\n", "path": "ivy/functional/backends/numpy/__init__.py"}]}
| 2,876 | 168 |
gh_patches_debug_32253
|
rasdani/github-patches
|
git_diff
|
aws__aws-cli-2044
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
[aws deploy push] Destination bundle type does not match extension
When specifying a destination with a suffix of ".zip" or ".tar" or ".tar.gz" for use with the `aws deploy push` command the resulting bundle is always only zipped.
```
$ aws deploy push --application-name test --s3-location s3://$AWS_DEPLOY_BUCKET/test/latest.tar --no-ignore-hidden-files --source .
To deploy with this revision, run:
aws deploy create-deployment --application-name test --s3-location bucket=BUCKET_NAME,key=test/latest.tar,bundleType=zip,eTag=... --deployment-group-name <deployment-group-name> --deployment-config-name <deployment-config-name> --description <description>
```
I downloaded and check the file it come back as a zip file.
```
$ file latest.tar
latest.tar: Zip archive data, at least v2.0 to extract
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `awscli/customizations/codedeploy/push.py`
Content:
```
1 # Copyright 2015 Amazon.com, Inc. or its affiliates. All Rights Reserved.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License"). You
4 # may not use this file except in compliance with the License. A copy of
5 # the License is located at
6 #
7 # http://aws.amazon.com/apache2.0/
8 #
9 # or in the "license" file accompanying this file. This file is
10 # distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
11 # ANY KIND, either express or implied. See the License for the specific
12 # language governing permissions and limitations under the License.
13
14 import os
15 import sys
16 import zipfile
17 import tempfile
18 import contextlib
19 from datetime import datetime
20
21 from botocore.exceptions import ClientError
22
23 from awscli.compat import six
24 from awscli.customizations.codedeploy.utils import validate_s3_location
25 from awscli.customizations.commands import BasicCommand
26 from awscli.compat import ZIP_COMPRESSION_MODE
27
28
29 ONE_MB = 1 << 20
30 MULTIPART_LIMIT = 6 * ONE_MB
31
32
33 class Push(BasicCommand):
34 NAME = 'push'
35
36 DESCRIPTION = (
37 'Bundles and uploads to Amazon Simple Storage Service (Amazon S3) an '
38 'application revision, which is an archive file that contains '
39 'deployable content and an accompanying Application Specification '
40 'file (AppSpec file). If the upload is successful, a message is '
41 'returned that describes how to call the create-deployment command to '
42 'deploy the application revision from Amazon S3 to target Amazon '
43 'Elastic Compute Cloud (Amazon EC2) instances.'
44 )
45
46 ARG_TABLE = [
47 {
48 'name': 'application-name',
49 'synopsis': '--application-name <app-name>',
50 'required': True,
51 'help_text': (
52 'Required. The name of the AWS CodeDeploy application to be '
53 'associated with the application revision.'
54 )
55 },
56 {
57 'name': 's3-location',
58 'synopsis': '--s3-location s3://<bucket>/<key>',
59 'required': True,
60 'help_text': (
61 'Required. Information about the location of the application '
62 'revision to be uploaded to Amazon S3. You must specify both '
63 'a bucket and a key that represent the Amazon S3 bucket name '
64 'and the object key name. Use the format '
65 's3://\<bucket\>/\<key\>'
66 )
67 },
68 {
69 'name': 'ignore-hidden-files',
70 'action': 'store_true',
71 'default': False,
72 'group_name': 'ignore-hidden-files',
73 'help_text': (
74 'Optional. Set the --ignore-hidden-files flag to not bundle '
75 'and upload hidden files to Amazon S3; otherwise, set the '
76 '--no-ignore-hidden-files flag (the default) to bundle and '
77 'upload hidden files to Amazon S3.'
78 )
79 },
80 {
81 'name': 'no-ignore-hidden-files',
82 'action': 'store_true',
83 'default': False,
84 'group_name': 'ignore-hidden-files'
85 },
86 {
87 'name': 'source',
88 'synopsis': '--source <path>',
89 'default': '.',
90 'help_text': (
91 'Optional. The location of the deployable content and the '
92 'accompanying AppSpec file on the development machine to be '
93 'bundled and uploaded to Amazon S3. If not specified, the '
94 'current directory is used.'
95 )
96 },
97 {
98 'name': 'description',
99 'synopsis': '--description <description>',
100 'help_text': (
101 'Optional. A comment that summarizes the application '
102 'revision. If not specified, the default string "Uploaded by '
103 'AWS CLI \'time\' UTC" is used, where \'time\' is the current '
104 'system time in Coordinated Universal Time (UTC).'
105 )
106 }
107 ]
108
109 def _run_main(self, parsed_args, parsed_globals):
110 self._validate_args(parsed_args)
111 self.codedeploy = self._session.create_client(
112 'codedeploy',
113 region_name=parsed_globals.region,
114 endpoint_url=parsed_globals.endpoint_url,
115 verify=parsed_globals.verify_ssl
116 )
117 self.s3 = self._session.create_client(
118 's3',
119 region_name=parsed_globals.region
120 )
121 self._push(parsed_args)
122
123 def _validate_args(self, parsed_args):
124 validate_s3_location(parsed_args, 's3_location')
125 if parsed_args.ignore_hidden_files \
126 and parsed_args.no_ignore_hidden_files:
127 raise RuntimeError(
128 'You cannot specify both --ignore-hidden-files and '
129 '--no-ignore-hidden-files.'
130 )
131 if not parsed_args.description:
132 parsed_args.description = (
133 'Uploaded by AWS CLI {0} UTC'.format(
134 datetime.utcnow().isoformat()
135 )
136 )
137
138 def _push(self, params):
139 with self._compress(
140 params.source,
141 params.ignore_hidden_files
142 ) as bundle:
143 try:
144 upload_response = self._upload_to_s3(params, bundle)
145 params.eTag = upload_response['ETag'].replace('"', "")
146 if 'VersionId' in upload_response:
147 params.version = upload_response['VersionId']
148 except Exception as e:
149 raise RuntimeError(
150 'Failed to upload \'%s\' to \'%s\': %s' %
151 (params.source,
152 params.s3_location,
153 str(e))
154 )
155 self._register_revision(params)
156
157 if 'version' in params:
158 version_string = ',version={0}'.format(params.version)
159 else:
160 version_string = ''
161 s3location_string = (
162 '--s3-location bucket={0},key={1},'
163 'bundleType=zip,eTag={2}{3}'.format(
164 params.bucket,
165 params.key,
166 params.eTag,
167 version_string
168 )
169 )
170 sys.stdout.write(
171 'To deploy with this revision, run:\n'
172 'aws deploy create-deployment '
173 '--application-name {0} {1} '
174 '--deployment-group-name <deployment-group-name> '
175 '--deployment-config-name <deployment-config-name> '
176 '--description <description>\n'.format(
177 params.application_name,
178 s3location_string
179 )
180 )
181
182 @contextlib.contextmanager
183 def _compress(self, source, ignore_hidden_files=False):
184 source_path = os.path.abspath(source)
185 appspec_path = os.path.sep.join([source_path, 'appspec.yml'])
186 with tempfile.TemporaryFile('w+b') as tf:
187 zf = zipfile.ZipFile(tf, 'w', allowZip64=True)
188 # Using 'try'/'finally' instead of 'with' statement since ZipFile
189 # does not have support context manager in Python 2.6.
190 try:
191 contains_appspec = False
192 for root, dirs, files in os.walk(source, topdown=True):
193 if ignore_hidden_files:
194 files = [fn for fn in files if not fn.startswith('.')]
195 dirs[:] = [dn for dn in dirs if not dn.startswith('.')]
196 for fn in files:
197 filename = os.path.join(root, fn)
198 filename = os.path.abspath(filename)
199 arcname = filename[len(source_path) + 1:]
200 if filename == appspec_path:
201 contains_appspec = True
202 zf.write(filename, arcname, ZIP_COMPRESSION_MODE)
203 if not contains_appspec:
204 raise RuntimeError(
205 '{0} was not found'.format(appspec_path)
206 )
207 finally:
208 zf.close()
209 yield tf
210
211 def _upload_to_s3(self, params, bundle):
212 size_remaining = self._bundle_size(bundle)
213 if size_remaining < MULTIPART_LIMIT:
214 return self.s3.put_object(
215 Bucket=params.bucket,
216 Key=params.key,
217 Body=bundle
218 )
219 else:
220 return self._multipart_upload_to_s3(
221 params,
222 bundle,
223 size_remaining
224 )
225
226 def _bundle_size(self, bundle):
227 bundle.seek(0, 2)
228 size = bundle.tell()
229 bundle.seek(0)
230 return size
231
232 def _multipart_upload_to_s3(self, params, bundle, size_remaining):
233 create_response = self.s3.create_multipart_upload(
234 Bucket=params.bucket,
235 Key=params.key
236 )
237 upload_id = create_response['UploadId']
238 try:
239 part_num = 1
240 multipart_list = []
241 bundle.seek(0)
242 while size_remaining > 0:
243 data = bundle.read(MULTIPART_LIMIT)
244 upload_response = self.s3.upload_part(
245 Bucket=params.bucket,
246 Key=params.key,
247 UploadId=upload_id,
248 PartNumber=part_num,
249 Body=six.BytesIO(data)
250 )
251 multipart_list.append({
252 'PartNumber': part_num,
253 'ETag': upload_response['ETag']
254 })
255 part_num += 1
256 size_remaining -= len(data)
257 return self.s3.complete_multipart_upload(
258 Bucket=params.bucket,
259 Key=params.key,
260 UploadId=upload_id,
261 MultipartUpload={'Parts': multipart_list}
262 )
263 except ClientError as e:
264 self.s3.abort_multipart_upload(
265 Bucket=params.bucket,
266 Key=params.key,
267 UploadId=upload_id
268 )
269 raise e
270
271 def _register_revision(self, params):
272 revision = {
273 'revisionType': 'S3',
274 's3Location': {
275 'bucket': params.bucket,
276 'key': params.key,
277 'bundleType': 'zip',
278 'eTag': params.eTag
279 }
280 }
281 if 'version' in params:
282 revision['s3Location']['version'] = params.version
283 self.codedeploy.register_application_revision(
284 applicationName=params.application_name,
285 revision=revision,
286 description=params.description
287 )
288
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/awscli/customizations/codedeploy/push.py b/awscli/customizations/codedeploy/push.py
--- a/awscli/customizations/codedeploy/push.py
+++ b/awscli/customizations/codedeploy/push.py
@@ -35,7 +35,7 @@
DESCRIPTION = (
'Bundles and uploads to Amazon Simple Storage Service (Amazon S3) an '
- 'application revision, which is an archive file that contains '
+ 'application revision, which is a zip archive file that contains '
'deployable content and an accompanying Application Specification '
'file (AppSpec file). If the upload is successful, a message is '
'returned that describes how to call the create-deployment command to '
@@ -61,8 +61,8 @@
'Required. Information about the location of the application '
'revision to be uploaded to Amazon S3. You must specify both '
'a bucket and a key that represent the Amazon S3 bucket name '
- 'and the object key name. Use the format '
- 's3://\<bucket\>/\<key\>'
+ 'and the object key name. Content will be zipped before '
+ 'uploading. Use the format s3://\<bucket\>/\<key\>'
)
},
{
@@ -90,7 +90,7 @@
'help_text': (
'Optional. The location of the deployable content and the '
'accompanying AppSpec file on the development machine to be '
- 'bundled and uploaded to Amazon S3. If not specified, the '
+ 'zipped and uploaded to Amazon S3. If not specified, the '
'current directory is used.'
)
},
|
{"golden_diff": "diff --git a/awscli/customizations/codedeploy/push.py b/awscli/customizations/codedeploy/push.py\n--- a/awscli/customizations/codedeploy/push.py\n+++ b/awscli/customizations/codedeploy/push.py\n@@ -35,7 +35,7 @@\n \n DESCRIPTION = (\n 'Bundles and uploads to Amazon Simple Storage Service (Amazon S3) an '\n- 'application revision, which is an archive file that contains '\n+ 'application revision, which is a zip archive file that contains '\n 'deployable content and an accompanying Application Specification '\n 'file (AppSpec file). If the upload is successful, a message is '\n 'returned that describes how to call the create-deployment command to '\n@@ -61,8 +61,8 @@\n 'Required. Information about the location of the application '\n 'revision to be uploaded to Amazon S3. You must specify both '\n 'a bucket and a key that represent the Amazon S3 bucket name '\n- 'and the object key name. Use the format '\n- 's3://\\<bucket\\>/\\<key\\>'\n+ 'and the object key name. Content will be zipped before '\n+ 'uploading. Use the format s3://\\<bucket\\>/\\<key\\>'\n )\n },\n {\n@@ -90,7 +90,7 @@\n 'help_text': (\n 'Optional. The location of the deployable content and the '\n 'accompanying AppSpec file on the development machine to be '\n- 'bundled and uploaded to Amazon S3. If not specified, the '\n+ 'zipped and uploaded to Amazon S3. If not specified, the '\n 'current directory is used.'\n )\n },\n", "issue": "[aws deploy push] Destination bundle type does not match extension\nWhen specifying a destination with a suffix of \".zip\" or \".tar\" or \".tar.gz\" for use with the `aws deploy push` command the resulting bundle is always only zipped.\n\n```\n$ aws deploy push --application-name test --s3-location s3://$AWS_DEPLOY_BUCKET/test/latest.tar --no-ignore-hidden-files --source .\nTo deploy with this revision, run:\naws deploy create-deployment --application-name test --s3-location bucket=BUCKET_NAME,key=test/latest.tar,bundleType=zip,eTag=... --deployment-group-name <deployment-group-name> --deployment-config-name <deployment-config-name> --description <description>\n```\n\nI downloaded and check the file it come back as a zip file.\n\n```\n$ file latest.tar \nlatest.tar: Zip archive data, at least v2.0 to extract\n```\n\n", "before_files": [{"content": "# Copyright 2015 Amazon.com, Inc. or its affiliates. All Rights Reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\"). You\n# may not use this file except in compliance with the License. A copy of\n# the License is located at\n#\n# http://aws.amazon.com/apache2.0/\n#\n# or in the \"license\" file accompanying this file. This file is\n# distributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF\n# ANY KIND, either express or implied. See the License for the specific\n# language governing permissions and limitations under the License.\n\nimport os\nimport sys\nimport zipfile\nimport tempfile\nimport contextlib\nfrom datetime import datetime\n\nfrom botocore.exceptions import ClientError\n\nfrom awscli.compat import six\nfrom awscli.customizations.codedeploy.utils import validate_s3_location\nfrom awscli.customizations.commands import BasicCommand\nfrom awscli.compat import ZIP_COMPRESSION_MODE\n\n\nONE_MB = 1 << 20\nMULTIPART_LIMIT = 6 * ONE_MB\n\n\nclass Push(BasicCommand):\n NAME = 'push'\n\n DESCRIPTION = (\n 'Bundles and uploads to Amazon Simple Storage Service (Amazon S3) an '\n 'application revision, which is an archive file that contains '\n 'deployable content and an accompanying Application Specification '\n 'file (AppSpec file). If the upload is successful, a message is '\n 'returned that describes how to call the create-deployment command to '\n 'deploy the application revision from Amazon S3 to target Amazon '\n 'Elastic Compute Cloud (Amazon EC2) instances.'\n )\n\n ARG_TABLE = [\n {\n 'name': 'application-name',\n 'synopsis': '--application-name <app-name>',\n 'required': True,\n 'help_text': (\n 'Required. The name of the AWS CodeDeploy application to be '\n 'associated with the application revision.'\n )\n },\n {\n 'name': 's3-location',\n 'synopsis': '--s3-location s3://<bucket>/<key>',\n 'required': True,\n 'help_text': (\n 'Required. Information about the location of the application '\n 'revision to be uploaded to Amazon S3. You must specify both '\n 'a bucket and a key that represent the Amazon S3 bucket name '\n 'and the object key name. Use the format '\n 's3://\\<bucket\\>/\\<key\\>'\n )\n },\n {\n 'name': 'ignore-hidden-files',\n 'action': 'store_true',\n 'default': False,\n 'group_name': 'ignore-hidden-files',\n 'help_text': (\n 'Optional. Set the --ignore-hidden-files flag to not bundle '\n 'and upload hidden files to Amazon S3; otherwise, set the '\n '--no-ignore-hidden-files flag (the default) to bundle and '\n 'upload hidden files to Amazon S3.'\n )\n },\n {\n 'name': 'no-ignore-hidden-files',\n 'action': 'store_true',\n 'default': False,\n 'group_name': 'ignore-hidden-files'\n },\n {\n 'name': 'source',\n 'synopsis': '--source <path>',\n 'default': '.',\n 'help_text': (\n 'Optional. The location of the deployable content and the '\n 'accompanying AppSpec file on the development machine to be '\n 'bundled and uploaded to Amazon S3. If not specified, the '\n 'current directory is used.'\n )\n },\n {\n 'name': 'description',\n 'synopsis': '--description <description>',\n 'help_text': (\n 'Optional. A comment that summarizes the application '\n 'revision. If not specified, the default string \"Uploaded by '\n 'AWS CLI \\'time\\' UTC\" is used, where \\'time\\' is the current '\n 'system time in Coordinated Universal Time (UTC).'\n )\n }\n ]\n\n def _run_main(self, parsed_args, parsed_globals):\n self._validate_args(parsed_args)\n self.codedeploy = self._session.create_client(\n 'codedeploy',\n region_name=parsed_globals.region,\n endpoint_url=parsed_globals.endpoint_url,\n verify=parsed_globals.verify_ssl\n )\n self.s3 = self._session.create_client(\n 's3',\n region_name=parsed_globals.region\n )\n self._push(parsed_args)\n\n def _validate_args(self, parsed_args):\n validate_s3_location(parsed_args, 's3_location')\n if parsed_args.ignore_hidden_files \\\n and parsed_args.no_ignore_hidden_files:\n raise RuntimeError(\n 'You cannot specify both --ignore-hidden-files and '\n '--no-ignore-hidden-files.'\n )\n if not parsed_args.description:\n parsed_args.description = (\n 'Uploaded by AWS CLI {0} UTC'.format(\n datetime.utcnow().isoformat()\n )\n )\n\n def _push(self, params):\n with self._compress(\n params.source,\n params.ignore_hidden_files\n ) as bundle:\n try:\n upload_response = self._upload_to_s3(params, bundle)\n params.eTag = upload_response['ETag'].replace('\"', \"\")\n if 'VersionId' in upload_response:\n params.version = upload_response['VersionId']\n except Exception as e:\n raise RuntimeError(\n 'Failed to upload \\'%s\\' to \\'%s\\': %s' %\n (params.source,\n params.s3_location,\n str(e))\n )\n self._register_revision(params)\n\n if 'version' in params:\n version_string = ',version={0}'.format(params.version)\n else:\n version_string = ''\n s3location_string = (\n '--s3-location bucket={0},key={1},'\n 'bundleType=zip,eTag={2}{3}'.format(\n params.bucket,\n params.key,\n params.eTag,\n version_string\n )\n )\n sys.stdout.write(\n 'To deploy with this revision, run:\\n'\n 'aws deploy create-deployment '\n '--application-name {0} {1} '\n '--deployment-group-name <deployment-group-name> '\n '--deployment-config-name <deployment-config-name> '\n '--description <description>\\n'.format(\n params.application_name,\n s3location_string\n )\n )\n\n @contextlib.contextmanager\n def _compress(self, source, ignore_hidden_files=False):\n source_path = os.path.abspath(source)\n appspec_path = os.path.sep.join([source_path, 'appspec.yml'])\n with tempfile.TemporaryFile('w+b') as tf:\n zf = zipfile.ZipFile(tf, 'w', allowZip64=True)\n # Using 'try'/'finally' instead of 'with' statement since ZipFile\n # does not have support context manager in Python 2.6.\n try:\n contains_appspec = False\n for root, dirs, files in os.walk(source, topdown=True):\n if ignore_hidden_files:\n files = [fn for fn in files if not fn.startswith('.')]\n dirs[:] = [dn for dn in dirs if not dn.startswith('.')]\n for fn in files:\n filename = os.path.join(root, fn)\n filename = os.path.abspath(filename)\n arcname = filename[len(source_path) + 1:]\n if filename == appspec_path:\n contains_appspec = True\n zf.write(filename, arcname, ZIP_COMPRESSION_MODE)\n if not contains_appspec:\n raise RuntimeError(\n '{0} was not found'.format(appspec_path)\n )\n finally:\n zf.close()\n yield tf\n\n def _upload_to_s3(self, params, bundle):\n size_remaining = self._bundle_size(bundle)\n if size_remaining < MULTIPART_LIMIT:\n return self.s3.put_object(\n Bucket=params.bucket,\n Key=params.key,\n Body=bundle\n )\n else:\n return self._multipart_upload_to_s3(\n params,\n bundle,\n size_remaining\n )\n\n def _bundle_size(self, bundle):\n bundle.seek(0, 2)\n size = bundle.tell()\n bundle.seek(0)\n return size\n\n def _multipart_upload_to_s3(self, params, bundle, size_remaining):\n create_response = self.s3.create_multipart_upload(\n Bucket=params.bucket,\n Key=params.key\n )\n upload_id = create_response['UploadId']\n try:\n part_num = 1\n multipart_list = []\n bundle.seek(0)\n while size_remaining > 0:\n data = bundle.read(MULTIPART_LIMIT)\n upload_response = self.s3.upload_part(\n Bucket=params.bucket,\n Key=params.key,\n UploadId=upload_id,\n PartNumber=part_num,\n Body=six.BytesIO(data)\n )\n multipart_list.append({\n 'PartNumber': part_num,\n 'ETag': upload_response['ETag']\n })\n part_num += 1\n size_remaining -= len(data)\n return self.s3.complete_multipart_upload(\n Bucket=params.bucket,\n Key=params.key,\n UploadId=upload_id,\n MultipartUpload={'Parts': multipart_list}\n )\n except ClientError as e:\n self.s3.abort_multipart_upload(\n Bucket=params.bucket,\n Key=params.key,\n UploadId=upload_id\n )\n raise e\n\n def _register_revision(self, params):\n revision = {\n 'revisionType': 'S3',\n 's3Location': {\n 'bucket': params.bucket,\n 'key': params.key,\n 'bundleType': 'zip',\n 'eTag': params.eTag\n }\n }\n if 'version' in params:\n revision['s3Location']['version'] = params.version\n self.codedeploy.register_application_revision(\n applicationName=params.application_name,\n revision=revision,\n description=params.description\n )\n", "path": "awscli/customizations/codedeploy/push.py"}], "after_files": [{"content": "# Copyright 2015 Amazon.com, Inc. or its affiliates. All Rights Reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\"). You\n# may not use this file except in compliance with the License. A copy of\n# the License is located at\n#\n# http://aws.amazon.com/apache2.0/\n#\n# or in the \"license\" file accompanying this file. This file is\n# distributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF\n# ANY KIND, either express or implied. See the License for the specific\n# language governing permissions and limitations under the License.\n\nimport os\nimport sys\nimport zipfile\nimport tempfile\nimport contextlib\nfrom datetime import datetime\n\nfrom botocore.exceptions import ClientError\n\nfrom awscli.compat import six\nfrom awscli.customizations.codedeploy.utils import validate_s3_location\nfrom awscli.customizations.commands import BasicCommand\nfrom awscli.compat import ZIP_COMPRESSION_MODE\n\n\nONE_MB = 1 << 20\nMULTIPART_LIMIT = 6 * ONE_MB\n\n\nclass Push(BasicCommand):\n NAME = 'push'\n\n DESCRIPTION = (\n 'Bundles and uploads to Amazon Simple Storage Service (Amazon S3) an '\n 'application revision, which is a zip archive file that contains '\n 'deployable content and an accompanying Application Specification '\n 'file (AppSpec file). If the upload is successful, a message is '\n 'returned that describes how to call the create-deployment command to '\n 'deploy the application revision from Amazon S3 to target Amazon '\n 'Elastic Compute Cloud (Amazon EC2) instances.'\n )\n\n ARG_TABLE = [\n {\n 'name': 'application-name',\n 'synopsis': '--application-name <app-name>',\n 'required': True,\n 'help_text': (\n 'Required. The name of the AWS CodeDeploy application to be '\n 'associated with the application revision.'\n )\n },\n {\n 'name': 's3-location',\n 'synopsis': '--s3-location s3://<bucket>/<key>',\n 'required': True,\n 'help_text': (\n 'Required. Information about the location of the application '\n 'revision to be uploaded to Amazon S3. You must specify both '\n 'a bucket and a key that represent the Amazon S3 bucket name '\n 'and the object key name. Content will be zipped before '\n 'uploading. Use the format s3://\\<bucket\\>/\\<key\\>'\n )\n },\n {\n 'name': 'ignore-hidden-files',\n 'action': 'store_true',\n 'default': False,\n 'group_name': 'ignore-hidden-files',\n 'help_text': (\n 'Optional. Set the --ignore-hidden-files flag to not bundle '\n 'and upload hidden files to Amazon S3; otherwise, set the '\n '--no-ignore-hidden-files flag (the default) to bundle and '\n 'upload hidden files to Amazon S3.'\n )\n },\n {\n 'name': 'no-ignore-hidden-files',\n 'action': 'store_true',\n 'default': False,\n 'group_name': 'ignore-hidden-files'\n },\n {\n 'name': 'source',\n 'synopsis': '--source <path>',\n 'default': '.',\n 'help_text': (\n 'Optional. The location of the deployable content and the '\n 'accompanying AppSpec file on the development machine to be '\n 'zipped and uploaded to Amazon S3. If not specified, the '\n 'current directory is used.'\n )\n },\n {\n 'name': 'description',\n 'synopsis': '--description <description>',\n 'help_text': (\n 'Optional. A comment that summarizes the application '\n 'revision. If not specified, the default string \"Uploaded by '\n 'AWS CLI \\'time\\' UTC\" is used, where \\'time\\' is the current '\n 'system time in Coordinated Universal Time (UTC).'\n )\n }\n ]\n\n def _run_main(self, parsed_args, parsed_globals):\n self._validate_args(parsed_args)\n self.codedeploy = self._session.create_client(\n 'codedeploy',\n region_name=parsed_globals.region,\n endpoint_url=parsed_globals.endpoint_url,\n verify=parsed_globals.verify_ssl\n )\n self.s3 = self._session.create_client(\n 's3',\n region_name=parsed_globals.region\n )\n self._push(parsed_args)\n\n def _validate_args(self, parsed_args):\n validate_s3_location(parsed_args, 's3_location')\n if parsed_args.ignore_hidden_files \\\n and parsed_args.no_ignore_hidden_files:\n raise RuntimeError(\n 'You cannot specify both --ignore-hidden-files and '\n '--no-ignore-hidden-files.'\n )\n if not parsed_args.description:\n parsed_args.description = (\n 'Uploaded by AWS CLI {0} UTC'.format(\n datetime.utcnow().isoformat()\n )\n )\n\n def _push(self, params):\n with self._compress(\n params.source,\n params.ignore_hidden_files\n ) as bundle:\n try:\n upload_response = self._upload_to_s3(params, bundle)\n params.eTag = upload_response['ETag'].replace('\"', \"\")\n if 'VersionId' in upload_response:\n params.version = upload_response['VersionId']\n except Exception as e:\n raise RuntimeError(\n 'Failed to upload \\'%s\\' to \\'%s\\': %s' %\n (params.source,\n params.s3_location,\n str(e))\n )\n self._register_revision(params)\n\n if 'version' in params:\n version_string = ',version={0}'.format(params.version)\n else:\n version_string = ''\n s3location_string = (\n '--s3-location bucket={0},key={1},'\n 'bundleType=zip,eTag={2}{3}'.format(\n params.bucket,\n params.key,\n params.eTag,\n version_string\n )\n )\n sys.stdout.write(\n 'To deploy with this revision, run:\\n'\n 'aws deploy create-deployment '\n '--application-name {0} {1} '\n '--deployment-group-name <deployment-group-name> '\n '--deployment-config-name <deployment-config-name> '\n '--description <description>\\n'.format(\n params.application_name,\n s3location_string\n )\n )\n\n @contextlib.contextmanager\n def _compress(self, source, ignore_hidden_files=False):\n source_path = os.path.abspath(source)\n appspec_path = os.path.sep.join([source_path, 'appspec.yml'])\n with tempfile.TemporaryFile('w+b') as tf:\n zf = zipfile.ZipFile(tf, 'w', allowZip64=True)\n # Using 'try'/'finally' instead of 'with' statement since ZipFile\n # does not have support context manager in Python 2.6.\n try:\n contains_appspec = False\n for root, dirs, files in os.walk(source, topdown=True):\n if ignore_hidden_files:\n files = [fn for fn in files if not fn.startswith('.')]\n dirs[:] = [dn for dn in dirs if not dn.startswith('.')]\n for fn in files:\n filename = os.path.join(root, fn)\n filename = os.path.abspath(filename)\n arcname = filename[len(source_path) + 1:]\n if filename == appspec_path:\n contains_appspec = True\n zf.write(filename, arcname, ZIP_COMPRESSION_MODE)\n if not contains_appspec:\n raise RuntimeError(\n '{0} was not found'.format(appspec_path)\n )\n finally:\n zf.close()\n yield tf\n\n def _upload_to_s3(self, params, bundle):\n size_remaining = self._bundle_size(bundle)\n if size_remaining < MULTIPART_LIMIT:\n return self.s3.put_object(\n Bucket=params.bucket,\n Key=params.key,\n Body=bundle\n )\n else:\n return self._multipart_upload_to_s3(\n params,\n bundle,\n size_remaining\n )\n\n def _bundle_size(self, bundle):\n bundle.seek(0, 2)\n size = bundle.tell()\n bundle.seek(0)\n return size\n\n def _multipart_upload_to_s3(self, params, bundle, size_remaining):\n create_response = self.s3.create_multipart_upload(\n Bucket=params.bucket,\n Key=params.key\n )\n upload_id = create_response['UploadId']\n try:\n part_num = 1\n multipart_list = []\n bundle.seek(0)\n while size_remaining > 0:\n data = bundle.read(MULTIPART_LIMIT)\n upload_response = self.s3.upload_part(\n Bucket=params.bucket,\n Key=params.key,\n UploadId=upload_id,\n PartNumber=part_num,\n Body=six.BytesIO(data)\n )\n multipart_list.append({\n 'PartNumber': part_num,\n 'ETag': upload_response['ETag']\n })\n part_num += 1\n size_remaining -= len(data)\n return self.s3.complete_multipart_upload(\n Bucket=params.bucket,\n Key=params.key,\n UploadId=upload_id,\n MultipartUpload={'Parts': multipart_list}\n )\n except ClientError as e:\n self.s3.abort_multipart_upload(\n Bucket=params.bucket,\n Key=params.key,\n UploadId=upload_id\n )\n raise e\n\n def _register_revision(self, params):\n revision = {\n 'revisionType': 'S3',\n 's3Location': {\n 'bucket': params.bucket,\n 'key': params.key,\n 'bundleType': 'zip',\n 'eTag': params.eTag\n }\n }\n if 'version' in params:\n revision['s3Location']['version'] = params.version\n self.codedeploy.register_application_revision(\n applicationName=params.application_name,\n revision=revision,\n description=params.description\n )\n", "path": "awscli/customizations/codedeploy/push.py"}]}
| 3,338 | 384 |
gh_patches_debug_10110
|
rasdani/github-patches
|
git_diff
|
spack__spack-40298
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Installation issue: [email protected] +cuda %[email protected]
### Steps to reproduce the issue
I ran into this when trying to build `mpich %[email protected] +cuda netmod=ucx pmi=pmix ^[email protected] +allow-unsupported-compilers`
```console
$ spack spec -l mpich%[email protected]+cuda netmod=ucx pmi=pmix ^[email protected]
Input spec
--------------------------------
- mpich%[email protected]+cuda netmod=ucx pmi=pmix
- ^[email protected]
Concretized
--------------------------------
- vl25zhp [email protected]%[email protected]~argobots+cuda+fortran~hcoll+hwloc~hydra+libxml2+pci~rocm+romio~slurm~vci~verbs+wrapperrpath build_system=autotools cuda_arch=80 datatype-engine=auto device=ch4 netmod=ucx pmi=pmix arch=linux-rhel8-zen2
[e] tatyw2o ^[email protected]%[email protected]+allow-unsupported-compilers~dev build_system=generic arch=linux-rhel8-zen2
[+] oaezgck ^[email protected]%[email protected] build_system=autotools patches=440b954 arch=linux-rhel8-zen2
[+] wda76ac ^[email protected]%[email protected]~cairo+cuda~gl~libudev+libxml2~netloc~nvml~oneapi-level-zero~opencl+pci~rocm build_system=autotools cuda_arch=80 libs=shared,static arch=linux-rhel8-zen2
[+] v3xl3ra ^[email protected]%[email protected]~symlinks+termlib abi=none build_system=autotools arch=linux-rhel8-zen2
[e] jxaxqp2 ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[+] a25ibkd ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[e] ljdxawj ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[-] 6gqawar ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[+] 6tqy7tj ^[email protected]%[email protected]+pic~python+shared build_system=autotools arch=linux-rhel8-zen2
[+] gmdjnou ^[email protected]%[email protected] build_system=autotools libs=shared,static arch=linux-rhel8-zen2
[+] wv6bhnf ^[email protected]%[email protected]+pic build_system=autotools libs=shared,static arch=linux-rhel8-zen2
[+] gl4jfjp ^[email protected]%[email protected]+compat+opt build_system=autotools patches=299b958,ae9077a,b692621 arch=linux-rhel8-zen2
[e] jxaxqp2 ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[+] iiz3ymd ^[email protected]%[email protected]~docs+pmi_backwards_compatibility~python~restful build_system=autotools arch=linux-rhel8-zen2
[+] zpd4eva ^[email protected]%[email protected]+openssl build_system=autotools arch=linux-rhel8-zen2
[+] vfrxdbw ^[email protected]%[email protected]~docs+shared build_system=generic certs=mozilla arch=linux-rhel8-zen2
[-] f7zqyjr ^ca-certificates-mozilla@2023-05-30%[email protected] build_system=generic arch=linux-rhel8-zen2
[e] mbywbad ^[email protected]%[email protected]+cpanm+opcode+open+shared+threads build_system=generic patches=8cf4302 arch=linux-rhel8-zen2
[+] giw5sed ^[email protected]%[email protected]~assertions~backtrace_detail~cma~cuda~dc~debug~dm+examples~gdrcopy~gtest~ib_hw_tm~java~knem~logging~mlx5_dv+numa+openmp+optimizations~parameter_checking+pic~rc~rdmacm~rocm+thread_multiple~ucg~ud~verbs~vfs~xpmem build_system=autotools libs=shared,static opt=3 simd=auto arch=linux-rhel8-zen2
[+] 2hrbodu ^[email protected]%[email protected] build_system=autotools patches=4e1d78c,62fc8a8,ff37630 arch=linux-rhel8-zen2
[e] 34ciftm ^[email protected]%[email protected] build_system=autotools patches=7793209 arch=linux-rhel8-zen2
[e] 4awjffi ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[e] v6g426c ^[email protected]%[email protected]+sigsegv build_system=autotools patches=3877ab5,fc9b616 arch=linux-rhel8-zen2
- 3gp6itg ^[email protected]%[email protected]+cuda~rocm build_system=autotools cuda_arch=80 arch=linux-rhel8-zen2
[e] 34ciftm ^[email protected]%[email protected] build_system=autotools patches=7793209 arch=linux-rhel8-zen2
[e] 4awjffi ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[e] ljdxawj ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2
[e] v6g426c ^[email protected]%[email protected]+sigsegv build_system=autotools patches=3877ab5,fc9b616 arch=linux-rhel8-zen2
[e] vij5hij ^[email protected]%[email protected]+bz2+crypt+ctypes+dbm~debug+libxml2+lzma~nis~optimizations+pic+pyexpat+pythoncmd+readline+shared+sqlite3+ssl~tkinter+uuid+zlib build_system=generic patches=13fa8bf,b0615b2,ebdca64,f2fd060 arch=linux-rhel8-zen2
```
### Error message
<details><summary>Error message</summary>
<pre>
==> Error: ProcessError: Command exited with status 1:
'/scratch/wp11/spack/stage/spack-stage-yaksa-0.2-3gp6itg5vlljusyvsifmuuceq7q77vp5/spack-src/configure' '--prefix=/projects/deploy/install/linux-rhel8-zen2/gcc-12.3.0/yaksa-0.2-3gp6itg5vlljusyvsifmuuceq7q77vp5' '--with-cuda=/usr/local/cuda-11.8' '--with-cuda-sm=80' '--without-hip'
7 errors found in build log:
28 libtoolize: copying file 'm4/ltsugar.m4'
29 libtoolize: copying file 'm4/ltversion.m4'
30 libtoolize: copying file 'm4/lt~obsolete.m4'
31 autoreconf: running: /projects/pkgs/autotools-ac-2.69-am-1.15.1-lt-2.4.6/bin/autoconf --force
32 autoreconf: running: /projects/pkgs/autotools-ac-2.69-am-1.15.1-lt-2.4.6/bin/autoheader --force
33 autoreconf: running: automake --add-missing --copy --force-missing
>> 34 configure.ac:81: installing 'm4/ar-lib'
>> 35 configure.ac:78: installing 'm4/compile'
>> 36 configure.ac:83: installing 'm4/config.guess'
>> 37 configure.ac:83: installing 'm4/config.sub'
>> 38 configure.ac:74: installing 'm4/install-sh'
>> 39 configure.ac:74: installing 'm4/missing'
40 Makefile.am: installing 'm4/depcomp'
41 autoreconf: Leaving directory `.'
42 === done ===
43
44 Generating a helper maint/Version... done
45 ==> yaksa: Executing phase: 'configure'
...
198 checking alignment of long double... 16
199 checking cuda_runtime_api.h usability... yes
200 checking cuda_runtime_api.h presence... yes
201 checking for cuda_runtime_api.h... yes
202 checking for cudaStreamSynchronize in -lcudart... yes
203 checking whether nvcc works... no
>> 204 configure: error: CUDA was requested but it is not functional
</pre></details>
### Information on your system
* **Spack:** 0.21.0.dev0 (b6f08f1d4ef3b0ca56430c1a465d660828b45ed2)
* **Python:** 3.6.8
* **Platform:** linux-rhel8-zen2
* **Concretizer:** clingo
### Additional information
- [spack-build-out.txt](https://github.com/spack/spack/files/12778111/spack-build-out.txt)
- [spack-build-env.txt](https://github.com/spack/spack/files/12778112/spack-build-env.txt)
I can confirm that the `nvcc` from CUDA 11.8 in the system works just fine by compiling and running a CUDA dot product test code.
```
$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:33:58_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0
```
Summoning `yaksa` maintainers @hzhou @raffenet @yfguo
### General information
- [X] I have run `spack debug report` and reported the version of Spack/Python/Platform
- [X] I have run `spack maintainers <name-of-the-package>` and **@mentioned** any maintainers
- [X] I have uploaded the build log and environment files
- [X] I have searched the issues of this repo and believe this is not a duplicate
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `var/spack/repos/builtin/packages/yaksa/package.py`
Content:
```
1 # Copyright 2013-2023 Lawrence Livermore National Security, LLC and other
2 # Spack Project Developers. See the top-level COPYRIGHT file for details.
3 #
4 # SPDX-License-Identifier: (Apache-2.0 OR MIT)
5
6 from spack.package import *
7
8
9 class Yaksa(AutotoolsPackage, CudaPackage, ROCmPackage):
10 """Yaksa is a high-performance datatype engine for expressing,
11 managing and manipulating data present in noncontiguous memory
12 regions. It provides portable abstractions for structured
13 noncontiguous data layouts that are much more comprehensive compared
14 with traditional I/O vectors.
15
16 Yaksa imitates parts of the MPI Datatype system, but adds additional
17 functionality that would allow it to be used independent of MPI. It
18 provides routines for packing/unpacking, creating I/O vectors (array
19 of contiguous segments) and flattening/unflattening datatypes into
20 process-portable formats.
21
22 Yaksa's backend includes support for CPUs as well as different
23 GPUs."""
24
25 homepage = "https://www.yaksa.org"
26 url = "https://github.com/pmodels/yaksa/archive/refs/tags/v0.2.tar.gz"
27 maintainers("raffenet", "yfguo", "hzhou")
28
29 version("0.2", sha256="9401cb6153dc8c34ddb9781bbabd418fd26b0a27b5da3294ecc21af7be9c86f2")
30
31 depends_on("autoconf", type="build")
32 depends_on("automake", type="build")
33 depends_on("libtool", type="build")
34 depends_on("m4", type="build")
35 depends_on("python@3:", type="build")
36
37 def autoreconf(self, spec, prefix):
38 sh = which("sh")
39 sh("autogen.sh")
40
41 def configure_args(self):
42 spec = self.spec
43 config_args = []
44
45 config_args += self.with_or_without("cuda", activation_value="prefix")
46 if "+cuda" in spec:
47 cuda_archs = spec.variants["cuda_arch"].value
48 if "none" not in cuda_archs:
49 config_args.append("--with-cuda-sm={0}".format(",".join(cuda_archs)))
50
51 if "+rocm" in spec:
52 config_args.append("--with-hip={0}".format(spec["hip"].prefix))
53 rocm_archs = spec.variants["amdgpu_target"].value
54 if "none" not in rocm_archs:
55 config_args.append("--with-hip-sm={0}".format(",".join(rocm_archs)))
56 else:
57 config_args.append("--without-hip")
58
59 return config_args
60
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/var/spack/repos/builtin/packages/yaksa/package.py b/var/spack/repos/builtin/packages/yaksa/package.py
--- a/var/spack/repos/builtin/packages/yaksa/package.py
+++ b/var/spack/repos/builtin/packages/yaksa/package.py
@@ -47,6 +47,8 @@
cuda_archs = spec.variants["cuda_arch"].value
if "none" not in cuda_archs:
config_args.append("--with-cuda-sm={0}".format(",".join(cuda_archs)))
+ if "^cuda+allow-unsupported-compilers" in self.spec:
+ config_args.append("NVCC_FLAGS=-allow-unsupported-compiler")
if "+rocm" in spec:
config_args.append("--with-hip={0}".format(spec["hip"].prefix))
|
{"golden_diff": "diff --git a/var/spack/repos/builtin/packages/yaksa/package.py b/var/spack/repos/builtin/packages/yaksa/package.py\n--- a/var/spack/repos/builtin/packages/yaksa/package.py\n+++ b/var/spack/repos/builtin/packages/yaksa/package.py\n@@ -47,6 +47,8 @@\n cuda_archs = spec.variants[\"cuda_arch\"].value\n if \"none\" not in cuda_archs:\n config_args.append(\"--with-cuda-sm={0}\".format(\",\".join(cuda_archs)))\n+ if \"^cuda+allow-unsupported-compilers\" in self.spec:\n+ config_args.append(\"NVCC_FLAGS=-allow-unsupported-compiler\")\n \n if \"+rocm\" in spec:\n config_args.append(\"--with-hip={0}\".format(spec[\"hip\"].prefix))\n", "issue": "Installation issue: [email protected] +cuda %[email protected]\n### Steps to reproduce the issue\n\nI ran into this when trying to build `mpich %[email protected] +cuda netmod=ucx pmi=pmix ^[email protected] +allow-unsupported-compilers`\r\n\r\n```console\r\n$ spack spec -l mpich%[email protected]+cuda netmod=ucx pmi=pmix ^[email protected]\r\nInput spec\r\n--------------------------------\r\n - mpich%[email protected]+cuda netmod=ucx pmi=pmix\r\n - ^[email protected]\r\n \r\n Concretized\r\n--------------------------------\r\n - vl25zhp [email protected]%[email protected]~argobots+cuda+fortran~hcoll+hwloc~hydra+libxml2+pci~rocm+romio~slurm~vci~verbs+wrapperrpath build_system=autotools cuda_arch=80 datatype-engine=auto device=ch4 netmod=ucx pmi=pmix arch=linux-rhel8-zen2\r\n[e] tatyw2o ^[email protected]%[email protected]+allow-unsupported-compilers~dev build_system=generic arch=linux-rhel8-zen2\r\n[+] oaezgck ^[email protected]%[email protected] build_system=autotools patches=440b954 arch=linux-rhel8-zen2\r\n[+] wda76ac ^[email protected]%[email protected]~cairo+cuda~gl~libudev+libxml2~netloc~nvml~oneapi-level-zero~opencl+pci~rocm build_system=autotools cuda_arch=80 libs=shared,static arch=linux-rhel8-zen2\r\n[+] v3xl3ra ^[email protected]%[email protected]~symlinks+termlib abi=none build_system=autotools arch=linux-rhel8-zen2\r\n[e] jxaxqp2 ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[+] a25ibkd ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[e] ljdxawj ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[-] 6gqawar ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[+] 6tqy7tj ^[email protected]%[email protected]+pic~python+shared build_system=autotools arch=linux-rhel8-zen2\r\n[+] gmdjnou ^[email protected]%[email protected] build_system=autotools libs=shared,static arch=linux-rhel8-zen2\r\n[+] wv6bhnf ^[email protected]%[email protected]+pic build_system=autotools libs=shared,static arch=linux-rhel8-zen2\r\n[+] gl4jfjp ^[email protected]%[email protected]+compat+opt build_system=autotools patches=299b958,ae9077a,b692621 arch=linux-rhel8-zen2\r\n[e] jxaxqp2 ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[+] iiz3ymd ^[email protected]%[email protected]~docs+pmi_backwards_compatibility~python~restful build_system=autotools arch=linux-rhel8-zen2\r\n[+] zpd4eva ^[email protected]%[email protected]+openssl build_system=autotools arch=linux-rhel8-zen2\r\n[+] vfrxdbw ^[email protected]%[email protected]~docs+shared build_system=generic certs=mozilla arch=linux-rhel8-zen2\r\n[-] f7zqyjr ^ca-certificates-mozilla@2023-05-30%[email protected] build_system=generic arch=linux-rhel8-zen2\r\n[e] mbywbad ^[email protected]%[email protected]+cpanm+opcode+open+shared+threads build_system=generic patches=8cf4302 arch=linux-rhel8-zen2\r\n[+] giw5sed ^[email protected]%[email protected]~assertions~backtrace_detail~cma~cuda~dc~debug~dm+examples~gdrcopy~gtest~ib_hw_tm~java~knem~logging~mlx5_dv+numa+openmp+optimizations~parameter_checking+pic~rc~rdmacm~rocm+thread_multiple~ucg~ud~verbs~vfs~xpmem build_system=autotools libs=shared,static opt=3 simd=auto arch=linux-rhel8-zen2\r\n[+] 2hrbodu ^[email protected]%[email protected] build_system=autotools patches=4e1d78c,62fc8a8,ff37630 arch=linux-rhel8-zen2\r\n[e] 34ciftm ^[email protected]%[email protected] build_system=autotools patches=7793209 arch=linux-rhel8-zen2\r\n[e] 4awjffi ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[e] v6g426c ^[email protected]%[email protected]+sigsegv build_system=autotools patches=3877ab5,fc9b616 arch=linux-rhel8-zen2\r\n - 3gp6itg ^[email protected]%[email protected]+cuda~rocm build_system=autotools cuda_arch=80 arch=linux-rhel8-zen2\r\n[e] 34ciftm ^[email protected]%[email protected] build_system=autotools patches=7793209 arch=linux-rhel8-zen2\r\n[e] 4awjffi ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[e] ljdxawj ^[email protected]%[email protected] build_system=autotools arch=linux-rhel8-zen2\r\n[e] v6g426c ^[email protected]%[email protected]+sigsegv build_system=autotools patches=3877ab5,fc9b616 arch=linux-rhel8-zen2\r\n[e] vij5hij ^[email protected]%[email protected]+bz2+crypt+ctypes+dbm~debug+libxml2+lzma~nis~optimizations+pic+pyexpat+pythoncmd+readline+shared+sqlite3+ssl~tkinter+uuid+zlib build_system=generic patches=13fa8bf,b0615b2,ebdca64,f2fd060 arch=linux-rhel8-zen2\r\n```\r\n\r\n\n\n### Error message\n\n<details><summary>Error message</summary>\r\n\r\n<pre>\r\n==> Error: ProcessError: Command exited with status 1:\r\n '/scratch/wp11/spack/stage/spack-stage-yaksa-0.2-3gp6itg5vlljusyvsifmuuceq7q77vp5/spack-src/configure' '--prefix=/projects/deploy/install/linux-rhel8-zen2/gcc-12.3.0/yaksa-0.2-3gp6itg5vlljusyvsifmuuceq7q77vp5' '--with-cuda=/usr/local/cuda-11.8' '--with-cuda-sm=80' '--without-hip'\r\n\r\n7 errors found in build log:\r\n 28 libtoolize: copying file 'm4/ltsugar.m4'\r\n 29 libtoolize: copying file 'm4/ltversion.m4'\r\n 30 libtoolize: copying file 'm4/lt~obsolete.m4'\r\n 31 autoreconf: running: /projects/pkgs/autotools-ac-2.69-am-1.15.1-lt-2.4.6/bin/autoconf --force\r\n 32 autoreconf: running: /projects/pkgs/autotools-ac-2.69-am-1.15.1-lt-2.4.6/bin/autoheader --force\r\n 33 autoreconf: running: automake --add-missing --copy --force-missing\r\n >> 34 configure.ac:81: installing 'm4/ar-lib'\r\n >> 35 configure.ac:78: installing 'm4/compile'\r\n >> 36 configure.ac:83: installing 'm4/config.guess'\r\n >> 37 configure.ac:83: installing 'm4/config.sub'\r\n >> 38 configure.ac:74: installing 'm4/install-sh'\r\n >> 39 configure.ac:74: installing 'm4/missing'\r\n 40 Makefile.am: installing 'm4/depcomp'\r\n 41 autoreconf: Leaving directory `.'\r\n 42 === done ===\r\n 43 \r\n 44 Generating a helper maint/Version... done\r\n 45 ==> yaksa: Executing phase: 'configure'\r\n\r\n ...\r\n\r\n 198 checking alignment of long double... 16\r\n 199 checking cuda_runtime_api.h usability... yes\r\n 200 checking cuda_runtime_api.h presence... yes\r\n 201 checking for cuda_runtime_api.h... yes\r\n 202 checking for cudaStreamSynchronize in -lcudart... yes\r\n 203 checking whether nvcc works... no\r\n >> 204 configure: error: CUDA was requested but it is not functional\r\n</pre></details>\r\n\n\n### Information on your system\n\n* **Spack:** 0.21.0.dev0 (b6f08f1d4ef3b0ca56430c1a465d660828b45ed2)\r\n* **Python:** 3.6.8\r\n* **Platform:** linux-rhel8-zen2\r\n* **Concretizer:** clingo\n\n### Additional information\n\n- [spack-build-out.txt](https://github.com/spack/spack/files/12778111/spack-build-out.txt)\r\n- [spack-build-env.txt](https://github.com/spack/spack/files/12778112/spack-build-env.txt)\r\n\r\nI can confirm that the `nvcc` from CUDA 11.8 in the system works just fine by compiling and running a CUDA dot product test code.\r\n\r\n```\r\n$ nvcc --version\r\nnvcc: NVIDIA (R) Cuda compiler driver\r\nCopyright (c) 2005-2022 NVIDIA Corporation\r\nBuilt on Wed_Sep_21_10:33:58_PDT_2022\r\nCuda compilation tools, release 11.8, V11.8.89\r\nBuild cuda_11.8.r11.8/compiler.31833905_0\r\n```\r\n\r\nSummoning `yaksa` maintainers @hzhou @raffenet @yfguo\n\n### General information\n\n- [X] I have run `spack debug report` and reported the version of Spack/Python/Platform\n- [X] I have run `spack maintainers <name-of-the-package>` and **@mentioned** any maintainers\n- [X] I have uploaded the build log and environment files\n- [X] I have searched the issues of this repo and believe this is not a duplicate\n", "before_files": [{"content": "# Copyright 2013-2023 Lawrence Livermore National Security, LLC and other\n# Spack Project Developers. See the top-level COPYRIGHT file for details.\n#\n# SPDX-License-Identifier: (Apache-2.0 OR MIT)\n\nfrom spack.package import *\n\n\nclass Yaksa(AutotoolsPackage, CudaPackage, ROCmPackage):\n \"\"\"Yaksa is a high-performance datatype engine for expressing,\n managing and manipulating data present in noncontiguous memory\n regions. It provides portable abstractions for structured\n noncontiguous data layouts that are much more comprehensive compared\n with traditional I/O vectors.\n\n Yaksa imitates parts of the MPI Datatype system, but adds additional\n functionality that would allow it to be used independent of MPI. It\n provides routines for packing/unpacking, creating I/O vectors (array\n of contiguous segments) and flattening/unflattening datatypes into\n process-portable formats.\n\n Yaksa's backend includes support for CPUs as well as different\n GPUs.\"\"\"\n\n homepage = \"https://www.yaksa.org\"\n url = \"https://github.com/pmodels/yaksa/archive/refs/tags/v0.2.tar.gz\"\n maintainers(\"raffenet\", \"yfguo\", \"hzhou\")\n\n version(\"0.2\", sha256=\"9401cb6153dc8c34ddb9781bbabd418fd26b0a27b5da3294ecc21af7be9c86f2\")\n\n depends_on(\"autoconf\", type=\"build\")\n depends_on(\"automake\", type=\"build\")\n depends_on(\"libtool\", type=\"build\")\n depends_on(\"m4\", type=\"build\")\n depends_on(\"python@3:\", type=\"build\")\n\n def autoreconf(self, spec, prefix):\n sh = which(\"sh\")\n sh(\"autogen.sh\")\n\n def configure_args(self):\n spec = self.spec\n config_args = []\n\n config_args += self.with_or_without(\"cuda\", activation_value=\"prefix\")\n if \"+cuda\" in spec:\n cuda_archs = spec.variants[\"cuda_arch\"].value\n if \"none\" not in cuda_archs:\n config_args.append(\"--with-cuda-sm={0}\".format(\",\".join(cuda_archs)))\n\n if \"+rocm\" in spec:\n config_args.append(\"--with-hip={0}\".format(spec[\"hip\"].prefix))\n rocm_archs = spec.variants[\"amdgpu_target\"].value\n if \"none\" not in rocm_archs:\n config_args.append(\"--with-hip-sm={0}\".format(\",\".join(rocm_archs)))\n else:\n config_args.append(\"--without-hip\")\n\n return config_args\n", "path": "var/spack/repos/builtin/packages/yaksa/package.py"}], "after_files": [{"content": "# Copyright 2013-2023 Lawrence Livermore National Security, LLC and other\n# Spack Project Developers. See the top-level COPYRIGHT file for details.\n#\n# SPDX-License-Identifier: (Apache-2.0 OR MIT)\n\nfrom spack.package import *\n\n\nclass Yaksa(AutotoolsPackage, CudaPackage, ROCmPackage):\n \"\"\"Yaksa is a high-performance datatype engine for expressing,\n managing and manipulating data present in noncontiguous memory\n regions. It provides portable abstractions for structured\n noncontiguous data layouts that are much more comprehensive compared\n with traditional I/O vectors.\n\n Yaksa imitates parts of the MPI Datatype system, but adds additional\n functionality that would allow it to be used independent of MPI. It\n provides routines for packing/unpacking, creating I/O vectors (array\n of contiguous segments) and flattening/unflattening datatypes into\n process-portable formats.\n\n Yaksa's backend includes support for CPUs as well as different\n GPUs.\"\"\"\n\n homepage = \"https://www.yaksa.org\"\n url = \"https://github.com/pmodels/yaksa/archive/refs/tags/v0.2.tar.gz\"\n maintainers(\"raffenet\", \"yfguo\", \"hzhou\")\n\n version(\"0.2\", sha256=\"9401cb6153dc8c34ddb9781bbabd418fd26b0a27b5da3294ecc21af7be9c86f2\")\n\n depends_on(\"autoconf\", type=\"build\")\n depends_on(\"automake\", type=\"build\")\n depends_on(\"libtool\", type=\"build\")\n depends_on(\"m4\", type=\"build\")\n depends_on(\"python@3:\", type=\"build\")\n\n def autoreconf(self, spec, prefix):\n sh = which(\"sh\")\n sh(\"autogen.sh\")\n\n def configure_args(self):\n spec = self.spec\n config_args = []\n\n config_args += self.with_or_without(\"cuda\", activation_value=\"prefix\")\n if \"+cuda\" in spec:\n cuda_archs = spec.variants[\"cuda_arch\"].value\n if \"none\" not in cuda_archs:\n config_args.append(\"--with-cuda-sm={0}\".format(\",\".join(cuda_archs)))\n if \"^cuda+allow-unsupported-compilers\" in self.spec:\n config_args.append(\"NVCC_FLAGS=-allow-unsupported-compiler\")\n\n if \"+rocm\" in spec:\n config_args.append(\"--with-hip={0}\".format(spec[\"hip\"].prefix))\n rocm_archs = spec.variants[\"amdgpu_target\"].value\n if \"none\" not in rocm_archs:\n config_args.append(\"--with-hip-sm={0}\".format(\",\".join(rocm_archs)))\n else:\n config_args.append(\"--without-hip\")\n\n return config_args\n", "path": "var/spack/repos/builtin/packages/yaksa/package.py"}]}
| 4,005 | 177 |
gh_patches_debug_35132
|
rasdani/github-patches
|
git_diff
|
CTFd__CTFd-1352
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Submission search
Search submissions akin to how users are searched
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `CTFd/admin/submissions.py`
Content:
```
1 from flask import render_template, request
2
3 from CTFd.admin import admin
4 from CTFd.models import Challenges, Submissions
5 from CTFd.utils.decorators import admins_only
6 from CTFd.utils.modes import get_model
7
8
9 @admin.route("/admin/submissions", defaults={"submission_type": None})
10 @admin.route("/admin/submissions/<submission_type>")
11 @admins_only
12 def submissions_listing(submission_type):
13 filters = {}
14 if submission_type:
15 filters["type"] = submission_type
16
17 curr_page = abs(int(request.args.get("page", 1, type=int)))
18 results_per_page = 50
19 page_start = results_per_page * (curr_page - 1)
20 page_end = results_per_page * (curr_page - 1) + results_per_page
21 sub_count = Submissions.query.filter_by(**filters).count()
22 page_count = int(sub_count / results_per_page) + (sub_count % results_per_page > 0)
23
24 Model = get_model()
25
26 submissions = (
27 Submissions.query.add_columns(
28 Submissions.id,
29 Submissions.type,
30 Submissions.challenge_id,
31 Submissions.provided,
32 Submissions.account_id,
33 Submissions.date,
34 Challenges.name.label("challenge_name"),
35 Model.name.label("team_name"),
36 )
37 .filter_by(**filters)
38 .join(Challenges)
39 .join(Model)
40 .order_by(Submissions.date.desc())
41 .slice(page_start, page_end)
42 .all()
43 )
44
45 return render_template(
46 "admin/submissions.html",
47 submissions=submissions,
48 page_count=page_count,
49 curr_page=curr_page,
50 type=submission_type,
51 )
52
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/CTFd/admin/submissions.py b/CTFd/admin/submissions.py
--- a/CTFd/admin/submissions.py
+++ b/CTFd/admin/submissions.py
@@ -1,4 +1,4 @@
-from flask import render_template, request
+from flask import render_template, request, url_for
from CTFd.admin import admin
from CTFd.models import Challenges, Submissions
@@ -10,16 +10,21 @@
@admin.route("/admin/submissions/<submission_type>")
@admins_only
def submissions_listing(submission_type):
- filters = {}
+ filters_by = {}
if submission_type:
- filters["type"] = submission_type
+ filters_by["type"] = submission_type
+ filters = []
- curr_page = abs(int(request.args.get("page", 1, type=int)))
- results_per_page = 50
- page_start = results_per_page * (curr_page - 1)
- page_end = results_per_page * (curr_page - 1) + results_per_page
- sub_count = Submissions.query.filter_by(**filters).count()
- page_count = int(sub_count / results_per_page) + (sub_count % results_per_page > 0)
+ q = request.args.get("q")
+ field = request.args.get("field")
+ page = abs(request.args.get("page", 1, type=int))
+
+ if q:
+ submissions = []
+ if Submissions.__mapper__.has_property(
+ field
+ ): # The field exists as an exposed column
+ filters.append(getattr(Submissions, field).like("%{}%".format(q)))
Model = get_model()
@@ -34,18 +39,27 @@
Challenges.name.label("challenge_name"),
Model.name.label("team_name"),
)
- .filter_by(**filters)
+ .filter_by(**filters_by)
+ .filter(*filters)
.join(Challenges)
.join(Model)
.order_by(Submissions.date.desc())
- .slice(page_start, page_end)
- .all()
+ .paginate(page=page, per_page=50)
)
+ args = dict(request.args)
+ args.pop("page", 1)
+
return render_template(
"admin/submissions.html",
submissions=submissions,
- page_count=page_count,
- curr_page=curr_page,
+ prev_page=url_for(
+ request.endpoint, type=submission_type, page=submissions.prev_num, **args
+ ),
+ next_page=url_for(
+ request.endpoint, type=submission_type, page=submissions.next_num, **args
+ ),
type=submission_type,
+ q=q,
+ field=field,
)
|
{"golden_diff": "diff --git a/CTFd/admin/submissions.py b/CTFd/admin/submissions.py\n--- a/CTFd/admin/submissions.py\n+++ b/CTFd/admin/submissions.py\n@@ -1,4 +1,4 @@\n-from flask import render_template, request\n+from flask import render_template, request, url_for\n \n from CTFd.admin import admin\n from CTFd.models import Challenges, Submissions\n@@ -10,16 +10,21 @@\n @admin.route(\"/admin/submissions/<submission_type>\")\n @admins_only\n def submissions_listing(submission_type):\n- filters = {}\n+ filters_by = {}\n if submission_type:\n- filters[\"type\"] = submission_type\n+ filters_by[\"type\"] = submission_type\n+ filters = []\n \n- curr_page = abs(int(request.args.get(\"page\", 1, type=int)))\n- results_per_page = 50\n- page_start = results_per_page * (curr_page - 1)\n- page_end = results_per_page * (curr_page - 1) + results_per_page\n- sub_count = Submissions.query.filter_by(**filters).count()\n- page_count = int(sub_count / results_per_page) + (sub_count % results_per_page > 0)\n+ q = request.args.get(\"q\")\n+ field = request.args.get(\"field\")\n+ page = abs(request.args.get(\"page\", 1, type=int))\n+\n+ if q:\n+ submissions = []\n+ if Submissions.__mapper__.has_property(\n+ field\n+ ): # The field exists as an exposed column\n+ filters.append(getattr(Submissions, field).like(\"%{}%\".format(q)))\n \n Model = get_model()\n \n@@ -34,18 +39,27 @@\n Challenges.name.label(\"challenge_name\"),\n Model.name.label(\"team_name\"),\n )\n- .filter_by(**filters)\n+ .filter_by(**filters_by)\n+ .filter(*filters)\n .join(Challenges)\n .join(Model)\n .order_by(Submissions.date.desc())\n- .slice(page_start, page_end)\n- .all()\n+ .paginate(page=page, per_page=50)\n )\n \n+ args = dict(request.args)\n+ args.pop(\"page\", 1)\n+\n return render_template(\n \"admin/submissions.html\",\n submissions=submissions,\n- page_count=page_count,\n- curr_page=curr_page,\n+ prev_page=url_for(\n+ request.endpoint, type=submission_type, page=submissions.prev_num, **args\n+ ),\n+ next_page=url_for(\n+ request.endpoint, type=submission_type, page=submissions.next_num, **args\n+ ),\n type=submission_type,\n+ q=q,\n+ field=field,\n )\n", "issue": "Submission search\nSearch submissions akin to how users are searched\n", "before_files": [{"content": "from flask import render_template, request\n\nfrom CTFd.admin import admin\nfrom CTFd.models import Challenges, Submissions\nfrom CTFd.utils.decorators import admins_only\nfrom CTFd.utils.modes import get_model\n\n\[email protected](\"/admin/submissions\", defaults={\"submission_type\": None})\[email protected](\"/admin/submissions/<submission_type>\")\n@admins_only\ndef submissions_listing(submission_type):\n filters = {}\n if submission_type:\n filters[\"type\"] = submission_type\n\n curr_page = abs(int(request.args.get(\"page\", 1, type=int)))\n results_per_page = 50\n page_start = results_per_page * (curr_page - 1)\n page_end = results_per_page * (curr_page - 1) + results_per_page\n sub_count = Submissions.query.filter_by(**filters).count()\n page_count = int(sub_count / results_per_page) + (sub_count % results_per_page > 0)\n\n Model = get_model()\n\n submissions = (\n Submissions.query.add_columns(\n Submissions.id,\n Submissions.type,\n Submissions.challenge_id,\n Submissions.provided,\n Submissions.account_id,\n Submissions.date,\n Challenges.name.label(\"challenge_name\"),\n Model.name.label(\"team_name\"),\n )\n .filter_by(**filters)\n .join(Challenges)\n .join(Model)\n .order_by(Submissions.date.desc())\n .slice(page_start, page_end)\n .all()\n )\n\n return render_template(\n \"admin/submissions.html\",\n submissions=submissions,\n page_count=page_count,\n curr_page=curr_page,\n type=submission_type,\n )\n", "path": "CTFd/admin/submissions.py"}], "after_files": [{"content": "from flask import render_template, request, url_for\n\nfrom CTFd.admin import admin\nfrom CTFd.models import Challenges, Submissions\nfrom CTFd.utils.decorators import admins_only\nfrom CTFd.utils.modes import get_model\n\n\[email protected](\"/admin/submissions\", defaults={\"submission_type\": None})\[email protected](\"/admin/submissions/<submission_type>\")\n@admins_only\ndef submissions_listing(submission_type):\n filters_by = {}\n if submission_type:\n filters_by[\"type\"] = submission_type\n filters = []\n\n q = request.args.get(\"q\")\n field = request.args.get(\"field\")\n page = abs(request.args.get(\"page\", 1, type=int))\n\n if q:\n submissions = []\n if Submissions.__mapper__.has_property(\n field\n ): # The field exists as an exposed column\n filters.append(getattr(Submissions, field).like(\"%{}%\".format(q)))\n\n Model = get_model()\n\n submissions = (\n Submissions.query.add_columns(\n Submissions.id,\n Submissions.type,\n Submissions.challenge_id,\n Submissions.provided,\n Submissions.account_id,\n Submissions.date,\n Challenges.name.label(\"challenge_name\"),\n Model.name.label(\"team_name\"),\n )\n .filter_by(**filters_by)\n .filter(*filters)\n .join(Challenges)\n .join(Model)\n .order_by(Submissions.date.desc())\n .paginate(page=page, per_page=50)\n )\n\n args = dict(request.args)\n args.pop(\"page\", 1)\n\n return render_template(\n \"admin/submissions.html\",\n submissions=submissions,\n prev_page=url_for(\n request.endpoint, type=submission_type, page=submissions.prev_num, **args\n ),\n next_page=url_for(\n request.endpoint, type=submission_type, page=submissions.next_num, **args\n ),\n type=submission_type,\n q=q,\n field=field,\n )\n", "path": "CTFd/admin/submissions.py"}]}
| 728 | 615 |
gh_patches_debug_11056
|
rasdani/github-patches
|
git_diff
|
pantsbuild__pants-14584
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
coursier post processing script choking on null dependency file in report json
**Describe the bug**
One of our 3rdparty jars (`org.geotools:gt-main:9.2` from the `https://repo.osgeo.org/repository/release` repositiory) transitively depends on a `javax.media:jai_core:1.1.3` jar. For whatever reason, Coursier's resolve report json lists `"file": null` for that jar, which the post processing script doesn't currently handle.
**Pants version**
2.9.0
**OS**
Encountered on MacOS, though expect we would see this on Linux as well
**Additional info**
Coursier config:
```
[coursier]
repos = [
"https://maven-central.storage-download.googleapis.com/maven2",
"https://repo1.maven.org/maven2",
"https://repo.osgeo.org/repository/release",
]
```
affected jvm_artifact:
```
jvm_artifact(
group="org.geotools",
artifact="gt-main",
version="9.2",
)
```
[slack discussion](https://pantsbuild.slack.com/archives/C046T6T9U/p1645598534013879) with links to full resolve output and json
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `src/python/pants/jvm/resolve/coursier_setup.py`
Content:
```
1 # Copyright 2021 Pants project contributors (see CONTRIBUTORS.md).
2 # Licensed under the Apache License, Version 2.0 (see LICENSE).
3
4 from __future__ import annotations
5
6 import os
7 import shlex
8 import textwrap
9 from dataclasses import dataclass
10 from typing import ClassVar, Iterable, Tuple
11
12 from pants.core.util_rules import external_tool
13 from pants.core.util_rules.external_tool import (
14 DownloadedExternalTool,
15 ExternalToolRequest,
16 TemplatedExternalTool,
17 )
18 from pants.engine.fs import CreateDigest, Digest, FileContent, MergeDigests
19 from pants.engine.platform import Platform
20 from pants.engine.process import BashBinary, Process
21 from pants.engine.rules import Get, MultiGet, collect_rules, rule
22 from pants.python.binaries import PythonBinary
23 from pants.util.logging import LogLevel
24
25 COURSIER_POST_PROCESSING_SCRIPT = textwrap.dedent(
26 """\
27 import json
28 import sys
29 import os
30 from pathlib import PurePath
31 from shutil import copyfile
32
33 report = json.load(open(sys.argv[1]))
34
35 # Mapping from dest path to source path. It is ok to capture the same output filename multiple
36 # times if the source is the same as well.
37 classpath = dict()
38 for dep in report['dependencies']:
39 source = PurePath(dep['file'])
40 dest_name = dep['coord'].replace(":", "_")
41 _, ext = os.path.splitext(source)
42 classpath_dest = f"classpath/{dest_name}{ext}"
43
44 existing_source = classpath.get(classpath_dest)
45 if existing_source:
46 if existing_source == source:
47 # We've already captured this file.
48 continue
49 raise Exception(
50 f"Duplicate jar name {classpath_dest} with incompatible source:\\n"
51 f" {source}\\n"
52 f" {existing_source}\\n"
53 )
54 classpath[classpath_dest] = source
55 copyfile(source, classpath_dest)
56 """
57 )
58
59 COURSIER_FETCH_WRAPPER_SCRIPT = textwrap.dedent(
60 """\
61 set -eux
62
63 coursier_exe="$1"
64 shift
65 json_output_file="$1"
66 shift
67
68 working_dir="$(pwd)"
69 "$coursier_exe" fetch {repos_args} \
70 --json-output-file="$json_output_file" \
71 "${{@//{coursier_working_directory}/$working_dir}}"
72 /bin/mkdir -p classpath
73 {python_path} {coursier_bin_dir}/coursier_post_processing_script.py "$json_output_file"
74 """
75 )
76
77
78 # TODO: Coursier renders setrlimit error line on macOS.
79 # see https://github.com/pantsbuild/pants/issues/13942.
80 POST_PROCESS_COURSIER_STDERR_SCRIPT = textwrap.dedent(
81 """\
82 #!{python_path}
83 import sys
84 from subprocess import run, PIPE
85
86 proc = run(sys.argv[1:], stdout=PIPE, stderr=PIPE)
87
88 sys.stdout.buffer.write(proc.stdout)
89 sys.stderr.buffer.write(proc.stderr.replace(b"setrlimit to increase file descriptor limit failed, errno 22\\n", b""))
90 sys.exit(proc.returncode)
91 """
92 )
93
94
95 class CoursierSubsystem(TemplatedExternalTool):
96 options_scope = "coursier"
97 name = "coursier"
98 help = "A dependency resolver for the Maven ecosystem."
99
100 default_version = "v2.0.16-169-g194ebc55c"
101 default_known_versions = [
102 "v2.0.16-169-g194ebc55c|linux_arm64 |da38c97d55967505b8454c20a90370c518044829398b9bce8b637d194d79abb3|18114472",
103 "v2.0.16-169-g194ebc55c|linux_x86_64|4c61a634c4bd2773b4543fe0fc32210afd343692891121cddb447204b48672e8|18486946",
104 "v2.0.16-169-g194ebc55c|macos_arm64 |15bce235d223ef1d022da30b67b4c64e9228d236b876c834b64e029bbe824c6f|17957182",
105 "v2.0.16-169-g194ebc55c|macos_x86_64|15bce235d223ef1d022da30b67b4c64e9228d236b876c834b64e029bbe824c6f|17957182",
106 ]
107 default_url_template = (
108 "https://github.com/coursier/coursier/releases/download/{version}/cs-{platform}.gz"
109 )
110 default_url_platform_mapping = {
111 "macos_arm64": "x86_64-apple-darwin",
112 "macos_x86_64": "x86_64-apple-darwin",
113 "linux_arm64": "aarch64-pc-linux",
114 "linux_x86_64": "x86_64-pc-linux",
115 }
116
117 @classmethod
118 def register_options(cls, register) -> None:
119 super().register_options(register)
120 register(
121 "--repos",
122 type=list,
123 member_type=str,
124 default=[
125 "https://maven-central.storage-download.googleapis.com/maven2",
126 "https://repo1.maven.org/maven2",
127 ],
128 help=("Maven style repositories to resolve artifacts from."),
129 )
130
131 def generate_exe(self, plat: Platform) -> str:
132 archive_filename = os.path.basename(self.generate_url(plat))
133 filename = os.path.splitext(archive_filename)[0]
134 return f"./{filename}"
135
136
137 @dataclass(frozen=True)
138 class Coursier:
139 """The Coursier tool and various utilities, prepared for use via `immutable_input_digests`."""
140
141 coursier: DownloadedExternalTool
142 _digest: Digest
143
144 bin_dir: ClassVar[str] = "__coursier"
145 fetch_wrapper_script: ClassVar[str] = f"{bin_dir}/coursier_fetch_wrapper_script.sh"
146 post_processing_script: ClassVar[str] = f"{bin_dir}/coursier_post_processing_script.py"
147 post_process_stderr: ClassVar[str] = f"{bin_dir}/coursier_post_process_stderr.py"
148 cache_name: ClassVar[str] = "coursier"
149 cache_dir: ClassVar[str] = ".cache"
150 working_directory_placeholder: ClassVar[str] = "___COURSIER_WORKING_DIRECTORY___"
151
152 def args(self, args: Iterable[str], *, wrapper: Iterable[str] = ()) -> tuple[str, ...]:
153 return (
154 self.post_process_stderr,
155 *wrapper,
156 os.path.join(self.bin_dir, self.coursier.exe),
157 *args,
158 )
159
160 @property
161 def env(self) -> dict[str, str]:
162 # NB: These variables have changed a few times, and they change again on `main`. But as of
163 # `v2.0.16+73-gddc6d9cc9` they are accurate. See:
164 # https://github.com/coursier/coursier/blob/v2.0.16+73-gddc6d9cc9/modules/paths/src/main/java/coursier/paths/CoursierPaths.java#L38-L48
165 return {
166 "COURSIER_CACHE": f"{self.cache_dir}/jdk",
167 "COURSIER_ARCHIVE_CACHE": f"{self.cache_dir}/arc",
168 "COURSIER_JVM_CACHE": f"{self.cache_dir}/v1",
169 }
170
171 @property
172 def append_only_caches(self) -> dict[str, str]:
173 return {self.cache_name: self.cache_dir}
174
175 @property
176 def immutable_input_digests(self) -> dict[str, Digest]:
177 return {self.bin_dir: self._digest}
178
179
180 @dataclass(frozen=True)
181 class CoursierWrapperProcess:
182
183 args: Tuple[str, ...]
184 input_digest: Digest
185 output_directories: Tuple[str, ...]
186 output_files: Tuple[str, ...]
187 description: str
188
189
190 @rule
191 async def invoke_coursier_wrapper(
192 bash: BashBinary,
193 coursier: Coursier,
194 request: CoursierWrapperProcess,
195 ) -> Process:
196
197 return Process(
198 argv=coursier.args(
199 request.args,
200 wrapper=[bash.path, coursier.fetch_wrapper_script],
201 ),
202 input_digest=request.input_digest,
203 immutable_input_digests=coursier.immutable_input_digests,
204 output_directories=request.output_directories,
205 output_files=request.output_files,
206 append_only_caches=coursier.append_only_caches,
207 env=coursier.env,
208 description=request.description,
209 level=LogLevel.DEBUG,
210 )
211
212
213 @rule
214 async def setup_coursier(
215 coursier_subsystem: CoursierSubsystem,
216 python: PythonBinary,
217 ) -> Coursier:
218 repos_args = " ".join(f"-r={shlex.quote(repo)}" for repo in coursier_subsystem.options.repos)
219 coursier_wrapper_script = COURSIER_FETCH_WRAPPER_SCRIPT.format(
220 repos_args=repos_args,
221 coursier_working_directory=Coursier.working_directory_placeholder,
222 python_path=python.path,
223 coursier_bin_dir=Coursier.bin_dir,
224 )
225
226 post_process_stderr = POST_PROCESS_COURSIER_STDERR_SCRIPT.format(python_path=python.path)
227
228 downloaded_coursier_get = Get(
229 DownloadedExternalTool,
230 ExternalToolRequest,
231 coursier_subsystem.get_request(Platform.current),
232 )
233 wrapper_scripts_digest_get = Get(
234 Digest,
235 CreateDigest(
236 [
237 FileContent(
238 os.path.basename(Coursier.fetch_wrapper_script),
239 coursier_wrapper_script.encode("utf-8"),
240 is_executable=True,
241 ),
242 FileContent(
243 os.path.basename(Coursier.post_processing_script),
244 COURSIER_POST_PROCESSING_SCRIPT.encode("utf-8"),
245 is_executable=True,
246 ),
247 FileContent(
248 os.path.basename(Coursier.post_process_stderr),
249 post_process_stderr.encode("utf-8"),
250 is_executable=True,
251 ),
252 ]
253 ),
254 )
255
256 downloaded_coursier, wrapper_scripts_digest = await MultiGet(
257 downloaded_coursier_get, wrapper_scripts_digest_get
258 )
259
260 return Coursier(
261 coursier=downloaded_coursier,
262 _digest=await Get(
263 Digest,
264 MergeDigests(
265 [
266 downloaded_coursier.digest,
267 wrapper_scripts_digest,
268 ]
269 ),
270 ),
271 )
272
273
274 def rules():
275 return [
276 *collect_rules(),
277 *external_tool.rules(),
278 ]
279
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/src/python/pants/jvm/resolve/coursier_setup.py b/src/python/pants/jvm/resolve/coursier_setup.py
--- a/src/python/pants/jvm/resolve/coursier_setup.py
+++ b/src/python/pants/jvm/resolve/coursier_setup.py
@@ -215,7 +215,10 @@
coursier_subsystem: CoursierSubsystem,
python: PythonBinary,
) -> Coursier:
- repos_args = " ".join(f"-r={shlex.quote(repo)}" for repo in coursier_subsystem.options.repos)
+ repos_args = (
+ " ".join(f"-r={shlex.quote(repo)}" for repo in coursier_subsystem.options.repos)
+ + " --no-default"
+ )
coursier_wrapper_script = COURSIER_FETCH_WRAPPER_SCRIPT.format(
repos_args=repos_args,
coursier_working_directory=Coursier.working_directory_placeholder,
|
{"golden_diff": "diff --git a/src/python/pants/jvm/resolve/coursier_setup.py b/src/python/pants/jvm/resolve/coursier_setup.py\n--- a/src/python/pants/jvm/resolve/coursier_setup.py\n+++ b/src/python/pants/jvm/resolve/coursier_setup.py\n@@ -215,7 +215,10 @@\n coursier_subsystem: CoursierSubsystem,\n python: PythonBinary,\n ) -> Coursier:\n- repos_args = \" \".join(f\"-r={shlex.quote(repo)}\" for repo in coursier_subsystem.options.repos)\n+ repos_args = (\n+ \" \".join(f\"-r={shlex.quote(repo)}\" for repo in coursier_subsystem.options.repos)\n+ + \" --no-default\"\n+ )\n coursier_wrapper_script = COURSIER_FETCH_WRAPPER_SCRIPT.format(\n repos_args=repos_args,\n coursier_working_directory=Coursier.working_directory_placeholder,\n", "issue": "coursier post processing script choking on null dependency file in report json\n**Describe the bug**\r\nOne of our 3rdparty jars (`org.geotools:gt-main:9.2` from the `https://repo.osgeo.org/repository/release` repositiory) transitively depends on a `javax.media:jai_core:1.1.3` jar. For whatever reason, Coursier's resolve report json lists `\"file\": null` for that jar, which the post processing script doesn't currently handle.\r\n\r\n**Pants version**\r\n2.9.0\r\n\r\n**OS**\r\nEncountered on MacOS, though expect we would see this on Linux as well\r\n\r\n**Additional info**\r\nCoursier config:\r\n```\r\n[coursier]\r\nrepos = [\r\n \"https://maven-central.storage-download.googleapis.com/maven2\",\r\n \"https://repo1.maven.org/maven2\",\r\n \"https://repo.osgeo.org/repository/release\",\r\n]\r\n```\r\n\r\naffected jvm_artifact:\r\n```\r\njvm_artifact(\r\n group=\"org.geotools\",\r\n artifact=\"gt-main\",\r\n version=\"9.2\",\r\n)\r\n```\r\n\r\n[slack discussion](https://pantsbuild.slack.com/archives/C046T6T9U/p1645598534013879) with links to full resolve output and json\r\n\n", "before_files": [{"content": "# Copyright 2021 Pants project contributors (see CONTRIBUTORS.md).\n# Licensed under the Apache License, Version 2.0 (see LICENSE).\n\nfrom __future__ import annotations\n\nimport os\nimport shlex\nimport textwrap\nfrom dataclasses import dataclass\nfrom typing import ClassVar, Iterable, Tuple\n\nfrom pants.core.util_rules import external_tool\nfrom pants.core.util_rules.external_tool import (\n DownloadedExternalTool,\n ExternalToolRequest,\n TemplatedExternalTool,\n)\nfrom pants.engine.fs import CreateDigest, Digest, FileContent, MergeDigests\nfrom pants.engine.platform import Platform\nfrom pants.engine.process import BashBinary, Process\nfrom pants.engine.rules import Get, MultiGet, collect_rules, rule\nfrom pants.python.binaries import PythonBinary\nfrom pants.util.logging import LogLevel\n\nCOURSIER_POST_PROCESSING_SCRIPT = textwrap.dedent(\n \"\"\"\\\n import json\n import sys\n import os\n from pathlib import PurePath\n from shutil import copyfile\n\n report = json.load(open(sys.argv[1]))\n\n # Mapping from dest path to source path. It is ok to capture the same output filename multiple\n # times if the source is the same as well.\n classpath = dict()\n for dep in report['dependencies']:\n source = PurePath(dep['file'])\n dest_name = dep['coord'].replace(\":\", \"_\")\n _, ext = os.path.splitext(source)\n classpath_dest = f\"classpath/{dest_name}{ext}\"\n\n existing_source = classpath.get(classpath_dest)\n if existing_source:\n if existing_source == source:\n # We've already captured this file.\n continue\n raise Exception(\n f\"Duplicate jar name {classpath_dest} with incompatible source:\\\\n\"\n f\" {source}\\\\n\"\n f\" {existing_source}\\\\n\"\n )\n classpath[classpath_dest] = source\n copyfile(source, classpath_dest)\n \"\"\"\n)\n\nCOURSIER_FETCH_WRAPPER_SCRIPT = textwrap.dedent(\n \"\"\"\\\n set -eux\n\n coursier_exe=\"$1\"\n shift\n json_output_file=\"$1\"\n shift\n\n working_dir=\"$(pwd)\"\n \"$coursier_exe\" fetch {repos_args} \\\n --json-output-file=\"$json_output_file\" \\\n \"${{@//{coursier_working_directory}/$working_dir}}\"\n /bin/mkdir -p classpath\n {python_path} {coursier_bin_dir}/coursier_post_processing_script.py \"$json_output_file\"\n \"\"\"\n)\n\n\n# TODO: Coursier renders setrlimit error line on macOS.\n# see https://github.com/pantsbuild/pants/issues/13942.\nPOST_PROCESS_COURSIER_STDERR_SCRIPT = textwrap.dedent(\n \"\"\"\\\n #!{python_path}\n import sys\n from subprocess import run, PIPE\n\n proc = run(sys.argv[1:], stdout=PIPE, stderr=PIPE)\n\n sys.stdout.buffer.write(proc.stdout)\n sys.stderr.buffer.write(proc.stderr.replace(b\"setrlimit to increase file descriptor limit failed, errno 22\\\\n\", b\"\"))\n sys.exit(proc.returncode)\n \"\"\"\n)\n\n\nclass CoursierSubsystem(TemplatedExternalTool):\n options_scope = \"coursier\"\n name = \"coursier\"\n help = \"A dependency resolver for the Maven ecosystem.\"\n\n default_version = \"v2.0.16-169-g194ebc55c\"\n default_known_versions = [\n \"v2.0.16-169-g194ebc55c|linux_arm64 |da38c97d55967505b8454c20a90370c518044829398b9bce8b637d194d79abb3|18114472\",\n \"v2.0.16-169-g194ebc55c|linux_x86_64|4c61a634c4bd2773b4543fe0fc32210afd343692891121cddb447204b48672e8|18486946\",\n \"v2.0.16-169-g194ebc55c|macos_arm64 |15bce235d223ef1d022da30b67b4c64e9228d236b876c834b64e029bbe824c6f|17957182\",\n \"v2.0.16-169-g194ebc55c|macos_x86_64|15bce235d223ef1d022da30b67b4c64e9228d236b876c834b64e029bbe824c6f|17957182\",\n ]\n default_url_template = (\n \"https://github.com/coursier/coursier/releases/download/{version}/cs-{platform}.gz\"\n )\n default_url_platform_mapping = {\n \"macos_arm64\": \"x86_64-apple-darwin\",\n \"macos_x86_64\": \"x86_64-apple-darwin\",\n \"linux_arm64\": \"aarch64-pc-linux\",\n \"linux_x86_64\": \"x86_64-pc-linux\",\n }\n\n @classmethod\n def register_options(cls, register) -> None:\n super().register_options(register)\n register(\n \"--repos\",\n type=list,\n member_type=str,\n default=[\n \"https://maven-central.storage-download.googleapis.com/maven2\",\n \"https://repo1.maven.org/maven2\",\n ],\n help=(\"Maven style repositories to resolve artifacts from.\"),\n )\n\n def generate_exe(self, plat: Platform) -> str:\n archive_filename = os.path.basename(self.generate_url(plat))\n filename = os.path.splitext(archive_filename)[0]\n return f\"./{filename}\"\n\n\n@dataclass(frozen=True)\nclass Coursier:\n \"\"\"The Coursier tool and various utilities, prepared for use via `immutable_input_digests`.\"\"\"\n\n coursier: DownloadedExternalTool\n _digest: Digest\n\n bin_dir: ClassVar[str] = \"__coursier\"\n fetch_wrapper_script: ClassVar[str] = f\"{bin_dir}/coursier_fetch_wrapper_script.sh\"\n post_processing_script: ClassVar[str] = f\"{bin_dir}/coursier_post_processing_script.py\"\n post_process_stderr: ClassVar[str] = f\"{bin_dir}/coursier_post_process_stderr.py\"\n cache_name: ClassVar[str] = \"coursier\"\n cache_dir: ClassVar[str] = \".cache\"\n working_directory_placeholder: ClassVar[str] = \"___COURSIER_WORKING_DIRECTORY___\"\n\n def args(self, args: Iterable[str], *, wrapper: Iterable[str] = ()) -> tuple[str, ...]:\n return (\n self.post_process_stderr,\n *wrapper,\n os.path.join(self.bin_dir, self.coursier.exe),\n *args,\n )\n\n @property\n def env(self) -> dict[str, str]:\n # NB: These variables have changed a few times, and they change again on `main`. But as of\n # `v2.0.16+73-gddc6d9cc9` they are accurate. See:\n # https://github.com/coursier/coursier/blob/v2.0.16+73-gddc6d9cc9/modules/paths/src/main/java/coursier/paths/CoursierPaths.java#L38-L48\n return {\n \"COURSIER_CACHE\": f\"{self.cache_dir}/jdk\",\n \"COURSIER_ARCHIVE_CACHE\": f\"{self.cache_dir}/arc\",\n \"COURSIER_JVM_CACHE\": f\"{self.cache_dir}/v1\",\n }\n\n @property\n def append_only_caches(self) -> dict[str, str]:\n return {self.cache_name: self.cache_dir}\n\n @property\n def immutable_input_digests(self) -> dict[str, Digest]:\n return {self.bin_dir: self._digest}\n\n\n@dataclass(frozen=True)\nclass CoursierWrapperProcess:\n\n args: Tuple[str, ...]\n input_digest: Digest\n output_directories: Tuple[str, ...]\n output_files: Tuple[str, ...]\n description: str\n\n\n@rule\nasync def invoke_coursier_wrapper(\n bash: BashBinary,\n coursier: Coursier,\n request: CoursierWrapperProcess,\n) -> Process:\n\n return Process(\n argv=coursier.args(\n request.args,\n wrapper=[bash.path, coursier.fetch_wrapper_script],\n ),\n input_digest=request.input_digest,\n immutable_input_digests=coursier.immutable_input_digests,\n output_directories=request.output_directories,\n output_files=request.output_files,\n append_only_caches=coursier.append_only_caches,\n env=coursier.env,\n description=request.description,\n level=LogLevel.DEBUG,\n )\n\n\n@rule\nasync def setup_coursier(\n coursier_subsystem: CoursierSubsystem,\n python: PythonBinary,\n) -> Coursier:\n repos_args = \" \".join(f\"-r={shlex.quote(repo)}\" for repo in coursier_subsystem.options.repos)\n coursier_wrapper_script = COURSIER_FETCH_WRAPPER_SCRIPT.format(\n repos_args=repos_args,\n coursier_working_directory=Coursier.working_directory_placeholder,\n python_path=python.path,\n coursier_bin_dir=Coursier.bin_dir,\n )\n\n post_process_stderr = POST_PROCESS_COURSIER_STDERR_SCRIPT.format(python_path=python.path)\n\n downloaded_coursier_get = Get(\n DownloadedExternalTool,\n ExternalToolRequest,\n coursier_subsystem.get_request(Platform.current),\n )\n wrapper_scripts_digest_get = Get(\n Digest,\n CreateDigest(\n [\n FileContent(\n os.path.basename(Coursier.fetch_wrapper_script),\n coursier_wrapper_script.encode(\"utf-8\"),\n is_executable=True,\n ),\n FileContent(\n os.path.basename(Coursier.post_processing_script),\n COURSIER_POST_PROCESSING_SCRIPT.encode(\"utf-8\"),\n is_executable=True,\n ),\n FileContent(\n os.path.basename(Coursier.post_process_stderr),\n post_process_stderr.encode(\"utf-8\"),\n is_executable=True,\n ),\n ]\n ),\n )\n\n downloaded_coursier, wrapper_scripts_digest = await MultiGet(\n downloaded_coursier_get, wrapper_scripts_digest_get\n )\n\n return Coursier(\n coursier=downloaded_coursier,\n _digest=await Get(\n Digest,\n MergeDigests(\n [\n downloaded_coursier.digest,\n wrapper_scripts_digest,\n ]\n ),\n ),\n )\n\n\ndef rules():\n return [\n *collect_rules(),\n *external_tool.rules(),\n ]\n", "path": "src/python/pants/jvm/resolve/coursier_setup.py"}], "after_files": [{"content": "# Copyright 2021 Pants project contributors (see CONTRIBUTORS.md).\n# Licensed under the Apache License, Version 2.0 (see LICENSE).\n\nfrom __future__ import annotations\n\nimport os\nimport shlex\nimport textwrap\nfrom dataclasses import dataclass\nfrom typing import ClassVar, Iterable, Tuple\n\nfrom pants.core.util_rules import external_tool\nfrom pants.core.util_rules.external_tool import (\n DownloadedExternalTool,\n ExternalToolRequest,\n TemplatedExternalTool,\n)\nfrom pants.engine.fs import CreateDigest, Digest, FileContent, MergeDigests\nfrom pants.engine.platform import Platform\nfrom pants.engine.process import BashBinary, Process\nfrom pants.engine.rules import Get, MultiGet, collect_rules, rule\nfrom pants.python.binaries import PythonBinary\nfrom pants.util.logging import LogLevel\n\nCOURSIER_POST_PROCESSING_SCRIPT = textwrap.dedent(\n \"\"\"\\\n import json\n import sys\n import os\n from pathlib import PurePath\n from shutil import copyfile\n\n report = json.load(open(sys.argv[1]))\n\n # Mapping from dest path to source path. It is ok to capture the same output filename multiple\n # times if the source is the same as well.\n classpath = dict()\n for dep in report['dependencies']:\n source = PurePath(dep['file'])\n dest_name = dep['coord'].replace(\":\", \"_\")\n _, ext = os.path.splitext(source)\n classpath_dest = f\"classpath/{dest_name}{ext}\"\n\n existing_source = classpath.get(classpath_dest)\n if existing_source:\n if existing_source == source:\n # We've already captured this file.\n continue\n raise Exception(\n f\"Duplicate jar name {classpath_dest} with incompatible source:\\\\n\"\n f\" {source}\\\\n\"\n f\" {existing_source}\\\\n\"\n )\n classpath[classpath_dest] = source\n copyfile(source, classpath_dest)\n \"\"\"\n)\n\nCOURSIER_FETCH_WRAPPER_SCRIPT = textwrap.dedent(\n \"\"\"\\\n set -eux\n\n coursier_exe=\"$1\"\n shift\n json_output_file=\"$1\"\n shift\n\n working_dir=\"$(pwd)\"\n \"$coursier_exe\" fetch {repos_args} \\\n --json-output-file=\"$json_output_file\" \\\n \"${{@//{coursier_working_directory}/$working_dir}}\"\n /bin/mkdir -p classpath\n {python_path} {coursier_bin_dir}/coursier_post_processing_script.py \"$json_output_file\"\n \"\"\"\n)\n\n\n# TODO: Coursier renders setrlimit error line on macOS.\n# see https://github.com/pantsbuild/pants/issues/13942.\nPOST_PROCESS_COURSIER_STDERR_SCRIPT = textwrap.dedent(\n \"\"\"\\\n #!{python_path}\n import sys\n from subprocess import run, PIPE\n\n proc = run(sys.argv[1:], stdout=PIPE, stderr=PIPE)\n\n sys.stdout.buffer.write(proc.stdout)\n sys.stderr.buffer.write(proc.stderr.replace(b\"setrlimit to increase file descriptor limit failed, errno 22\\\\n\", b\"\"))\n sys.exit(proc.returncode)\n \"\"\"\n)\n\n\nclass CoursierSubsystem(TemplatedExternalTool):\n options_scope = \"coursier\"\n name = \"coursier\"\n help = \"A dependency resolver for the Maven ecosystem.\"\n\n default_version = \"v2.0.16-169-g194ebc55c\"\n default_known_versions = [\n \"v2.0.16-169-g194ebc55c|linux_arm64 |da38c97d55967505b8454c20a90370c518044829398b9bce8b637d194d79abb3|18114472\",\n \"v2.0.16-169-g194ebc55c|linux_x86_64|4c61a634c4bd2773b4543fe0fc32210afd343692891121cddb447204b48672e8|18486946\",\n \"v2.0.16-169-g194ebc55c|macos_arm64 |15bce235d223ef1d022da30b67b4c64e9228d236b876c834b64e029bbe824c6f|17957182\",\n \"v2.0.16-169-g194ebc55c|macos_x86_64|15bce235d223ef1d022da30b67b4c64e9228d236b876c834b64e029bbe824c6f|17957182\",\n ]\n default_url_template = (\n \"https://github.com/coursier/coursier/releases/download/{version}/cs-{platform}.gz\"\n )\n default_url_platform_mapping = {\n \"macos_arm64\": \"x86_64-apple-darwin\",\n \"macos_x86_64\": \"x86_64-apple-darwin\",\n \"linux_arm64\": \"aarch64-pc-linux\",\n \"linux_x86_64\": \"x86_64-pc-linux\",\n }\n\n @classmethod\n def register_options(cls, register) -> None:\n super().register_options(register)\n register(\n \"--repos\",\n type=list,\n member_type=str,\n default=[\n \"https://maven-central.storage-download.googleapis.com/maven2\",\n \"https://repo1.maven.org/maven2\",\n ],\n help=(\"Maven style repositories to resolve artifacts from.\"),\n )\n\n def generate_exe(self, plat: Platform) -> str:\n archive_filename = os.path.basename(self.generate_url(plat))\n filename = os.path.splitext(archive_filename)[0]\n return f\"./{filename}\"\n\n\n@dataclass(frozen=True)\nclass Coursier:\n \"\"\"The Coursier tool and various utilities, prepared for use via `immutable_input_digests`.\"\"\"\n\n coursier: DownloadedExternalTool\n _digest: Digest\n\n bin_dir: ClassVar[str] = \"__coursier\"\n fetch_wrapper_script: ClassVar[str] = f\"{bin_dir}/coursier_fetch_wrapper_script.sh\"\n post_processing_script: ClassVar[str] = f\"{bin_dir}/coursier_post_processing_script.py\"\n post_process_stderr: ClassVar[str] = f\"{bin_dir}/coursier_post_process_stderr.py\"\n cache_name: ClassVar[str] = \"coursier\"\n cache_dir: ClassVar[str] = \".cache\"\n working_directory_placeholder: ClassVar[str] = \"___COURSIER_WORKING_DIRECTORY___\"\n\n def args(self, args: Iterable[str], *, wrapper: Iterable[str] = ()) -> tuple[str, ...]:\n return (\n self.post_process_stderr,\n *wrapper,\n os.path.join(self.bin_dir, self.coursier.exe),\n *args,\n )\n\n @property\n def env(self) -> dict[str, str]:\n # NB: These variables have changed a few times, and they change again on `main`. But as of\n # `v2.0.16+73-gddc6d9cc9` they are accurate. See:\n # https://github.com/coursier/coursier/blob/v2.0.16+73-gddc6d9cc9/modules/paths/src/main/java/coursier/paths/CoursierPaths.java#L38-L48\n return {\n \"COURSIER_CACHE\": f\"{self.cache_dir}/jdk\",\n \"COURSIER_ARCHIVE_CACHE\": f\"{self.cache_dir}/arc\",\n \"COURSIER_JVM_CACHE\": f\"{self.cache_dir}/v1\",\n }\n\n @property\n def append_only_caches(self) -> dict[str, str]:\n return {self.cache_name: self.cache_dir}\n\n @property\n def immutable_input_digests(self) -> dict[str, Digest]:\n return {self.bin_dir: self._digest}\n\n\n@dataclass(frozen=True)\nclass CoursierWrapperProcess:\n\n args: Tuple[str, ...]\n input_digest: Digest\n output_directories: Tuple[str, ...]\n output_files: Tuple[str, ...]\n description: str\n\n\n@rule\nasync def invoke_coursier_wrapper(\n bash: BashBinary,\n coursier: Coursier,\n request: CoursierWrapperProcess,\n) -> Process:\n\n return Process(\n argv=coursier.args(\n request.args,\n wrapper=[bash.path, coursier.fetch_wrapper_script],\n ),\n input_digest=request.input_digest,\n immutable_input_digests=coursier.immutable_input_digests,\n output_directories=request.output_directories,\n output_files=request.output_files,\n append_only_caches=coursier.append_only_caches,\n env=coursier.env,\n description=request.description,\n level=LogLevel.DEBUG,\n )\n\n\n@rule\nasync def setup_coursier(\n coursier_subsystem: CoursierSubsystem,\n python: PythonBinary,\n) -> Coursier:\n repos_args = (\n \" \".join(f\"-r={shlex.quote(repo)}\" for repo in coursier_subsystem.options.repos)\n + \" --no-default\"\n )\n coursier_wrapper_script = COURSIER_FETCH_WRAPPER_SCRIPT.format(\n repos_args=repos_args,\n coursier_working_directory=Coursier.working_directory_placeholder,\n python_path=python.path,\n coursier_bin_dir=Coursier.bin_dir,\n )\n\n post_process_stderr = POST_PROCESS_COURSIER_STDERR_SCRIPT.format(python_path=python.path)\n\n downloaded_coursier_get = Get(\n DownloadedExternalTool,\n ExternalToolRequest,\n coursier_subsystem.get_request(Platform.current),\n )\n wrapper_scripts_digest_get = Get(\n Digest,\n CreateDigest(\n [\n FileContent(\n os.path.basename(Coursier.fetch_wrapper_script),\n coursier_wrapper_script.encode(\"utf-8\"),\n is_executable=True,\n ),\n FileContent(\n os.path.basename(Coursier.post_processing_script),\n COURSIER_POST_PROCESSING_SCRIPT.encode(\"utf-8\"),\n is_executable=True,\n ),\n FileContent(\n os.path.basename(Coursier.post_process_stderr),\n post_process_stderr.encode(\"utf-8\"),\n is_executable=True,\n ),\n ]\n ),\n )\n\n downloaded_coursier, wrapper_scripts_digest = await MultiGet(\n downloaded_coursier_get, wrapper_scripts_digest_get\n )\n\n return Coursier(\n coursier=downloaded_coursier,\n _digest=await Get(\n Digest,\n MergeDigests(\n [\n downloaded_coursier.digest,\n wrapper_scripts_digest,\n ]\n ),\n ),\n )\n\n\ndef rules():\n return [\n *collect_rules(),\n *external_tool.rules(),\n ]\n", "path": "src/python/pants/jvm/resolve/coursier_setup.py"}]}
| 3,776 | 208 |
gh_patches_debug_51710
|
rasdani/github-patches
|
git_diff
|
getsentry__sentry-python-2069
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Cannot import appengine
### How do you use Sentry?
Sentry Saas (sentry.io)
### Version
1.18.0
### Steps to Reproduce
Install the SDK within any project that is not pinning urllib3 < 2.0.0
### Expected Result
ability to import appengine
### Actual Result
Cannot import appengine as gaecontrib.
As per urllib 2.0.0 release: https://github.com/urllib3/urllib3/tree/2.0.0
Removed urllib3.contrib.appengine.AppEngineManager and support for Google App Engine Standard Environment (https://github.com/urllib3/urllib3/issues/2044).
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 #!/usr/bin/env python
2
3 """
4 Sentry-Python - Sentry SDK for Python
5 =====================================
6
7 **Sentry-Python is an SDK for Sentry.** Check out `GitHub
8 <https://github.com/getsentry/sentry-python>`_ to find out more.
9 """
10
11 import os
12 from setuptools import setup, find_packages
13
14 here = os.path.abspath(os.path.dirname(__file__))
15
16
17 def get_file_text(file_name):
18 with open(os.path.join(here, file_name)) as in_file:
19 return in_file.read()
20
21
22 setup(
23 name="sentry-sdk",
24 version="1.21.1",
25 author="Sentry Team and Contributors",
26 author_email="[email protected]",
27 url="https://github.com/getsentry/sentry-python",
28 project_urls={
29 "Documentation": "https://docs.sentry.io/platforms/python/",
30 "Changelog": "https://github.com/getsentry/sentry-python/blob/master/CHANGELOG.md",
31 },
32 description="Python client for Sentry (https://sentry.io)",
33 long_description=get_file_text("README.md"),
34 long_description_content_type="text/markdown",
35 packages=find_packages(exclude=("tests", "tests.*")),
36 # PEP 561
37 package_data={"sentry_sdk": ["py.typed"]},
38 zip_safe=False,
39 license="MIT",
40 install_requires=[
41 'urllib3>=1.25.7; python_version<="3.4"',
42 'urllib3>=1.26.9; python_version=="3.5"',
43 'urllib3>=1.26.11; python_version >="3.6"',
44 "certifi",
45 ],
46 extras_require={
47 "flask": ["flask>=0.11", "blinker>=1.1"],
48 "quart": ["quart>=0.16.1", "blinker>=1.1"],
49 "bottle": ["bottle>=0.12.13"],
50 "falcon": ["falcon>=1.4"],
51 "django": ["django>=1.8"],
52 "sanic": ["sanic>=0.8"],
53 "celery": ["celery>=3"],
54 "huey": ["huey>=2"],
55 "beam": ["apache-beam>=2.12"],
56 "arq": ["arq>=0.23"],
57 "rq": ["rq>=0.6"],
58 "aiohttp": ["aiohttp>=3.5"],
59 "tornado": ["tornado>=5"],
60 "sqlalchemy": ["sqlalchemy>=1.2"],
61 "pyspark": ["pyspark>=2.4.4"],
62 "pure_eval": ["pure_eval", "executing", "asttokens"],
63 "chalice": ["chalice>=1.16.0"],
64 "httpx": ["httpx>=0.16.0"],
65 "starlette": ["starlette>=0.19.1"],
66 "starlite": ["starlite>=1.48"],
67 "fastapi": ["fastapi>=0.79.0"],
68 "pymongo": ["pymongo>=3.1"],
69 "opentelemetry": ["opentelemetry-distro>=0.35b0"],
70 "grpcio": ["grpcio>=1.21.1"]
71 },
72 classifiers=[
73 "Development Status :: 5 - Production/Stable",
74 "Environment :: Web Environment",
75 "Intended Audience :: Developers",
76 "License :: OSI Approved :: BSD License",
77 "Operating System :: OS Independent",
78 "Programming Language :: Python",
79 "Programming Language :: Python :: 2",
80 "Programming Language :: Python :: 2.7",
81 "Programming Language :: Python :: 3",
82 "Programming Language :: Python :: 3.4",
83 "Programming Language :: Python :: 3.5",
84 "Programming Language :: Python :: 3.6",
85 "Programming Language :: Python :: 3.7",
86 "Programming Language :: Python :: 3.8",
87 "Programming Language :: Python :: 3.9",
88 "Programming Language :: Python :: 3.10",
89 "Topic :: Software Development :: Libraries :: Python Modules",
90 ],
91 options={"bdist_wheel": {"universal": "1"}},
92 )
93
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -41,6 +41,7 @@
'urllib3>=1.25.7; python_version<="3.4"',
'urllib3>=1.26.9; python_version=="3.5"',
'urllib3>=1.26.11; python_version >="3.6"',
+ 'urllib3<2.0.0',
"certifi",
],
extras_require={
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -41,6 +41,7 @@\n 'urllib3>=1.25.7; python_version<=\"3.4\"',\n 'urllib3>=1.26.9; python_version==\"3.5\"',\n 'urllib3>=1.26.11; python_version >=\"3.6\"',\n+ 'urllib3<2.0.0',\n \"certifi\",\n ],\n extras_require={\n", "issue": "Cannot import appengine\n### How do you use Sentry?\n\nSentry Saas (sentry.io)\n\n### Version\n\n1.18.0\n\n### Steps to Reproduce\n\nInstall the SDK within any project that is not pinning urllib3 < 2.0.0\n\n### Expected Result\n\nability to import appengine\n\n### Actual Result\n\nCannot import appengine as gaecontrib.\r\nAs per urllib 2.0.0 release: https://github.com/urllib3/urllib3/tree/2.0.0\r\n\r\nRemoved urllib3.contrib.appengine.AppEngineManager and support for Google App Engine Standard Environment (https://github.com/urllib3/urllib3/issues/2044).\n", "before_files": [{"content": "#!/usr/bin/env python\n\n\"\"\"\nSentry-Python - Sentry SDK for Python\n=====================================\n\n**Sentry-Python is an SDK for Sentry.** Check out `GitHub\n<https://github.com/getsentry/sentry-python>`_ to find out more.\n\"\"\"\n\nimport os\nfrom setuptools import setup, find_packages\n\nhere = os.path.abspath(os.path.dirname(__file__))\n\n\ndef get_file_text(file_name):\n with open(os.path.join(here, file_name)) as in_file:\n return in_file.read()\n\n\nsetup(\n name=\"sentry-sdk\",\n version=\"1.21.1\",\n author=\"Sentry Team and Contributors\",\n author_email=\"[email protected]\",\n url=\"https://github.com/getsentry/sentry-python\",\n project_urls={\n \"Documentation\": \"https://docs.sentry.io/platforms/python/\",\n \"Changelog\": \"https://github.com/getsentry/sentry-python/blob/master/CHANGELOG.md\",\n },\n description=\"Python client for Sentry (https://sentry.io)\",\n long_description=get_file_text(\"README.md\"),\n long_description_content_type=\"text/markdown\",\n packages=find_packages(exclude=(\"tests\", \"tests.*\")),\n # PEP 561\n package_data={\"sentry_sdk\": [\"py.typed\"]},\n zip_safe=False,\n license=\"MIT\",\n install_requires=[\n 'urllib3>=1.25.7; python_version<=\"3.4\"',\n 'urllib3>=1.26.9; python_version==\"3.5\"',\n 'urllib3>=1.26.11; python_version >=\"3.6\"',\n \"certifi\",\n ],\n extras_require={\n \"flask\": [\"flask>=0.11\", \"blinker>=1.1\"],\n \"quart\": [\"quart>=0.16.1\", \"blinker>=1.1\"],\n \"bottle\": [\"bottle>=0.12.13\"],\n \"falcon\": [\"falcon>=1.4\"],\n \"django\": [\"django>=1.8\"],\n \"sanic\": [\"sanic>=0.8\"],\n \"celery\": [\"celery>=3\"],\n \"huey\": [\"huey>=2\"],\n \"beam\": [\"apache-beam>=2.12\"],\n \"arq\": [\"arq>=0.23\"],\n \"rq\": [\"rq>=0.6\"],\n \"aiohttp\": [\"aiohttp>=3.5\"],\n \"tornado\": [\"tornado>=5\"],\n \"sqlalchemy\": [\"sqlalchemy>=1.2\"],\n \"pyspark\": [\"pyspark>=2.4.4\"],\n \"pure_eval\": [\"pure_eval\", \"executing\", \"asttokens\"],\n \"chalice\": [\"chalice>=1.16.0\"],\n \"httpx\": [\"httpx>=0.16.0\"],\n \"starlette\": [\"starlette>=0.19.1\"],\n \"starlite\": [\"starlite>=1.48\"],\n \"fastapi\": [\"fastapi>=0.79.0\"],\n \"pymongo\": [\"pymongo>=3.1\"],\n \"opentelemetry\": [\"opentelemetry-distro>=0.35b0\"],\n \"grpcio\": [\"grpcio>=1.21.1\"]\n },\n classifiers=[\n \"Development Status :: 5 - Production/Stable\",\n \"Environment :: Web Environment\",\n \"Intended Audience :: Developers\",\n \"License :: OSI Approved :: BSD License\",\n \"Operating System :: OS Independent\",\n \"Programming Language :: Python\",\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.4\",\n \"Programming Language :: Python :: 3.5\",\n \"Programming Language :: Python :: 3.6\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n \"Programming Language :: Python :: 3.9\",\n \"Programming Language :: Python :: 3.10\",\n \"Topic :: Software Development :: Libraries :: Python Modules\",\n ],\n options={\"bdist_wheel\": {\"universal\": \"1\"}},\n)\n", "path": "setup.py"}], "after_files": [{"content": "#!/usr/bin/env python\n\n\"\"\"\nSentry-Python - Sentry SDK for Python\n=====================================\n\n**Sentry-Python is an SDK for Sentry.** Check out `GitHub\n<https://github.com/getsentry/sentry-python>`_ to find out more.\n\"\"\"\n\nimport os\nfrom setuptools import setup, find_packages\n\nhere = os.path.abspath(os.path.dirname(__file__))\n\n\ndef get_file_text(file_name):\n with open(os.path.join(here, file_name)) as in_file:\n return in_file.read()\n\n\nsetup(\n name=\"sentry-sdk\",\n version=\"1.21.1\",\n author=\"Sentry Team and Contributors\",\n author_email=\"[email protected]\",\n url=\"https://github.com/getsentry/sentry-python\",\n project_urls={\n \"Documentation\": \"https://docs.sentry.io/platforms/python/\",\n \"Changelog\": \"https://github.com/getsentry/sentry-python/blob/master/CHANGELOG.md\",\n },\n description=\"Python client for Sentry (https://sentry.io)\",\n long_description=get_file_text(\"README.md\"),\n long_description_content_type=\"text/markdown\",\n packages=find_packages(exclude=(\"tests\", \"tests.*\")),\n # PEP 561\n package_data={\"sentry_sdk\": [\"py.typed\"]},\n zip_safe=False,\n license=\"MIT\",\n install_requires=[\n 'urllib3>=1.25.7; python_version<=\"3.4\"',\n 'urllib3>=1.26.9; python_version==\"3.5\"',\n 'urllib3>=1.26.11; python_version >=\"3.6\"',\n 'urllib3<2.0.0',\n \"certifi\",\n ],\n extras_require={\n \"flask\": [\"flask>=0.11\", \"blinker>=1.1\"],\n \"quart\": [\"quart>=0.16.1\", \"blinker>=1.1\"],\n \"bottle\": [\"bottle>=0.12.13\"],\n \"falcon\": [\"falcon>=1.4\"],\n \"django\": [\"django>=1.8\"],\n \"sanic\": [\"sanic>=0.8\"],\n \"celery\": [\"celery>=3\"],\n \"huey\": [\"huey>=2\"],\n \"beam\": [\"apache-beam>=2.12\"],\n \"arq\": [\"arq>=0.23\"],\n \"rq\": [\"rq>=0.6\"],\n \"aiohttp\": [\"aiohttp>=3.5\"],\n \"tornado\": [\"tornado>=5\"],\n \"sqlalchemy\": [\"sqlalchemy>=1.2\"],\n \"pyspark\": [\"pyspark>=2.4.4\"],\n \"pure_eval\": [\"pure_eval\", \"executing\", \"asttokens\"],\n \"chalice\": [\"chalice>=1.16.0\"],\n \"httpx\": [\"httpx>=0.16.0\"],\n \"starlette\": [\"starlette>=0.19.1\"],\n \"starlite\": [\"starlite>=1.48\"],\n \"fastapi\": [\"fastapi>=0.79.0\"],\n \"pymongo\": [\"pymongo>=3.1\"],\n \"opentelemetry\": [\"opentelemetry-distro>=0.35b0\"],\n \"grpcio\": [\"grpcio>=1.21.1\"]\n },\n classifiers=[\n \"Development Status :: 5 - Production/Stable\",\n \"Environment :: Web Environment\",\n \"Intended Audience :: Developers\",\n \"License :: OSI Approved :: BSD License\",\n \"Operating System :: OS Independent\",\n \"Programming Language :: Python\",\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.4\",\n \"Programming Language :: Python :: 3.5\",\n \"Programming Language :: Python :: 3.6\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n \"Programming Language :: Python :: 3.9\",\n \"Programming Language :: Python :: 3.10\",\n \"Topic :: Software Development :: Libraries :: Python Modules\",\n ],\n options={\"bdist_wheel\": {\"universal\": \"1\"}},\n)\n", "path": "setup.py"}]}
| 1,514 | 119 |
gh_patches_debug_3474
|
rasdani/github-patches
|
git_diff
|
pymedusa__Medusa-4725
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
YGGTorrent : Unable to bdecode torrent
**Describe the bug**
The YggTorrent provider seems to have a bug. The downloads are not correctly handled to rtorrent. The "unable to bdecode torrent" occurs. Thank you for your help.
**Medusa (please complete the following information):**
Branch: master
Commit: e7c4ff3bc9a48b47c932b0e40a539d62e3a62f64 Version: v0.2.6 Database: 44.11
Python Version: | 2.7.12 (default, Dec 4 2017, 14:50:18) [GCC 5.4.0 20160609]
SSL Version: | OpenSSL 1.0.2g 1 Mar 2016
OS: | Linux-4.12.14-041214-generic-x86_64-with-Ubuntu-16.04-xenial
**Logs:**
<details>
```
2018-07-23 12:45:32 WARNING SEARCHQUEUE-FORCED-325517 :: [e7c4ff3] Unable to bdecode torrent. Invalid torrent: Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD. Deleting cached result if exists
2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [e7c4ff3] Downloading Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD with 36 seeders and 0 leechers and size 938.52 MB from Yggtorrent
2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Picked Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD as the best result.
2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Quality of Salvation.S02E01.(FASTSUB.VOSTFR.720p.WEBRip.x265.NSP) is 720p WEB-DL
2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Quality of Salvation.S02E01.FASTSUB.VOSTFR.720p.HDTV.x264.-.ZKH is 720p HDTV
2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Quality of Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD is 720p WEB-DL
2018-07-23 12:45:31 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Performing episode search for Salvation```
</details>
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `medusa/providers/torrent/html/yggtorrent.py`
Content:
```
1 # coding=utf-8
2
3 """Provider code for Yggtorrent."""
4
5 from __future__ import unicode_literals
6
7 import logging
8 import re
9
10 from medusa import tv
11 from medusa.bs4_parser import BS4Parser
12 from medusa.helper.common import (
13 convert_size,
14 try_int,
15 )
16 from medusa.logger.adapters.style import BraceAdapter
17 from medusa.providers.torrent.torrent_provider import TorrentProvider
18
19 from requests.compat import urljoin
20
21 log = BraceAdapter(logging.getLogger(__name__))
22 log.logger.addHandler(logging.NullHandler())
23
24
25 class YggtorrentProvider(TorrentProvider):
26 """Yggtorrent Torrent provider."""
27
28 torrent_id_pattern = re.compile(r'\/(\d+)-')
29
30 def __init__(self):
31 """Initialize the class."""
32 super(YggtorrentProvider, self).__init__('Yggtorrent')
33
34 # Credentials
35 self.username = None
36 self.password = None
37
38 # URLs
39 self.url = 'https://ww1.yggtorrent.is'
40 self.urls = {
41 'login': urljoin(self.url, 'user/login'),
42 'search': urljoin(self.url, 'engine/search'),
43 'download': urljoin(self.url, 'engine/download_torrent?id={0}')
44 }
45
46 # Proper Strings
47 self.proper_strings = ['PROPER', 'REPACK', 'REAL', 'RERIP']
48
49 # Torrent Stats
50 self.minseed = None
51 self.minleech = None
52
53 # Cache
54 self.cache = tv.Cache(self, min_time=20)
55
56 def search(self, search_strings, age=0, ep_obj=None, **kwargs):
57 """
58 Search a provider and parse the results.
59
60 :param search_strings: A dict with mode (key) and the search value (value)
61 :param age: Not used
62 :param ep_obj: Not used
63 :returns: A list of search results (structure)
64 """
65 results = []
66 if not self.login():
67 return results
68
69 # Search Params
70 search_params = {
71 'category': 2145,
72 'do': 'search'
73 }
74
75 for mode in search_strings:
76 log.debug('Search mode: {0}', mode)
77
78 for search_string in search_strings[mode]:
79
80 if mode != 'RSS':
81 log.debug('Search string: {search}',
82 {'search': search_string})
83
84 search_params['name'] = re.sub(r'[()]', '', search_string)
85
86 response = self.session.get(self.urls['search'], params=search_params)
87 if not response or not response.text:
88 log.debug('No data returned from provider')
89 continue
90
91 results += self.parse(response.text, mode)
92
93 return results
94
95 def parse(self, data, mode):
96 """
97 Parse search results for items.
98
99 :param data: The raw response from a search
100 :param mode: The current mode used to search, e.g. RSS
101
102 :return: A list of items found
103 """
104 # Units
105 units = ['O', 'KO', 'MO', 'GO', 'TO', 'PO']
106
107 items = []
108
109 with BS4Parser(data, 'html5lib') as html:
110 torrent_table = html.find(class_='table-responsive results')
111 torrent_rows = torrent_table('tr') if torrent_table else []
112
113 # Continue only if at least one Release is found
114 if len(torrent_rows) < 2:
115 log.debug('Data returned from provider does not contain any torrents')
116 return items
117
118 # Skip column headers
119 for result in torrent_rows[1:]:
120 cells = result('td')
121 if len(cells) < 9:
122 continue
123
124 try:
125 info = cells[1].find('a')
126 title = info.get_text(strip=True)
127 download_url = info.get('href')
128 if not (title and download_url):
129 continue
130
131 torrent_id = self.torrent_id_pattern.search(download_url)
132 download_url = self.urls['download'].format(torrent_id.group(1))
133
134 seeders = try_int(cells[7].get_text(strip=True), 0)
135 leechers = try_int(cells[8].get_text(strip=True), 0)
136
137 # Filter unseeded torrent
138 if seeders < min(self.minseed, 1):
139 if mode != 'RSS':
140 log.debug("Discarding torrent because it doesn't meet the"
141 " minimum seeders: {0}. Seeders: {1}",
142 title, seeders)
143 continue
144
145 torrent_size = cells[5].get_text()
146 size = convert_size(torrent_size, sep='', units=units, default=-1)
147
148 pubdate_raw = cells[4].find('div', class_='hidden').get_text(strip=True)
149 pubdate = self.parse_pubdate(pubdate_raw, fromtimestamp=True)
150
151 item = {
152 'title': title,
153 'link': download_url,
154 'size': size,
155 'seeders': seeders,
156 'leechers': leechers,
157 'pubdate': pubdate,
158 }
159 if mode != 'RSS':
160 log.debug('Found result: {0} with {1} seeders and {2} leechers',
161 title, seeders, leechers)
162
163 items.append(item)
164 except (AttributeError, TypeError, KeyError, ValueError, IndexError):
165 log.exception('Failed parsing provider.')
166
167 return items
168
169 def login(self):
170 """Login method used for logging in before doing search and torrent downloads."""
171 login_params = {
172 'id': self.username,
173 'pass': self.password
174 }
175
176 login_resp = self.session.post(self.urls['login'], data=login_params)
177 if not login_resp:
178 log.warning('Invalid username or password. Check your settings')
179 return False
180
181 response = self.session.get(self.url)
182 if not response:
183 log.warning('Unable to connect to provider')
184 return False
185
186 if 'Bienvenue' not in response.text:
187 log.warning('Unable to login to provider')
188 return False
189
190 return True
191
192
193 provider = YggtorrentProvider()
194
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/medusa/providers/torrent/html/yggtorrent.py b/medusa/providers/torrent/html/yggtorrent.py
--- a/medusa/providers/torrent/html/yggtorrent.py
+++ b/medusa/providers/torrent/html/yggtorrent.py
@@ -36,7 +36,7 @@
self.password = None
# URLs
- self.url = 'https://ww1.yggtorrent.is'
+ self.url = 'https://ww2.yggtorrent.is'
self.urls = {
'login': urljoin(self.url, 'user/login'),
'search': urljoin(self.url, 'engine/search'),
|
{"golden_diff": "diff --git a/medusa/providers/torrent/html/yggtorrent.py b/medusa/providers/torrent/html/yggtorrent.py\n--- a/medusa/providers/torrent/html/yggtorrent.py\n+++ b/medusa/providers/torrent/html/yggtorrent.py\n@@ -36,7 +36,7 @@\n self.password = None\n \n # URLs\n- self.url = 'https://ww1.yggtorrent.is'\n+ self.url = 'https://ww2.yggtorrent.is'\n self.urls = {\n 'login': urljoin(self.url, 'user/login'),\n 'search': urljoin(self.url, 'engine/search'),\n", "issue": "YGGTorrent : Unable to bdecode torrent\n**Describe the bug**\r\nThe YggTorrent provider seems to have a bug. The downloads are not correctly handled to rtorrent. The \"unable to bdecode torrent\" occurs. Thank you for your help. \r\n\r\n\r\n**Medusa (please complete the following information):**\r\n\r\nBranch:\u00a0master\u00a0\r\nCommit:\u00a0e7c4ff3bc9a48b47c932b0e40a539d62e3a62f64\u00a0Version:\u00a0v0.2.6\u00a0Database:\u00a044.11\r\nPython Version: | 2.7.12 (default, Dec 4 2017, 14:50:18) [GCC 5.4.0 20160609]\r\nSSL Version: | OpenSSL 1.0.2g 1 Mar 2016\r\nOS: | Linux-4.12.14-041214-generic-x86_64-with-Ubuntu-16.04-xenial\r\n\r\n**Logs:**\r\n<details>\r\n\r\n```\r\n2018-07-23 12:45:32 WARNING SEARCHQUEUE-FORCED-325517 :: [e7c4ff3] Unable to bdecode torrent. Invalid torrent: Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD. Deleting cached result if exists\r\n2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [e7c4ff3] Downloading Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD with 36 seeders and 0 leechers and size 938.52 MB from Yggtorrent\r\n2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Picked Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD as the best result.\r\n2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Quality of Salvation.S02E01.(FASTSUB.VOSTFR.720p.WEBRip.x265.NSP) is 720p WEB-DL\r\n2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Quality of Salvation.S02E01.FASTSUB.VOSTFR.720p.HDTV.x264.-.ZKH is 720p HDTV\r\n2018-07-23 12:45:32 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Quality of Salvation.S02E01.FASTSUB.VOSTFR.720p.AMZN.WEB-DL.DDP5.1.H.264-GOLD is 720p WEB-DL\r\n2018-07-23 12:45:31 INFO SEARCHQUEUE-FORCED-325517 :: [Yggtorrent] :: [e7c4ff3] Performing episode search for Salvation```\r\n</details>\r\n\r\n\n", "before_files": [{"content": "# coding=utf-8\n\n\"\"\"Provider code for Yggtorrent.\"\"\"\n\nfrom __future__ import unicode_literals\n\nimport logging\nimport re\n\nfrom medusa import tv\nfrom medusa.bs4_parser import BS4Parser\nfrom medusa.helper.common import (\n convert_size,\n try_int,\n)\nfrom medusa.logger.adapters.style import BraceAdapter\nfrom medusa.providers.torrent.torrent_provider import TorrentProvider\n\nfrom requests.compat import urljoin\n\nlog = BraceAdapter(logging.getLogger(__name__))\nlog.logger.addHandler(logging.NullHandler())\n\n\nclass YggtorrentProvider(TorrentProvider):\n \"\"\"Yggtorrent Torrent provider.\"\"\"\n\n torrent_id_pattern = re.compile(r'\\/(\\d+)-')\n\n def __init__(self):\n \"\"\"Initialize the class.\"\"\"\n super(YggtorrentProvider, self).__init__('Yggtorrent')\n\n # Credentials\n self.username = None\n self.password = None\n\n # URLs\n self.url = 'https://ww1.yggtorrent.is'\n self.urls = {\n 'login': urljoin(self.url, 'user/login'),\n 'search': urljoin(self.url, 'engine/search'),\n 'download': urljoin(self.url, 'engine/download_torrent?id={0}')\n }\n\n # Proper Strings\n self.proper_strings = ['PROPER', 'REPACK', 'REAL', 'RERIP']\n\n # Torrent Stats\n self.minseed = None\n self.minleech = None\n\n # Cache\n self.cache = tv.Cache(self, min_time=20)\n\n def search(self, search_strings, age=0, ep_obj=None, **kwargs):\n \"\"\"\n Search a provider and parse the results.\n\n :param search_strings: A dict with mode (key) and the search value (value)\n :param age: Not used\n :param ep_obj: Not used\n :returns: A list of search results (structure)\n \"\"\"\n results = []\n if not self.login():\n return results\n\n # Search Params\n search_params = {\n 'category': 2145,\n 'do': 'search'\n }\n\n for mode in search_strings:\n log.debug('Search mode: {0}', mode)\n\n for search_string in search_strings[mode]:\n\n if mode != 'RSS':\n log.debug('Search string: {search}',\n {'search': search_string})\n\n search_params['name'] = re.sub(r'[()]', '', search_string)\n\n response = self.session.get(self.urls['search'], params=search_params)\n if not response or not response.text:\n log.debug('No data returned from provider')\n continue\n\n results += self.parse(response.text, mode)\n\n return results\n\n def parse(self, data, mode):\n \"\"\"\n Parse search results for items.\n\n :param data: The raw response from a search\n :param mode: The current mode used to search, e.g. RSS\n\n :return: A list of items found\n \"\"\"\n # Units\n units = ['O', 'KO', 'MO', 'GO', 'TO', 'PO']\n\n items = []\n\n with BS4Parser(data, 'html5lib') as html:\n torrent_table = html.find(class_='table-responsive results')\n torrent_rows = torrent_table('tr') if torrent_table else []\n\n # Continue only if at least one Release is found\n if len(torrent_rows) < 2:\n log.debug('Data returned from provider does not contain any torrents')\n return items\n\n # Skip column headers\n for result in torrent_rows[1:]:\n cells = result('td')\n if len(cells) < 9:\n continue\n\n try:\n info = cells[1].find('a')\n title = info.get_text(strip=True)\n download_url = info.get('href')\n if not (title and download_url):\n continue\n\n torrent_id = self.torrent_id_pattern.search(download_url)\n download_url = self.urls['download'].format(torrent_id.group(1))\n\n seeders = try_int(cells[7].get_text(strip=True), 0)\n leechers = try_int(cells[8].get_text(strip=True), 0)\n\n # Filter unseeded torrent\n if seeders < min(self.minseed, 1):\n if mode != 'RSS':\n log.debug(\"Discarding torrent because it doesn't meet the\"\n \" minimum seeders: {0}. Seeders: {1}\",\n title, seeders)\n continue\n\n torrent_size = cells[5].get_text()\n size = convert_size(torrent_size, sep='', units=units, default=-1)\n\n pubdate_raw = cells[4].find('div', class_='hidden').get_text(strip=True)\n pubdate = self.parse_pubdate(pubdate_raw, fromtimestamp=True)\n\n item = {\n 'title': title,\n 'link': download_url,\n 'size': size,\n 'seeders': seeders,\n 'leechers': leechers,\n 'pubdate': pubdate,\n }\n if mode != 'RSS':\n log.debug('Found result: {0} with {1} seeders and {2} leechers',\n title, seeders, leechers)\n\n items.append(item)\n except (AttributeError, TypeError, KeyError, ValueError, IndexError):\n log.exception('Failed parsing provider.')\n\n return items\n\n def login(self):\n \"\"\"Login method used for logging in before doing search and torrent downloads.\"\"\"\n login_params = {\n 'id': self.username,\n 'pass': self.password\n }\n\n login_resp = self.session.post(self.urls['login'], data=login_params)\n if not login_resp:\n log.warning('Invalid username or password. Check your settings')\n return False\n\n response = self.session.get(self.url)\n if not response:\n log.warning('Unable to connect to provider')\n return False\n\n if 'Bienvenue' not in response.text:\n log.warning('Unable to login to provider')\n return False\n\n return True\n\n\nprovider = YggtorrentProvider()\n", "path": "medusa/providers/torrent/html/yggtorrent.py"}], "after_files": [{"content": "# coding=utf-8\n\n\"\"\"Provider code for Yggtorrent.\"\"\"\n\nfrom __future__ import unicode_literals\n\nimport logging\nimport re\n\nfrom medusa import tv\nfrom medusa.bs4_parser import BS4Parser\nfrom medusa.helper.common import (\n convert_size,\n try_int,\n)\nfrom medusa.logger.adapters.style import BraceAdapter\nfrom medusa.providers.torrent.torrent_provider import TorrentProvider\n\nfrom requests.compat import urljoin\n\nlog = BraceAdapter(logging.getLogger(__name__))\nlog.logger.addHandler(logging.NullHandler())\n\n\nclass YggtorrentProvider(TorrentProvider):\n \"\"\"Yggtorrent Torrent provider.\"\"\"\n\n torrent_id_pattern = re.compile(r'\\/(\\d+)-')\n\n def __init__(self):\n \"\"\"Initialize the class.\"\"\"\n super(YggtorrentProvider, self).__init__('Yggtorrent')\n\n # Credentials\n self.username = None\n self.password = None\n\n # URLs\n self.url = 'https://ww2.yggtorrent.is'\n self.urls = {\n 'login': urljoin(self.url, 'user/login'),\n 'search': urljoin(self.url, 'engine/search'),\n 'download': urljoin(self.url, 'engine/download_torrent?id={0}')\n }\n\n # Proper Strings\n self.proper_strings = ['PROPER', 'REPACK', 'REAL', 'RERIP']\n\n # Torrent Stats\n self.minseed = None\n self.minleech = None\n\n # Cache\n self.cache = tv.Cache(self, min_time=20)\n\n def search(self, search_strings, age=0, ep_obj=None, **kwargs):\n \"\"\"\n Search a provider and parse the results.\n\n :param search_strings: A dict with mode (key) and the search value (value)\n :param age: Not used\n :param ep_obj: Not used\n :returns: A list of search results (structure)\n \"\"\"\n results = []\n if not self.login():\n return results\n\n # Search Params\n search_params = {\n 'category': 2145,\n 'do': 'search'\n }\n\n for mode in search_strings:\n log.debug('Search mode: {0}', mode)\n\n for search_string in search_strings[mode]:\n\n if mode != 'RSS':\n log.debug('Search string: {search}',\n {'search': search_string})\n\n search_params['name'] = re.sub(r'[()]', '', search_string)\n\n response = self.session.get(self.urls['search'], params=search_params)\n if not response or not response.text:\n log.debug('No data returned from provider')\n continue\n\n results += self.parse(response.text, mode)\n\n return results\n\n def parse(self, data, mode):\n \"\"\"\n Parse search results for items.\n\n :param data: The raw response from a search\n :param mode: The current mode used to search, e.g. RSS\n\n :return: A list of items found\n \"\"\"\n # Units\n units = ['O', 'KO', 'MO', 'GO', 'TO', 'PO']\n\n items = []\n\n with BS4Parser(data, 'html5lib') as html:\n torrent_table = html.find(class_='table-responsive results')\n torrent_rows = torrent_table('tr') if torrent_table else []\n\n # Continue only if at least one Release is found\n if len(torrent_rows) < 2:\n log.debug('Data returned from provider does not contain any torrents')\n return items\n\n # Skip column headers\n for result in torrent_rows[1:]:\n cells = result('td')\n if len(cells) < 9:\n continue\n\n try:\n info = cells[1].find('a')\n title = info.get_text(strip=True)\n download_url = info.get('href')\n if not (title and download_url):\n continue\n\n torrent_id = self.torrent_id_pattern.search(download_url)\n download_url = self.urls['download'].format(torrent_id.group(1))\n\n seeders = try_int(cells[7].get_text(strip=True), 0)\n leechers = try_int(cells[8].get_text(strip=True), 0)\n\n # Filter unseeded torrent\n if seeders < min(self.minseed, 1):\n if mode != 'RSS':\n log.debug(\"Discarding torrent because it doesn't meet the\"\n \" minimum seeders: {0}. Seeders: {1}\",\n title, seeders)\n continue\n\n torrent_size = cells[5].get_text()\n size = convert_size(torrent_size, sep='', units=units, default=-1)\n\n pubdate_raw = cells[4].find('div', class_='hidden').get_text(strip=True)\n pubdate = self.parse_pubdate(pubdate_raw, fromtimestamp=True)\n\n item = {\n 'title': title,\n 'link': download_url,\n 'size': size,\n 'seeders': seeders,\n 'leechers': leechers,\n 'pubdate': pubdate,\n }\n if mode != 'RSS':\n log.debug('Found result: {0} with {1} seeders and {2} leechers',\n title, seeders, leechers)\n\n items.append(item)\n except (AttributeError, TypeError, KeyError, ValueError, IndexError):\n log.exception('Failed parsing provider.')\n\n return items\n\n def login(self):\n \"\"\"Login method used for logging in before doing search and torrent downloads.\"\"\"\n login_params = {\n 'id': self.username,\n 'pass': self.password\n }\n\n login_resp = self.session.post(self.urls['login'], data=login_params)\n if not login_resp:\n log.warning('Invalid username or password. Check your settings')\n return False\n\n response = self.session.get(self.url)\n if not response:\n log.warning('Unable to connect to provider')\n return False\n\n if 'Bienvenue' not in response.text:\n log.warning('Unable to login to provider')\n return False\n\n return True\n\n\nprovider = YggtorrentProvider()\n", "path": "medusa/providers/torrent/html/yggtorrent.py"}]}
| 2,961 | 145 |
gh_patches_debug_51406
|
rasdani/github-patches
|
git_diff
|
pytorch__ignite-1016
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
PyTorch dependency is lacking version constraint
## 🐛 Bug description
<!-- A clear and concise description of what the bug is. -->
PyTorch is a dependency of Ignite and, thus, is specified in `setup.py`
https://github.com/pytorch/ignite/blob/4b311cc82fe45b3082661125cd7ee54007283fb0/setup.py#L24-L26
and `conda.recipe/meta.yaml`:
https://github.com/pytorch/ignite/blob/4b311cc82fe45b3082661125cd7ee54007283fb0/conda.recipe/meta.yaml#L15-L23
The PyTorch dependency is lacking a version constraint which may work fine right now, but there is no guarantee that Ignite will be compatible with any future major PyTorch release (e.g. PyTorch v2.x).
I suggest to constrain the PyTorch version that Ignite is compatible with, e.g. `>=1.0,<2` or `<2` if any `0.x` and `1.x` version works. If PyTorch has a new major release, even previous Ignite versions can become compatible with the new major PyTorch release (especially if no changes to the code are necessary) by making new bug fix releases with relaxed version constraints to include the new PyTorch version.
In my opinion, it is highly preferable to be conservative about dependency version constraints through a [compatible release constraint](https://www.python.org/dev/peps/pep-0440/#compatible-release) in case the dependency conforms with semantic versioning. It is impossible to guarantee compatibility with a future major release of a dependency as its API can change arbitrarily.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `setup.py`
Content:
```
1 import os
2 import io
3 import re
4 from setuptools import setup, find_packages
5
6
7 def read(*names, **kwargs):
8 with io.open(os.path.join(os.path.dirname(__file__), *names), encoding=kwargs.get("encoding", "utf8")) as fp:
9 return fp.read()
10
11
12 def find_version(*file_paths):
13 version_file = read(*file_paths)
14 version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]", version_file, re.M)
15 if version_match:
16 return version_match.group(1)
17 raise RuntimeError("Unable to find version string.")
18
19
20 readme = read("README.md")
21
22 VERSION = find_version("ignite", "__init__.py")
23
24 requirements = [
25 "torch",
26 ]
27
28 setup(
29 # Metadata
30 name="pytorch-ignite",
31 version=VERSION,
32 author="PyTorch Core Team",
33 author_email="[email protected]",
34 url="https://github.com/pytorch/ignite",
35 description="A lightweight library to help with training neural networks in PyTorch.",
36 long_description_content_type="text/markdown",
37 long_description=readme,
38 license="BSD",
39 # Package info
40 packages=find_packages(exclude=("tests", "tests.*",)),
41 zip_safe=True,
42 install_requires=requirements,
43 )
44
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -22,7 +22,7 @@
VERSION = find_version("ignite", "__init__.py")
requirements = [
- "torch",
+ "torch>=1.0,<2",
]
setup(
|
{"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -22,7 +22,7 @@\n VERSION = find_version(\"ignite\", \"__init__.py\")\n \n requirements = [\n- \"torch\",\n+ \"torch>=1.0,<2\",\n ]\n \n setup(\n", "issue": "PyTorch dependency is lacking version constraint\n## \ud83d\udc1b Bug description\r\n\r\n<!-- A clear and concise description of what the bug is. -->\r\nPyTorch is a dependency of Ignite and, thus, is specified in `setup.py`\r\n\r\nhttps://github.com/pytorch/ignite/blob/4b311cc82fe45b3082661125cd7ee54007283fb0/setup.py#L24-L26\r\n\r\nand `conda.recipe/meta.yaml`:\r\n\r\nhttps://github.com/pytorch/ignite/blob/4b311cc82fe45b3082661125cd7ee54007283fb0/conda.recipe/meta.yaml#L15-L23\r\n\r\nThe PyTorch dependency is lacking a version constraint which may work fine right now, but there is no guarantee that Ignite will be compatible with any future major PyTorch release (e.g. PyTorch v2.x).\r\n\r\nI suggest to constrain the PyTorch version that Ignite is compatible with, e.g. `>=1.0,<2` or `<2` if any `0.x` and `1.x` version works. If PyTorch has a new major release, even previous Ignite versions can become compatible with the new major PyTorch release (especially if no changes to the code are necessary) by making new bug fix releases with relaxed version constraints to include the new PyTorch version.\r\n\r\nIn my opinion, it is highly preferable to be conservative about dependency version constraints through a [compatible release constraint](https://www.python.org/dev/peps/pep-0440/#compatible-release) in case the dependency conforms with semantic versioning. It is impossible to guarantee compatibility with a future major release of a dependency as its API can change arbitrarily.\n", "before_files": [{"content": "import os\nimport io\nimport re\nfrom setuptools import setup, find_packages\n\n\ndef read(*names, **kwargs):\n with io.open(os.path.join(os.path.dirname(__file__), *names), encoding=kwargs.get(\"encoding\", \"utf8\")) as fp:\n return fp.read()\n\n\ndef find_version(*file_paths):\n version_file = read(*file_paths)\n version_match = re.search(r\"^__version__ = ['\\\"]([^'\\\"]*)['\\\"]\", version_file, re.M)\n if version_match:\n return version_match.group(1)\n raise RuntimeError(\"Unable to find version string.\")\n\n\nreadme = read(\"README.md\")\n\nVERSION = find_version(\"ignite\", \"__init__.py\")\n\nrequirements = [\n \"torch\",\n]\n\nsetup(\n # Metadata\n name=\"pytorch-ignite\",\n version=VERSION,\n author=\"PyTorch Core Team\",\n author_email=\"[email protected]\",\n url=\"https://github.com/pytorch/ignite\",\n description=\"A lightweight library to help with training neural networks in PyTorch.\",\n long_description_content_type=\"text/markdown\",\n long_description=readme,\n license=\"BSD\",\n # Package info\n packages=find_packages(exclude=(\"tests\", \"tests.*\",)),\n zip_safe=True,\n install_requires=requirements,\n)\n", "path": "setup.py"}], "after_files": [{"content": "import os\nimport io\nimport re\nfrom setuptools import setup, find_packages\n\n\ndef read(*names, **kwargs):\n with io.open(os.path.join(os.path.dirname(__file__), *names), encoding=kwargs.get(\"encoding\", \"utf8\")) as fp:\n return fp.read()\n\n\ndef find_version(*file_paths):\n version_file = read(*file_paths)\n version_match = re.search(r\"^__version__ = ['\\\"]([^'\\\"]*)['\\\"]\", version_file, re.M)\n if version_match:\n return version_match.group(1)\n raise RuntimeError(\"Unable to find version string.\")\n\n\nreadme = read(\"README.md\")\n\nVERSION = find_version(\"ignite\", \"__init__.py\")\n\nrequirements = [\n \"torch>=1.0,<2\",\n]\n\nsetup(\n # Metadata\n name=\"pytorch-ignite\",\n version=VERSION,\n author=\"PyTorch Core Team\",\n author_email=\"[email protected]\",\n url=\"https://github.com/pytorch/ignite\",\n description=\"A lightweight library to help with training neural networks in PyTorch.\",\n long_description_content_type=\"text/markdown\",\n long_description=readme,\n license=\"BSD\",\n # Package info\n packages=find_packages(exclude=(\"tests\", \"tests.*\",)),\n zip_safe=True,\n install_requires=requirements,\n)\n", "path": "setup.py"}]}
| 1,012 | 68 |
gh_patches_debug_64103
|
rasdani/github-patches
|
git_diff
|
strawberry-graphql__strawberry-2411
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
App breaking when using Enum as field for Generic
<!-- Provide a general summary of the bug in the title above. -->
When using an Enum as a field on a Generic, the app breaks, throwing a `NotImplementedError`.
<!--- This template is entirely optional and can be removed, but is here to help both you and us. -->
<!--- Anything on lines wrapped in comments like these will not show up in the final text. -->
## Describe the Bug
The below code is an example of the error.
```python
from enum import Enum
from typing import Generic, Optional, TypeVar
import strawberry
T = TypeVar("T")
@strawberry.enum
class EstimatedValueEnum(Enum):
test = "test"
testtest = "testtest"
@strawberry.type
class EstimatedValue(Generic[T]):
value: T
type: EstimatedValueEnum
@strawberry.type
class Query:
id_translations: Optional[EstimatedValue[int]]
schema = strawberry.Schema(query=Query)
```
Are we doing something wrong and this is intended or is this a bug?
<!-- A clear and concise description of what the bug is. -->
## System Information
- Operating system: Docker
- Strawberry version (if applicable): Since [0.149.2](https://github.com/strawberry-graphql/strawberry/blob/main/CHANGELOG.md#01492---2022-12-09)
<!-- Add any other relevant information about the problem here. -->
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `strawberry/enum.py`
Content:
```
1 import dataclasses
2 from enum import EnumMeta
3 from typing import (
4 Any,
5 Callable,
6 Iterable,
7 List,
8 Mapping,
9 Optional,
10 TypeVar,
11 Union,
12 overload,
13 )
14
15 from strawberry.type import StrawberryType
16
17 from .exceptions import ObjectIsNotAnEnumError
18
19
20 @dataclasses.dataclass
21 class EnumValue:
22 name: str
23 value: Any
24 deprecation_reason: Optional[str] = None
25 directives: Iterable[object] = ()
26 description: Optional[str] = None
27
28
29 @dataclasses.dataclass
30 class EnumDefinition(StrawberryType):
31 wrapped_cls: EnumMeta
32 name: str
33 values: List[EnumValue]
34 description: Optional[str]
35 directives: Iterable[object] = ()
36
37 def __hash__(self) -> int:
38 # TODO: Is this enough for unique-ness?
39 return hash(self.name)
40
41 def copy_with(
42 self, type_var_map: Mapping[TypeVar, Union[StrawberryType, type]]
43 ) -> Union[StrawberryType, type]:
44 return super().copy_with(type_var_map) # type: ignore[safe-super]
45
46 @property
47 def is_generic(self) -> bool:
48 return False
49
50
51 # TODO: remove duplication of EnumValueDefinition and EnumValue
52 @dataclasses.dataclass
53 class EnumValueDefinition:
54 value: Any
55 deprecation_reason: Optional[str] = None
56 directives: Iterable[object] = ()
57 description: Optional[str] = None
58
59
60 def enum_value(
61 value: Any,
62 deprecation_reason: Optional[str] = None,
63 directives: Iterable[object] = (),
64 description: Optional[str] = None,
65 ) -> EnumValueDefinition:
66 return EnumValueDefinition(
67 value=value,
68 deprecation_reason=deprecation_reason,
69 directives=directives,
70 description=description,
71 )
72
73
74 EnumType = TypeVar("EnumType", bound=EnumMeta)
75
76
77 def _process_enum(
78 cls: EnumType,
79 name: Optional[str] = None,
80 description: Optional[str] = None,
81 directives: Iterable[object] = (),
82 ) -> EnumType:
83 if not isinstance(cls, EnumMeta):
84 raise ObjectIsNotAnEnumError(cls)
85
86 if not name:
87 name = cls.__name__
88
89 description = description
90
91 values = []
92 for item in cls: # type: ignore
93 item_value = item.value
94 item_name = item.name
95 deprecation_reason = None
96 item_directives: Iterable[object] = ()
97 enum_value_description = None
98
99 if isinstance(item_value, EnumValueDefinition):
100 item_directives = item_value.directives
101 enum_value_description = item_value.description
102 deprecation_reason = item_value.deprecation_reason
103 item_value = item_value.value
104
105 # update _value2member_map_ so that doing `MyEnum.MY_VALUE` and
106 # `MyEnum['MY_VALUE']` both work
107 cls._value2member_map_[item_value] = item
108 cls._member_map_[item_name]._value_ = item_value
109
110 value = EnumValue(
111 item_name,
112 item_value,
113 deprecation_reason=deprecation_reason,
114 directives=item_directives,
115 description=enum_value_description,
116 )
117 values.append(value)
118
119 cls._enum_definition = EnumDefinition( # type: ignore
120 wrapped_cls=cls,
121 name=name,
122 values=values,
123 description=description,
124 directives=directives,
125 )
126
127 return cls
128
129
130 @overload
131 def enum(
132 _cls: EnumType,
133 *,
134 name: Optional[str] = None,
135 description: Optional[str] = None,
136 directives: Iterable[object] = ()
137 ) -> EnumType:
138 ...
139
140
141 @overload
142 def enum(
143 _cls: None = None,
144 *,
145 name: Optional[str] = None,
146 description: Optional[str] = None,
147 directives: Iterable[object] = ()
148 ) -> Callable[[EnumType], EnumType]:
149 ...
150
151
152 def enum(
153 _cls: Optional[EnumType] = None,
154 *,
155 name: Optional[str] = None,
156 description: Optional[str] = None,
157 directives: Iterable[object] = ()
158 ) -> Union[EnumType, Callable[[EnumType], EnumType]]:
159 """Registers the enum in the GraphQL type system.
160
161 If name is passed, the name of the GraphQL type will be
162 the value passed of name instead of the Enum class name.
163 """
164
165 def wrap(cls: EnumType) -> EnumType:
166 return _process_enum(cls, name, description, directives=directives)
167
168 if not _cls:
169 return wrap
170
171 return wrap(_cls)
172
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/strawberry/enum.py b/strawberry/enum.py
--- a/strawberry/enum.py
+++ b/strawberry/enum.py
@@ -41,7 +41,8 @@
def copy_with(
self, type_var_map: Mapping[TypeVar, Union[StrawberryType, type]]
) -> Union[StrawberryType, type]:
- return super().copy_with(type_var_map) # type: ignore[safe-super]
+ # enum don't support type parameters, so we can safely return self
+ return self
@property
def is_generic(self) -> bool:
|
{"golden_diff": "diff --git a/strawberry/enum.py b/strawberry/enum.py\n--- a/strawberry/enum.py\n+++ b/strawberry/enum.py\n@@ -41,7 +41,8 @@\n def copy_with(\n self, type_var_map: Mapping[TypeVar, Union[StrawberryType, type]]\n ) -> Union[StrawberryType, type]:\n- return super().copy_with(type_var_map) # type: ignore[safe-super]\n+ # enum don't support type parameters, so we can safely return self\n+ return self\n \n @property\n def is_generic(self) -> bool:\n", "issue": "App breaking when using Enum as field for Generic\n<!-- Provide a general summary of the bug in the title above. -->\r\nWhen using an Enum as a field on a Generic, the app breaks, throwing a `NotImplementedError`.\r\n\r\n<!--- This template is entirely optional and can be removed, but is here to help both you and us. -->\r\n<!--- Anything on lines wrapped in comments like these will not show up in the final text. -->\r\n\r\n## Describe the Bug\r\nThe below code is an example of the error.\r\n```python\r\nfrom enum import Enum\r\nfrom typing import Generic, Optional, TypeVar\r\n\r\nimport strawberry\r\n\r\nT = TypeVar(\"T\")\r\n\r\n\r\[email protected]\r\nclass EstimatedValueEnum(Enum):\r\n test = \"test\"\r\n testtest = \"testtest\"\r\n\r\n\r\[email protected]\r\nclass EstimatedValue(Generic[T]):\r\n value: T\r\n type: EstimatedValueEnum\r\n\r\n\r\[email protected]\r\nclass Query:\r\n id_translations: Optional[EstimatedValue[int]]\r\n\r\n\r\nschema = strawberry.Schema(query=Query)\r\n```\r\nAre we doing something wrong and this is intended or is this a bug?\r\n<!-- A clear and concise description of what the bug is. -->\r\n\r\n## System Information\r\n\r\n - Operating system: Docker\r\n - Strawberry version (if applicable): Since [0.149.2](https://github.com/strawberry-graphql/strawberry/blob/main/CHANGELOG.md#01492---2022-12-09)\r\n\r\n<!-- Add any other relevant information about the problem here. -->\r\n\n", "before_files": [{"content": "import dataclasses\nfrom enum import EnumMeta\nfrom typing import (\n Any,\n Callable,\n Iterable,\n List,\n Mapping,\n Optional,\n TypeVar,\n Union,\n overload,\n)\n\nfrom strawberry.type import StrawberryType\n\nfrom .exceptions import ObjectIsNotAnEnumError\n\n\[email protected]\nclass EnumValue:\n name: str\n value: Any\n deprecation_reason: Optional[str] = None\n directives: Iterable[object] = ()\n description: Optional[str] = None\n\n\[email protected]\nclass EnumDefinition(StrawberryType):\n wrapped_cls: EnumMeta\n name: str\n values: List[EnumValue]\n description: Optional[str]\n directives: Iterable[object] = ()\n\n def __hash__(self) -> int:\n # TODO: Is this enough for unique-ness?\n return hash(self.name)\n\n def copy_with(\n self, type_var_map: Mapping[TypeVar, Union[StrawberryType, type]]\n ) -> Union[StrawberryType, type]:\n return super().copy_with(type_var_map) # type: ignore[safe-super]\n\n @property\n def is_generic(self) -> bool:\n return False\n\n\n# TODO: remove duplication of EnumValueDefinition and EnumValue\[email protected]\nclass EnumValueDefinition:\n value: Any\n deprecation_reason: Optional[str] = None\n directives: Iterable[object] = ()\n description: Optional[str] = None\n\n\ndef enum_value(\n value: Any,\n deprecation_reason: Optional[str] = None,\n directives: Iterable[object] = (),\n description: Optional[str] = None,\n) -> EnumValueDefinition:\n return EnumValueDefinition(\n value=value,\n deprecation_reason=deprecation_reason,\n directives=directives,\n description=description,\n )\n\n\nEnumType = TypeVar(\"EnumType\", bound=EnumMeta)\n\n\ndef _process_enum(\n cls: EnumType,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = (),\n) -> EnumType:\n if not isinstance(cls, EnumMeta):\n raise ObjectIsNotAnEnumError(cls)\n\n if not name:\n name = cls.__name__\n\n description = description\n\n values = []\n for item in cls: # type: ignore\n item_value = item.value\n item_name = item.name\n deprecation_reason = None\n item_directives: Iterable[object] = ()\n enum_value_description = None\n\n if isinstance(item_value, EnumValueDefinition):\n item_directives = item_value.directives\n enum_value_description = item_value.description\n deprecation_reason = item_value.deprecation_reason\n item_value = item_value.value\n\n # update _value2member_map_ so that doing `MyEnum.MY_VALUE` and\n # `MyEnum['MY_VALUE']` both work\n cls._value2member_map_[item_value] = item\n cls._member_map_[item_name]._value_ = item_value\n\n value = EnumValue(\n item_name,\n item_value,\n deprecation_reason=deprecation_reason,\n directives=item_directives,\n description=enum_value_description,\n )\n values.append(value)\n\n cls._enum_definition = EnumDefinition( # type: ignore\n wrapped_cls=cls,\n name=name,\n values=values,\n description=description,\n directives=directives,\n )\n\n return cls\n\n\n@overload\ndef enum(\n _cls: EnumType,\n *,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = ()\n) -> EnumType:\n ...\n\n\n@overload\ndef enum(\n _cls: None = None,\n *,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = ()\n) -> Callable[[EnumType], EnumType]:\n ...\n\n\ndef enum(\n _cls: Optional[EnumType] = None,\n *,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = ()\n) -> Union[EnumType, Callable[[EnumType], EnumType]]:\n \"\"\"Registers the enum in the GraphQL type system.\n\n If name is passed, the name of the GraphQL type will be\n the value passed of name instead of the Enum class name.\n \"\"\"\n\n def wrap(cls: EnumType) -> EnumType:\n return _process_enum(cls, name, description, directives=directives)\n\n if not _cls:\n return wrap\n\n return wrap(_cls)\n", "path": "strawberry/enum.py"}], "after_files": [{"content": "import dataclasses\nfrom enum import EnumMeta\nfrom typing import (\n Any,\n Callable,\n Iterable,\n List,\n Mapping,\n Optional,\n TypeVar,\n Union,\n overload,\n)\n\nfrom strawberry.type import StrawberryType\n\nfrom .exceptions import ObjectIsNotAnEnumError\n\n\[email protected]\nclass EnumValue:\n name: str\n value: Any\n deprecation_reason: Optional[str] = None\n directives: Iterable[object] = ()\n description: Optional[str] = None\n\n\[email protected]\nclass EnumDefinition(StrawberryType):\n wrapped_cls: EnumMeta\n name: str\n values: List[EnumValue]\n description: Optional[str]\n directives: Iterable[object] = ()\n\n def __hash__(self) -> int:\n # TODO: Is this enough for unique-ness?\n return hash(self.name)\n\n def copy_with(\n self, type_var_map: Mapping[TypeVar, Union[StrawberryType, type]]\n ) -> Union[StrawberryType, type]:\n # enum don't support type parameters, so we can safely return self\n return self\n\n @property\n def is_generic(self) -> bool:\n return False\n\n\n# TODO: remove duplication of EnumValueDefinition and EnumValue\[email protected]\nclass EnumValueDefinition:\n value: Any\n deprecation_reason: Optional[str] = None\n directives: Iterable[object] = ()\n description: Optional[str] = None\n\n\ndef enum_value(\n value: Any,\n deprecation_reason: Optional[str] = None,\n directives: Iterable[object] = (),\n description: Optional[str] = None,\n) -> EnumValueDefinition:\n return EnumValueDefinition(\n value=value,\n deprecation_reason=deprecation_reason,\n directives=directives,\n description=description,\n )\n\n\nEnumType = TypeVar(\"EnumType\", bound=EnumMeta)\n\n\ndef _process_enum(\n cls: EnumType,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = (),\n) -> EnumType:\n if not isinstance(cls, EnumMeta):\n raise ObjectIsNotAnEnumError(cls)\n\n if not name:\n name = cls.__name__\n\n description = description\n\n values = []\n for item in cls: # type: ignore\n item_value = item.value\n item_name = item.name\n deprecation_reason = None\n item_directives: Iterable[object] = ()\n enum_value_description = None\n\n if isinstance(item_value, EnumValueDefinition):\n item_directives = item_value.directives\n enum_value_description = item_value.description\n deprecation_reason = item_value.deprecation_reason\n item_value = item_value.value\n\n # update _value2member_map_ so that doing `MyEnum.MY_VALUE` and\n # `MyEnum['MY_VALUE']` both work\n cls._value2member_map_[item_value] = item\n cls._member_map_[item_name]._value_ = item_value\n\n value = EnumValue(\n item_name,\n item_value,\n deprecation_reason=deprecation_reason,\n directives=item_directives,\n description=enum_value_description,\n )\n values.append(value)\n\n cls._enum_definition = EnumDefinition( # type: ignore\n wrapped_cls=cls,\n name=name,\n values=values,\n description=description,\n directives=directives,\n )\n\n return cls\n\n\n@overload\ndef enum(\n _cls: EnumType,\n *,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = ()\n) -> EnumType:\n ...\n\n\n@overload\ndef enum(\n _cls: None = None,\n *,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = ()\n) -> Callable[[EnumType], EnumType]:\n ...\n\n\ndef enum(\n _cls: Optional[EnumType] = None,\n *,\n name: Optional[str] = None,\n description: Optional[str] = None,\n directives: Iterable[object] = ()\n) -> Union[EnumType, Callable[[EnumType], EnumType]]:\n \"\"\"Registers the enum in the GraphQL type system.\n\n If name is passed, the name of the GraphQL type will be\n the value passed of name instead of the Enum class name.\n \"\"\"\n\n def wrap(cls: EnumType) -> EnumType:\n return _process_enum(cls, name, description, directives=directives)\n\n if not _cls:\n return wrap\n\n return wrap(_cls)\n", "path": "strawberry/enum.py"}]}
| 2,021 | 146 |
gh_patches_debug_26348
|
rasdani/github-patches
|
git_diff
|
wagtail__wagtail-4805
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
When changing your password from with admin a user is presented with an edit button.
I've just reset my password from within admin and I get this horrible large edit button.
<img width="1267" alt="screen shot 2018-01-16 at 12 33 46" src="https://user-images.githubusercontent.com/7290588/34989276-e10b3338-fab9-11e7-9e69-05d1c7846af4.png">
Can we remove the edit button and amend the message to say 'Your details have been updated. You've been logged out for security reasons, please login to continue.' or something like this.
When changing your password from with admin a user is presented with an edit button.
I've just reset my password from within admin and I get this horrible large edit button.
<img width="1267" alt="screen shot 2018-01-16 at 12 33 46" src="https://user-images.githubusercontent.com/7290588/34989276-e10b3338-fab9-11e7-9e69-05d1c7846af4.png">
Can we remove the edit button and amend the message to say 'Your details have been updated. You've been logged out for security reasons, please login to continue.' or something like this.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `wagtail/users/views/users.py`
Content:
```
1 from django.conf import settings
2 from django.contrib.auth import get_user_model
3 from django.db.models import Q
4 from django.shortcuts import get_object_or_404, redirect, render
5 from django.urls import reverse
6 from django.utils.translation import ugettext as _
7 from django.views.decorators.vary import vary_on_headers
8
9 from wagtail.admin import messages
10 from wagtail.admin.forms.search import SearchForm
11 from wagtail.admin.utils import any_permission_required, permission_denied, permission_required
12 from wagtail.core import hooks
13 from wagtail.core.compat import AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME
14 from wagtail.users.forms import UserCreationForm, UserEditForm
15 from wagtail.users.utils import user_can_delete_user
16 from wagtail.utils.loading import get_custom_form
17 from wagtail.utils.pagination import paginate
18
19 User = get_user_model()
20
21 # Typically we would check the permission 'auth.change_user' (and 'auth.add_user' /
22 # 'auth.delete_user') for user management actions, but this may vary according to
23 # the AUTH_USER_MODEL setting
24 add_user_perm = "{0}.add_{1}".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())
25 change_user_perm = "{0}.change_{1}".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())
26 delete_user_perm = "{0}.delete_{1}".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())
27
28
29 def get_user_creation_form():
30 form_setting = 'WAGTAIL_USER_CREATION_FORM'
31 if hasattr(settings, form_setting):
32 return get_custom_form(form_setting)
33 else:
34 return UserCreationForm
35
36
37 def get_user_edit_form():
38 form_setting = 'WAGTAIL_USER_EDIT_FORM'
39 if hasattr(settings, form_setting):
40 return get_custom_form(form_setting)
41 else:
42 return UserEditForm
43
44
45 @any_permission_required(add_user_perm, change_user_perm, delete_user_perm)
46 @vary_on_headers('X-Requested-With')
47 def index(request):
48 q = None
49 is_searching = False
50
51 model_fields = [f.name for f in User._meta.get_fields()]
52
53 if 'q' in request.GET:
54 form = SearchForm(request.GET, placeholder=_("Search users"))
55 if form.is_valid():
56 q = form.cleaned_data['q']
57 is_searching = True
58 conditions = Q()
59
60 for term in q.split():
61 if 'username' in model_fields:
62 conditions |= Q(username__icontains=term)
63
64 if 'first_name' in model_fields:
65 conditions |= Q(first_name__icontains=term)
66
67 if 'last_name' in model_fields:
68 conditions |= Q(last_name__icontains=term)
69
70 if 'email' in model_fields:
71 conditions |= Q(email__icontains=term)
72
73 users = User.objects.filter(conditions)
74 else:
75 form = SearchForm(placeholder=_("Search users"))
76
77 if not is_searching:
78 users = User.objects.all()
79
80 if 'last_name' in model_fields and 'first_name' in model_fields:
81 users = users.order_by('last_name', 'first_name')
82
83 if 'ordering' in request.GET:
84 ordering = request.GET['ordering']
85
86 if ordering == 'username':
87 users = users.order_by(User.USERNAME_FIELD)
88 else:
89 ordering = 'name'
90
91 paginator, users = paginate(request, users)
92
93 if request.is_ajax():
94 return render(request, "wagtailusers/users/results.html", {
95 'users': users,
96 'is_searching': is_searching,
97 'query_string': q,
98 'ordering': ordering,
99 })
100 else:
101 return render(request, "wagtailusers/users/index.html", {
102 'search_form': form,
103 'users': users,
104 'is_searching': is_searching,
105 'ordering': ordering,
106 'query_string': q,
107 })
108
109
110 @permission_required(add_user_perm)
111 def create(request):
112 for fn in hooks.get_hooks('before_create_user'):
113 result = fn(request)
114 if hasattr(result, 'status_code'):
115 return result
116 if request.method == 'POST':
117 form = get_user_creation_form()(request.POST, request.FILES)
118 if form.is_valid():
119 user = form.save()
120 messages.success(request, _("User '{0}' created.").format(user), buttons=[
121 messages.button(reverse('wagtailusers_users:edit', args=(user.pk,)), _('Edit'))
122 ])
123 for fn in hooks.get_hooks('after_create_user'):
124 result = fn(request, user)
125 if hasattr(result, 'status_code'):
126 return result
127 return redirect('wagtailusers_users:index')
128 else:
129 messages.error(request, _("The user could not be created due to errors."))
130 else:
131 form = get_user_creation_form()()
132
133 return render(request, 'wagtailusers/users/create.html', {
134 'form': form,
135 })
136
137
138 @permission_required(change_user_perm)
139 def edit(request, user_id):
140 user = get_object_or_404(User, pk=user_id)
141 can_delete = user_can_delete_user(request.user, user)
142 editing_self = request.user == user
143
144 for fn in hooks.get_hooks('before_edit_user'):
145 result = fn(request, user)
146 if hasattr(result, 'status_code'):
147 return result
148 if request.method == 'POST':
149 form = get_user_edit_form()(request.POST, request.FILES, instance=user, editing_self=editing_self)
150 if form.is_valid():
151 user = form.save()
152 messages.success(request, _("Your details have been updated. You've been logged out for security reasons, "
153 "please login to continue."))
154 for fn in hooks.get_hooks('after_edit_user'):
155 result = fn(request, user)
156 if hasattr(result, 'status_code'):
157 return result
158 return redirect('wagtailusers_users:index')
159 else:
160 messages.error(request, _("The user could not be saved due to errors."))
161 else:
162 form = get_user_edit_form()(instance=user, editing_self=editing_self)
163
164 return render(request, 'wagtailusers/users/edit.html', {
165 'user': user,
166 'form': form,
167 'can_delete': can_delete,
168 })
169
170
171 @permission_required(delete_user_perm)
172 def delete(request, user_id):
173 user = get_object_or_404(User, pk=user_id)
174
175 if not user_can_delete_user(request.user, user):
176 return permission_denied(request)
177
178 for fn in hooks.get_hooks('before_delete_user'):
179 result = fn(request, user)
180 if hasattr(result, 'status_code'):
181 return result
182 if request.method == 'POST':
183 user.delete()
184 messages.success(request, _("User '{0}' deleted.").format(user))
185 for fn in hooks.get_hooks('after_delete_user'):
186 result = fn(request, user)
187 if hasattr(result, 'status_code'):
188 return result
189 return redirect('wagtailusers_users:index')
190
191 return render(request, "wagtailusers/users/confirm_delete.html", {
192 'user': user,
193 })
194
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/wagtail/users/views/users.py b/wagtail/users/views/users.py
--- a/wagtail/users/views/users.py
+++ b/wagtail/users/views/users.py
@@ -1,5 +1,5 @@
from django.conf import settings
-from django.contrib.auth import get_user_model
+from django.contrib.auth import get_user_model, update_session_auth_hash
from django.db.models import Q
from django.shortcuts import get_object_or_404, redirect, render
from django.urls import reverse
@@ -149,8 +149,14 @@
form = get_user_edit_form()(request.POST, request.FILES, instance=user, editing_self=editing_self)
if form.is_valid():
user = form.save()
- messages.success(request, _("Your details have been updated. You've been logged out for security reasons, "
- "please login to continue."))
+
+ if user == request.user and 'password1' in form.changed_data:
+ # User is changing their own password; need to update their session hash
+ update_session_auth_hash(request, user)
+
+ messages.success(request, _("User '{0}' updated.").format(user), buttons=[
+ messages.button(reverse('wagtailusers_users:edit', args=(user.pk,)), _('Edit'))
+ ])
for fn in hooks.get_hooks('after_edit_user'):
result = fn(request, user)
if hasattr(result, 'status_code'):
|
{"golden_diff": "diff --git a/wagtail/users/views/users.py b/wagtail/users/views/users.py\n--- a/wagtail/users/views/users.py\n+++ b/wagtail/users/views/users.py\n@@ -1,5 +1,5 @@\n from django.conf import settings\n-from django.contrib.auth import get_user_model\n+from django.contrib.auth import get_user_model, update_session_auth_hash\n from django.db.models import Q\n from django.shortcuts import get_object_or_404, redirect, render\n from django.urls import reverse\n@@ -149,8 +149,14 @@\n form = get_user_edit_form()(request.POST, request.FILES, instance=user, editing_self=editing_self)\n if form.is_valid():\n user = form.save()\n- messages.success(request, _(\"Your details have been updated. You've been logged out for security reasons, \"\n- \"please login to continue.\"))\n+\n+ if user == request.user and 'password1' in form.changed_data:\n+ # User is changing their own password; need to update their session hash\n+ update_session_auth_hash(request, user)\n+\n+ messages.success(request, _(\"User '{0}' updated.\").format(user), buttons=[\n+ messages.button(reverse('wagtailusers_users:edit', args=(user.pk,)), _('Edit'))\n+ ])\n for fn in hooks.get_hooks('after_edit_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n", "issue": "When changing your password from with admin a user is presented with an edit button. \nI've just reset my password from within admin and I get this horrible large edit button. \r\n<img width=\"1267\" alt=\"screen shot 2018-01-16 at 12 33 46\" src=\"https://user-images.githubusercontent.com/7290588/34989276-e10b3338-fab9-11e7-9e69-05d1c7846af4.png\">\r\n\r\nCan we remove the edit button and amend the message to say 'Your details have been updated. You've been logged out for security reasons, please login to continue.' or something like this. \nWhen changing your password from with admin a user is presented with an edit button. \nI've just reset my password from within admin and I get this horrible large edit button. \r\n<img width=\"1267\" alt=\"screen shot 2018-01-16 at 12 33 46\" src=\"https://user-images.githubusercontent.com/7290588/34989276-e10b3338-fab9-11e7-9e69-05d1c7846af4.png\">\r\n\r\nCan we remove the edit button and amend the message to say 'Your details have been updated. You've been logged out for security reasons, please login to continue.' or something like this. \n", "before_files": [{"content": "from django.conf import settings\nfrom django.contrib.auth import get_user_model\nfrom django.db.models import Q\nfrom django.shortcuts import get_object_or_404, redirect, render\nfrom django.urls import reverse\nfrom django.utils.translation import ugettext as _\nfrom django.views.decorators.vary import vary_on_headers\n\nfrom wagtail.admin import messages\nfrom wagtail.admin.forms.search import SearchForm\nfrom wagtail.admin.utils import any_permission_required, permission_denied, permission_required\nfrom wagtail.core import hooks\nfrom wagtail.core.compat import AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME\nfrom wagtail.users.forms import UserCreationForm, UserEditForm\nfrom wagtail.users.utils import user_can_delete_user\nfrom wagtail.utils.loading import get_custom_form\nfrom wagtail.utils.pagination import paginate\n\nUser = get_user_model()\n\n# Typically we would check the permission 'auth.change_user' (and 'auth.add_user' /\n# 'auth.delete_user') for user management actions, but this may vary according to\n# the AUTH_USER_MODEL setting\nadd_user_perm = \"{0}.add_{1}\".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())\nchange_user_perm = \"{0}.change_{1}\".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())\ndelete_user_perm = \"{0}.delete_{1}\".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())\n\n\ndef get_user_creation_form():\n form_setting = 'WAGTAIL_USER_CREATION_FORM'\n if hasattr(settings, form_setting):\n return get_custom_form(form_setting)\n else:\n return UserCreationForm\n\n\ndef get_user_edit_form():\n form_setting = 'WAGTAIL_USER_EDIT_FORM'\n if hasattr(settings, form_setting):\n return get_custom_form(form_setting)\n else:\n return UserEditForm\n\n\n@any_permission_required(add_user_perm, change_user_perm, delete_user_perm)\n@vary_on_headers('X-Requested-With')\ndef index(request):\n q = None\n is_searching = False\n\n model_fields = [f.name for f in User._meta.get_fields()]\n\n if 'q' in request.GET:\n form = SearchForm(request.GET, placeholder=_(\"Search users\"))\n if form.is_valid():\n q = form.cleaned_data['q']\n is_searching = True\n conditions = Q()\n\n for term in q.split():\n if 'username' in model_fields:\n conditions |= Q(username__icontains=term)\n\n if 'first_name' in model_fields:\n conditions |= Q(first_name__icontains=term)\n\n if 'last_name' in model_fields:\n conditions |= Q(last_name__icontains=term)\n\n if 'email' in model_fields:\n conditions |= Q(email__icontains=term)\n\n users = User.objects.filter(conditions)\n else:\n form = SearchForm(placeholder=_(\"Search users\"))\n\n if not is_searching:\n users = User.objects.all()\n\n if 'last_name' in model_fields and 'first_name' in model_fields:\n users = users.order_by('last_name', 'first_name')\n\n if 'ordering' in request.GET:\n ordering = request.GET['ordering']\n\n if ordering == 'username':\n users = users.order_by(User.USERNAME_FIELD)\n else:\n ordering = 'name'\n\n paginator, users = paginate(request, users)\n\n if request.is_ajax():\n return render(request, \"wagtailusers/users/results.html\", {\n 'users': users,\n 'is_searching': is_searching,\n 'query_string': q,\n 'ordering': ordering,\n })\n else:\n return render(request, \"wagtailusers/users/index.html\", {\n 'search_form': form,\n 'users': users,\n 'is_searching': is_searching,\n 'ordering': ordering,\n 'query_string': q,\n })\n\n\n@permission_required(add_user_perm)\ndef create(request):\n for fn in hooks.get_hooks('before_create_user'):\n result = fn(request)\n if hasattr(result, 'status_code'):\n return result\n if request.method == 'POST':\n form = get_user_creation_form()(request.POST, request.FILES)\n if form.is_valid():\n user = form.save()\n messages.success(request, _(\"User '{0}' created.\").format(user), buttons=[\n messages.button(reverse('wagtailusers_users:edit', args=(user.pk,)), _('Edit'))\n ])\n for fn in hooks.get_hooks('after_create_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n return redirect('wagtailusers_users:index')\n else:\n messages.error(request, _(\"The user could not be created due to errors.\"))\n else:\n form = get_user_creation_form()()\n\n return render(request, 'wagtailusers/users/create.html', {\n 'form': form,\n })\n\n\n@permission_required(change_user_perm)\ndef edit(request, user_id):\n user = get_object_or_404(User, pk=user_id)\n can_delete = user_can_delete_user(request.user, user)\n editing_self = request.user == user\n\n for fn in hooks.get_hooks('before_edit_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n if request.method == 'POST':\n form = get_user_edit_form()(request.POST, request.FILES, instance=user, editing_self=editing_self)\n if form.is_valid():\n user = form.save()\n messages.success(request, _(\"Your details have been updated. You've been logged out for security reasons, \"\n \"please login to continue.\"))\n for fn in hooks.get_hooks('after_edit_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n return redirect('wagtailusers_users:index')\n else:\n messages.error(request, _(\"The user could not be saved due to errors.\"))\n else:\n form = get_user_edit_form()(instance=user, editing_self=editing_self)\n\n return render(request, 'wagtailusers/users/edit.html', {\n 'user': user,\n 'form': form,\n 'can_delete': can_delete,\n })\n\n\n@permission_required(delete_user_perm)\ndef delete(request, user_id):\n user = get_object_or_404(User, pk=user_id)\n\n if not user_can_delete_user(request.user, user):\n return permission_denied(request)\n\n for fn in hooks.get_hooks('before_delete_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n if request.method == 'POST':\n user.delete()\n messages.success(request, _(\"User '{0}' deleted.\").format(user))\n for fn in hooks.get_hooks('after_delete_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n return redirect('wagtailusers_users:index')\n\n return render(request, \"wagtailusers/users/confirm_delete.html\", {\n 'user': user,\n })\n", "path": "wagtail/users/views/users.py"}], "after_files": [{"content": "from django.conf import settings\nfrom django.contrib.auth import get_user_model, update_session_auth_hash\nfrom django.db.models import Q\nfrom django.shortcuts import get_object_or_404, redirect, render\nfrom django.urls import reverse\nfrom django.utils.translation import ugettext as _\nfrom django.views.decorators.vary import vary_on_headers\n\nfrom wagtail.admin import messages\nfrom wagtail.admin.forms.search import SearchForm\nfrom wagtail.admin.utils import any_permission_required, permission_denied, permission_required\nfrom wagtail.core import hooks\nfrom wagtail.core.compat import AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME\nfrom wagtail.users.forms import UserCreationForm, UserEditForm\nfrom wagtail.users.utils import user_can_delete_user\nfrom wagtail.utils.loading import get_custom_form\nfrom wagtail.utils.pagination import paginate\n\nUser = get_user_model()\n\n# Typically we would check the permission 'auth.change_user' (and 'auth.add_user' /\n# 'auth.delete_user') for user management actions, but this may vary according to\n# the AUTH_USER_MODEL setting\nadd_user_perm = \"{0}.add_{1}\".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())\nchange_user_perm = \"{0}.change_{1}\".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())\ndelete_user_perm = \"{0}.delete_{1}\".format(AUTH_USER_APP_LABEL, AUTH_USER_MODEL_NAME.lower())\n\n\ndef get_user_creation_form():\n form_setting = 'WAGTAIL_USER_CREATION_FORM'\n if hasattr(settings, form_setting):\n return get_custom_form(form_setting)\n else:\n return UserCreationForm\n\n\ndef get_user_edit_form():\n form_setting = 'WAGTAIL_USER_EDIT_FORM'\n if hasattr(settings, form_setting):\n return get_custom_form(form_setting)\n else:\n return UserEditForm\n\n\n@any_permission_required(add_user_perm, change_user_perm, delete_user_perm)\n@vary_on_headers('X-Requested-With')\ndef index(request):\n q = None\n is_searching = False\n\n model_fields = [f.name for f in User._meta.get_fields()]\n\n if 'q' in request.GET:\n form = SearchForm(request.GET, placeholder=_(\"Search users\"))\n if form.is_valid():\n q = form.cleaned_data['q']\n is_searching = True\n conditions = Q()\n\n for term in q.split():\n if 'username' in model_fields:\n conditions |= Q(username__icontains=term)\n\n if 'first_name' in model_fields:\n conditions |= Q(first_name__icontains=term)\n\n if 'last_name' in model_fields:\n conditions |= Q(last_name__icontains=term)\n\n if 'email' in model_fields:\n conditions |= Q(email__icontains=term)\n\n users = User.objects.filter(conditions)\n else:\n form = SearchForm(placeholder=_(\"Search users\"))\n\n if not is_searching:\n users = User.objects.all()\n\n if 'last_name' in model_fields and 'first_name' in model_fields:\n users = users.order_by('last_name', 'first_name')\n\n if 'ordering' in request.GET:\n ordering = request.GET['ordering']\n\n if ordering == 'username':\n users = users.order_by(User.USERNAME_FIELD)\n else:\n ordering = 'name'\n\n paginator, users = paginate(request, users)\n\n if request.is_ajax():\n return render(request, \"wagtailusers/users/results.html\", {\n 'users': users,\n 'is_searching': is_searching,\n 'query_string': q,\n 'ordering': ordering,\n })\n else:\n return render(request, \"wagtailusers/users/index.html\", {\n 'search_form': form,\n 'users': users,\n 'is_searching': is_searching,\n 'ordering': ordering,\n 'query_string': q,\n })\n\n\n@permission_required(add_user_perm)\ndef create(request):\n for fn in hooks.get_hooks('before_create_user'):\n result = fn(request)\n if hasattr(result, 'status_code'):\n return result\n if request.method == 'POST':\n form = get_user_creation_form()(request.POST, request.FILES)\n if form.is_valid():\n user = form.save()\n messages.success(request, _(\"User '{0}' created.\").format(user), buttons=[\n messages.button(reverse('wagtailusers_users:edit', args=(user.pk,)), _('Edit'))\n ])\n for fn in hooks.get_hooks('after_create_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n return redirect('wagtailusers_users:index')\n else:\n messages.error(request, _(\"The user could not be created due to errors.\"))\n else:\n form = get_user_creation_form()()\n\n return render(request, 'wagtailusers/users/create.html', {\n 'form': form,\n })\n\n\n@permission_required(change_user_perm)\ndef edit(request, user_id):\n user = get_object_or_404(User, pk=user_id)\n can_delete = user_can_delete_user(request.user, user)\n editing_self = request.user == user\n\n for fn in hooks.get_hooks('before_edit_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n if request.method == 'POST':\n form = get_user_edit_form()(request.POST, request.FILES, instance=user, editing_self=editing_self)\n if form.is_valid():\n user = form.save()\n\n if user == request.user and 'password1' in form.changed_data:\n # User is changing their own password; need to update their session hash\n update_session_auth_hash(request, user)\n\n messages.success(request, _(\"User '{0}' updated.\").format(user), buttons=[\n messages.button(reverse('wagtailusers_users:edit', args=(user.pk,)), _('Edit'))\n ])\n for fn in hooks.get_hooks('after_edit_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n return redirect('wagtailusers_users:index')\n else:\n messages.error(request, _(\"The user could not be saved due to errors.\"))\n else:\n form = get_user_edit_form()(instance=user, editing_self=editing_self)\n\n return render(request, 'wagtailusers/users/edit.html', {\n 'user': user,\n 'form': form,\n 'can_delete': can_delete,\n })\n\n\n@permission_required(delete_user_perm)\ndef delete(request, user_id):\n user = get_object_or_404(User, pk=user_id)\n\n if not user_can_delete_user(request.user, user):\n return permission_denied(request)\n\n for fn in hooks.get_hooks('before_delete_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n if request.method == 'POST':\n user.delete()\n messages.success(request, _(\"User '{0}' deleted.\").format(user))\n for fn in hooks.get_hooks('after_delete_user'):\n result = fn(request, user)\n if hasattr(result, 'status_code'):\n return result\n return redirect('wagtailusers_users:index')\n\n return render(request, \"wagtailusers/users/confirm_delete.html\", {\n 'user': user,\n })\n", "path": "wagtail/users/views/users.py"}]}
| 2,578 | 310 |
gh_patches_debug_9098
|
rasdani/github-patches
|
git_diff
|
mindsdb__mindsdb-1590
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Add option to list tables in PostgreSQL integration :bookmark_tabs:
When users create a connection to the database it will be useful to show them tips with a list of tables. To be able to do this we need a new method `get_tables_list` implemented in the PostgreSQL integration class.
## Steps :male_detective: :female_detective:
- Frok MindsDB repo
- Add new implementation in https://github.com/mindsdb/mindsdb/blob/stable/mindsdb/integrations/postgres/postgres.py#L37
- Make a PR to staging branch
## Additional rewards :1st_place_medal:
Each code PR brings :three: point for entry into the draw for a :computer: Deep Learning Laptop powered by the NVIDIA RTX 3080 Max-Q GPU or other swag :shirt: :bear: . For more info check out https://mindsdb.com/hacktoberfest/
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `mindsdb/integrations/postgres/postgres.py`
Content:
```
1 from contextlib import closing
2 import pg8000
3
4 from lightwood.api import dtype
5 from mindsdb.integrations.base import Integration
6 from mindsdb.utilities.log import log
7
8
9 class PostgreSQLConnectionChecker:
10 def __init__(self, **kwargs):
11 self.host = kwargs.get('host')
12 self.port = kwargs.get('port')
13 self.user = kwargs.get('user')
14 self.password = kwargs.get('password')
15 self.database = kwargs.get('database', 'postgres')
16
17 def _get_connection(self):
18 return pg8000.connect(
19 database=self.database,
20 user=self.user,
21 password=self.password,
22 host=self.host,
23 port=self.port
24 )
25
26 def check_connection(self):
27 try:
28 con = self._get_connection()
29 with closing(con) as con:
30 con.run('select 1;')
31 connected = True
32 except Exception:
33 connected = False
34 return connected
35
36
37 class PostgreSQL(Integration, PostgreSQLConnectionChecker):
38 def __init__(self, config, name, db_info):
39 super().__init__(config, name)
40 self.user = db_info.get('user')
41 self.password = db_info.get('password')
42 self.host = db_info.get('host')
43 self.port = db_info.get('port')
44 self.database = db_info.get('database', 'postgres')
45
46 def _to_postgres_table(self, dtype_dict, predicted_cols, columns):
47 subtype_map = {
48 dtype.integer: ' int8',
49 dtype.float: 'float8',
50 dtype.binary: 'bool',
51 dtype.date: 'date',
52 dtype.datetime: 'timestamp',
53 dtype.binary: 'text',
54 dtype.categorical: 'text',
55 dtype.tags: 'text',
56 dtype.image: 'text',
57 dtype.video: 'text',
58 dtype.audio: 'text',
59 dtype.short_text: 'text',
60 dtype.rich_text: 'text',
61 dtype.array: 'text'
62 }
63
64 column_declaration = []
65 for name in columns:
66 try:
67 col_subtype = dtype_dict[name]
68 new_type = subtype_map[col_subtype]
69 column_declaration.append(f' "{name}" {new_type} ')
70 if name in predicted_cols:
71 column_declaration.append(f' "{name}_original" {new_type} ')
72 except Exception as e:
73 log.error(f'Error: can not determine postgres data type for column {name}: {e}')
74
75 return column_declaration
76
77 def _escape_table_name(self, name):
78 return '"' + name.replace('"', '""') + '"'
79
80 def _query(self, query):
81 con = self._get_connection()
82 with closing(con) as con:
83
84 cur = con.cursor()
85 res = True
86 cur.execute(query)
87
88 try:
89 rows = cur.fetchall()
90 keys = [k[0] if isinstance(k[0], str) else k[0].decode('ascii') for k in cur.description]
91 res = [dict(zip(keys, row)) for row in rows]
92 except Exception:
93 pass
94
95 con.commit()
96
97 return res
98
99 def setup(self):
100 user = f"{self.config['api']['mysql']['user']}_{self.name}"
101 password = self.config['api']['mysql']['password']
102 host = self.config['api']['mysql']['host']
103 port = self.config['api']['mysql']['port']
104
105 try:
106 self._query('''
107 DO $$
108 begin
109 if not exists (SELECT 1 FROM pg_extension where extname = 'mysql_fdw') then
110 CREATE EXTENSION mysql_fdw;
111 end if;
112 END
113 $$;
114 ''')
115 except Exception:
116 print('Error: cant find or activate mysql_fdw extension for PostgreSQL.')
117
118 self._query(f'DROP SCHEMA IF EXISTS {self.mindsdb_database} CASCADE')
119
120 self._query(f"DROP USER MAPPING IF EXISTS FOR {self.user} SERVER server_{self.mindsdb_database}")
121
122 self._query(f'DROP SERVER IF EXISTS server_{self.mindsdb_database} CASCADE')
123
124 self._query(f'''
125 CREATE SERVER server_{self.mindsdb_database}
126 FOREIGN DATA WRAPPER mysql_fdw
127 OPTIONS (host '{host}', port '{port}');
128 ''')
129
130 self._query(f'''
131 CREATE USER MAPPING FOR {self.user}
132 SERVER server_{self.mindsdb_database}
133 OPTIONS (username '{user}', password '{password}');
134 ''')
135
136 self._query(f'CREATE SCHEMA {self.mindsdb_database}')
137
138 q = f"""
139 CREATE FOREIGN TABLE IF NOT EXISTS {self.mindsdb_database}.predictors (
140 name text,
141 status text,
142 accuracy text,
143 predict text,
144 select_data_query text,
145 external_datasource text,
146 training_options text
147 )
148 SERVER server_{self.mindsdb_database}
149 OPTIONS (dbname 'mindsdb', table_name 'predictors');
150 """
151 self._query(q)
152
153 q = f"""
154 CREATE FOREIGN TABLE IF NOT EXISTS {self.mindsdb_database}.commands (
155 command text
156 ) SERVER server_{self.mindsdb_database}
157 OPTIONS (dbname 'mindsdb', table_name 'commands');
158 """
159 self._query(q)
160
161 def register_predictors(self, model_data_arr):
162 for model_meta in model_data_arr:
163 name = model_meta['name']
164 predict = model_meta['predict']
165 if not isinstance(predict, list):
166 predict = [predict]
167 columns_sql = ','.join(self._to_postgres_table(
168 model_meta['dtype_dict'],
169 predict,
170 list(model_meta['dtype_dict'].keys())
171 ))
172 columns_sql += ',"select_data_query" text'
173 columns_sql += ',"external_datasource" text'
174 for col in predict:
175 columns_sql += f',"{col}_confidence" float8'
176 if model_meta['dtype_dict'][col] in (dtype.integer, dtype.float):
177 columns_sql += f',"{col}_min" float8'
178 columns_sql += f',"{col}_max" float8'
179 columns_sql += f',"{col}_explain" text'
180
181 self.unregister_predictor(name)
182 q = f"""
183 CREATE FOREIGN TABLE {self.mindsdb_database}.{self._escape_table_name(name)} (
184 {columns_sql}
185 ) SERVER server_{self.mindsdb_database}
186 OPTIONS (dbname 'mindsdb', table_name '{name}');
187 """
188 self._query(q)
189
190 def unregister_predictor(self, name):
191 q = f"""
192 DROP FOREIGN TABLE IF EXISTS {self.mindsdb_database}.{self._escape_table_name(name)};
193 """
194 self._query(q)
195
196 def get_row_count(self, query):
197 q = f"""
198 SELECT COUNT(*) as count
199 FROM ({query}) as query;"""
200 result = self._query(q)
201 return result[0]['count']
202
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/mindsdb/integrations/postgres/postgres.py b/mindsdb/integrations/postgres/postgres.py
--- a/mindsdb/integrations/postgres/postgres.py
+++ b/mindsdb/integrations/postgres/postgres.py
@@ -199,3 +199,13 @@
FROM ({query}) as query;"""
result = self._query(q)
return result[0]['count']
+
+ def get_tables_list(self):
+ q = f""" SELECT table_schema, table_name
+ FROM information_schema.tables
+ WHERE table_schema != 'pg_catalog'
+ AND table_schema != 'information_schema'
+ ORDER BY table_schema, table_name"""
+ tables_list = self._query(q)
+ tables= [f"{table['table_schema']}.{table['table_name']}" for table in tables_list]
+ return tables
\ No newline at end of file
|
{"golden_diff": "diff --git a/mindsdb/integrations/postgres/postgres.py b/mindsdb/integrations/postgres/postgres.py\n--- a/mindsdb/integrations/postgres/postgres.py\n+++ b/mindsdb/integrations/postgres/postgres.py\n@@ -199,3 +199,13 @@\n FROM ({query}) as query;\"\"\"\n result = self._query(q)\n return result[0]['count']\n+ \n+ def get_tables_list(self):\n+ q = f\"\"\" SELECT table_schema, table_name\n+ FROM information_schema.tables\n+ WHERE table_schema != 'pg_catalog'\n+ AND table_schema != 'information_schema'\n+ ORDER BY table_schema, table_name\"\"\"\n+ tables_list = self._query(q)\n+ tables= [f\"{table['table_schema']}.{table['table_name']}\" for table in tables_list]\n+ return tables\n\\ No newline at end of file\n", "issue": "Add option to list tables in PostgreSQL integration :bookmark_tabs: \nWhen users create a connection to the database it will be useful to show them tips with a list of tables. To be able to do this we need a new method `get_tables_list` implemented in the PostgreSQL integration class.\r\n\r\n## Steps :male_detective: :female_detective: \r\n\r\n- Frok MindsDB repo\r\n- Add new implementation in https://github.com/mindsdb/mindsdb/blob/stable/mindsdb/integrations/postgres/postgres.py#L37\r\n- Make a PR to staging branch\r\n\r\n## Additional rewards :1st_place_medal: \r\n\r\nEach code PR brings :three: point for entry into the draw for a :computer: Deep Learning Laptop powered by the NVIDIA RTX 3080 Max-Q GPU or other swag :shirt: :bear: . For more info check out https://mindsdb.com/hacktoberfest/\n", "before_files": [{"content": "from contextlib import closing\nimport pg8000\n\nfrom lightwood.api import dtype\nfrom mindsdb.integrations.base import Integration\nfrom mindsdb.utilities.log import log\n\n\nclass PostgreSQLConnectionChecker:\n def __init__(self, **kwargs):\n self.host = kwargs.get('host')\n self.port = kwargs.get('port')\n self.user = kwargs.get('user')\n self.password = kwargs.get('password')\n self.database = kwargs.get('database', 'postgres')\n\n def _get_connection(self):\n return pg8000.connect(\n database=self.database,\n user=self.user,\n password=self.password,\n host=self.host,\n port=self.port\n )\n\n def check_connection(self):\n try:\n con = self._get_connection()\n with closing(con) as con:\n con.run('select 1;')\n connected = True\n except Exception:\n connected = False\n return connected\n\n\nclass PostgreSQL(Integration, PostgreSQLConnectionChecker):\n def __init__(self, config, name, db_info):\n super().__init__(config, name)\n self.user = db_info.get('user')\n self.password = db_info.get('password')\n self.host = db_info.get('host')\n self.port = db_info.get('port')\n self.database = db_info.get('database', 'postgres')\n\n def _to_postgres_table(self, dtype_dict, predicted_cols, columns):\n subtype_map = {\n dtype.integer: ' int8',\n dtype.float: 'float8',\n dtype.binary: 'bool',\n dtype.date: 'date',\n dtype.datetime: 'timestamp',\n dtype.binary: 'text',\n dtype.categorical: 'text',\n dtype.tags: 'text',\n dtype.image: 'text',\n dtype.video: 'text',\n dtype.audio: 'text',\n dtype.short_text: 'text',\n dtype.rich_text: 'text',\n dtype.array: 'text'\n }\n\n column_declaration = []\n for name in columns:\n try:\n col_subtype = dtype_dict[name]\n new_type = subtype_map[col_subtype]\n column_declaration.append(f' \"{name}\" {new_type} ')\n if name in predicted_cols:\n column_declaration.append(f' \"{name}_original\" {new_type} ')\n except Exception as e:\n log.error(f'Error: can not determine postgres data type for column {name}: {e}')\n\n return column_declaration\n\n def _escape_table_name(self, name):\n return '\"' + name.replace('\"', '\"\"') + '\"'\n\n def _query(self, query):\n con = self._get_connection()\n with closing(con) as con:\n\n cur = con.cursor()\n res = True\n cur.execute(query)\n\n try:\n rows = cur.fetchall()\n keys = [k[0] if isinstance(k[0], str) else k[0].decode('ascii') for k in cur.description]\n res = [dict(zip(keys, row)) for row in rows]\n except Exception:\n pass\n\n con.commit()\n\n return res\n\n def setup(self):\n user = f\"{self.config['api']['mysql']['user']}_{self.name}\"\n password = self.config['api']['mysql']['password']\n host = self.config['api']['mysql']['host']\n port = self.config['api']['mysql']['port']\n\n try:\n self._query('''\n DO $$\n begin\n if not exists (SELECT 1 FROM pg_extension where extname = 'mysql_fdw') then\n CREATE EXTENSION mysql_fdw;\n end if;\n END\n $$;\n ''')\n except Exception:\n print('Error: cant find or activate mysql_fdw extension for PostgreSQL.')\n\n self._query(f'DROP SCHEMA IF EXISTS {self.mindsdb_database} CASCADE')\n\n self._query(f\"DROP USER MAPPING IF EXISTS FOR {self.user} SERVER server_{self.mindsdb_database}\")\n\n self._query(f'DROP SERVER IF EXISTS server_{self.mindsdb_database} CASCADE')\n\n self._query(f'''\n CREATE SERVER server_{self.mindsdb_database}\n FOREIGN DATA WRAPPER mysql_fdw\n OPTIONS (host '{host}', port '{port}');\n ''')\n\n self._query(f'''\n CREATE USER MAPPING FOR {self.user}\n SERVER server_{self.mindsdb_database}\n OPTIONS (username '{user}', password '{password}');\n ''')\n\n self._query(f'CREATE SCHEMA {self.mindsdb_database}')\n\n q = f\"\"\"\n CREATE FOREIGN TABLE IF NOT EXISTS {self.mindsdb_database}.predictors (\n name text,\n status text,\n accuracy text,\n predict text,\n select_data_query text,\n external_datasource text,\n training_options text\n )\n SERVER server_{self.mindsdb_database}\n OPTIONS (dbname 'mindsdb', table_name 'predictors');\n \"\"\"\n self._query(q)\n\n q = f\"\"\"\n CREATE FOREIGN TABLE IF NOT EXISTS {self.mindsdb_database}.commands (\n command text\n ) SERVER server_{self.mindsdb_database}\n OPTIONS (dbname 'mindsdb', table_name 'commands');\n \"\"\"\n self._query(q)\n\n def register_predictors(self, model_data_arr):\n for model_meta in model_data_arr:\n name = model_meta['name']\n predict = model_meta['predict']\n if not isinstance(predict, list):\n predict = [predict]\n columns_sql = ','.join(self._to_postgres_table(\n model_meta['dtype_dict'],\n predict,\n list(model_meta['dtype_dict'].keys())\n ))\n columns_sql += ',\"select_data_query\" text'\n columns_sql += ',\"external_datasource\" text'\n for col in predict:\n columns_sql += f',\"{col}_confidence\" float8'\n if model_meta['dtype_dict'][col] in (dtype.integer, dtype.float):\n columns_sql += f',\"{col}_min\" float8'\n columns_sql += f',\"{col}_max\" float8'\n columns_sql += f',\"{col}_explain\" text'\n\n self.unregister_predictor(name)\n q = f\"\"\"\n CREATE FOREIGN TABLE {self.mindsdb_database}.{self._escape_table_name(name)} (\n {columns_sql}\n ) SERVER server_{self.mindsdb_database}\n OPTIONS (dbname 'mindsdb', table_name '{name}');\n \"\"\"\n self._query(q)\n\n def unregister_predictor(self, name):\n q = f\"\"\"\n DROP FOREIGN TABLE IF EXISTS {self.mindsdb_database}.{self._escape_table_name(name)};\n \"\"\"\n self._query(q)\n\n def get_row_count(self, query):\n q = f\"\"\" \n SELECT COUNT(*) as count\n FROM ({query}) as query;\"\"\"\n result = self._query(q)\n return result[0]['count']\n", "path": "mindsdb/integrations/postgres/postgres.py"}], "after_files": [{"content": "from contextlib import closing\nimport pg8000\n\nfrom lightwood.api import dtype\nfrom mindsdb.integrations.base import Integration\nfrom mindsdb.utilities.log import log\n\n\nclass PostgreSQLConnectionChecker:\n def __init__(self, **kwargs):\n self.host = kwargs.get('host')\n self.port = kwargs.get('port')\n self.user = kwargs.get('user')\n self.password = kwargs.get('password')\n self.database = kwargs.get('database', 'postgres')\n\n def _get_connection(self):\n return pg8000.connect(\n database=self.database,\n user=self.user,\n password=self.password,\n host=self.host,\n port=self.port\n )\n\n def check_connection(self):\n try:\n con = self._get_connection()\n with closing(con) as con:\n con.run('select 1;')\n connected = True\n except Exception:\n connected = False\n return connected\n\n\nclass PostgreSQL(Integration, PostgreSQLConnectionChecker):\n def __init__(self, config, name, db_info):\n super().__init__(config, name)\n self.user = db_info.get('user')\n self.password = db_info.get('password')\n self.host = db_info.get('host')\n self.port = db_info.get('port')\n self.database = db_info.get('database', 'postgres')\n\n def _to_postgres_table(self, dtype_dict, predicted_cols, columns):\n subtype_map = {\n dtype.integer: ' int8',\n dtype.float: 'float8',\n dtype.binary: 'bool',\n dtype.date: 'date',\n dtype.datetime: 'timestamp',\n dtype.binary: 'text',\n dtype.categorical: 'text',\n dtype.tags: 'text',\n dtype.image: 'text',\n dtype.video: 'text',\n dtype.audio: 'text',\n dtype.short_text: 'text',\n dtype.rich_text: 'text',\n dtype.array: 'text'\n }\n\n column_declaration = []\n for name in columns:\n try:\n col_subtype = dtype_dict[name]\n new_type = subtype_map[col_subtype]\n column_declaration.append(f' \"{name}\" {new_type} ')\n if name in predicted_cols:\n column_declaration.append(f' \"{name}_original\" {new_type} ')\n except Exception as e:\n log.error(f'Error: can not determine postgres data type for column {name}: {e}')\n\n return column_declaration\n\n def _escape_table_name(self, name):\n return '\"' + name.replace('\"', '\"\"') + '\"'\n\n def _query(self, query):\n con = self._get_connection()\n with closing(con) as con:\n\n cur = con.cursor()\n res = True\n cur.execute(query)\n\n try:\n rows = cur.fetchall()\n keys = [k[0] if isinstance(k[0], str) else k[0].decode('ascii') for k in cur.description]\n res = [dict(zip(keys, row)) for row in rows]\n except Exception:\n pass\n\n con.commit()\n\n return res\n\n def setup(self):\n user = f\"{self.config['api']['mysql']['user']}_{self.name}\"\n password = self.config['api']['mysql']['password']\n host = self.config['api']['mysql']['host']\n port = self.config['api']['mysql']['port']\n\n try:\n self._query('''\n DO $$\n begin\n if not exists (SELECT 1 FROM pg_extension where extname = 'mysql_fdw') then\n CREATE EXTENSION mysql_fdw;\n end if;\n END\n $$;\n ''')\n except Exception:\n print('Error: cant find or activate mysql_fdw extension for PostgreSQL.')\n\n self._query(f'DROP SCHEMA IF EXISTS {self.mindsdb_database} CASCADE')\n\n self._query(f\"DROP USER MAPPING IF EXISTS FOR {self.user} SERVER server_{self.mindsdb_database}\")\n\n self._query(f'DROP SERVER IF EXISTS server_{self.mindsdb_database} CASCADE')\n\n self._query(f'''\n CREATE SERVER server_{self.mindsdb_database}\n FOREIGN DATA WRAPPER mysql_fdw\n OPTIONS (host '{host}', port '{port}');\n ''')\n\n self._query(f'''\n CREATE USER MAPPING FOR {self.user}\n SERVER server_{self.mindsdb_database}\n OPTIONS (username '{user}', password '{password}');\n ''')\n\n self._query(f'CREATE SCHEMA {self.mindsdb_database}')\n\n q = f\"\"\"\n CREATE FOREIGN TABLE IF NOT EXISTS {self.mindsdb_database}.predictors (\n name text,\n status text,\n accuracy text,\n predict text,\n select_data_query text,\n external_datasource text,\n training_options text\n )\n SERVER server_{self.mindsdb_database}\n OPTIONS (dbname 'mindsdb', table_name 'predictors');\n \"\"\"\n self._query(q)\n\n q = f\"\"\"\n CREATE FOREIGN TABLE IF NOT EXISTS {self.mindsdb_database}.commands (\n command text\n ) SERVER server_{self.mindsdb_database}\n OPTIONS (dbname 'mindsdb', table_name 'commands');\n \"\"\"\n self._query(q)\n\n def register_predictors(self, model_data_arr):\n for model_meta in model_data_arr:\n name = model_meta['name']\n predict = model_meta['predict']\n if not isinstance(predict, list):\n predict = [predict]\n columns_sql = ','.join(self._to_postgres_table(\n model_meta['dtype_dict'],\n predict,\n list(model_meta['dtype_dict'].keys())\n ))\n columns_sql += ',\"select_data_query\" text'\n columns_sql += ',\"external_datasource\" text'\n for col in predict:\n columns_sql += f',\"{col}_confidence\" float8'\n if model_meta['dtype_dict'][col] in (dtype.integer, dtype.float):\n columns_sql += f',\"{col}_min\" float8'\n columns_sql += f',\"{col}_max\" float8'\n columns_sql += f',\"{col}_explain\" text'\n\n self.unregister_predictor(name)\n q = f\"\"\"\n CREATE FOREIGN TABLE {self.mindsdb_database}.{self._escape_table_name(name)} (\n {columns_sql}\n ) SERVER server_{self.mindsdb_database}\n OPTIONS (dbname 'mindsdb', table_name '{name}');\n \"\"\"\n self._query(q)\n\n def unregister_predictor(self, name):\n q = f\"\"\"\n DROP FOREIGN TABLE IF EXISTS {self.mindsdb_database}.{self._escape_table_name(name)};\n \"\"\"\n self._query(q)\n\n def get_row_count(self, query):\n q = f\"\"\" \n SELECT COUNT(*) as count\n FROM ({query}) as query;\"\"\"\n result = self._query(q)\n return result[0]['count']\n \n def get_tables_list(self):\n q = f\"\"\" SELECT table_schema, table_name\n FROM information_schema.tables\n WHERE table_schema != 'pg_catalog'\n AND table_schema != 'information_schema'\n ORDER BY table_schema, table_name\"\"\"\n tables_list = self._query(q)\n tables= [f\"{table['table_schema']}.{table['table_name']}\" for table in tables_list]\n return tables", "path": "mindsdb/integrations/postgres/postgres.py"}]}
| 2,427 | 204 |
gh_patches_debug_27460
|
rasdani/github-patches
|
git_diff
|
googleapis__python-bigquery-442
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Too noise logging about telemetry
Hello,
In the Apache Airflow project, we use the BigQuery library, but recently we've started to see annoying log message when the library is loaded. It is enough that the library is loaded and there is an message every time.
In my opinion, this message should be of a lower level (DEBUG) so that it is not displayed much less often or is displayed only when the client is initialized.
```
import logging
logging.basicConfig(level=logging.INFO)
from google.cloud import bigquery
```
Output:
```
INFO:google.cloud.bigquery.opentelemetry_tracing:This service is instrumented using OpenTelemetry. OpenTelemetry could not be imported; please add opentelemetry-api and opentelemetry-instrumentation packages in order to get BigQuery Tracing data.
```
Related issue: https://github.com/apache/airflow/issues/13131
CC: @tswast
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `google/cloud/bigquery/opentelemetry_tracing.py`
Content:
```
1 # Copyright 2020 Google LLC
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 import logging
16 from contextlib import contextmanager
17 from google.api_core.exceptions import GoogleAPICallError
18
19 logger = logging.getLogger(__name__)
20 try:
21 from opentelemetry import trace
22 from opentelemetry.instrumentation.utils import http_status_to_canonical_code
23 from opentelemetry.trace.status import Status
24
25 HAS_OPENTELEMETRY = True
26
27 except ImportError:
28 logger.info(
29 "This service is instrumented using OpenTelemetry. "
30 "OpenTelemetry could not be imported; please "
31 "add opentelemetry-api and opentelemetry-instrumentation "
32 "packages in order to get BigQuery Tracing data."
33 )
34
35 HAS_OPENTELEMETRY = False
36
37 _default_attributes = {
38 "db.system": "BigQuery"
39 } # static, default values assigned to all spans
40
41
42 @contextmanager
43 def create_span(name, attributes=None, client=None, job_ref=None):
44 """Creates a ContextManager for a Span to be exported to the configured exporter.
45 If no configuration exists yields None.
46
47 Args:
48 name (str): Name that will be set for the span being created
49 attributes (Optional[dict]):
50 Additional attributes that pertain to
51 the specific API call (i.e. not a default attribute)
52 client (Optional[google.cloud.bigquery.client.Client]):
53 Pass in a Client object to extract any attributes that may be
54 relevant to it and add them to the created spans.
55 job_ref (Optional[google.cloud.bigquery.job._AsyncJob])
56 Pass in a _AsyncJob object to extract any attributes that may be
57 relevant to it and add them to the created spans.
58
59 Yields:
60 opentelemetry.trace.Span: Yields the newly created Span.
61
62 Raises:
63 google.api_core.exceptions.GoogleAPICallError:
64 Raised if a span could not be yielded or issue with call to
65 OpenTelemetry.
66 """
67 final_attributes = _get_final_span_attributes(attributes, client, job_ref)
68 if not HAS_OPENTELEMETRY:
69 yield None
70 return
71 tracer = trace.get_tracer(__name__)
72
73 # yield new span value
74 with tracer.start_as_current_span(name=name, attributes=final_attributes) as span:
75 try:
76 yield span
77 except GoogleAPICallError as error:
78 if error.code is not None:
79 span.set_status(Status(http_status_to_canonical_code(error.code)))
80 raise
81
82
83 def _get_final_span_attributes(attributes=None, client=None, job_ref=None):
84 final_attributes = {}
85 final_attributes.update(_default_attributes.copy())
86 if client:
87 client_attributes = _set_client_attributes(client)
88 final_attributes.update(client_attributes)
89 if job_ref:
90 job_attributes = _set_job_attributes(job_ref)
91 final_attributes.update(job_attributes)
92 if attributes:
93 final_attributes.update(attributes)
94 return final_attributes
95
96
97 def _set_client_attributes(client):
98 return {"db.name": client.project, "location": client.location}
99
100
101 def _set_job_attributes(job_ref):
102 job_attributes = {
103 "db.name": job_ref.project,
104 "location": job_ref.location,
105 "num_child_jobs": job_ref.num_child_jobs,
106 "job_id": job_ref.job_id,
107 "parent_job_id": job_ref.parent_job_id,
108 "state": job_ref.state,
109 }
110
111 job_attributes["hasErrors"] = job_ref.error_result is not None
112
113 if job_ref.created is not None:
114 job_attributes["timeCreated"] = job_ref.created.isoformat()
115
116 if job_ref.started is not None:
117 job_attributes["timeStarted"] = job_ref.started.isoformat()
118
119 if job_ref.ended is not None:
120 job_attributes["timeEnded"] = job_ref.ended.isoformat()
121
122 return job_attributes
123
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/google/cloud/bigquery/opentelemetry_tracing.py b/google/cloud/bigquery/opentelemetry_tracing.py
--- a/google/cloud/bigquery/opentelemetry_tracing.py
+++ b/google/cloud/bigquery/opentelemetry_tracing.py
@@ -23,16 +23,11 @@
from opentelemetry.trace.status import Status
HAS_OPENTELEMETRY = True
+ _warned_telemetry = True
except ImportError:
- logger.info(
- "This service is instrumented using OpenTelemetry. "
- "OpenTelemetry could not be imported; please "
- "add opentelemetry-api and opentelemetry-instrumentation "
- "packages in order to get BigQuery Tracing data."
- )
-
HAS_OPENTELEMETRY = False
+ _warned_telemetry = False
_default_attributes = {
"db.system": "BigQuery"
@@ -64,8 +59,18 @@
Raised if a span could not be yielded or issue with call to
OpenTelemetry.
"""
+ global _warned_telemetry
final_attributes = _get_final_span_attributes(attributes, client, job_ref)
if not HAS_OPENTELEMETRY:
+ if not _warned_telemetry:
+ logger.debug(
+ "This service is instrumented using OpenTelemetry. "
+ "OpenTelemetry could not be imported; please "
+ "add opentelemetry-api and opentelemetry-instrumentation "
+ "packages in order to get BigQuery Tracing data."
+ )
+ _warned_telemetry = True
+
yield None
return
tracer = trace.get_tracer(__name__)
|
{"golden_diff": "diff --git a/google/cloud/bigquery/opentelemetry_tracing.py b/google/cloud/bigquery/opentelemetry_tracing.py\n--- a/google/cloud/bigquery/opentelemetry_tracing.py\n+++ b/google/cloud/bigquery/opentelemetry_tracing.py\n@@ -23,16 +23,11 @@\n from opentelemetry.trace.status import Status\n \n HAS_OPENTELEMETRY = True\n+ _warned_telemetry = True\n \n except ImportError:\n- logger.info(\n- \"This service is instrumented using OpenTelemetry. \"\n- \"OpenTelemetry could not be imported; please \"\n- \"add opentelemetry-api and opentelemetry-instrumentation \"\n- \"packages in order to get BigQuery Tracing data.\"\n- )\n-\n HAS_OPENTELEMETRY = False\n+ _warned_telemetry = False\n \n _default_attributes = {\n \"db.system\": \"BigQuery\"\n@@ -64,8 +59,18 @@\n Raised if a span could not be yielded or issue with call to\n OpenTelemetry.\n \"\"\"\n+ global _warned_telemetry\n final_attributes = _get_final_span_attributes(attributes, client, job_ref)\n if not HAS_OPENTELEMETRY:\n+ if not _warned_telemetry:\n+ logger.debug(\n+ \"This service is instrumented using OpenTelemetry. \"\n+ \"OpenTelemetry could not be imported; please \"\n+ \"add opentelemetry-api and opentelemetry-instrumentation \"\n+ \"packages in order to get BigQuery Tracing data.\"\n+ )\n+ _warned_telemetry = True\n+\n yield None\n return\n tracer = trace.get_tracer(__name__)\n", "issue": "Too noise logging about telemetry\nHello,\r\n\r\nIn the Apache Airflow project, we use the BigQuery library, but recently we've started to see annoying log message when the library is loaded. It is enough that the library is loaded and there is an message every time. \r\n\r\nIn my opinion, this message should be of a lower level (DEBUG) so that it is not displayed much less often or is displayed only when the client is initialized. \r\n```\r\nimport logging\r\nlogging.basicConfig(level=logging.INFO)\r\n\r\nfrom google.cloud import bigquery\r\n```\r\nOutput: \r\n```\r\nINFO:google.cloud.bigquery.opentelemetry_tracing:This service is instrumented using OpenTelemetry. OpenTelemetry could not be imported; please add opentelemetry-api and opentelemetry-instrumentation packages in order to get BigQuery Tracing data.\r\n```\r\n\r\nRelated issue: https://github.com/apache/airflow/issues/13131\r\n\r\nCC: @tswast \n", "before_files": [{"content": "# Copyright 2020 Google LLC\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport logging\nfrom contextlib import contextmanager\nfrom google.api_core.exceptions import GoogleAPICallError\n\nlogger = logging.getLogger(__name__)\ntry:\n from opentelemetry import trace\n from opentelemetry.instrumentation.utils import http_status_to_canonical_code\n from opentelemetry.trace.status import Status\n\n HAS_OPENTELEMETRY = True\n\nexcept ImportError:\n logger.info(\n \"This service is instrumented using OpenTelemetry. \"\n \"OpenTelemetry could not be imported; please \"\n \"add opentelemetry-api and opentelemetry-instrumentation \"\n \"packages in order to get BigQuery Tracing data.\"\n )\n\n HAS_OPENTELEMETRY = False\n\n_default_attributes = {\n \"db.system\": \"BigQuery\"\n} # static, default values assigned to all spans\n\n\n@contextmanager\ndef create_span(name, attributes=None, client=None, job_ref=None):\n \"\"\"Creates a ContextManager for a Span to be exported to the configured exporter.\n If no configuration exists yields None.\n\n Args:\n name (str): Name that will be set for the span being created\n attributes (Optional[dict]):\n Additional attributes that pertain to\n the specific API call (i.e. not a default attribute)\n client (Optional[google.cloud.bigquery.client.Client]):\n Pass in a Client object to extract any attributes that may be\n relevant to it and add them to the created spans.\n job_ref (Optional[google.cloud.bigquery.job._AsyncJob])\n Pass in a _AsyncJob object to extract any attributes that may be\n relevant to it and add them to the created spans.\n\n Yields:\n opentelemetry.trace.Span: Yields the newly created Span.\n\n Raises:\n google.api_core.exceptions.GoogleAPICallError:\n Raised if a span could not be yielded or issue with call to\n OpenTelemetry.\n \"\"\"\n final_attributes = _get_final_span_attributes(attributes, client, job_ref)\n if not HAS_OPENTELEMETRY:\n yield None\n return\n tracer = trace.get_tracer(__name__)\n\n # yield new span value\n with tracer.start_as_current_span(name=name, attributes=final_attributes) as span:\n try:\n yield span\n except GoogleAPICallError as error:\n if error.code is not None:\n span.set_status(Status(http_status_to_canonical_code(error.code)))\n raise\n\n\ndef _get_final_span_attributes(attributes=None, client=None, job_ref=None):\n final_attributes = {}\n final_attributes.update(_default_attributes.copy())\n if client:\n client_attributes = _set_client_attributes(client)\n final_attributes.update(client_attributes)\n if job_ref:\n job_attributes = _set_job_attributes(job_ref)\n final_attributes.update(job_attributes)\n if attributes:\n final_attributes.update(attributes)\n return final_attributes\n\n\ndef _set_client_attributes(client):\n return {\"db.name\": client.project, \"location\": client.location}\n\n\ndef _set_job_attributes(job_ref):\n job_attributes = {\n \"db.name\": job_ref.project,\n \"location\": job_ref.location,\n \"num_child_jobs\": job_ref.num_child_jobs,\n \"job_id\": job_ref.job_id,\n \"parent_job_id\": job_ref.parent_job_id,\n \"state\": job_ref.state,\n }\n\n job_attributes[\"hasErrors\"] = job_ref.error_result is not None\n\n if job_ref.created is not None:\n job_attributes[\"timeCreated\"] = job_ref.created.isoformat()\n\n if job_ref.started is not None:\n job_attributes[\"timeStarted\"] = job_ref.started.isoformat()\n\n if job_ref.ended is not None:\n job_attributes[\"timeEnded\"] = job_ref.ended.isoformat()\n\n return job_attributes\n", "path": "google/cloud/bigquery/opentelemetry_tracing.py"}], "after_files": [{"content": "# Copyright 2020 Google LLC\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport logging\nfrom contextlib import contextmanager\nfrom google.api_core.exceptions import GoogleAPICallError\n\nlogger = logging.getLogger(__name__)\ntry:\n from opentelemetry import trace\n from opentelemetry.instrumentation.utils import http_status_to_canonical_code\n from opentelemetry.trace.status import Status\n\n HAS_OPENTELEMETRY = True\n _warned_telemetry = True\n\nexcept ImportError:\n HAS_OPENTELEMETRY = False\n _warned_telemetry = False\n\n_default_attributes = {\n \"db.system\": \"BigQuery\"\n} # static, default values assigned to all spans\n\n\n@contextmanager\ndef create_span(name, attributes=None, client=None, job_ref=None):\n \"\"\"Creates a ContextManager for a Span to be exported to the configured exporter.\n If no configuration exists yields None.\n\n Args:\n name (str): Name that will be set for the span being created\n attributes (Optional[dict]):\n Additional attributes that pertain to\n the specific API call (i.e. not a default attribute)\n client (Optional[google.cloud.bigquery.client.Client]):\n Pass in a Client object to extract any attributes that may be\n relevant to it and add them to the created spans.\n job_ref (Optional[google.cloud.bigquery.job._AsyncJob])\n Pass in a _AsyncJob object to extract any attributes that may be\n relevant to it and add them to the created spans.\n\n Yields:\n opentelemetry.trace.Span: Yields the newly created Span.\n\n Raises:\n google.api_core.exceptions.GoogleAPICallError:\n Raised if a span could not be yielded or issue with call to\n OpenTelemetry.\n \"\"\"\n global _warned_telemetry\n final_attributes = _get_final_span_attributes(attributes, client, job_ref)\n if not HAS_OPENTELEMETRY:\n if not _warned_telemetry:\n logger.debug(\n \"This service is instrumented using OpenTelemetry. \"\n \"OpenTelemetry could not be imported; please \"\n \"add opentelemetry-api and opentelemetry-instrumentation \"\n \"packages in order to get BigQuery Tracing data.\"\n )\n _warned_telemetry = True\n\n yield None\n return\n tracer = trace.get_tracer(__name__)\n\n # yield new span value\n with tracer.start_as_current_span(name=name, attributes=final_attributes) as span:\n try:\n yield span\n except GoogleAPICallError as error:\n if error.code is not None:\n span.set_status(Status(http_status_to_canonical_code(error.code)))\n raise\n\n\ndef _get_final_span_attributes(attributes=None, client=None, job_ref=None):\n final_attributes = {}\n final_attributes.update(_default_attributes.copy())\n if client:\n client_attributes = _set_client_attributes(client)\n final_attributes.update(client_attributes)\n if job_ref:\n job_attributes = _set_job_attributes(job_ref)\n final_attributes.update(job_attributes)\n if attributes:\n final_attributes.update(attributes)\n return final_attributes\n\n\ndef _set_client_attributes(client):\n return {\"db.name\": client.project, \"location\": client.location}\n\n\ndef _set_job_attributes(job_ref):\n job_attributes = {\n \"db.name\": job_ref.project,\n \"location\": job_ref.location,\n \"num_child_jobs\": job_ref.num_child_jobs,\n \"job_id\": job_ref.job_id,\n \"parent_job_id\": job_ref.parent_job_id,\n \"state\": job_ref.state,\n }\n\n job_attributes[\"hasErrors\"] = job_ref.error_result is not None\n\n if job_ref.created is not None:\n job_attributes[\"timeCreated\"] = job_ref.created.isoformat()\n\n if job_ref.started is not None:\n job_attributes[\"timeStarted\"] = job_ref.started.isoformat()\n\n if job_ref.ended is not None:\n job_attributes[\"timeEnded\"] = job_ref.ended.isoformat()\n\n return job_attributes\n", "path": "google/cloud/bigquery/opentelemetry_tracing.py"}]}
| 1,662 | 377 |
gh_patches_debug_16868
|
rasdani/github-patches
|
git_diff
|
open-telemetry__opentelemetry-python-2544
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Implement Drop aggregation
See [Drop aggregation](https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/metrics/sdk.md#drop-aggregation)
> The Drop Aggregation informs the SDK to ignore/drop all Instrument Measurements for this Aggregation.
This is a bit of a special case. The implementation should probably avoid creating a `ViewInstrumentMatch` altogether when we encounter this aggregation to save memory.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py`
Content:
```
1 # Copyright The OpenTelemetry Authors
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 from abc import ABC, abstractmethod
16 from bisect import bisect_left
17 from dataclasses import replace
18 from logging import getLogger
19 from math import inf
20 from threading import Lock
21 from typing import Generic, List, Optional, Sequence, TypeVar
22
23 from opentelemetry._metrics.instrument import (
24 Asynchronous,
25 Instrument,
26 Synchronous,
27 _Monotonic,
28 )
29 from opentelemetry.sdk._metrics.measurement import Measurement
30 from opentelemetry.sdk._metrics.point import (
31 AggregationTemporality,
32 Gauge,
33 Histogram,
34 PointT,
35 Sum,
36 )
37 from opentelemetry.util._time import _time_ns
38
39 _PointVarT = TypeVar("_PointVarT", bound=PointT)
40
41 _logger = getLogger(__name__)
42
43
44 class _Aggregation(ABC, Generic[_PointVarT]):
45 def __init__(self):
46 self._lock = Lock()
47
48 @abstractmethod
49 def aggregate(self, measurement: Measurement) -> None:
50 pass
51
52 @abstractmethod
53 def collect(self) -> Optional[_PointVarT]:
54 pass
55
56
57 class _SumAggregation(_Aggregation[Sum]):
58 def __init__(
59 self,
60 instrument_is_monotonic: bool,
61 instrument_temporality: AggregationTemporality,
62 ):
63 super().__init__()
64
65 self._start_time_unix_nano = _time_ns()
66 self._instrument_temporality = instrument_temporality
67 self._instrument_is_monotonic = instrument_is_monotonic
68
69 if self._instrument_temporality is AggregationTemporality.DELTA:
70 self._value = 0
71 else:
72 self._value = None
73
74 def aggregate(self, measurement: Measurement) -> None:
75 with self._lock:
76 if self._value is None:
77 self._value = 0
78 self._value = self._value + measurement.value
79
80 def collect(self) -> Optional[Sum]:
81 """
82 Atomically return a point for the current value of the metric and
83 reset the aggregation value.
84 """
85 now = _time_ns()
86
87 if self._instrument_temporality is AggregationTemporality.DELTA:
88
89 with self._lock:
90 value = self._value
91 start_time_unix_nano = self._start_time_unix_nano
92
93 self._value = 0
94 self._start_time_unix_nano = now + 1
95
96 return Sum(
97 aggregation_temporality=AggregationTemporality.DELTA,
98 is_monotonic=self._instrument_is_monotonic,
99 start_time_unix_nano=start_time_unix_nano,
100 time_unix_nano=now,
101 value=value,
102 )
103
104 with self._lock:
105 if self._value is None:
106 return None
107 value = self._value
108 self._value = None
109
110 return Sum(
111 aggregation_temporality=AggregationTemporality.CUMULATIVE,
112 is_monotonic=self._instrument_is_monotonic,
113 start_time_unix_nano=self._start_time_unix_nano,
114 time_unix_nano=now,
115 value=value,
116 )
117
118
119 class _LastValueAggregation(_Aggregation[Gauge]):
120 def __init__(self):
121 super().__init__()
122 self._value = None
123
124 def aggregate(self, measurement: Measurement):
125 with self._lock:
126 self._value = measurement.value
127
128 def collect(self) -> Optional[Gauge]:
129 """
130 Atomically return a point for the current value of the metric.
131 """
132 with self._lock:
133 if self._value is None:
134 return None
135 value = self._value
136 self._value = None
137
138 return Gauge(
139 time_unix_nano=_time_ns(),
140 value=value,
141 )
142
143
144 class _ExplicitBucketHistogramAggregation(_Aggregation[Histogram]):
145 def __init__(
146 self,
147 boundaries: Sequence[float] = (
148 0.0,
149 5.0,
150 10.0,
151 25.0,
152 50.0,
153 75.0,
154 100.0,
155 250.0,
156 500.0,
157 1000.0,
158 ),
159 record_min_max: bool = True,
160 ):
161 super().__init__()
162 self._boundaries = tuple(boundaries)
163 self._bucket_counts = self._get_empty_bucket_counts()
164 self._min = inf
165 self._max = -inf
166 self._sum = 0
167 self._record_min_max = record_min_max
168 self._start_time_unix_nano = _time_ns()
169
170 def _get_empty_bucket_counts(self) -> List[int]:
171 return [0] * (len(self._boundaries) + 1)
172
173 def aggregate(self, measurement: Measurement) -> None:
174
175 value = measurement.value
176
177 if self._record_min_max:
178 self._min = min(self._min, value)
179 self._max = max(self._max, value)
180
181 self._sum += value
182
183 self._bucket_counts[bisect_left(self._boundaries, value)] += 1
184
185 def collect(self) -> Histogram:
186 """
187 Atomically return a point for the current value of the metric.
188 """
189 now = _time_ns()
190
191 with self._lock:
192 value = self._bucket_counts
193 start_time_unix_nano = self._start_time_unix_nano
194 histogram_sum = self._sum
195
196 self._bucket_counts = self._get_empty_bucket_counts()
197 self._start_time_unix_nano = now + 1
198 self._sum = 0
199
200 return Histogram(
201 start_time_unix_nano=start_time_unix_nano,
202 time_unix_nano=now,
203 bucket_counts=tuple(value),
204 explicit_bounds=self._boundaries,
205 aggregation_temporality=AggregationTemporality.DELTA,
206 sum=histogram_sum,
207 )
208
209
210 # pylint: disable=too-many-return-statements,too-many-branches
211 def _convert_aggregation_temporality(
212 previous_point: Optional[_PointVarT],
213 current_point: _PointVarT,
214 aggregation_temporality: AggregationTemporality,
215 ) -> _PointVarT:
216 """Converts `current_point` to the requested `aggregation_temporality`
217 given the `previous_point`.
218
219 `previous_point` must have `CUMULATIVE` temporality. `current_point` may
220 have `DELTA` or `CUMULATIVE` temporality.
221
222 The output point will have temporality `aggregation_temporality`. Since
223 `GAUGE` points have no temporality, they are returned unchanged.
224 """
225
226 current_point_type = type(current_point)
227
228 if current_point_type is Gauge:
229 return current_point
230
231 if previous_point is not None and type(previous_point) is not type(
232 current_point
233 ):
234 _logger.warning(
235 "convert_aggregation_temporality called with mismatched "
236 "point types: %s and %s",
237 type(previous_point),
238 current_point_type,
239 )
240
241 return current_point
242
243 if current_point_type is Sum:
244 if previous_point is None:
245 # Output CUMULATIVE for a synchronous instrument
246 # There is no previous value, return the delta point as a
247 # cumulative
248 return replace(
249 current_point, aggregation_temporality=aggregation_temporality
250 )
251 if previous_point.aggregation_temporality is not (
252 AggregationTemporality.CUMULATIVE
253 ):
254 raise Exception(
255 "previous_point aggregation temporality must be CUMULATIVE"
256 )
257
258 if current_point.aggregation_temporality is aggregation_temporality:
259 # Output DELTA for a synchronous instrument
260 # Output CUMULATIVE for an asynchronous instrument
261 return current_point
262
263 if aggregation_temporality is AggregationTemporality.DELTA:
264 # Output temporality DELTA for an asynchronous instrument
265 value = current_point.value - previous_point.value
266 output_start_time_unix_nano = previous_point.time_unix_nano
267
268 else:
269 # Output CUMULATIVE for a synchronous instrument
270 value = current_point.value + previous_point.value
271 output_start_time_unix_nano = previous_point.start_time_unix_nano
272
273 is_monotonic = (
274 previous_point.is_monotonic and current_point.is_monotonic
275 )
276
277 return Sum(
278 start_time_unix_nano=output_start_time_unix_nano,
279 time_unix_nano=current_point.time_unix_nano,
280 value=value,
281 aggregation_temporality=aggregation_temporality,
282 is_monotonic=is_monotonic,
283 )
284
285 if current_point_type is Histogram:
286 if previous_point is None:
287 return replace(
288 current_point, aggregation_temporality=aggregation_temporality
289 )
290 if previous_point.aggregation_temporality is not (
291 AggregationTemporality.CUMULATIVE
292 ):
293 raise Exception(
294 "previous_point aggregation temporality must be CUMULATIVE"
295 )
296
297 if current_point.aggregation_temporality is aggregation_temporality:
298 return current_point
299
300 if aggregation_temporality is AggregationTemporality.CUMULATIVE:
301 start_time_unix_nano = previous_point.start_time_unix_nano
302 sum_ = current_point.sum + previous_point.sum
303 bucket_counts = [
304 curr_count + prev_count
305 for curr_count, prev_count in zip(
306 current_point.bucket_counts, previous_point.bucket_counts
307 )
308 ]
309 else:
310 start_time_unix_nano = previous_point.time_unix_nano
311 sum_ = current_point.sum - previous_point.sum
312 bucket_counts = [
313 curr_count - prev_count
314 for curr_count, prev_count in zip(
315 current_point.bucket_counts, previous_point.bucket_counts
316 )
317 ]
318
319 return Histogram(
320 start_time_unix_nano=start_time_unix_nano,
321 time_unix_nano=current_point.time_unix_nano,
322 bucket_counts=bucket_counts,
323 explicit_bounds=current_point.explicit_bounds,
324 sum=sum_,
325 aggregation_temporality=aggregation_temporality,
326 )
327 return None
328
329
330 class _AggregationFactory(ABC):
331 @abstractmethod
332 def _create_aggregation(self, instrument: Instrument) -> _Aggregation:
333 """Creates an aggregation"""
334
335
336 class ExplicitBucketHistogramAggregation(_AggregationFactory):
337 def __init__(
338 self,
339 boundaries: Sequence[float] = (
340 0.0,
341 5.0,
342 10.0,
343 25.0,
344 50.0,
345 75.0,
346 100.0,
347 250.0,
348 500.0,
349 1000.0,
350 ),
351 record_min_max: bool = True,
352 ) -> None:
353 self._boundaries = boundaries
354 self._record_min_max = record_min_max
355
356 def _create_aggregation(self, instrument: Instrument) -> _Aggregation:
357 return _ExplicitBucketHistogramAggregation(
358 boundaries=self._boundaries,
359 record_min_max=self._record_min_max,
360 )
361
362
363 class SumAggregation(_AggregationFactory):
364 def _create_aggregation(self, instrument: Instrument) -> _Aggregation:
365
366 temporality = AggregationTemporality.UNSPECIFIED
367 if isinstance(instrument, Synchronous):
368 temporality = AggregationTemporality.DELTA
369 elif isinstance(instrument, Asynchronous):
370 temporality = AggregationTemporality.CUMULATIVE
371
372 return _SumAggregation(
373 isinstance(instrument, _Monotonic),
374 temporality,
375 )
376
377
378 class LastValueAggregation(_AggregationFactory):
379 def _create_aggregation(self, instrument: Instrument) -> _Aggregation:
380 return _LastValueAggregation()
381
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py b/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py
--- a/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py
+++ b/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py
@@ -54,6 +54,14 @@
pass
+class _DropAggregation(_Aggregation):
+ def aggregate(self, measurement: Measurement) -> None:
+ pass
+
+ def collect(self) -> Optional[_PointVarT]:
+ pass
+
+
class _SumAggregation(_Aggregation[Sum]):
def __init__(
self,
@@ -378,3 +386,10 @@
class LastValueAggregation(_AggregationFactory):
def _create_aggregation(self, instrument: Instrument) -> _Aggregation:
return _LastValueAggregation()
+
+
+class DropAggregation(_AggregationFactory):
+ """Using this aggregation will make all measurements be ignored."""
+
+ def _create_aggregation(self, instrument: Instrument) -> _Aggregation:
+ return _DropAggregation()
|
{"golden_diff": "diff --git a/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py b/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py\n--- a/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py\n+++ b/opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py\n@@ -54,6 +54,14 @@\n pass\n \n \n+class _DropAggregation(_Aggregation):\n+ def aggregate(self, measurement: Measurement) -> None:\n+ pass\n+\n+ def collect(self) -> Optional[_PointVarT]:\n+ pass\n+\n+\n class _SumAggregation(_Aggregation[Sum]):\n def __init__(\n self,\n@@ -378,3 +386,10 @@\n class LastValueAggregation(_AggregationFactory):\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n return _LastValueAggregation()\n+\n+\n+class DropAggregation(_AggregationFactory):\n+ \"\"\"Using this aggregation will make all measurements be ignored.\"\"\"\n+\n+ def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n+ return _DropAggregation()\n", "issue": "Implement Drop aggregation\nSee [Drop aggregation](https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/metrics/sdk.md#drop-aggregation)\r\n\r\n> The Drop Aggregation informs the SDK to ignore/drop all Instrument Measurements for this Aggregation.\r\n\r\nThis is a bit of a special case. The implementation should probably avoid creating a `ViewInstrumentMatch` altogether when we encounter this aggregation to save memory.\n", "before_files": [{"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom abc import ABC, abstractmethod\nfrom bisect import bisect_left\nfrom dataclasses import replace\nfrom logging import getLogger\nfrom math import inf\nfrom threading import Lock\nfrom typing import Generic, List, Optional, Sequence, TypeVar\n\nfrom opentelemetry._metrics.instrument import (\n Asynchronous,\n Instrument,\n Synchronous,\n _Monotonic,\n)\nfrom opentelemetry.sdk._metrics.measurement import Measurement\nfrom opentelemetry.sdk._metrics.point import (\n AggregationTemporality,\n Gauge,\n Histogram,\n PointT,\n Sum,\n)\nfrom opentelemetry.util._time import _time_ns\n\n_PointVarT = TypeVar(\"_PointVarT\", bound=PointT)\n\n_logger = getLogger(__name__)\n\n\nclass _Aggregation(ABC, Generic[_PointVarT]):\n def __init__(self):\n self._lock = Lock()\n\n @abstractmethod\n def aggregate(self, measurement: Measurement) -> None:\n pass\n\n @abstractmethod\n def collect(self) -> Optional[_PointVarT]:\n pass\n\n\nclass _SumAggregation(_Aggregation[Sum]):\n def __init__(\n self,\n instrument_is_monotonic: bool,\n instrument_temporality: AggregationTemporality,\n ):\n super().__init__()\n\n self._start_time_unix_nano = _time_ns()\n self._instrument_temporality = instrument_temporality\n self._instrument_is_monotonic = instrument_is_monotonic\n\n if self._instrument_temporality is AggregationTemporality.DELTA:\n self._value = 0\n else:\n self._value = None\n\n def aggregate(self, measurement: Measurement) -> None:\n with self._lock:\n if self._value is None:\n self._value = 0\n self._value = self._value + measurement.value\n\n def collect(self) -> Optional[Sum]:\n \"\"\"\n Atomically return a point for the current value of the metric and\n reset the aggregation value.\n \"\"\"\n now = _time_ns()\n\n if self._instrument_temporality is AggregationTemporality.DELTA:\n\n with self._lock:\n value = self._value\n start_time_unix_nano = self._start_time_unix_nano\n\n self._value = 0\n self._start_time_unix_nano = now + 1\n\n return Sum(\n aggregation_temporality=AggregationTemporality.DELTA,\n is_monotonic=self._instrument_is_monotonic,\n start_time_unix_nano=start_time_unix_nano,\n time_unix_nano=now,\n value=value,\n )\n\n with self._lock:\n if self._value is None:\n return None\n value = self._value\n self._value = None\n\n return Sum(\n aggregation_temporality=AggregationTemporality.CUMULATIVE,\n is_monotonic=self._instrument_is_monotonic,\n start_time_unix_nano=self._start_time_unix_nano,\n time_unix_nano=now,\n value=value,\n )\n\n\nclass _LastValueAggregation(_Aggregation[Gauge]):\n def __init__(self):\n super().__init__()\n self._value = None\n\n def aggregate(self, measurement: Measurement):\n with self._lock:\n self._value = measurement.value\n\n def collect(self) -> Optional[Gauge]:\n \"\"\"\n Atomically return a point for the current value of the metric.\n \"\"\"\n with self._lock:\n if self._value is None:\n return None\n value = self._value\n self._value = None\n\n return Gauge(\n time_unix_nano=_time_ns(),\n value=value,\n )\n\n\nclass _ExplicitBucketHistogramAggregation(_Aggregation[Histogram]):\n def __init__(\n self,\n boundaries: Sequence[float] = (\n 0.0,\n 5.0,\n 10.0,\n 25.0,\n 50.0,\n 75.0,\n 100.0,\n 250.0,\n 500.0,\n 1000.0,\n ),\n record_min_max: bool = True,\n ):\n super().__init__()\n self._boundaries = tuple(boundaries)\n self._bucket_counts = self._get_empty_bucket_counts()\n self._min = inf\n self._max = -inf\n self._sum = 0\n self._record_min_max = record_min_max\n self._start_time_unix_nano = _time_ns()\n\n def _get_empty_bucket_counts(self) -> List[int]:\n return [0] * (len(self._boundaries) + 1)\n\n def aggregate(self, measurement: Measurement) -> None:\n\n value = measurement.value\n\n if self._record_min_max:\n self._min = min(self._min, value)\n self._max = max(self._max, value)\n\n self._sum += value\n\n self._bucket_counts[bisect_left(self._boundaries, value)] += 1\n\n def collect(self) -> Histogram:\n \"\"\"\n Atomically return a point for the current value of the metric.\n \"\"\"\n now = _time_ns()\n\n with self._lock:\n value = self._bucket_counts\n start_time_unix_nano = self._start_time_unix_nano\n histogram_sum = self._sum\n\n self._bucket_counts = self._get_empty_bucket_counts()\n self._start_time_unix_nano = now + 1\n self._sum = 0\n\n return Histogram(\n start_time_unix_nano=start_time_unix_nano,\n time_unix_nano=now,\n bucket_counts=tuple(value),\n explicit_bounds=self._boundaries,\n aggregation_temporality=AggregationTemporality.DELTA,\n sum=histogram_sum,\n )\n\n\n# pylint: disable=too-many-return-statements,too-many-branches\ndef _convert_aggregation_temporality(\n previous_point: Optional[_PointVarT],\n current_point: _PointVarT,\n aggregation_temporality: AggregationTemporality,\n) -> _PointVarT:\n \"\"\"Converts `current_point` to the requested `aggregation_temporality`\n given the `previous_point`.\n\n `previous_point` must have `CUMULATIVE` temporality. `current_point` may\n have `DELTA` or `CUMULATIVE` temporality.\n\n The output point will have temporality `aggregation_temporality`. Since\n `GAUGE` points have no temporality, they are returned unchanged.\n \"\"\"\n\n current_point_type = type(current_point)\n\n if current_point_type is Gauge:\n return current_point\n\n if previous_point is not None and type(previous_point) is not type(\n current_point\n ):\n _logger.warning(\n \"convert_aggregation_temporality called with mismatched \"\n \"point types: %s and %s\",\n type(previous_point),\n current_point_type,\n )\n\n return current_point\n\n if current_point_type is Sum:\n if previous_point is None:\n # Output CUMULATIVE for a synchronous instrument\n # There is no previous value, return the delta point as a\n # cumulative\n return replace(\n current_point, aggregation_temporality=aggregation_temporality\n )\n if previous_point.aggregation_temporality is not (\n AggregationTemporality.CUMULATIVE\n ):\n raise Exception(\n \"previous_point aggregation temporality must be CUMULATIVE\"\n )\n\n if current_point.aggregation_temporality is aggregation_temporality:\n # Output DELTA for a synchronous instrument\n # Output CUMULATIVE for an asynchronous instrument\n return current_point\n\n if aggregation_temporality is AggregationTemporality.DELTA:\n # Output temporality DELTA for an asynchronous instrument\n value = current_point.value - previous_point.value\n output_start_time_unix_nano = previous_point.time_unix_nano\n\n else:\n # Output CUMULATIVE for a synchronous instrument\n value = current_point.value + previous_point.value\n output_start_time_unix_nano = previous_point.start_time_unix_nano\n\n is_monotonic = (\n previous_point.is_monotonic and current_point.is_monotonic\n )\n\n return Sum(\n start_time_unix_nano=output_start_time_unix_nano,\n time_unix_nano=current_point.time_unix_nano,\n value=value,\n aggregation_temporality=aggregation_temporality,\n is_monotonic=is_monotonic,\n )\n\n if current_point_type is Histogram:\n if previous_point is None:\n return replace(\n current_point, aggregation_temporality=aggregation_temporality\n )\n if previous_point.aggregation_temporality is not (\n AggregationTemporality.CUMULATIVE\n ):\n raise Exception(\n \"previous_point aggregation temporality must be CUMULATIVE\"\n )\n\n if current_point.aggregation_temporality is aggregation_temporality:\n return current_point\n\n if aggregation_temporality is AggregationTemporality.CUMULATIVE:\n start_time_unix_nano = previous_point.start_time_unix_nano\n sum_ = current_point.sum + previous_point.sum\n bucket_counts = [\n curr_count + prev_count\n for curr_count, prev_count in zip(\n current_point.bucket_counts, previous_point.bucket_counts\n )\n ]\n else:\n start_time_unix_nano = previous_point.time_unix_nano\n sum_ = current_point.sum - previous_point.sum\n bucket_counts = [\n curr_count - prev_count\n for curr_count, prev_count in zip(\n current_point.bucket_counts, previous_point.bucket_counts\n )\n ]\n\n return Histogram(\n start_time_unix_nano=start_time_unix_nano,\n time_unix_nano=current_point.time_unix_nano,\n bucket_counts=bucket_counts,\n explicit_bounds=current_point.explicit_bounds,\n sum=sum_,\n aggregation_temporality=aggregation_temporality,\n )\n return None\n\n\nclass _AggregationFactory(ABC):\n @abstractmethod\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n \"\"\"Creates an aggregation\"\"\"\n\n\nclass ExplicitBucketHistogramAggregation(_AggregationFactory):\n def __init__(\n self,\n boundaries: Sequence[float] = (\n 0.0,\n 5.0,\n 10.0,\n 25.0,\n 50.0,\n 75.0,\n 100.0,\n 250.0,\n 500.0,\n 1000.0,\n ),\n record_min_max: bool = True,\n ) -> None:\n self._boundaries = boundaries\n self._record_min_max = record_min_max\n\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n return _ExplicitBucketHistogramAggregation(\n boundaries=self._boundaries,\n record_min_max=self._record_min_max,\n )\n\n\nclass SumAggregation(_AggregationFactory):\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n\n temporality = AggregationTemporality.UNSPECIFIED\n if isinstance(instrument, Synchronous):\n temporality = AggregationTemporality.DELTA\n elif isinstance(instrument, Asynchronous):\n temporality = AggregationTemporality.CUMULATIVE\n\n return _SumAggregation(\n isinstance(instrument, _Monotonic),\n temporality,\n )\n\n\nclass LastValueAggregation(_AggregationFactory):\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n return _LastValueAggregation()\n", "path": "opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py"}], "after_files": [{"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom abc import ABC, abstractmethod\nfrom bisect import bisect_left\nfrom dataclasses import replace\nfrom logging import getLogger\nfrom math import inf\nfrom threading import Lock\nfrom typing import Generic, List, Optional, Sequence, TypeVar\n\nfrom opentelemetry._metrics.instrument import (\n Asynchronous,\n Instrument,\n Synchronous,\n _Monotonic,\n)\nfrom opentelemetry.sdk._metrics.measurement import Measurement\nfrom opentelemetry.sdk._metrics.point import (\n AggregationTemporality,\n Gauge,\n Histogram,\n PointT,\n Sum,\n)\nfrom opentelemetry.util._time import _time_ns\n\n_PointVarT = TypeVar(\"_PointVarT\", bound=PointT)\n\n_logger = getLogger(__name__)\n\n\nclass _Aggregation(ABC, Generic[_PointVarT]):\n def __init__(self):\n self._lock = Lock()\n\n @abstractmethod\n def aggregate(self, measurement: Measurement) -> None:\n pass\n\n @abstractmethod\n def collect(self) -> Optional[_PointVarT]:\n pass\n\n\nclass _DropAggregation(_Aggregation):\n def aggregate(self, measurement: Measurement) -> None:\n pass\n\n def collect(self) -> Optional[_PointVarT]:\n pass\n\n\nclass _SumAggregation(_Aggregation[Sum]):\n def __init__(\n self,\n instrument_is_monotonic: bool,\n instrument_temporality: AggregationTemporality,\n ):\n super().__init__()\n\n self._start_time_unix_nano = _time_ns()\n self._instrument_temporality = instrument_temporality\n self._instrument_is_monotonic = instrument_is_monotonic\n\n if self._instrument_temporality is AggregationTemporality.DELTA:\n self._value = 0\n else:\n self._value = None\n\n def aggregate(self, measurement: Measurement) -> None:\n with self._lock:\n if self._value is None:\n self._value = 0\n self._value = self._value + measurement.value\n\n def collect(self) -> Optional[Sum]:\n \"\"\"\n Atomically return a point for the current value of the metric and\n reset the aggregation value.\n \"\"\"\n now = _time_ns()\n\n if self._instrument_temporality is AggregationTemporality.DELTA:\n\n with self._lock:\n value = self._value\n start_time_unix_nano = self._start_time_unix_nano\n\n self._value = 0\n self._start_time_unix_nano = now + 1\n\n return Sum(\n aggregation_temporality=AggregationTemporality.DELTA,\n is_monotonic=self._instrument_is_monotonic,\n start_time_unix_nano=start_time_unix_nano,\n time_unix_nano=now,\n value=value,\n )\n\n with self._lock:\n if self._value is None:\n return None\n value = self._value\n self._value = None\n\n return Sum(\n aggregation_temporality=AggregationTemporality.CUMULATIVE,\n is_monotonic=self._instrument_is_monotonic,\n start_time_unix_nano=self._start_time_unix_nano,\n time_unix_nano=now,\n value=value,\n )\n\n\nclass _LastValueAggregation(_Aggregation[Gauge]):\n def __init__(self):\n super().__init__()\n self._value = None\n\n def aggregate(self, measurement: Measurement):\n with self._lock:\n self._value = measurement.value\n\n def collect(self) -> Optional[Gauge]:\n \"\"\"\n Atomically return a point for the current value of the metric.\n \"\"\"\n with self._lock:\n if self._value is None:\n return None\n value = self._value\n self._value = None\n\n return Gauge(\n time_unix_nano=_time_ns(),\n value=value,\n )\n\n\nclass _ExplicitBucketHistogramAggregation(_Aggregation[Histogram]):\n def __init__(\n self,\n boundaries: Sequence[float] = (\n 0.0,\n 5.0,\n 10.0,\n 25.0,\n 50.0,\n 75.0,\n 100.0,\n 250.0,\n 500.0,\n 1000.0,\n ),\n record_min_max: bool = True,\n ):\n super().__init__()\n self._boundaries = tuple(boundaries)\n self._bucket_counts = self._get_empty_bucket_counts()\n self._min = inf\n self._max = -inf\n self._sum = 0\n self._record_min_max = record_min_max\n self._start_time_unix_nano = _time_ns()\n\n def _get_empty_bucket_counts(self) -> List[int]:\n return [0] * (len(self._boundaries) + 1)\n\n def aggregate(self, measurement: Measurement) -> None:\n\n value = measurement.value\n\n if self._record_min_max:\n self._min = min(self._min, value)\n self._max = max(self._max, value)\n\n self._sum += value\n\n self._bucket_counts[bisect_left(self._boundaries, value)] += 1\n\n def collect(self) -> Histogram:\n \"\"\"\n Atomically return a point for the current value of the metric.\n \"\"\"\n now = _time_ns()\n\n with self._lock:\n value = self._bucket_counts\n start_time_unix_nano = self._start_time_unix_nano\n histogram_sum = self._sum\n\n self._bucket_counts = self._get_empty_bucket_counts()\n self._start_time_unix_nano = now + 1\n self._sum = 0\n\n return Histogram(\n start_time_unix_nano=start_time_unix_nano,\n time_unix_nano=now,\n bucket_counts=tuple(value),\n explicit_bounds=self._boundaries,\n aggregation_temporality=AggregationTemporality.DELTA,\n sum=histogram_sum,\n )\n\n\n# pylint: disable=too-many-return-statements,too-many-branches\ndef _convert_aggregation_temporality(\n previous_point: Optional[_PointVarT],\n current_point: _PointVarT,\n aggregation_temporality: AggregationTemporality,\n) -> _PointVarT:\n \"\"\"Converts `current_point` to the requested `aggregation_temporality`\n given the `previous_point`.\n\n `previous_point` must have `CUMULATIVE` temporality. `current_point` may\n have `DELTA` or `CUMULATIVE` temporality.\n\n The output point will have temporality `aggregation_temporality`. Since\n `GAUGE` points have no temporality, they are returned unchanged.\n \"\"\"\n\n current_point_type = type(current_point)\n\n if current_point_type is Gauge:\n return current_point\n\n if previous_point is not None and type(previous_point) is not type(\n current_point\n ):\n _logger.warning(\n \"convert_aggregation_temporality called with mismatched \"\n \"point types: %s and %s\",\n type(previous_point),\n current_point_type,\n )\n\n return current_point\n\n if current_point_type is Sum:\n if previous_point is None:\n # Output CUMULATIVE for a synchronous instrument\n # There is no previous value, return the delta point as a\n # cumulative\n return replace(\n current_point, aggregation_temporality=aggregation_temporality\n )\n if previous_point.aggregation_temporality is not (\n AggregationTemporality.CUMULATIVE\n ):\n raise Exception(\n \"previous_point aggregation temporality must be CUMULATIVE\"\n )\n\n if current_point.aggregation_temporality is aggregation_temporality:\n # Output DELTA for a synchronous instrument\n # Output CUMULATIVE for an asynchronous instrument\n return current_point\n\n if aggregation_temporality is AggregationTemporality.DELTA:\n # Output temporality DELTA for an asynchronous instrument\n value = current_point.value - previous_point.value\n output_start_time_unix_nano = previous_point.time_unix_nano\n\n else:\n # Output CUMULATIVE for a synchronous instrument\n value = current_point.value + previous_point.value\n output_start_time_unix_nano = previous_point.start_time_unix_nano\n\n is_monotonic = (\n previous_point.is_monotonic and current_point.is_monotonic\n )\n\n return Sum(\n start_time_unix_nano=output_start_time_unix_nano,\n time_unix_nano=current_point.time_unix_nano,\n value=value,\n aggregation_temporality=aggregation_temporality,\n is_monotonic=is_monotonic,\n )\n\n if current_point_type is Histogram:\n if previous_point is None:\n return replace(\n current_point, aggregation_temporality=aggregation_temporality\n )\n if previous_point.aggregation_temporality is not (\n AggregationTemporality.CUMULATIVE\n ):\n raise Exception(\n \"previous_point aggregation temporality must be CUMULATIVE\"\n )\n\n if current_point.aggregation_temporality is aggregation_temporality:\n return current_point\n\n if aggregation_temporality is AggregationTemporality.CUMULATIVE:\n start_time_unix_nano = previous_point.start_time_unix_nano\n sum_ = current_point.sum + previous_point.sum\n bucket_counts = [\n curr_count + prev_count\n for curr_count, prev_count in zip(\n current_point.bucket_counts, previous_point.bucket_counts\n )\n ]\n else:\n start_time_unix_nano = previous_point.time_unix_nano\n sum_ = current_point.sum - previous_point.sum\n bucket_counts = [\n curr_count - prev_count\n for curr_count, prev_count in zip(\n current_point.bucket_counts, previous_point.bucket_counts\n )\n ]\n\n return Histogram(\n start_time_unix_nano=start_time_unix_nano,\n time_unix_nano=current_point.time_unix_nano,\n bucket_counts=bucket_counts,\n explicit_bounds=current_point.explicit_bounds,\n sum=sum_,\n aggregation_temporality=aggregation_temporality,\n )\n return None\n\n\nclass _AggregationFactory(ABC):\n @abstractmethod\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n \"\"\"Creates an aggregation\"\"\"\n\n\nclass ExplicitBucketHistogramAggregation(_AggregationFactory):\n def __init__(\n self,\n boundaries: Sequence[float] = (\n 0.0,\n 5.0,\n 10.0,\n 25.0,\n 50.0,\n 75.0,\n 100.0,\n 250.0,\n 500.0,\n 1000.0,\n ),\n record_min_max: bool = True,\n ) -> None:\n self._boundaries = boundaries\n self._record_min_max = record_min_max\n\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n return _ExplicitBucketHistogramAggregation(\n boundaries=self._boundaries,\n record_min_max=self._record_min_max,\n )\n\n\nclass SumAggregation(_AggregationFactory):\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n\n temporality = AggregationTemporality.UNSPECIFIED\n if isinstance(instrument, Synchronous):\n temporality = AggregationTemporality.DELTA\n elif isinstance(instrument, Asynchronous):\n temporality = AggregationTemporality.CUMULATIVE\n\n return _SumAggregation(\n isinstance(instrument, _Monotonic),\n temporality,\n )\n\n\nclass LastValueAggregation(_AggregationFactory):\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n return _LastValueAggregation()\n\n\nclass DropAggregation(_AggregationFactory):\n \"\"\"Using this aggregation will make all measurements be ignored.\"\"\"\n\n def _create_aggregation(self, instrument: Instrument) -> _Aggregation:\n return _DropAggregation()\n", "path": "opentelemetry-sdk/src/opentelemetry/sdk/_metrics/aggregation.py"}]}
| 4,087 | 253 |
gh_patches_debug_9151
|
rasdani/github-patches
|
git_diff
|
python-discord__bot-1199
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Race condition in wait_for_deletion between a manual delete and reacting
Sentry Issue: [BOT-86](https://sentry.io/organizations/python-discord/issues/1861537034/?referrer=github_integration)
The message may be deleted before `wait_for_deletion` has a chance to add a reaction.
```
NotFound: 404 Not Found (error code: 10008): Unknown Message
File "bot/utils/messages.py", line 38, in wait_for_deletion
await message.add_reaction(emoji)
File "discord/message.py", line 953, in add_reaction
await self._state.http.add_reaction(self.channel.id, self.id, emoji)
File "discord/http.py", line 243, in request
raise NotFound(r, data)
Task exception was never retrieved
future: <Task finished name='Task-333258' coro=<wait_for_deletion() done, defined at /bot/bot/utils/messages.py:19> exception=NotFound('404 Not Found (error code: 10008): Unknown Message')>
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `bot/utils/messages.py`
Content:
```
1 import asyncio
2 import contextlib
3 import logging
4 import random
5 import re
6 from io import BytesIO
7 from typing import List, Optional, Sequence, Union
8
9 import discord
10 from discord.errors import HTTPException
11 from discord.ext.commands import Context
12
13 from bot.constants import Emojis, NEGATIVE_REPLIES
14
15 log = logging.getLogger(__name__)
16
17
18 async def wait_for_deletion(
19 message: discord.Message,
20 user_ids: Sequence[discord.abc.Snowflake],
21 client: discord.Client,
22 deletion_emojis: Sequence[str] = (Emojis.trashcan,),
23 timeout: float = 60 * 5,
24 attach_emojis: bool = True,
25 ) -> None:
26 """
27 Wait for up to `timeout` seconds for a reaction by any of the specified `user_ids` to delete the message.
28
29 An `attach_emojis` bool may be specified to determine whether to attach the given
30 `deletion_emojis` to the message in the given `context`.
31 """
32 if message.guild is None:
33 raise ValueError("Message must be sent on a guild")
34
35 if attach_emojis:
36 for emoji in deletion_emojis:
37 await message.add_reaction(emoji)
38
39 def check(reaction: discord.Reaction, user: discord.Member) -> bool:
40 """Check that the deletion emoji is reacted by the appropriate user."""
41 return (
42 reaction.message.id == message.id
43 and str(reaction.emoji) in deletion_emojis
44 and user.id in user_ids
45 )
46
47 with contextlib.suppress(asyncio.TimeoutError):
48 await client.wait_for('reaction_add', check=check, timeout=timeout)
49 await message.delete()
50
51
52 async def send_attachments(
53 message: discord.Message,
54 destination: Union[discord.TextChannel, discord.Webhook],
55 link_large: bool = True
56 ) -> List[str]:
57 """
58 Re-upload the message's attachments to the destination and return a list of their new URLs.
59
60 Each attachment is sent as a separate message to more easily comply with the request/file size
61 limit. If link_large is True, attachments which are too large are instead grouped into a single
62 embed which links to them.
63 """
64 large = []
65 urls = []
66 for attachment in message.attachments:
67 failure_msg = (
68 f"Failed to re-upload attachment {attachment.filename} from message {message.id}"
69 )
70
71 try:
72 # Allow 512 bytes of leeway for the rest of the request.
73 # This should avoid most files that are too large,
74 # but some may get through hence the try-catch.
75 if attachment.size <= destination.guild.filesize_limit - 512:
76 with BytesIO() as file:
77 await attachment.save(file, use_cached=True)
78 attachment_file = discord.File(file, filename=attachment.filename)
79
80 if isinstance(destination, discord.TextChannel):
81 msg = await destination.send(file=attachment_file)
82 urls.append(msg.attachments[0].url)
83 else:
84 await destination.send(
85 file=attachment_file,
86 username=sub_clyde(message.author.display_name),
87 avatar_url=message.author.avatar_url
88 )
89 elif link_large:
90 large.append(attachment)
91 else:
92 log.info(f"{failure_msg} because it's too large.")
93 except HTTPException as e:
94 if link_large and e.status == 413:
95 large.append(attachment)
96 else:
97 log.warning(f"{failure_msg} with status {e.status}.", exc_info=e)
98
99 if link_large and large:
100 desc = "\n".join(f"[{attachment.filename}]({attachment.url})" for attachment in large)
101 embed = discord.Embed(description=desc)
102 embed.set_footer(text="Attachments exceed upload size limit.")
103
104 if isinstance(destination, discord.TextChannel):
105 await destination.send(embed=embed)
106 else:
107 await destination.send(
108 embed=embed,
109 username=sub_clyde(message.author.display_name),
110 avatar_url=message.author.avatar_url
111 )
112
113 return urls
114
115
116 def sub_clyde(username: Optional[str]) -> Optional[str]:
117 """
118 Replace "e"/"E" in any "clyde" in `username` with a Cyrillic "е"/"E" and return the new string.
119
120 Discord disallows "clyde" anywhere in the username for webhooks. It will return a 400.
121 Return None only if `username` is None.
122 """
123 def replace_e(match: re.Match) -> str:
124 char = "е" if match[2] == "e" else "Е"
125 return match[1] + char
126
127 if username:
128 return re.sub(r"(clyd)(e)", replace_e, username, flags=re.I)
129 else:
130 return username # Empty string or None
131
132
133 async def send_denial(ctx: Context, reason: str) -> None:
134 """Send an embed denying the user with the given reason."""
135 embed = discord.Embed()
136 embed.colour = discord.Colour.red()
137 embed.title = random.choice(NEGATIVE_REPLIES)
138 embed.description = reason
139
140 await ctx.send(embed=embed)
141
142
143 def format_user(user: discord.abc.User) -> str:
144 """Return a string for `user` which has their mention and ID."""
145 return f"{user.mention} (`{user.id}`)"
146
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/bot/utils/messages.py b/bot/utils/messages.py
--- a/bot/utils/messages.py
+++ b/bot/utils/messages.py
@@ -34,7 +34,11 @@
if attach_emojis:
for emoji in deletion_emojis:
- await message.add_reaction(emoji)
+ try:
+ await message.add_reaction(emoji)
+ except discord.NotFound:
+ log.trace(f"Aborting wait_for_deletion: message {message.id} deleted prematurely.")
+ return
def check(reaction: discord.Reaction, user: discord.Member) -> bool:
"""Check that the deletion emoji is reacted by the appropriate user."""
|
{"golden_diff": "diff --git a/bot/utils/messages.py b/bot/utils/messages.py\n--- a/bot/utils/messages.py\n+++ b/bot/utils/messages.py\n@@ -34,7 +34,11 @@\n \n if attach_emojis:\n for emoji in deletion_emojis:\n- await message.add_reaction(emoji)\n+ try:\n+ await message.add_reaction(emoji)\n+ except discord.NotFound:\n+ log.trace(f\"Aborting wait_for_deletion: message {message.id} deleted prematurely.\")\n+ return\n \n def check(reaction: discord.Reaction, user: discord.Member) -> bool:\n \"\"\"Check that the deletion emoji is reacted by the appropriate user.\"\"\"\n", "issue": "Race condition in wait_for_deletion between a manual delete and reacting\nSentry Issue: [BOT-86](https://sentry.io/organizations/python-discord/issues/1861537034/?referrer=github_integration)\r\n\r\nThe message may be deleted before `wait_for_deletion` has a chance to add a reaction.\r\n\r\n```\r\nNotFound: 404 Not Found (error code: 10008): Unknown Message\r\n File \"bot/utils/messages.py\", line 38, in wait_for_deletion\r\n await message.add_reaction(emoji)\r\n File \"discord/message.py\", line 953, in add_reaction\r\n await self._state.http.add_reaction(self.channel.id, self.id, emoji)\r\n File \"discord/http.py\", line 243, in request\r\n raise NotFound(r, data)\r\n\r\nTask exception was never retrieved\r\nfuture: <Task finished name='Task-333258' coro=<wait_for_deletion() done, defined at /bot/bot/utils/messages.py:19> exception=NotFound('404 Not Found (error code: 10008): Unknown Message')>\r\n```\n", "before_files": [{"content": "import asyncio\nimport contextlib\nimport logging\nimport random\nimport re\nfrom io import BytesIO\nfrom typing import List, Optional, Sequence, Union\n\nimport discord\nfrom discord.errors import HTTPException\nfrom discord.ext.commands import Context\n\nfrom bot.constants import Emojis, NEGATIVE_REPLIES\n\nlog = logging.getLogger(__name__)\n\n\nasync def wait_for_deletion(\n message: discord.Message,\n user_ids: Sequence[discord.abc.Snowflake],\n client: discord.Client,\n deletion_emojis: Sequence[str] = (Emojis.trashcan,),\n timeout: float = 60 * 5,\n attach_emojis: bool = True,\n) -> None:\n \"\"\"\n Wait for up to `timeout` seconds for a reaction by any of the specified `user_ids` to delete the message.\n\n An `attach_emojis` bool may be specified to determine whether to attach the given\n `deletion_emojis` to the message in the given `context`.\n \"\"\"\n if message.guild is None:\n raise ValueError(\"Message must be sent on a guild\")\n\n if attach_emojis:\n for emoji in deletion_emojis:\n await message.add_reaction(emoji)\n\n def check(reaction: discord.Reaction, user: discord.Member) -> bool:\n \"\"\"Check that the deletion emoji is reacted by the appropriate user.\"\"\"\n return (\n reaction.message.id == message.id\n and str(reaction.emoji) in deletion_emojis\n and user.id in user_ids\n )\n\n with contextlib.suppress(asyncio.TimeoutError):\n await client.wait_for('reaction_add', check=check, timeout=timeout)\n await message.delete()\n\n\nasync def send_attachments(\n message: discord.Message,\n destination: Union[discord.TextChannel, discord.Webhook],\n link_large: bool = True\n) -> List[str]:\n \"\"\"\n Re-upload the message's attachments to the destination and return a list of their new URLs.\n\n Each attachment is sent as a separate message to more easily comply with the request/file size\n limit. If link_large is True, attachments which are too large are instead grouped into a single\n embed which links to them.\n \"\"\"\n large = []\n urls = []\n for attachment in message.attachments:\n failure_msg = (\n f\"Failed to re-upload attachment {attachment.filename} from message {message.id}\"\n )\n\n try:\n # Allow 512 bytes of leeway for the rest of the request.\n # This should avoid most files that are too large,\n # but some may get through hence the try-catch.\n if attachment.size <= destination.guild.filesize_limit - 512:\n with BytesIO() as file:\n await attachment.save(file, use_cached=True)\n attachment_file = discord.File(file, filename=attachment.filename)\n\n if isinstance(destination, discord.TextChannel):\n msg = await destination.send(file=attachment_file)\n urls.append(msg.attachments[0].url)\n else:\n await destination.send(\n file=attachment_file,\n username=sub_clyde(message.author.display_name),\n avatar_url=message.author.avatar_url\n )\n elif link_large:\n large.append(attachment)\n else:\n log.info(f\"{failure_msg} because it's too large.\")\n except HTTPException as e:\n if link_large and e.status == 413:\n large.append(attachment)\n else:\n log.warning(f\"{failure_msg} with status {e.status}.\", exc_info=e)\n\n if link_large and large:\n desc = \"\\n\".join(f\"[{attachment.filename}]({attachment.url})\" for attachment in large)\n embed = discord.Embed(description=desc)\n embed.set_footer(text=\"Attachments exceed upload size limit.\")\n\n if isinstance(destination, discord.TextChannel):\n await destination.send(embed=embed)\n else:\n await destination.send(\n embed=embed,\n username=sub_clyde(message.author.display_name),\n avatar_url=message.author.avatar_url\n )\n\n return urls\n\n\ndef sub_clyde(username: Optional[str]) -> Optional[str]:\n \"\"\"\n Replace \"e\"/\"E\" in any \"clyde\" in `username` with a Cyrillic \"\u0435\"/\"E\" and return the new string.\n\n Discord disallows \"clyde\" anywhere in the username for webhooks. It will return a 400.\n Return None only if `username` is None.\n \"\"\"\n def replace_e(match: re.Match) -> str:\n char = \"\u0435\" if match[2] == \"e\" else \"\u0415\"\n return match[1] + char\n\n if username:\n return re.sub(r\"(clyd)(e)\", replace_e, username, flags=re.I)\n else:\n return username # Empty string or None\n\n\nasync def send_denial(ctx: Context, reason: str) -> None:\n \"\"\"Send an embed denying the user with the given reason.\"\"\"\n embed = discord.Embed()\n embed.colour = discord.Colour.red()\n embed.title = random.choice(NEGATIVE_REPLIES)\n embed.description = reason\n\n await ctx.send(embed=embed)\n\n\ndef format_user(user: discord.abc.User) -> str:\n \"\"\"Return a string for `user` which has their mention and ID.\"\"\"\n return f\"{user.mention} (`{user.id}`)\"\n", "path": "bot/utils/messages.py"}], "after_files": [{"content": "import asyncio\nimport contextlib\nimport logging\nimport random\nimport re\nfrom io import BytesIO\nfrom typing import List, Optional, Sequence, Union\n\nimport discord\nfrom discord.errors import HTTPException\nfrom discord.ext.commands import Context\n\nfrom bot.constants import Emojis, NEGATIVE_REPLIES\n\nlog = logging.getLogger(__name__)\n\n\nasync def wait_for_deletion(\n message: discord.Message,\n user_ids: Sequence[discord.abc.Snowflake],\n client: discord.Client,\n deletion_emojis: Sequence[str] = (Emojis.trashcan,),\n timeout: float = 60 * 5,\n attach_emojis: bool = True,\n) -> None:\n \"\"\"\n Wait for up to `timeout` seconds for a reaction by any of the specified `user_ids` to delete the message.\n\n An `attach_emojis` bool may be specified to determine whether to attach the given\n `deletion_emojis` to the message in the given `context`.\n \"\"\"\n if message.guild is None:\n raise ValueError(\"Message must be sent on a guild\")\n\n if attach_emojis:\n for emoji in deletion_emojis:\n try:\n await message.add_reaction(emoji)\n except discord.NotFound:\n log.trace(f\"Aborting wait_for_deletion: message {message.id} deleted prematurely.\")\n return\n\n def check(reaction: discord.Reaction, user: discord.Member) -> bool:\n \"\"\"Check that the deletion emoji is reacted by the appropriate user.\"\"\"\n return (\n reaction.message.id == message.id\n and str(reaction.emoji) in deletion_emojis\n and user.id in user_ids\n )\n\n with contextlib.suppress(asyncio.TimeoutError):\n await client.wait_for('reaction_add', check=check, timeout=timeout)\n await message.delete()\n\n\nasync def send_attachments(\n message: discord.Message,\n destination: Union[discord.TextChannel, discord.Webhook],\n link_large: bool = True\n) -> List[str]:\n \"\"\"\n Re-upload the message's attachments to the destination and return a list of their new URLs.\n\n Each attachment is sent as a separate message to more easily comply with the request/file size\n limit. If link_large is True, attachments which are too large are instead grouped into a single\n embed which links to them.\n \"\"\"\n large = []\n urls = []\n for attachment in message.attachments:\n failure_msg = (\n f\"Failed to re-upload attachment {attachment.filename} from message {message.id}\"\n )\n\n try:\n # Allow 512 bytes of leeway for the rest of the request.\n # This should avoid most files that are too large,\n # but some may get through hence the try-catch.\n if attachment.size <= destination.guild.filesize_limit - 512:\n with BytesIO() as file:\n await attachment.save(file, use_cached=True)\n attachment_file = discord.File(file, filename=attachment.filename)\n\n if isinstance(destination, discord.TextChannel):\n msg = await destination.send(file=attachment_file)\n urls.append(msg.attachments[0].url)\n else:\n await destination.send(\n file=attachment_file,\n username=sub_clyde(message.author.display_name),\n avatar_url=message.author.avatar_url\n )\n elif link_large:\n large.append(attachment)\n else:\n log.info(f\"{failure_msg} because it's too large.\")\n except HTTPException as e:\n if link_large and e.status == 413:\n large.append(attachment)\n else:\n log.warning(f\"{failure_msg} with status {e.status}.\", exc_info=e)\n\n if link_large and large:\n desc = \"\\n\".join(f\"[{attachment.filename}]({attachment.url})\" for attachment in large)\n embed = discord.Embed(description=desc)\n embed.set_footer(text=\"Attachments exceed upload size limit.\")\n\n if isinstance(destination, discord.TextChannel):\n await destination.send(embed=embed)\n else:\n await destination.send(\n embed=embed,\n username=sub_clyde(message.author.display_name),\n avatar_url=message.author.avatar_url\n )\n\n return urls\n\n\ndef sub_clyde(username: Optional[str]) -> Optional[str]:\n \"\"\"\n Replace \"e\"/\"E\" in any \"clyde\" in `username` with a Cyrillic \"\u0435\"/\"E\" and return the new string.\n\n Discord disallows \"clyde\" anywhere in the username for webhooks. It will return a 400.\n Return None only if `username` is None.\n \"\"\"\n def replace_e(match: re.Match) -> str:\n char = \"\u0435\" if match[2] == \"e\" else \"\u0415\"\n return match[1] + char\n\n if username:\n return re.sub(r\"(clyd)(e)\", replace_e, username, flags=re.I)\n else:\n return username # Empty string or None\n\n\nasync def send_denial(ctx: Context, reason: str) -> None:\n \"\"\"Send an embed denying the user with the given reason.\"\"\"\n embed = discord.Embed()\n embed.colour = discord.Colour.red()\n embed.title = random.choice(NEGATIVE_REPLIES)\n embed.description = reason\n\n await ctx.send(embed=embed)\n\n\ndef format_user(user: discord.abc.User) -> str:\n \"\"\"Return a string for `user` which has their mention and ID.\"\"\"\n return f\"{user.mention} (`{user.id}`)\"\n", "path": "bot/utils/messages.py"}]}
| 1,989 | 147 |
gh_patches_debug_7832
|
rasdani/github-patches
|
git_diff
|
Mailu__Mailu-1974
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
DEFER_ON_TLS_ERROR in mailu.env doesn't appear to be applied.
Thank you for opening an issue with Mailu. Please understand that issues are meant for bugs and enhancement-requests.
For **user-support questions**, reach out to us on [matrix](https://matrix.to/#/#mailu:tedomum.net).
To be able to help you best, we need some more information.
## Before you open your issue
- [X] Check if no issue or pull-request for this already exists.
- [X] Check [documentation](https://mailu.io/master/) and [FAQ](https://mailu.io/master/faq.html). (Tip, use the search function on the documentation page)
- [X] You understand `Mailu` is made by volunteers in their **free time** — be conscise, civil and accept that delays can occur.
- [X] The title of the issue should be short and simple. It should contain specific terms related to the actual issue. Be specific while writing the title.
## Environment & Versions
### Environment
- [X] docker-compose
- [ ] kubernetes
- [ ] docker swarm
### Versions
master (d464187)
## Description
DEFER_ON_TLS_ERROR in mailu.env doesn't appear to be applied. I've set this environment variable to "false" and my emails still appear to be deferred according to the SMTP container.
`(status=deferred (client TLS configuration problem))`
I've set this to "false" because MTA-STS isn't as widely deployed as one would hope, and I don't want my emails blackholed and deferred until my destination's policy is published (which may be never)...
## Replication Steps
In mailu.env - set `DEFER_ON_TLS_ERROR=false`, reload containers, then try sending an email to a domain without an MTA-STS policy...
Then output logs for the SMTP container and note the message deferral.
## Expected behaviour
I expect the email to continue being sent despite the MTA-STS error.
## Logs
```
smtp_1 | Sep 09 13:42:08 mail postfix/cleanup[416]: 85B6147DDA: message-id=<[email protected]>
smtp_1 | Sep 09 13:42:09 mail postfix/qmgr[391]: 85B6147DDA: from=<[email protected]>, size=6074, nrcpt=1 (queue active)
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: connect to /tmp/mta-sts.socket: No such file or directory
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: table socketmap:unix:/tmp/mta-sts.socket:postfix lookup error: No such file or directory
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: socketmap:unix:/tmp/mta-sts.socket:postfix lookup error for "ssl-tools.net"
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: smtp_tls_policy_maps, next-hop destination "ssl-tools.net": policy table lookup error
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: TLS policy lookup for ssl-tools.net/ssl-tools.net: client TLS configuration problem
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: TLS policy lookup for ssl-tools.net/ssl-tools.net: client TLS configuration problem
smtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: 85B6147DDA: to=<[email protected]>, relay=none, delay=1.1, delays=1/0.03/0.01/0, dsn=4.7.5, status=deferred (client TLS configuration problem)
```
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `core/postfix/start.py`
Content:
```
1 #!/usr/bin/python3
2
3 import os
4 import glob
5 import shutil
6 import multiprocessing
7 import logging as log
8 import sys
9
10 from podop import run_server
11 from pwd import getpwnam
12 from socrate import system, conf
13
14 log.basicConfig(stream=sys.stderr, level=os.environ.get("LOG_LEVEL", "WARNING"))
15
16 def start_podop():
17 os.setuid(getpwnam('postfix').pw_uid)
18 os.mkdir('/dev/shm/postfix',mode=0o700)
19 url = "http://" + os.environ["ADMIN_ADDRESS"] + "/internal/postfix/"
20 # TODO: Remove verbosity setting from Podop?
21 run_server(0, "postfix", "/tmp/podop.socket", [
22 ("transport", "url", url + "transport/§"),
23 ("alias", "url", url + "alias/§"),
24 ("dane", "url", url + "dane/§"),
25 ("domain", "url", url + "domain/§"),
26 ("mailbox", "url", url + "mailbox/§"),
27 ("recipientmap", "url", url + "recipient/map/§"),
28 ("sendermap", "url", url + "sender/map/§"),
29 ("senderaccess", "url", url + "sender/access/§"),
30 ("senderlogin", "url", url + "sender/login/§"),
31 ("senderrate", "url", url + "sender/rate/§")
32 ])
33
34 def start_mta_sts_daemon():
35 os.chmod("/root/", 0o755) # read access to /root/.netrc required
36 os.setuid(getpwnam('postfix').pw_uid)
37 from postfix_mta_sts_resolver import daemon
38 daemon.main()
39
40 def is_valid_postconf_line(line):
41 return not line.startswith("#") \
42 and not line == ''
43
44 # Actual startup script
45 os.environ["FRONT_ADDRESS"] = system.get_host_address_from_environment("FRONT", "front")
46 os.environ["ADMIN_ADDRESS"] = system.get_host_address_from_environment("ADMIN", "admin")
47 os.environ["ANTISPAM_MILTER_ADDRESS"] = system.get_host_address_from_environment("ANTISPAM_MILTER", "antispam:11332")
48 os.environ["LMTP_ADDRESS"] = system.get_host_address_from_environment("LMTP", "imap:2525")
49 os.environ["OUTCLEAN"] = os.environ["HOSTNAMES"].split(",")[0]
50 try:
51 _to_lookup = os.environ["OUTCLEAN"]
52 # Ensure we lookup a FQDN: @see #1884
53 if not _to_lookup.endswith('.'):
54 _to_lookup += '.'
55 os.environ["OUTCLEAN_ADDRESS"] = system.resolve_hostname(_to_lookup)
56 except:
57 os.environ["OUTCLEAN_ADDRESS"] = "10.10.10.10"
58
59 for postfix_file in glob.glob("/conf/*.cf"):
60 conf.jinja(postfix_file, os.environ, os.path.join("/etc/postfix", os.path.basename(postfix_file)))
61
62 if os.path.exists("/overrides/postfix.cf"):
63 for line in open("/overrides/postfix.cf").read().strip().split("\n"):
64 if is_valid_postconf_line(line):
65 os.system('postconf -e "{}"'.format(line))
66
67 if os.path.exists("/overrides/postfix.master"):
68 for line in open("/overrides/postfix.master").read().strip().split("\n"):
69 if is_valid_postconf_line(line):
70 os.system('postconf -Me "{}"'.format(line))
71
72 for map_file in glob.glob("/overrides/*.map"):
73 destination = os.path.join("/etc/postfix", os.path.basename(map_file))
74 shutil.copyfile(map_file, destination)
75 os.system("postmap {}".format(destination))
76 os.remove(destination)
77
78 if os.path.exists("/overrides/mta-sts-daemon.yml"):
79 shutil.copyfile("/overrides/mta-sts-daemon.yml", "/etc/mta-sts-daemon.yml")
80 conf.jinja("/etc/mta-sts-daemon.yml", os.environ, "/etc/mta-sts-daemon.yml")
81
82 if not os.path.exists("/etc/postfix/tls_policy.map.lmdb"):
83 open("/etc/postfix/tls_policy.map", "a").close()
84 os.system("postmap /etc/postfix/tls_policy.map")
85
86 if "RELAYUSER" in os.environ:
87 path = "/etc/postfix/sasl_passwd"
88 conf.jinja("/conf/sasl_passwd", os.environ, path)
89 os.system("postmap {}".format(path))
90
91 # Run Podop and Postfix
92 multiprocessing.Process(target=start_podop).start()
93 multiprocessing.Process(target=start_mta_sts_daemon).start()
94 os.system("/usr/libexec/postfix/post-install meta_directory=/etc/postfix create-missing")
95 # Before starting postfix, we need to check permissions on /queue
96 # in the event that postfix,postdrop id have changed
97 os.system("postfix set-permissions")
98 os.system("postfix start-fg")
99
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/core/postfix/start.py b/core/postfix/start.py
--- a/core/postfix/start.py
+++ b/core/postfix/start.py
@@ -77,7 +77,8 @@
if os.path.exists("/overrides/mta-sts-daemon.yml"):
shutil.copyfile("/overrides/mta-sts-daemon.yml", "/etc/mta-sts-daemon.yml")
-conf.jinja("/etc/mta-sts-daemon.yml", os.environ, "/etc/mta-sts-daemon.yml")
+else:
+ conf.jinja("/conf/mta-sts-daemon.yml", os.environ, "/etc/mta-sts-daemon.yml")
if not os.path.exists("/etc/postfix/tls_policy.map.lmdb"):
open("/etc/postfix/tls_policy.map", "a").close()
|
{"golden_diff": "diff --git a/core/postfix/start.py b/core/postfix/start.py\n--- a/core/postfix/start.py\n+++ b/core/postfix/start.py\n@@ -77,7 +77,8 @@\n \n if os.path.exists(\"/overrides/mta-sts-daemon.yml\"):\n shutil.copyfile(\"/overrides/mta-sts-daemon.yml\", \"/etc/mta-sts-daemon.yml\")\n-conf.jinja(\"/etc/mta-sts-daemon.yml\", os.environ, \"/etc/mta-sts-daemon.yml\")\n+else:\n+ conf.jinja(\"/conf/mta-sts-daemon.yml\", os.environ, \"/etc/mta-sts-daemon.yml\")\n \n if not os.path.exists(\"/etc/postfix/tls_policy.map.lmdb\"):\n open(\"/etc/postfix/tls_policy.map\", \"a\").close()\n", "issue": "DEFER_ON_TLS_ERROR in mailu.env doesn't appear to be applied.\nThank you for opening an issue with Mailu. Please understand that issues are meant for bugs and enhancement-requests.\r\nFor **user-support questions**, reach out to us on [matrix](https://matrix.to/#/#mailu:tedomum.net).\r\n\r\nTo be able to help you best, we need some more information.\r\n\r\n## Before you open your issue\r\n- [X] Check if no issue or pull-request for this already exists.\r\n- [X] Check [documentation](https://mailu.io/master/) and [FAQ](https://mailu.io/master/faq.html). (Tip, use the search function on the documentation page)\r\n- [X] You understand `Mailu` is made by volunteers in their **free time** \u2014 be conscise, civil and accept that delays can occur.\r\n- [X] The title of the issue should be short and simple. It should contain specific terms related to the actual issue. Be specific while writing the title.\r\n\r\n## Environment & Versions\r\n### Environment\r\n - [X] docker-compose\r\n - [ ] kubernetes\r\n - [ ] docker swarm\r\n\r\n### Versions\r\nmaster (d464187)\r\n\r\n## Description\r\nDEFER_ON_TLS_ERROR in mailu.env doesn't appear to be applied. I've set this environment variable to \"false\" and my emails still appear to be deferred according to the SMTP container. \r\n`(status=deferred (client TLS configuration problem))`\r\n\r\nI've set this to \"false\" because MTA-STS isn't as widely deployed as one would hope, and I don't want my emails blackholed and deferred until my destination's policy is published (which may be never)... \r\n\r\n## Replication Steps\r\nIn mailu.env - set `DEFER_ON_TLS_ERROR=false`, reload containers, then try sending an email to a domain without an MTA-STS policy...\r\n\r\nThen output logs for the SMTP container and note the message deferral.\r\n\r\n## Expected behaviour\r\nI expect the email to continue being sent despite the MTA-STS error.\r\n\r\n## Logs\r\n```\r\nsmtp_1 | Sep 09 13:42:08 mail postfix/cleanup[416]: 85B6147DDA: message-id=<[email protected]>\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/qmgr[391]: 85B6147DDA: from=<[email protected]>, size=6074, nrcpt=1 (queue active)\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: connect to /tmp/mta-sts.socket: No such file or directory\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: table socketmap:unix:/tmp/mta-sts.socket:postfix lookup error: No such file or directory\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: socketmap:unix:/tmp/mta-sts.socket:postfix lookup error for \"ssl-tools.net\"\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: smtp_tls_policy_maps, next-hop destination \"ssl-tools.net\": policy table lookup error\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: TLS policy lookup for ssl-tools.net/ssl-tools.net: client TLS configuration problem\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: warning: TLS policy lookup for ssl-tools.net/ssl-tools.net: client TLS configuration problem\r\nsmtp_1 | Sep 09 13:42:09 mail postfix/smtp[417]: 85B6147DDA: to=<[email protected]>, relay=none, delay=1.1, delays=1/0.03/0.01/0, dsn=4.7.5, status=deferred (client TLS configuration problem)\r\n```\r\n\n", "before_files": [{"content": "#!/usr/bin/python3\n\nimport os\nimport glob\nimport shutil\nimport multiprocessing\nimport logging as log\nimport sys\n\nfrom podop import run_server\nfrom pwd import getpwnam\nfrom socrate import system, conf\n\nlog.basicConfig(stream=sys.stderr, level=os.environ.get(\"LOG_LEVEL\", \"WARNING\"))\n\ndef start_podop():\n os.setuid(getpwnam('postfix').pw_uid)\n os.mkdir('/dev/shm/postfix',mode=0o700)\n url = \"http://\" + os.environ[\"ADMIN_ADDRESS\"] + \"/internal/postfix/\"\n # TODO: Remove verbosity setting from Podop?\n run_server(0, \"postfix\", \"/tmp/podop.socket\", [\n (\"transport\", \"url\", url + \"transport/\u00a7\"),\n (\"alias\", \"url\", url + \"alias/\u00a7\"),\n (\"dane\", \"url\", url + \"dane/\u00a7\"),\n (\"domain\", \"url\", url + \"domain/\u00a7\"),\n (\"mailbox\", \"url\", url + \"mailbox/\u00a7\"),\n (\"recipientmap\", \"url\", url + \"recipient/map/\u00a7\"),\n (\"sendermap\", \"url\", url + \"sender/map/\u00a7\"),\n (\"senderaccess\", \"url\", url + \"sender/access/\u00a7\"),\n (\"senderlogin\", \"url\", url + \"sender/login/\u00a7\"),\n (\"senderrate\", \"url\", url + \"sender/rate/\u00a7\")\n ])\n\ndef start_mta_sts_daemon():\n os.chmod(\"/root/\", 0o755) # read access to /root/.netrc required\n os.setuid(getpwnam('postfix').pw_uid)\n from postfix_mta_sts_resolver import daemon\n daemon.main()\n\ndef is_valid_postconf_line(line):\n return not line.startswith(\"#\") \\\n and not line == ''\n\n# Actual startup script\nos.environ[\"FRONT_ADDRESS\"] = system.get_host_address_from_environment(\"FRONT\", \"front\")\nos.environ[\"ADMIN_ADDRESS\"] = system.get_host_address_from_environment(\"ADMIN\", \"admin\")\nos.environ[\"ANTISPAM_MILTER_ADDRESS\"] = system.get_host_address_from_environment(\"ANTISPAM_MILTER\", \"antispam:11332\")\nos.environ[\"LMTP_ADDRESS\"] = system.get_host_address_from_environment(\"LMTP\", \"imap:2525\")\nos.environ[\"OUTCLEAN\"] = os.environ[\"HOSTNAMES\"].split(\",\")[0]\ntry:\n _to_lookup = os.environ[\"OUTCLEAN\"]\n # Ensure we lookup a FQDN: @see #1884\n if not _to_lookup.endswith('.'):\n _to_lookup += '.'\n os.environ[\"OUTCLEAN_ADDRESS\"] = system.resolve_hostname(_to_lookup)\nexcept:\n os.environ[\"OUTCLEAN_ADDRESS\"] = \"10.10.10.10\"\n\nfor postfix_file in glob.glob(\"/conf/*.cf\"):\n conf.jinja(postfix_file, os.environ, os.path.join(\"/etc/postfix\", os.path.basename(postfix_file)))\n\nif os.path.exists(\"/overrides/postfix.cf\"):\n for line in open(\"/overrides/postfix.cf\").read().strip().split(\"\\n\"):\n if is_valid_postconf_line(line):\n os.system('postconf -e \"{}\"'.format(line))\n\nif os.path.exists(\"/overrides/postfix.master\"):\n for line in open(\"/overrides/postfix.master\").read().strip().split(\"\\n\"):\n if is_valid_postconf_line(line):\n os.system('postconf -Me \"{}\"'.format(line))\n\nfor map_file in glob.glob(\"/overrides/*.map\"):\n destination = os.path.join(\"/etc/postfix\", os.path.basename(map_file))\n shutil.copyfile(map_file, destination)\n os.system(\"postmap {}\".format(destination))\n os.remove(destination)\n\nif os.path.exists(\"/overrides/mta-sts-daemon.yml\"):\n shutil.copyfile(\"/overrides/mta-sts-daemon.yml\", \"/etc/mta-sts-daemon.yml\")\nconf.jinja(\"/etc/mta-sts-daemon.yml\", os.environ, \"/etc/mta-sts-daemon.yml\")\n\nif not os.path.exists(\"/etc/postfix/tls_policy.map.lmdb\"):\n open(\"/etc/postfix/tls_policy.map\", \"a\").close()\n os.system(\"postmap /etc/postfix/tls_policy.map\")\n\nif \"RELAYUSER\" in os.environ:\n path = \"/etc/postfix/sasl_passwd\"\n conf.jinja(\"/conf/sasl_passwd\", os.environ, path)\n os.system(\"postmap {}\".format(path))\n\n# Run Podop and Postfix\nmultiprocessing.Process(target=start_podop).start()\nmultiprocessing.Process(target=start_mta_sts_daemon).start()\nos.system(\"/usr/libexec/postfix/post-install meta_directory=/etc/postfix create-missing\")\n# Before starting postfix, we need to check permissions on /queue\n# in the event that postfix,postdrop id have changed\nos.system(\"postfix set-permissions\")\nos.system(\"postfix start-fg\")\n", "path": "core/postfix/start.py"}], "after_files": [{"content": "#!/usr/bin/python3\n\nimport os\nimport glob\nimport shutil\nimport multiprocessing\nimport logging as log\nimport sys\n\nfrom podop import run_server\nfrom pwd import getpwnam\nfrom socrate import system, conf\n\nlog.basicConfig(stream=sys.stderr, level=os.environ.get(\"LOG_LEVEL\", \"WARNING\"))\n\ndef start_podop():\n os.setuid(getpwnam('postfix').pw_uid)\n os.mkdir('/dev/shm/postfix',mode=0o700)\n url = \"http://\" + os.environ[\"ADMIN_ADDRESS\"] + \"/internal/postfix/\"\n # TODO: Remove verbosity setting from Podop?\n run_server(0, \"postfix\", \"/tmp/podop.socket\", [\n (\"transport\", \"url\", url + \"transport/\u00a7\"),\n (\"alias\", \"url\", url + \"alias/\u00a7\"),\n (\"dane\", \"url\", url + \"dane/\u00a7\"),\n (\"domain\", \"url\", url + \"domain/\u00a7\"),\n (\"mailbox\", \"url\", url + \"mailbox/\u00a7\"),\n (\"recipientmap\", \"url\", url + \"recipient/map/\u00a7\"),\n (\"sendermap\", \"url\", url + \"sender/map/\u00a7\"),\n (\"senderaccess\", \"url\", url + \"sender/access/\u00a7\"),\n (\"senderlogin\", \"url\", url + \"sender/login/\u00a7\"),\n (\"senderrate\", \"url\", url + \"sender/rate/\u00a7\")\n ])\n\ndef start_mta_sts_daemon():\n os.chmod(\"/root/\", 0o755) # read access to /root/.netrc required\n os.setuid(getpwnam('postfix').pw_uid)\n from postfix_mta_sts_resolver import daemon\n daemon.main()\n\ndef is_valid_postconf_line(line):\n return not line.startswith(\"#\") \\\n and not line == ''\n\n# Actual startup script\nos.environ[\"FRONT_ADDRESS\"] = system.get_host_address_from_environment(\"FRONT\", \"front\")\nos.environ[\"ADMIN_ADDRESS\"] = system.get_host_address_from_environment(\"ADMIN\", \"admin\")\nos.environ[\"ANTISPAM_MILTER_ADDRESS\"] = system.get_host_address_from_environment(\"ANTISPAM_MILTER\", \"antispam:11332\")\nos.environ[\"LMTP_ADDRESS\"] = system.get_host_address_from_environment(\"LMTP\", \"imap:2525\")\nos.environ[\"OUTCLEAN\"] = os.environ[\"HOSTNAMES\"].split(\",\")[0]\ntry:\n _to_lookup = os.environ[\"OUTCLEAN\"]\n # Ensure we lookup a FQDN: @see #1884\n if not _to_lookup.endswith('.'):\n _to_lookup += '.'\n os.environ[\"OUTCLEAN_ADDRESS\"] = system.resolve_hostname(_to_lookup)\nexcept:\n os.environ[\"OUTCLEAN_ADDRESS\"] = \"10.10.10.10\"\n\nfor postfix_file in glob.glob(\"/conf/*.cf\"):\n conf.jinja(postfix_file, os.environ, os.path.join(\"/etc/postfix\", os.path.basename(postfix_file)))\n\nif os.path.exists(\"/overrides/postfix.cf\"):\n for line in open(\"/overrides/postfix.cf\").read().strip().split(\"\\n\"):\n if is_valid_postconf_line(line):\n os.system('postconf -e \"{}\"'.format(line))\n\nif os.path.exists(\"/overrides/postfix.master\"):\n for line in open(\"/overrides/postfix.master\").read().strip().split(\"\\n\"):\n if is_valid_postconf_line(line):\n os.system('postconf -Me \"{}\"'.format(line))\n\nfor map_file in glob.glob(\"/overrides/*.map\"):\n destination = os.path.join(\"/etc/postfix\", os.path.basename(map_file))\n shutil.copyfile(map_file, destination)\n os.system(\"postmap {}\".format(destination))\n os.remove(destination)\n\nif os.path.exists(\"/overrides/mta-sts-daemon.yml\"):\n shutil.copyfile(\"/overrides/mta-sts-daemon.yml\", \"/etc/mta-sts-daemon.yml\")\nelse:\n conf.jinja(\"/conf/mta-sts-daemon.yml\", os.environ, \"/etc/mta-sts-daemon.yml\")\n\nif not os.path.exists(\"/etc/postfix/tls_policy.map.lmdb\"):\n open(\"/etc/postfix/tls_policy.map\", \"a\").close()\n os.system(\"postmap /etc/postfix/tls_policy.map\")\n\nif \"RELAYUSER\" in os.environ:\n path = \"/etc/postfix/sasl_passwd\"\n conf.jinja(\"/conf/sasl_passwd\", os.environ, path)\n os.system(\"postmap {}\".format(path))\n\n# Run Podop and Postfix\nmultiprocessing.Process(target=start_podop).start()\nmultiprocessing.Process(target=start_mta_sts_daemon).start()\nos.system(\"/usr/libexec/postfix/post-install meta_directory=/etc/postfix create-missing\")\n# Before starting postfix, we need to check permissions on /queue\n# in the event that postfix,postdrop id have changed\nos.system(\"postfix set-permissions\")\nos.system(\"postfix start-fg\")\n", "path": "core/postfix/start.py"}]}
| 2,494 | 180 |
gh_patches_debug_23666
|
rasdani/github-patches
|
git_diff
|
pypi__warehouse-7927
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Support for properly displaying the site translated to RTL languages
**What's the problem this feature will solve?**
Display PyPI.org propely when translated to RTL languages such as Arabic, Farsi and Hebrew.
**Describe the solution you'd like**
I can't suggest a specific technical solution, since I'm not familiar with the website's design and implementation.
**Additional context**
The context is the recent work on translation into additional languages.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `warehouse/i18n/__init__.py`
Content:
```
1 # Licensed under the Apache License, Version 2.0 (the "License");
2 # you may not use this file except in compliance with the License.
3 # You may obtain a copy of the License at
4 #
5 # http://www.apache.org/licenses/LICENSE-2.0
6 #
7 # Unless required by applicable law or agreed to in writing, software
8 # distributed under the License is distributed on an "AS IS" BASIS,
9 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10 # See the License for the specific language governing permissions and
11 # limitations under the License.
12
13 import functools
14
15 from babel.core import Locale
16 from pyramid import viewderivers
17 from pyramid.i18n import TranslationStringFactory, default_locale_negotiator
18 from pyramid.threadlocal import get_current_request
19
20 from warehouse.cache.http import add_vary
21
22 # Taken from:
23 # https://github.com/django/django/blob/master/django/conf/locale/__init__.py
24 KNOWN_LOCALES = {
25 "en": "English", # English
26 "es": "español", # Spanish
27 "fr": "français", # French
28 "ja": "日本語", # Japanese
29 "pt_BR": "Português Brasileiro", # Brazilian Portugeuse
30 "uk": "Українська", # Ukrainian
31 "el": "Ελληνικά", # Greek
32 "de": "Deutsch", # German
33 "zh_Hans": "简体中文", # Simplified Chinese
34 "ru": "Русский", # Russian
35 }
36
37 LOCALE_ATTR = "_LOCALE_"
38
39 _translation_factory = TranslationStringFactory("messages")
40
41
42 class LazyString:
43 def __init__(self, fn, *args, **kwargs):
44 self.fn = fn
45 self.args = args
46 self.mapping = kwargs.get("mapping", {})
47 self.kwargs = kwargs
48
49 def __json__(self, request):
50 return str(self)
51
52 def __mod__(self, new_mapping):
53 mapping = self.mapping.copy()
54 mapping.update(new_mapping)
55 return LazyString(self.fn, *self.args, mapping=new_mapping, **self.kwargs)
56
57 def __str__(self):
58 return self.fn(*self.args, **self.kwargs)
59
60
61 def _locale(request):
62 """
63 Computes a babel.core:Locale() object for this request.
64 """
65 return Locale.parse(request.locale_name, sep="_")
66
67
68 def _negotiate_locale(request):
69 locale_name = getattr(request, LOCALE_ATTR, None)
70 if locale_name is not None:
71 return locale_name
72
73 locale_name = request.params.get(LOCALE_ATTR)
74 if locale_name is not None:
75 return locale_name
76
77 locale_name = request.cookies.get(LOCALE_ATTR)
78 if locale_name is not None:
79 return locale_name
80
81 if not request.accept_language:
82 return default_locale_negotiator(request)
83
84 return request.accept_language.best_match(
85 tuple(KNOWN_LOCALES.keys()), default_match=default_locale_negotiator(request)
86 )
87
88
89 def _localize(request, message, **kwargs):
90 """
91 To be used on the request directly, e.g. `request._(message)`
92 """
93 return request.localizer.translate(_translation_factory(message, **kwargs))
94
95
96 def localize(message, **kwargs):
97 """
98 To be used when we don't have the request context, e.g.
99 `from warehouse.i18n import localize as _`
100 """
101
102 def _lazy_localize(message, **kwargs):
103 request = get_current_request()
104 return _localize(request, message, **kwargs)
105
106 return LazyString(_lazy_localize, message, **kwargs)
107
108
109 class InvalidLocalizer:
110 def _fail(self):
111 raise RuntimeError("Cannot use localizer without has_translations=True")
112
113 @property
114 def locale_name(self):
115 self._fail()
116
117 def pluralize(self, *args, **kwargs):
118 self._fail()
119
120 def translate(self, *args, **kwargs):
121 self._fail()
122
123
124 def translated_view(view, info):
125 if info.options.get("has_translations"):
126 # If this page can be translated, then we'll add a Vary: PyPI-Locale
127 # Vary header.
128 # Note: This will give weird results if hitting PyPI directly instead of through
129 # the Fastly VCL which sets PyPI-Locale.
130 return add_vary("PyPI-Locale")(view)
131 elif info.exception_only:
132 return view
133 else:
134 # If we're not using translations on this view, then we'll wrap the view
135 # with a wrapper that just ensures that the localizer cannot be used.
136 @functools.wraps(view)
137 def wrapped(context, request):
138 # This whole method is a little bit of an odd duck, we want to make
139 # sure that we don't actually *access* request.localizer, because
140 # doing so triggers the machinery to create a new localizer. So
141 # instead we will dig into the request object __dict__ to
142 # effectively do the same thing, just without triggering an access
143 # on request.localizer.
144
145 # Save the original session so that we can restore it once the
146 # inner views have been called.
147 nothing = object()
148 original_localizer = request.__dict__.get("localizer", nothing)
149
150 # This particular view hasn't been set to allow access to the
151 # translations, so we'll just assign an InvalidLocalizer to
152 # request.localizer
153 request.__dict__["localizer"] = InvalidLocalizer()
154
155 try:
156 # Invoke the real view
157 return view(context, request)
158 finally:
159 # Restore the original session so that things like
160 # pyramid_debugtoolbar can access it.
161 if original_localizer is nothing:
162 del request.__dict__["localizer"]
163 else:
164 request.__dict__["localizer"] = original_localizer
165
166 return wrapped
167
168
169 translated_view.options = {"has_translations"}
170
171
172 def includeme(config):
173 # Add the request attributes
174 config.add_request_method(_locale, name="locale", reify=True)
175 config.add_request_method(_localize, name="_")
176
177 # Register our translation directory.
178 config.add_translation_dirs("warehouse:locale/")
179
180 config.set_locale_negotiator(_negotiate_locale)
181
182 # Register our i18n/l10n filters for Jinja2
183 filters = config.get_settings().setdefault("jinja2.filters", {})
184 filters.setdefault("format_date", "warehouse.i18n.filters:format_date")
185 filters.setdefault("format_datetime", "warehouse.i18n.filters:format_datetime")
186 filters.setdefault(
187 "format_rfc822_datetime", "warehouse.i18n.filters:format_rfc822_datetime"
188 )
189 filters.setdefault("format_number", "warehouse.i18n.filters:format_number")
190
191 jglobals = config.get_settings().setdefault("jinja2.globals", {})
192 jglobals.setdefault("KNOWN_LOCALES", "warehouse.i18n:KNOWN_LOCALES")
193
194 config.add_view_deriver(
195 translated_view, over="rendered_view", under=viewderivers.INGRESS
196 )
197
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/warehouse/i18n/__init__.py b/warehouse/i18n/__init__.py
--- a/warehouse/i18n/__init__.py
+++ b/warehouse/i18n/__init__.py
@@ -19,19 +19,21 @@
from warehouse.cache.http import add_vary
-# Taken from:
-# https://github.com/django/django/blob/master/django/conf/locale/__init__.py
KNOWN_LOCALES = {
- "en": "English", # English
- "es": "español", # Spanish
- "fr": "français", # French
- "ja": "日本語", # Japanese
- "pt_BR": "Português Brasileiro", # Brazilian Portugeuse
- "uk": "Українська", # Ukrainian
- "el": "Ελληνικά", # Greek
- "de": "Deutsch", # German
- "zh_Hans": "简体中文", # Simplified Chinese
- "ru": "Русский", # Russian
+ identifier: Locale.parse(identifier, sep="_")
+ for identifier in [
+ "en", # English
+ "es", # Spanish
+ "fr", # French
+ "ja", # Japanese
+ "pt_BR", # Brazilian Portugeuse
+ "uk", # Ukranian
+ "el", # Greek
+ "de", # German
+ "zh_Hans", # Simplified Chinese
+ "ru", # Russian
+ "he", # Hebrew
+ ]
}
LOCALE_ATTR = "_LOCALE_"
@@ -60,9 +62,9 @@
def _locale(request):
"""
- Computes a babel.core:Locale() object for this request.
+ Gets a babel.core:Locale() object for this request.
"""
- return Locale.parse(request.locale_name, sep="_")
+ return KNOWN_LOCALES.get(request.locale_name, "en")
def _negotiate_locale(request):
|
{"golden_diff": "diff --git a/warehouse/i18n/__init__.py b/warehouse/i18n/__init__.py\n--- a/warehouse/i18n/__init__.py\n+++ b/warehouse/i18n/__init__.py\n@@ -19,19 +19,21 @@\n \n from warehouse.cache.http import add_vary\n \n-# Taken from:\n-# https://github.com/django/django/blob/master/django/conf/locale/__init__.py\n KNOWN_LOCALES = {\n- \"en\": \"English\", # English\n- \"es\": \"espa\u00f1ol\", # Spanish\n- \"fr\": \"fran\u00e7ais\", # French\n- \"ja\": \"\u65e5\u672c\u8a9e\", # Japanese\n- \"pt_BR\": \"Portugu\u00eas Brasileiro\", # Brazilian Portugeuse\n- \"uk\": \"\u0423\u043a\u0440\u0430\u0457\u043d\u0441\u044c\u043a\u0430\", # Ukrainian\n- \"el\": \"\u0395\u03bb\u03bb\u03b7\u03bd\u03b9\u03ba\u03ac\", # Greek\n- \"de\": \"Deutsch\", # German\n- \"zh_Hans\": \"\u7b80\u4f53\u4e2d\u6587\", # Simplified Chinese\n- \"ru\": \"\u0420\u0443\u0441\u0441\u043a\u0438\u0439\", # Russian\n+ identifier: Locale.parse(identifier, sep=\"_\")\n+ for identifier in [\n+ \"en\", # English\n+ \"es\", # Spanish\n+ \"fr\", # French\n+ \"ja\", # Japanese\n+ \"pt_BR\", # Brazilian Portugeuse\n+ \"uk\", # Ukranian\n+ \"el\", # Greek\n+ \"de\", # German\n+ \"zh_Hans\", # Simplified Chinese\n+ \"ru\", # Russian\n+ \"he\", # Hebrew\n+ ]\n }\n \n LOCALE_ATTR = \"_LOCALE_\"\n@@ -60,9 +62,9 @@\n \n def _locale(request):\n \"\"\"\n- Computes a babel.core:Locale() object for this request.\n+ Gets a babel.core:Locale() object for this request.\n \"\"\"\n- return Locale.parse(request.locale_name, sep=\"_\")\n+ return KNOWN_LOCALES.get(request.locale_name, \"en\")\n \n \n def _negotiate_locale(request):\n", "issue": "Support for properly displaying the site translated to RTL languages\n**What's the problem this feature will solve?**\r\nDisplay PyPI.org propely when translated to RTL languages such as Arabic, Farsi and Hebrew.\r\n\r\n**Describe the solution you'd like**\r\nI can't suggest a specific technical solution, since I'm not familiar with the website's design and implementation.\r\n\r\n**Additional context**\r\nThe context is the recent work on translation into additional languages.\n", "before_files": [{"content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport functools\n\nfrom babel.core import Locale\nfrom pyramid import viewderivers\nfrom pyramid.i18n import TranslationStringFactory, default_locale_negotiator\nfrom pyramid.threadlocal import get_current_request\n\nfrom warehouse.cache.http import add_vary\n\n# Taken from:\n# https://github.com/django/django/blob/master/django/conf/locale/__init__.py\nKNOWN_LOCALES = {\n \"en\": \"English\", # English\n \"es\": \"espa\u00f1ol\", # Spanish\n \"fr\": \"fran\u00e7ais\", # French\n \"ja\": \"\u65e5\u672c\u8a9e\", # Japanese\n \"pt_BR\": \"Portugu\u00eas Brasileiro\", # Brazilian Portugeuse\n \"uk\": \"\u0423\u043a\u0440\u0430\u0457\u043d\u0441\u044c\u043a\u0430\", # Ukrainian\n \"el\": \"\u0395\u03bb\u03bb\u03b7\u03bd\u03b9\u03ba\u03ac\", # Greek\n \"de\": \"Deutsch\", # German\n \"zh_Hans\": \"\u7b80\u4f53\u4e2d\u6587\", # Simplified Chinese\n \"ru\": \"\u0420\u0443\u0441\u0441\u043a\u0438\u0439\", # Russian\n}\n\nLOCALE_ATTR = \"_LOCALE_\"\n\n_translation_factory = TranslationStringFactory(\"messages\")\n\n\nclass LazyString:\n def __init__(self, fn, *args, **kwargs):\n self.fn = fn\n self.args = args\n self.mapping = kwargs.get(\"mapping\", {})\n self.kwargs = kwargs\n\n def __json__(self, request):\n return str(self)\n\n def __mod__(self, new_mapping):\n mapping = self.mapping.copy()\n mapping.update(new_mapping)\n return LazyString(self.fn, *self.args, mapping=new_mapping, **self.kwargs)\n\n def __str__(self):\n return self.fn(*self.args, **self.kwargs)\n\n\ndef _locale(request):\n \"\"\"\n Computes a babel.core:Locale() object for this request.\n \"\"\"\n return Locale.parse(request.locale_name, sep=\"_\")\n\n\ndef _negotiate_locale(request):\n locale_name = getattr(request, LOCALE_ATTR, None)\n if locale_name is not None:\n return locale_name\n\n locale_name = request.params.get(LOCALE_ATTR)\n if locale_name is not None:\n return locale_name\n\n locale_name = request.cookies.get(LOCALE_ATTR)\n if locale_name is not None:\n return locale_name\n\n if not request.accept_language:\n return default_locale_negotiator(request)\n\n return request.accept_language.best_match(\n tuple(KNOWN_LOCALES.keys()), default_match=default_locale_negotiator(request)\n )\n\n\ndef _localize(request, message, **kwargs):\n \"\"\"\n To be used on the request directly, e.g. `request._(message)`\n \"\"\"\n return request.localizer.translate(_translation_factory(message, **kwargs))\n\n\ndef localize(message, **kwargs):\n \"\"\"\n To be used when we don't have the request context, e.g.\n `from warehouse.i18n import localize as _`\n \"\"\"\n\n def _lazy_localize(message, **kwargs):\n request = get_current_request()\n return _localize(request, message, **kwargs)\n\n return LazyString(_lazy_localize, message, **kwargs)\n\n\nclass InvalidLocalizer:\n def _fail(self):\n raise RuntimeError(\"Cannot use localizer without has_translations=True\")\n\n @property\n def locale_name(self):\n self._fail()\n\n def pluralize(self, *args, **kwargs):\n self._fail()\n\n def translate(self, *args, **kwargs):\n self._fail()\n\n\ndef translated_view(view, info):\n if info.options.get(\"has_translations\"):\n # If this page can be translated, then we'll add a Vary: PyPI-Locale\n # Vary header.\n # Note: This will give weird results if hitting PyPI directly instead of through\n # the Fastly VCL which sets PyPI-Locale.\n return add_vary(\"PyPI-Locale\")(view)\n elif info.exception_only:\n return view\n else:\n # If we're not using translations on this view, then we'll wrap the view\n # with a wrapper that just ensures that the localizer cannot be used.\n @functools.wraps(view)\n def wrapped(context, request):\n # This whole method is a little bit of an odd duck, we want to make\n # sure that we don't actually *access* request.localizer, because\n # doing so triggers the machinery to create a new localizer. So\n # instead we will dig into the request object __dict__ to\n # effectively do the same thing, just without triggering an access\n # on request.localizer.\n\n # Save the original session so that we can restore it once the\n # inner views have been called.\n nothing = object()\n original_localizer = request.__dict__.get(\"localizer\", nothing)\n\n # This particular view hasn't been set to allow access to the\n # translations, so we'll just assign an InvalidLocalizer to\n # request.localizer\n request.__dict__[\"localizer\"] = InvalidLocalizer()\n\n try:\n # Invoke the real view\n return view(context, request)\n finally:\n # Restore the original session so that things like\n # pyramid_debugtoolbar can access it.\n if original_localizer is nothing:\n del request.__dict__[\"localizer\"]\n else:\n request.__dict__[\"localizer\"] = original_localizer\n\n return wrapped\n\n\ntranslated_view.options = {\"has_translations\"}\n\n\ndef includeme(config):\n # Add the request attributes\n config.add_request_method(_locale, name=\"locale\", reify=True)\n config.add_request_method(_localize, name=\"_\")\n\n # Register our translation directory.\n config.add_translation_dirs(\"warehouse:locale/\")\n\n config.set_locale_negotiator(_negotiate_locale)\n\n # Register our i18n/l10n filters for Jinja2\n filters = config.get_settings().setdefault(\"jinja2.filters\", {})\n filters.setdefault(\"format_date\", \"warehouse.i18n.filters:format_date\")\n filters.setdefault(\"format_datetime\", \"warehouse.i18n.filters:format_datetime\")\n filters.setdefault(\n \"format_rfc822_datetime\", \"warehouse.i18n.filters:format_rfc822_datetime\"\n )\n filters.setdefault(\"format_number\", \"warehouse.i18n.filters:format_number\")\n\n jglobals = config.get_settings().setdefault(\"jinja2.globals\", {})\n jglobals.setdefault(\"KNOWN_LOCALES\", \"warehouse.i18n:KNOWN_LOCALES\")\n\n config.add_view_deriver(\n translated_view, over=\"rendered_view\", under=viewderivers.INGRESS\n )\n", "path": "warehouse/i18n/__init__.py"}], "after_files": [{"content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport functools\n\nfrom babel.core import Locale\nfrom pyramid import viewderivers\nfrom pyramid.i18n import TranslationStringFactory, default_locale_negotiator\nfrom pyramid.threadlocal import get_current_request\n\nfrom warehouse.cache.http import add_vary\n\nKNOWN_LOCALES = {\n identifier: Locale.parse(identifier, sep=\"_\")\n for identifier in [\n \"en\", # English\n \"es\", # Spanish\n \"fr\", # French\n \"ja\", # Japanese\n \"pt_BR\", # Brazilian Portugeuse\n \"uk\", # Ukranian\n \"el\", # Greek\n \"de\", # German\n \"zh_Hans\", # Simplified Chinese\n \"ru\", # Russian\n \"he\", # Hebrew\n ]\n}\n\nLOCALE_ATTR = \"_LOCALE_\"\n\n_translation_factory = TranslationStringFactory(\"messages\")\n\n\nclass LazyString:\n def __init__(self, fn, *args, **kwargs):\n self.fn = fn\n self.args = args\n self.mapping = kwargs.get(\"mapping\", {})\n self.kwargs = kwargs\n\n def __json__(self, request):\n return str(self)\n\n def __mod__(self, new_mapping):\n mapping = self.mapping.copy()\n mapping.update(new_mapping)\n return LazyString(self.fn, *self.args, mapping=new_mapping, **self.kwargs)\n\n def __str__(self):\n return self.fn(*self.args, **self.kwargs)\n\n\ndef _locale(request):\n \"\"\"\n Gets a babel.core:Locale() object for this request.\n \"\"\"\n return KNOWN_LOCALES.get(request.locale_name, \"en\")\n\n\ndef _negotiate_locale(request):\n locale_name = getattr(request, LOCALE_ATTR, None)\n if locale_name is not None:\n return locale_name\n\n locale_name = request.params.get(LOCALE_ATTR)\n if locale_name is not None:\n return locale_name\n\n locale_name = request.cookies.get(LOCALE_ATTR)\n if locale_name is not None:\n return locale_name\n\n if not request.accept_language:\n return default_locale_negotiator(request)\n\n return request.accept_language.best_match(\n tuple(KNOWN_LOCALES.keys()), default_match=default_locale_negotiator(request)\n )\n\n\ndef _localize(request, message, **kwargs):\n \"\"\"\n To be used on the request directly, e.g. `request._(message)`\n \"\"\"\n return request.localizer.translate(_translation_factory(message, **kwargs))\n\n\ndef localize(message, **kwargs):\n \"\"\"\n To be used when we don't have the request context, e.g.\n `from warehouse.i18n import localize as _`\n \"\"\"\n\n def _lazy_localize(message, **kwargs):\n request = get_current_request()\n return _localize(request, message, **kwargs)\n\n return LazyString(_lazy_localize, message, **kwargs)\n\n\nclass InvalidLocalizer:\n def _fail(self):\n raise RuntimeError(\"Cannot use localizer without has_translations=True\")\n\n @property\n def locale_name(self):\n self._fail()\n\n def pluralize(self, *args, **kwargs):\n self._fail()\n\n def translate(self, *args, **kwargs):\n self._fail()\n\n\ndef translated_view(view, info):\n if info.options.get(\"has_translations\"):\n # If this page can be translated, then we'll add a Vary: PyPI-Locale\n # Vary header.\n # Note: This will give weird results if hitting PyPI directly instead of through\n # the Fastly VCL which sets PyPI-Locale.\n return add_vary(\"PyPI-Locale\")(view)\n elif info.exception_only:\n return view\n else:\n # If we're not using translations on this view, then we'll wrap the view\n # with a wrapper that just ensures that the localizer cannot be used.\n @functools.wraps(view)\n def wrapped(context, request):\n # This whole method is a little bit of an odd duck, we want to make\n # sure that we don't actually *access* request.localizer, because\n # doing so triggers the machinery to create a new localizer. So\n # instead we will dig into the request object __dict__ to\n # effectively do the same thing, just without triggering an access\n # on request.localizer.\n\n # Save the original session so that we can restore it once the\n # inner views have been called.\n nothing = object()\n original_localizer = request.__dict__.get(\"localizer\", nothing)\n\n # This particular view hasn't been set to allow access to the\n # translations, so we'll just assign an InvalidLocalizer to\n # request.localizer\n request.__dict__[\"localizer\"] = InvalidLocalizer()\n\n try:\n # Invoke the real view\n return view(context, request)\n finally:\n # Restore the original session so that things like\n # pyramid_debugtoolbar can access it.\n if original_localizer is nothing:\n del request.__dict__[\"localizer\"]\n else:\n request.__dict__[\"localizer\"] = original_localizer\n\n return wrapped\n\n\ntranslated_view.options = {\"has_translations\"}\n\n\ndef includeme(config):\n # Add the request attributes\n config.add_request_method(_locale, name=\"locale\", reify=True)\n config.add_request_method(_localize, name=\"_\")\n\n # Register our translation directory.\n config.add_translation_dirs(\"warehouse:locale/\")\n\n config.set_locale_negotiator(_negotiate_locale)\n\n # Register our i18n/l10n filters for Jinja2\n filters = config.get_settings().setdefault(\"jinja2.filters\", {})\n filters.setdefault(\"format_date\", \"warehouse.i18n.filters:format_date\")\n filters.setdefault(\"format_datetime\", \"warehouse.i18n.filters:format_datetime\")\n filters.setdefault(\n \"format_rfc822_datetime\", \"warehouse.i18n.filters:format_rfc822_datetime\"\n )\n filters.setdefault(\"format_number\", \"warehouse.i18n.filters:format_number\")\n\n jglobals = config.get_settings().setdefault(\"jinja2.globals\", {})\n jglobals.setdefault(\"KNOWN_LOCALES\", \"warehouse.i18n:KNOWN_LOCALES\")\n\n config.add_view_deriver(\n translated_view, over=\"rendered_view\", under=viewderivers.INGRESS\n )\n", "path": "warehouse/i18n/__init__.py"}]}
| 2,413 | 492 |
gh_patches_debug_13887
|
rasdani/github-patches
|
git_diff
|
apluslms__a-plus-474
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
The exercise results page does not show that a module is open for reading while the exercises are still closed.
The UI leaves the impression that the module is completely closed (between the reading opening time and the opening time). The "opens" badge in the module box also only shows the normal open time. The UI should show clearly that a module is open for reading. The collapsing box should be opened by default for read-open modules.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `exercise/templatetags/exercise.py`
Content:
```
1 import json
2 from django import template
3 from django.db.models import Max, Min
4 from django.template.loader import render_to_string
5 from django.utils import timezone
6 from django.utils.translation import ugettext_lazy as _
7
8 from course.models import CourseModule
9 from lib.errors import TagUsageError
10 from ..cache.content import CachedContent
11 from ..cache.points import CachedPoints
12 from ..exercise_summary import UserExerciseSummary
13 from ..models import LearningObjectDisplay, LearningObject, Submission, BaseExercise
14
15
16 register = template.Library()
17
18
19 def _prepare_now(context):
20 if not 'now' in context:
21 context['now'] = timezone.now()
22 return context['now']
23
24
25 def _prepare_context(context, student=None):
26 if not 'instance' in context:
27 raise TagUsageError()
28 instance = context['instance']
29 _prepare_now(context)
30 if not 'content' in context:
31 context['content'] = CachedContent(instance)
32 def points(user, key):
33 if not key in context:
34 context[key] = CachedPoints(instance, user, context['content'])
35 return context[key]
36 if student:
37 return points(student, 'studentpoints')
38 return points(context['request'].user, 'points')
39
40
41 def _get_toc(context, student=None):
42 points = _prepare_context(context, student)
43 context = context.flatten()
44 context.update({
45 'modules': points.modules_flatted(),
46 'categories': points.categories(),
47 'total': points.total(),
48 'is_course_staff': context.get('is_course_staff', False),
49 })
50 return context
51
52
53 def _is_accessible(context, entry, t):
54 if t and t > _prepare_now(context):
55 return False
56 if entry.get('requirements'):
57 points = _prepare_context(context)
58 module = CourseModule.objects.get(id=entry['id'])
59 return module.are_requirements_passed(points)
60 return True
61
62
63 @register.inclusion_tag("exercise/_user_results.html", takes_context=True)
64 def user_results(context, student=None):
65 values = _get_toc(context, student)
66 values['total_json'] = json.dumps(values['total'])
67 if student:
68 values['is_course_staff'] = False
69 return values
70
71
72 @register.inclusion_tag("exercise/_user_toc.html", takes_context=True)
73 def user_toc(context, student=None):
74 return _get_toc(context, student)
75
76
77 @register.inclusion_tag("exercise/_user_last.html", takes_context=True)
78 def user_last(context):
79 user = context['request'].user
80 points = _prepare_context(context)
81 if user.is_authenticated:
82 last = LearningObjectDisplay.objects.filter(
83 profile=user.userprofile,
84 learning_object__status=LearningObject.STATUS.READY,
85 learning_object__course_module__course_instance=context['instance'],
86 ).select_related('learning_object').order_by('-timestamp').first()
87 if last:
88 entry,_,_,_ = points.find(last.learning_object)
89 return {
90 'last': entry,
91 'last_time': last.timestamp,
92 }
93 return {
94 'begin': points.begin(),
95 'instance': context['instance'],
96 }
97
98
99 @register.inclusion_tag("exercise/_category_points.html", takes_context=True)
100 def category_points(context, student=None):
101 return _get_toc(context, student)
102
103
104 @register.inclusion_tag("exercise/_submission_list.html", takes_context=True)
105 def latest_submissions(context):
106 submissions = context["profile"].submissions \
107 .filter(exercise__course_module__course_instance=context["instance"]) \
108 .order_by("-id")[:10]
109 return {
110 "submissions": submissions,
111 "title": _("Latest submissions"),
112 "empty": _("No submissions for this course."),
113 }
114
115
116 @register.filter
117 def max_submissions(exercise, user_profile):
118 return exercise.max_submissions_for_student(user_profile)
119
120
121 @register.filter
122 def percent(decimal):
123 return int(decimal * 100)
124
125
126 @register.filter
127 def submission_status(status):
128 return Submission.STATUS[status]
129
130
131 def _points_data(obj, classes=None):
132 if isinstance(obj, UserExerciseSummary):
133 exercise = obj.exercise
134 data = {
135 'points': obj.get_points(),
136 'max': exercise.max_points,
137 'difficulty': exercise.difficulty,
138 'required': exercise.points_to_pass,
139 'confirm_the_level': exercise.category.confirm_the_level,
140 'missing_points': obj.is_missing_points(),
141 'passed': obj.is_passed(),
142 'full_score': obj.is_full_points(),
143 'submitted': obj.is_submitted(),
144 'graded': obj.is_graded(),
145 'official': not obj.is_unofficial(),
146 'exercise_page': True,
147 }
148 elif isinstance(obj, Submission):
149 exercise = obj.exercise
150 data = {
151 'points': obj.grade,
152 'max': exercise.max_points,
153 'difficulty': exercise.difficulty,
154 'required': exercise.points_to_pass,
155 'confirm_the_level': exercise.category.confirm_the_level,
156 'missing_points': obj.grade < exercise.points_to_pass,
157 'passed': obj.grade >= exercise.points_to_pass,
158 'full_score': obj.grade >= exercise.max_points,
159 'submitted': True,
160 'graded': obj.is_graded,
161 'official': obj.status != Submission.STATUS.UNOFFICIAL,
162 }
163 if not obj.is_graded and (
164 not exercise.category.confirm_the_level
165 or obj.status != Submission.STATUS.WAITING
166 ):
167 data['status'] = obj.status
168 else:
169 points = obj.get('points', 0)
170 max_points = obj.get('max_points', 0)
171 required = obj.get('points_to_pass', 0)
172 data = {
173 'points': points,
174 'max': max_points,
175 'difficulty': obj.get('difficulty', ''),
176 'required': required,
177 'confirm_the_level': obj.get('confirm_the_level', False),
178 'missing_points': points < required,
179 'passed': obj.get('passed', True),
180 'full_score': points >= max_points,
181 'submitted': obj.get('submission_count', 0) > 0,
182 'graded': obj.get('graded', True),
183 'status': obj.get('submission_status', False),
184 'unconfirmed': obj.get('unconfirmed', False),
185 'official': not obj.get('unofficial', False),
186 'confirmable_points': obj.get('confirmable_points', False),
187 }
188 percentage = 0
189 required_percentage = None
190 if data['max'] > 0:
191 percentage = int(round(100.0 * data['points'] / data['max']))
192 if data['required']:
193 required_percentage = int(round(100.0 * data['required'] / data['max']))
194 data.update({
195 'classes': classes,
196 'percentage': percentage,
197 'required_percentage': required_percentage,
198 })
199 return data
200
201
202 @register.inclusion_tag("exercise/_points_progress.html")
203 def points_progress(obj):
204 return _points_data(obj)
205
206
207 @register.inclusion_tag("exercise/_points_badge.html")
208 def points_badge(obj, classes=None):
209 return _points_data(obj, classes)
210
211
212 @register.simple_tag(takes_context=True)
213 def max_group_size(context):
214 points = _prepare_context(context)
215 return points.total()['max_group_size']
216
217
218 @register.simple_tag(takes_context=True)
219 def min_group_size(context):
220 points = _prepare_context(context)
221 return points.total()['min_group_size']
222
223
224 @register.simple_tag(takes_context=True)
225 def module_accessible(context, entry):
226 t = entry.get('reading_opening_time', entry.get('opening_time'))
227 return _is_accessible(context, entry, t)
228
229
230 @register.simple_tag(takes_context=True)
231 def exercise_accessible(context, entry):
232 t = entry.get('opening_time')
233 return _is_accessible(context, entry, t)
234
235
236 @register.simple_tag
237 def get_grading_errors(submission):
238 if not isinstance(submission.grading_data, dict):
239 return ""
240 grading_data = submission.grading_data.get('grading_data')
241 if not isinstance(grading_data, str):
242 return ""
243 if grading_data.startswith('<pre>'):
244 return grading_data[5:-6]
245 try:
246 return json.loads(grading_data).get('errors', "")
247 except (AttributeError, TypeError, ValueError):
248 return ""
249
250
251 @register.inclusion_tag("exercise/_text_stats.html", takes_context=True)
252 def exercise_text_stats(context, exercise):
253 if not 'instance' in context:
254 raise TagUsageError()
255 instance = context['instance']
256
257 if not 'student_count' in context:
258 context['student_count'] = instance.students.count()
259 total = context['student_count']
260
261 if isinstance(exercise, int):
262 num = instance.students.filter(submissions__exercise_id=exercise).distinct().count()
263 else:
264 num = exercise.number_of_submitters() if exercise else 0
265 return {
266 "number": num,
267 "percentage": int(100 * num / total) if total else 0,
268 }
269
270
271 @register.simple_tag
272 def get_format_info(format):
273 format_infos = {
274 'json' : {
275 'name': 'json',
276 'verbose_name': 'JSON',
277 },
278 'csv': {
279 'name': 'csv',
280 'verbose_name': 'CSV',
281 },
282 'excel.csv': {
283 'name': 'excel.csv',
284 'verbose_name': _('Excel compatible CSV'),
285 },
286 }
287 try:
288 return format_infos[format]
289 except KeyError as e:
290 raise RuntimeError('Invalid format: \'{}\''.format(format)) from e
291
292
293 @register.simple_tag
294 def get_format_info_list(formats):
295 return [get_format_info(format) for format in formats.split()]
296
297
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/exercise/templatetags/exercise.py b/exercise/templatetags/exercise.py
--- a/exercise/templatetags/exercise.py
+++ b/exercise/templatetags/exercise.py
@@ -223,8 +223,11 @@
@register.simple_tag(takes_context=True)
def module_accessible(context, entry):
- t = entry.get('reading_opening_time', entry.get('opening_time'))
- return _is_accessible(context, entry, t)
+ t = entry.get('reading_opening_time')
+ if t:
+ return _is_accessible(context, entry, t)
+ else:
+ return exercise_accessible(context, entry)
@register.simple_tag(takes_context=True)
@@ -293,4 +296,3 @@
@register.simple_tag
def get_format_info_list(formats):
return [get_format_info(format) for format in formats.split()]
-
|
{"golden_diff": "diff --git a/exercise/templatetags/exercise.py b/exercise/templatetags/exercise.py\n--- a/exercise/templatetags/exercise.py\n+++ b/exercise/templatetags/exercise.py\n@@ -223,8 +223,11 @@\n \n @register.simple_tag(takes_context=True)\n def module_accessible(context, entry):\n- t = entry.get('reading_opening_time', entry.get('opening_time'))\n- return _is_accessible(context, entry, t)\n+ t = entry.get('reading_opening_time')\n+ if t:\n+ return _is_accessible(context, entry, t)\n+ else:\n+ return exercise_accessible(context, entry)\n \n \n @register.simple_tag(takes_context=True)\n@@ -293,4 +296,3 @@\n @register.simple_tag\n def get_format_info_list(formats):\n return [get_format_info(format) for format in formats.split()]\n-\n", "issue": "The exercise results page does not show that a module is open for reading while the exercises are still closed.\nThe UI leaves the impression that the module is completely closed (between the reading opening time and the opening time). The \"opens\" badge in the module box also only shows the normal open time. The UI should show clearly that a module is open for reading. The collapsing box should be opened by default for read-open modules.\n", "before_files": [{"content": "import json\nfrom django import template\nfrom django.db.models import Max, Min\nfrom django.template.loader import render_to_string\nfrom django.utils import timezone\nfrom django.utils.translation import ugettext_lazy as _\n\nfrom course.models import CourseModule\nfrom lib.errors import TagUsageError\nfrom ..cache.content import CachedContent\nfrom ..cache.points import CachedPoints\nfrom ..exercise_summary import UserExerciseSummary\nfrom ..models import LearningObjectDisplay, LearningObject, Submission, BaseExercise\n\n\nregister = template.Library()\n\n\ndef _prepare_now(context):\n if not 'now' in context:\n context['now'] = timezone.now()\n return context['now']\n\n\ndef _prepare_context(context, student=None):\n if not 'instance' in context:\n raise TagUsageError()\n instance = context['instance']\n _prepare_now(context)\n if not 'content' in context:\n context['content'] = CachedContent(instance)\n def points(user, key):\n if not key in context:\n context[key] = CachedPoints(instance, user, context['content'])\n return context[key]\n if student:\n return points(student, 'studentpoints')\n return points(context['request'].user, 'points')\n\n\ndef _get_toc(context, student=None):\n points = _prepare_context(context, student)\n context = context.flatten()\n context.update({\n 'modules': points.modules_flatted(),\n 'categories': points.categories(),\n 'total': points.total(),\n 'is_course_staff': context.get('is_course_staff', False),\n })\n return context\n\n\ndef _is_accessible(context, entry, t):\n if t and t > _prepare_now(context):\n return False\n if entry.get('requirements'):\n points = _prepare_context(context)\n module = CourseModule.objects.get(id=entry['id'])\n return module.are_requirements_passed(points)\n return True\n\n\[email protected]_tag(\"exercise/_user_results.html\", takes_context=True)\ndef user_results(context, student=None):\n values = _get_toc(context, student)\n values['total_json'] = json.dumps(values['total'])\n if student:\n values['is_course_staff'] = False\n return values\n\n\[email protected]_tag(\"exercise/_user_toc.html\", takes_context=True)\ndef user_toc(context, student=None):\n return _get_toc(context, student)\n\n\[email protected]_tag(\"exercise/_user_last.html\", takes_context=True)\ndef user_last(context):\n user = context['request'].user\n points = _prepare_context(context)\n if user.is_authenticated:\n last = LearningObjectDisplay.objects.filter(\n profile=user.userprofile,\n learning_object__status=LearningObject.STATUS.READY,\n learning_object__course_module__course_instance=context['instance'],\n ).select_related('learning_object').order_by('-timestamp').first()\n if last:\n entry,_,_,_ = points.find(last.learning_object)\n return {\n 'last': entry,\n 'last_time': last.timestamp,\n }\n return {\n 'begin': points.begin(),\n 'instance': context['instance'],\n }\n\n\[email protected]_tag(\"exercise/_category_points.html\", takes_context=True)\ndef category_points(context, student=None):\n return _get_toc(context, student)\n\n\[email protected]_tag(\"exercise/_submission_list.html\", takes_context=True)\ndef latest_submissions(context):\n submissions = context[\"profile\"].submissions \\\n .filter(exercise__course_module__course_instance=context[\"instance\"]) \\\n .order_by(\"-id\")[:10]\n return {\n \"submissions\": submissions,\n \"title\": _(\"Latest submissions\"),\n \"empty\": _(\"No submissions for this course.\"),\n }\n\n\[email protected]\ndef max_submissions(exercise, user_profile):\n return exercise.max_submissions_for_student(user_profile)\n\n\[email protected]\ndef percent(decimal):\n return int(decimal * 100)\n\n\[email protected]\ndef submission_status(status):\n return Submission.STATUS[status]\n\n\ndef _points_data(obj, classes=None):\n if isinstance(obj, UserExerciseSummary):\n exercise = obj.exercise\n data = {\n 'points': obj.get_points(),\n 'max': exercise.max_points,\n 'difficulty': exercise.difficulty,\n 'required': exercise.points_to_pass,\n 'confirm_the_level': exercise.category.confirm_the_level,\n 'missing_points': obj.is_missing_points(),\n 'passed': obj.is_passed(),\n 'full_score': obj.is_full_points(),\n 'submitted': obj.is_submitted(),\n 'graded': obj.is_graded(),\n 'official': not obj.is_unofficial(),\n 'exercise_page': True,\n }\n elif isinstance(obj, Submission):\n exercise = obj.exercise\n data = {\n 'points': obj.grade,\n 'max': exercise.max_points,\n 'difficulty': exercise.difficulty,\n 'required': exercise.points_to_pass,\n 'confirm_the_level': exercise.category.confirm_the_level,\n 'missing_points': obj.grade < exercise.points_to_pass,\n 'passed': obj.grade >= exercise.points_to_pass,\n 'full_score': obj.grade >= exercise.max_points,\n 'submitted': True,\n 'graded': obj.is_graded,\n 'official': obj.status != Submission.STATUS.UNOFFICIAL,\n }\n if not obj.is_graded and (\n not exercise.category.confirm_the_level\n or obj.status != Submission.STATUS.WAITING\n ):\n data['status'] = obj.status\n else:\n points = obj.get('points', 0)\n max_points = obj.get('max_points', 0)\n required = obj.get('points_to_pass', 0)\n data = {\n 'points': points,\n 'max': max_points,\n 'difficulty': obj.get('difficulty', ''),\n 'required': required,\n 'confirm_the_level': obj.get('confirm_the_level', False),\n 'missing_points': points < required,\n 'passed': obj.get('passed', True),\n 'full_score': points >= max_points,\n 'submitted': obj.get('submission_count', 0) > 0,\n 'graded': obj.get('graded', True),\n 'status': obj.get('submission_status', False),\n 'unconfirmed': obj.get('unconfirmed', False),\n 'official': not obj.get('unofficial', False),\n 'confirmable_points': obj.get('confirmable_points', False),\n }\n percentage = 0\n required_percentage = None\n if data['max'] > 0:\n percentage = int(round(100.0 * data['points'] / data['max']))\n if data['required']:\n required_percentage = int(round(100.0 * data['required'] / data['max']))\n data.update({\n 'classes': classes,\n 'percentage': percentage,\n 'required_percentage': required_percentage,\n })\n return data\n\n\[email protected]_tag(\"exercise/_points_progress.html\")\ndef points_progress(obj):\n return _points_data(obj)\n\n\[email protected]_tag(\"exercise/_points_badge.html\")\ndef points_badge(obj, classes=None):\n return _points_data(obj, classes)\n\n\[email protected]_tag(takes_context=True)\ndef max_group_size(context):\n points = _prepare_context(context)\n return points.total()['max_group_size']\n\n\[email protected]_tag(takes_context=True)\ndef min_group_size(context):\n points = _prepare_context(context)\n return points.total()['min_group_size']\n\n\[email protected]_tag(takes_context=True)\ndef module_accessible(context, entry):\n t = entry.get('reading_opening_time', entry.get('opening_time'))\n return _is_accessible(context, entry, t)\n\n\[email protected]_tag(takes_context=True)\ndef exercise_accessible(context, entry):\n t = entry.get('opening_time')\n return _is_accessible(context, entry, t)\n\n\[email protected]_tag\ndef get_grading_errors(submission):\n if not isinstance(submission.grading_data, dict):\n return \"\"\n grading_data = submission.grading_data.get('grading_data')\n if not isinstance(grading_data, str):\n return \"\"\n if grading_data.startswith('<pre>'):\n return grading_data[5:-6]\n try:\n return json.loads(grading_data).get('errors', \"\")\n except (AttributeError, TypeError, ValueError):\n return \"\"\n\n\[email protected]_tag(\"exercise/_text_stats.html\", takes_context=True)\ndef exercise_text_stats(context, exercise):\n if not 'instance' in context:\n raise TagUsageError()\n instance = context['instance']\n\n if not 'student_count' in context:\n context['student_count'] = instance.students.count()\n total = context['student_count']\n\n if isinstance(exercise, int):\n num = instance.students.filter(submissions__exercise_id=exercise).distinct().count()\n else:\n num = exercise.number_of_submitters() if exercise else 0\n return {\n \"number\": num,\n \"percentage\": int(100 * num / total) if total else 0,\n }\n\n\[email protected]_tag\ndef get_format_info(format):\n format_infos = {\n 'json' : {\n 'name': 'json',\n 'verbose_name': 'JSON',\n },\n 'csv': {\n 'name': 'csv',\n 'verbose_name': 'CSV',\n },\n 'excel.csv': {\n 'name': 'excel.csv',\n 'verbose_name': _('Excel compatible CSV'),\n },\n }\n try:\n return format_infos[format]\n except KeyError as e:\n raise RuntimeError('Invalid format: \\'{}\\''.format(format)) from e\n\n\[email protected]_tag\ndef get_format_info_list(formats):\n return [get_format_info(format) for format in formats.split()]\n\n", "path": "exercise/templatetags/exercise.py"}], "after_files": [{"content": "import json\nfrom django import template\nfrom django.db.models import Max, Min\nfrom django.template.loader import render_to_string\nfrom django.utils import timezone\nfrom django.utils.translation import ugettext_lazy as _\n\nfrom course.models import CourseModule\nfrom lib.errors import TagUsageError\nfrom ..cache.content import CachedContent\nfrom ..cache.points import CachedPoints\nfrom ..exercise_summary import UserExerciseSummary\nfrom ..models import LearningObjectDisplay, LearningObject, Submission, BaseExercise\n\n\nregister = template.Library()\n\n\ndef _prepare_now(context):\n if not 'now' in context:\n context['now'] = timezone.now()\n return context['now']\n\n\ndef _prepare_context(context, student=None):\n if not 'instance' in context:\n raise TagUsageError()\n instance = context['instance']\n _prepare_now(context)\n if not 'content' in context:\n context['content'] = CachedContent(instance)\n def points(user, key):\n if not key in context:\n context[key] = CachedPoints(instance, user, context['content'])\n return context[key]\n if student:\n return points(student, 'studentpoints')\n return points(context['request'].user, 'points')\n\n\ndef _get_toc(context, student=None):\n points = _prepare_context(context, student)\n context = context.flatten()\n context.update({\n 'modules': points.modules_flatted(),\n 'categories': points.categories(),\n 'total': points.total(),\n 'is_course_staff': context.get('is_course_staff', False),\n })\n return context\n\n\ndef _is_accessible(context, entry, t):\n if t and t > _prepare_now(context):\n return False\n if entry.get('requirements'):\n points = _prepare_context(context)\n module = CourseModule.objects.get(id=entry['id'])\n return module.are_requirements_passed(points)\n return True\n\n\[email protected]_tag(\"exercise/_user_results.html\", takes_context=True)\ndef user_results(context, student=None):\n values = _get_toc(context, student)\n values['total_json'] = json.dumps(values['total'])\n if student:\n values['is_course_staff'] = False\n return values\n\n\[email protected]_tag(\"exercise/_user_toc.html\", takes_context=True)\ndef user_toc(context, student=None):\n return _get_toc(context, student)\n\n\[email protected]_tag(\"exercise/_user_last.html\", takes_context=True)\ndef user_last(context):\n user = context['request'].user\n points = _prepare_context(context)\n if user.is_authenticated:\n last = LearningObjectDisplay.objects.filter(\n profile=user.userprofile,\n learning_object__status=LearningObject.STATUS.READY,\n learning_object__course_module__course_instance=context['instance'],\n ).select_related('learning_object').order_by('-timestamp').first()\n if last:\n entry,_,_,_ = points.find(last.learning_object)\n return {\n 'last': entry,\n 'last_time': last.timestamp,\n }\n return {\n 'begin': points.begin(),\n 'instance': context['instance'],\n }\n\n\[email protected]_tag(\"exercise/_category_points.html\", takes_context=True)\ndef category_points(context, student=None):\n return _get_toc(context, student)\n\n\[email protected]_tag(\"exercise/_submission_list.html\", takes_context=True)\ndef latest_submissions(context):\n submissions = context[\"profile\"].submissions \\\n .filter(exercise__course_module__course_instance=context[\"instance\"]) \\\n .order_by(\"-id\")[:10]\n return {\n \"submissions\": submissions,\n \"title\": _(\"Latest submissions\"),\n \"empty\": _(\"No submissions for this course.\"),\n }\n\n\[email protected]\ndef max_submissions(exercise, user_profile):\n return exercise.max_submissions_for_student(user_profile)\n\n\[email protected]\ndef percent(decimal):\n return int(decimal * 100)\n\n\[email protected]\ndef submission_status(status):\n return Submission.STATUS[status]\n\n\ndef _points_data(obj, classes=None):\n if isinstance(obj, UserExerciseSummary):\n exercise = obj.exercise\n data = {\n 'points': obj.get_points(),\n 'max': exercise.max_points,\n 'difficulty': exercise.difficulty,\n 'required': exercise.points_to_pass,\n 'confirm_the_level': exercise.category.confirm_the_level,\n 'missing_points': obj.is_missing_points(),\n 'passed': obj.is_passed(),\n 'full_score': obj.is_full_points(),\n 'submitted': obj.is_submitted(),\n 'graded': obj.is_graded(),\n 'official': not obj.is_unofficial(),\n 'exercise_page': True,\n }\n elif isinstance(obj, Submission):\n exercise = obj.exercise\n data = {\n 'points': obj.grade,\n 'max': exercise.max_points,\n 'difficulty': exercise.difficulty,\n 'required': exercise.points_to_pass,\n 'confirm_the_level': exercise.category.confirm_the_level,\n 'missing_points': obj.grade < exercise.points_to_pass,\n 'passed': obj.grade >= exercise.points_to_pass,\n 'full_score': obj.grade >= exercise.max_points,\n 'submitted': True,\n 'graded': obj.is_graded,\n 'official': obj.status != Submission.STATUS.UNOFFICIAL,\n }\n if not obj.is_graded and (\n not exercise.category.confirm_the_level\n or obj.status != Submission.STATUS.WAITING\n ):\n data['status'] = obj.status\n else:\n points = obj.get('points', 0)\n max_points = obj.get('max_points', 0)\n required = obj.get('points_to_pass', 0)\n data = {\n 'points': points,\n 'max': max_points,\n 'difficulty': obj.get('difficulty', ''),\n 'required': required,\n 'confirm_the_level': obj.get('confirm_the_level', False),\n 'missing_points': points < required,\n 'passed': obj.get('passed', True),\n 'full_score': points >= max_points,\n 'submitted': obj.get('submission_count', 0) > 0,\n 'graded': obj.get('graded', True),\n 'status': obj.get('submission_status', False),\n 'unconfirmed': obj.get('unconfirmed', False),\n 'official': not obj.get('unofficial', False),\n 'confirmable_points': obj.get('confirmable_points', False),\n }\n percentage = 0\n required_percentage = None\n if data['max'] > 0:\n percentage = int(round(100.0 * data['points'] / data['max']))\n if data['required']:\n required_percentage = int(round(100.0 * data['required'] / data['max']))\n data.update({\n 'classes': classes,\n 'percentage': percentage,\n 'required_percentage': required_percentage,\n })\n return data\n\n\[email protected]_tag(\"exercise/_points_progress.html\")\ndef points_progress(obj):\n return _points_data(obj)\n\n\[email protected]_tag(\"exercise/_points_badge.html\")\ndef points_badge(obj, classes=None):\n return _points_data(obj, classes)\n\n\[email protected]_tag(takes_context=True)\ndef max_group_size(context):\n points = _prepare_context(context)\n return points.total()['max_group_size']\n\n\[email protected]_tag(takes_context=True)\ndef min_group_size(context):\n points = _prepare_context(context)\n return points.total()['min_group_size']\n\n\[email protected]_tag(takes_context=True)\ndef module_accessible(context, entry):\n t = entry.get('reading_opening_time')\n if t:\n return _is_accessible(context, entry, t)\n else:\n return exercise_accessible(context, entry)\n\n\[email protected]_tag(takes_context=True)\ndef exercise_accessible(context, entry):\n t = entry.get('opening_time')\n return _is_accessible(context, entry, t)\n\n\[email protected]_tag\ndef get_grading_errors(submission):\n if not isinstance(submission.grading_data, dict):\n return \"\"\n grading_data = submission.grading_data.get('grading_data')\n if not isinstance(grading_data, str):\n return \"\"\n if grading_data.startswith('<pre>'):\n return grading_data[5:-6]\n try:\n return json.loads(grading_data).get('errors', \"\")\n except (AttributeError, TypeError, ValueError):\n return \"\"\n\n\[email protected]_tag(\"exercise/_text_stats.html\", takes_context=True)\ndef exercise_text_stats(context, exercise):\n if not 'instance' in context:\n raise TagUsageError()\n instance = context['instance']\n\n if not 'student_count' in context:\n context['student_count'] = instance.students.count()\n total = context['student_count']\n\n if isinstance(exercise, int):\n num = instance.students.filter(submissions__exercise_id=exercise).distinct().count()\n else:\n num = exercise.number_of_submitters() if exercise else 0\n return {\n \"number\": num,\n \"percentage\": int(100 * num / total) if total else 0,\n }\n\n\[email protected]_tag\ndef get_format_info(format):\n format_infos = {\n 'json' : {\n 'name': 'json',\n 'verbose_name': 'JSON',\n },\n 'csv': {\n 'name': 'csv',\n 'verbose_name': 'CSV',\n },\n 'excel.csv': {\n 'name': 'excel.csv',\n 'verbose_name': _('Excel compatible CSV'),\n },\n }\n try:\n return format_infos[format]\n except KeyError as e:\n raise RuntimeError('Invalid format: \\'{}\\''.format(format)) from e\n\n\[email protected]_tag\ndef get_format_info_list(formats):\n return [get_format_info(format) for format in formats.split()]\n", "path": "exercise/templatetags/exercise.py"}]}
| 3,219 | 208 |
gh_patches_debug_35
|
rasdani/github-patches
|
git_diff
|
StackStorm__st2-5104
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Add version string to st2tests to make it installable
Prior to this change, this will fail:
cd st2tests/st2tests
pip install .
After this change that command successfully installs the `st2tests` package. This will also work for installing via GitHub as in:
pip install -e git+https://github.com/StackStorm/[email protected]#egg=st2tests&subdirectory=st2tests
The original request in #2574 is to get st2tests onto PyPI, and I'm not sure if this will accomplish that request, but this is a good first step.
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `st2tests/st2tests/__init__.py`
Content:
```
1 # Copyright 2020 The StackStorm Authors.
2 # Copyright 2019 Extreme Networks, Inc.
3 #
4 # Licensed under the Apache License, Version 2.0 (the "License");
5 # you may not use this file except in compliance with the License.
6 # You may obtain a copy of the License at
7 #
8 # http://www.apache.org/licenses/LICENSE-2.0
9 #
10 # Unless required by applicable law or agreed to in writing, software
11 # distributed under the License is distributed on an "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 # See the License for the specific language governing permissions and
14 # limitations under the License.
15
16 from __future__ import absolute_import
17
18 from st2tests.base import EventletTestCase
19 from st2tests.base import DbTestCase
20 from st2tests.base import ExecutionDbTestCase
21 from st2tests.base import DbModelTestCase
22 from st2tests.base import WorkflowTestCase
23
24
25 __all__ = [
26 'EventletTestCase',
27 'DbTestCase',
28 'ExecutionDbTestCase',
29 'DbModelTestCase',
30 'WorkflowTestCase'
31 ]
32
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/st2tests/st2tests/__init__.py b/st2tests/st2tests/__init__.py
--- a/st2tests/st2tests/__init__.py
+++ b/st2tests/st2tests/__init__.py
@@ -29,3 +29,5 @@
'DbModelTestCase',
'WorkflowTestCase'
]
+
+__version__ = '3.3dev'
|
{"golden_diff": "diff --git a/st2tests/st2tests/__init__.py b/st2tests/st2tests/__init__.py\n--- a/st2tests/st2tests/__init__.py\n+++ b/st2tests/st2tests/__init__.py\n@@ -29,3 +29,5 @@\n 'DbModelTestCase',\n 'WorkflowTestCase'\n ]\n+\n+__version__ = '3.3dev'\n", "issue": "Add version string to st2tests to make it installable\nPrior to this change, this will fail:\r\n\r\n cd st2tests/st2tests\r\n pip install .\r\n\r\nAfter this change that command successfully installs the `st2tests` package. This will also work for installing via GitHub as in:\r\n\r\n pip install -e git+https://github.com/StackStorm/[email protected]#egg=st2tests&subdirectory=st2tests\r\n\r\nThe original request in #2574 is to get st2tests onto PyPI, and I'm not sure if this will accomplish that request, but this is a good first step.\n", "before_files": [{"content": "# Copyright 2020 The StackStorm Authors.\n# Copyright 2019 Extreme Networks, Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom __future__ import absolute_import\n\nfrom st2tests.base import EventletTestCase\nfrom st2tests.base import DbTestCase\nfrom st2tests.base import ExecutionDbTestCase\nfrom st2tests.base import DbModelTestCase\nfrom st2tests.base import WorkflowTestCase\n\n\n__all__ = [\n 'EventletTestCase',\n 'DbTestCase',\n 'ExecutionDbTestCase',\n 'DbModelTestCase',\n 'WorkflowTestCase'\n]\n", "path": "st2tests/st2tests/__init__.py"}], "after_files": [{"content": "# Copyright 2020 The StackStorm Authors.\n# Copyright 2019 Extreme Networks, Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom __future__ import absolute_import\n\nfrom st2tests.base import EventletTestCase\nfrom st2tests.base import DbTestCase\nfrom st2tests.base import ExecutionDbTestCase\nfrom st2tests.base import DbModelTestCase\nfrom st2tests.base import WorkflowTestCase\n\n\n__all__ = [\n 'EventletTestCase',\n 'DbTestCase',\n 'ExecutionDbTestCase',\n 'DbModelTestCase',\n 'WorkflowTestCase'\n]\n\n__version__ = '3.3dev'\n", "path": "st2tests/st2tests/__init__.py"}]}
| 696 | 88 |
gh_patches_debug_24126
|
rasdani/github-patches
|
git_diff
|
kartoza__prj.app-279
|
We are currently solving the following issue within our repository. Here is the issue text:
--- BEGIN ISSUE ---
Sponsors for a release need to be filtered for the project and the date
There is a serious bug with the sponsors whereby if you set the release date for a release in one project, it will show on the release page sponsors from any other project.
<img width="1387" alt="screen shot 2016-03-31 at 13 36 43" src="https://cloud.githubusercontent.com/assets/178003/14167536/1eff7c90-f746-11e5-9a2e-ed648c9d22d6.png">
Note that you need to have a date for the version otherwise it does not replicate:
<img width="1210" alt="screen shot 2016-03-31 at 13 37 21" src="https://cloud.githubusercontent.com/assets/178003/14167565/50e68c58-f746-11e5-96b6-e59970bf6c14.png">
--- END ISSUE ---
Below are some code segments, each from a relevant file. One or more of these files may contain bugs.
--- BEGIN FILES ---
Path: `django_project/changes/models/version.py`
Content:
```
1 # coding=utf-8
2 from django.core.urlresolvers import reverse
3 # from django.utils.text import slugify
4 from common.utilities import version_slugify
5 import os
6 import logging
7 from core.settings.contrib import STOP_WORDS
8 from django.conf.global_settings import MEDIA_ROOT
9 from django.db import models
10 from .entry import Entry
11 from .sponsorship_period import SponsorshipPeriod
12 from django.contrib.auth.models import User
13 from django.utils.translation import ugettext_lazy as _
14
15 logger = logging.getLogger(__name__)
16
17
18 class ApprovedVersionManager(models.Manager):
19 """Custom version manager that shows only approved records."""
20
21 def get_queryset(self):
22 """Query set generator"""
23 return super(
24 ApprovedVersionManager, self).get_queryset().filter(
25 approved=True)
26
27
28 class UnapprovedVersionManager(models.Manager):
29 """Custom version manager that shows only unapproved records."""
30
31 def get_queryset(self):
32 """Query set generator"""
33 return super(
34 UnapprovedVersionManager, self).get_queryset().filter(
35 approved=False)
36
37
38 # noinspection PyUnresolvedReferences
39 class Version(models.Model):
40 """A version model that the changelog is associated with.."""
41
42 name = models.CharField(
43 help_text='Name of this release e.g. 1.0.1.',
44 max_length=255,
45 null=False,
46 blank=False,
47 unique=False)
48
49 padded_version = models.CharField(
50 help_text=(
51 'Numeric version for this release e.g. 001000001 for 1.0.1 '
52 'calculated by zero padding each component of maj/minor/bugfix '
53 'elements from name.'),
54 max_length=9,
55 null=False,
56 blank=True,
57 unique=False)
58
59 approved = models.BooleanField(
60 help_text=(
61 'Whether this version has been approved for use by the '
62 'project owner.'),
63 default=False)
64
65 image_file = models.ImageField(
66 help_text=(
67 'An optional image for this version e.g. a splashscreen. '
68 'Most browsers support dragging the image directly on to the '
69 '"Choose File" button above.'),
70 upload_to=os.path.join(MEDIA_ROOT, 'images/projects'),
71 blank=True)
72
73 description = models.TextField(
74 null=True,
75 blank=True,
76 help_text='Describe the new version. Markdown is supported.')
77
78 release_date = models.DateField(
79 _('Release date (yyyy-mm-dd)'),
80 help_text='Date of official release',
81 null=True,
82 blank=True)
83
84 author = models.ForeignKey(User)
85 slug = models.SlugField()
86 project = models.ForeignKey('base.Project')
87 objects = models.Manager()
88 approved_objects = ApprovedVersionManager()
89 unapproved_objects = UnapprovedVersionManager()
90
91 # noinspection PyClassicStyleClass
92 class Meta:
93 """Meta options for the version class."""
94 unique_together = (
95 ('name', 'project'),
96 ('slug', 'project'),
97 )
98 app_label = 'changes'
99 # ordering = ['-datetime_created']
100
101 def save(self, *args, **kwargs):
102 if not self.pk:
103 words = self.name.split()
104 filtered_words = [t for t in words if t.lower() not in STOP_WORDS]
105 new_list = ' '.join(filtered_words)
106 self.slug = version_slugify(new_list)[:50]
107 self.padded_version = self.pad_name(self.name)
108 super(Version, self).save(*args, **kwargs)
109
110 def pad_name(self, version):
111 """Create a 0 padded version of the version name.
112
113 e.g. input: 2.10.1
114 e.g. output: 002010100
115
116 This will ensure we have sortable version names.
117
118 :param version: A text version in the form 0.0.0 - if the version is
119 not in this form, we return the version unaltered.
120 :type version: str
121
122 :returns: Zero padded representation of the version e.g. 001010100
123 :rtype: str
124
125 """
126 tokens = version.split('.')
127 if len(tokens) != 3:
128 return version
129 result = ''
130 for token in tokens:
131 result += token.zfill(3)
132 return result
133
134 def __unicode__(self):
135 return u'%s : %s' % (self.project.name, self.name)
136
137 def get_absolute_url(self):
138 return reverse('version-detail', kwargs={
139 'slug': self.slug,
140 'project_slug': self.project.slug
141 })
142
143 def entries(self):
144 """Get the entries for this version."""
145 qs = Entry.objects.filter(version=self).order_by('category')
146 return qs
147
148 def _entries_for_category(self, category):
149 """All entries for this version and filtered by the given category.
150
151 :param category: Category to filter by.
152 :type category: Category
153
154 .. note:: only approved entries returned.
155 """
156 qs = Entry.objects.filter(version=self,
157 category=category,
158 approved=True)
159 return qs
160
161 def categories(self):
162 """Get a list of categories where there are one or more entries.
163
164 Example use in template::
165 {% for row in version.categories %}
166 <h2 class="text-muted">{{ row.category.name }}</h2>
167 <ul>
168 {% for entry in row.entries %}
169 <li>{{ entry.name }}</li>
170 {% endfor %}
171 </ul>
172 {% endfor %}
173 """
174 qs = self.entries()
175 used = []
176 categories = []
177 for entry in qs:
178 category = entry.category
179 if category not in used:
180 row = {
181 'category': category,
182 'entries': self._entries_for_category(category)
183 }
184 categories.append(row)
185 used.append(category)
186 return categories
187
188 def sponsors(self):
189 """Return a list of sponsors current at time of this version release.
190
191 :returns: A list of SponsorPeriod objects whose release date coincides
192 with the version release date. Only approved sponsors are returned.
193 Returns None if the release date (which is optional) is not set.
194 :rtype: Queryset, None
195 """
196 if self.release_date is None:
197 return None
198 sponsors = SponsorshipPeriod.approved_objects.filter(
199 end_date__gte=self.release_date).filter(
200 start_date__lte=self.release_date).order_by(
201 'start_date').order_by(
202 '-sponsorship_level__value')
203 return sponsors
204
```
--- END FILES ---
Please first localize the bug based on the issue statement, and then generate a patch according to the `git diff` format fenced by three backticks.
Here is an example:
```diff
diff --git a/examples/server_async.py b/examples/server_async.py
--- a/examples/server_async.py
+++ b/examples/server_async.py
@@ -313,4 +313,4 @@
if __name__ == "__main__":
- asyncio.run(run_async_server("."), debug=True)
+ asyncio.run(run_async_server(), debug=True)
diff --git a/examples/server_sync.py b/examples/server_sync.py
--- a/examples/server_sync.py
+++ b/examples/server_sync.py
@@ -313,5 +313,5 @@
if __name__ == "__main__":
- server = run_sync_server(".")
+ server = run_sync_server()
server.shutdown()
```
|
diff --git a/django_project/changes/models/version.py b/django_project/changes/models/version.py
--- a/django_project/changes/models/version.py
+++ b/django_project/changes/models/version.py
@@ -188,8 +188,9 @@
def sponsors(self):
"""Return a list of sponsors current at time of this version release.
- :returns: A list of SponsorPeriod objects whose release date coincides
- with the version release date. Only approved sponsors are returned.
+ :returns: A list of SponsorPeriod objects for current project
+ whose release date coincides with the version release date.
+ Only approved sponsors are returned.
Returns None if the release date (which is optional) is not set.
:rtype: Queryset, None
"""
@@ -197,7 +198,8 @@
return None
sponsors = SponsorshipPeriod.approved_objects.filter(
end_date__gte=self.release_date).filter(
- start_date__lte=self.release_date).order_by(
+ start_date__lte=self.release_date).filter(
+ project=self.project).order_by(
'start_date').order_by(
'-sponsorship_level__value')
return sponsors
|
{"golden_diff": "diff --git a/django_project/changes/models/version.py b/django_project/changes/models/version.py\n--- a/django_project/changes/models/version.py\n+++ b/django_project/changes/models/version.py\n@@ -188,8 +188,9 @@\n def sponsors(self):\n \"\"\"Return a list of sponsors current at time of this version release.\n \n- :returns: A list of SponsorPeriod objects whose release date coincides\n- with the version release date. Only approved sponsors are returned.\n+ :returns: A list of SponsorPeriod objects for current project\n+ whose release date coincides with the version release date.\n+ Only approved sponsors are returned.\n Returns None if the release date (which is optional) is not set.\n :rtype: Queryset, None\n \"\"\"\n@@ -197,7 +198,8 @@\n return None\n sponsors = SponsorshipPeriod.approved_objects.filter(\n end_date__gte=self.release_date).filter(\n- start_date__lte=self.release_date).order_by(\n+ start_date__lte=self.release_date).filter(\n+ project=self.project).order_by(\n 'start_date').order_by(\n '-sponsorship_level__value')\n return sponsors\n", "issue": "Sponsors for a release need to be filtered for the project and the date\nThere is a serious bug with the sponsors whereby if you set the release date for a release in one project, it will show on the release page sponsors from any other project.\n\n<img width=\"1387\" alt=\"screen shot 2016-03-31 at 13 36 43\" src=\"https://cloud.githubusercontent.com/assets/178003/14167536/1eff7c90-f746-11e5-9a2e-ed648c9d22d6.png\">\n\nNote that you need to have a date for the version otherwise it does not replicate:\n\n<img width=\"1210\" alt=\"screen shot 2016-03-31 at 13 37 21\" src=\"https://cloud.githubusercontent.com/assets/178003/14167565/50e68c58-f746-11e5-96b6-e59970bf6c14.png\">\n\n", "before_files": [{"content": "# coding=utf-8\nfrom django.core.urlresolvers import reverse\n# from django.utils.text import slugify\nfrom common.utilities import version_slugify\nimport os\nimport logging\nfrom core.settings.contrib import STOP_WORDS\nfrom django.conf.global_settings import MEDIA_ROOT\nfrom django.db import models\nfrom .entry import Entry\nfrom .sponsorship_period import SponsorshipPeriod\nfrom django.contrib.auth.models import User\nfrom django.utils.translation import ugettext_lazy as _\n\nlogger = logging.getLogger(__name__)\n\n\nclass ApprovedVersionManager(models.Manager):\n \"\"\"Custom version manager that shows only approved records.\"\"\"\n\n def get_queryset(self):\n \"\"\"Query set generator\"\"\"\n return super(\n ApprovedVersionManager, self).get_queryset().filter(\n approved=True)\n\n\nclass UnapprovedVersionManager(models.Manager):\n \"\"\"Custom version manager that shows only unapproved records.\"\"\"\n\n def get_queryset(self):\n \"\"\"Query set generator\"\"\"\n return super(\n UnapprovedVersionManager, self).get_queryset().filter(\n approved=False)\n\n\n# noinspection PyUnresolvedReferences\nclass Version(models.Model):\n \"\"\"A version model that the changelog is associated with..\"\"\"\n\n name = models.CharField(\n help_text='Name of this release e.g. 1.0.1.',\n max_length=255,\n null=False,\n blank=False,\n unique=False)\n\n padded_version = models.CharField(\n help_text=(\n 'Numeric version for this release e.g. 001000001 for 1.0.1 '\n 'calculated by zero padding each component of maj/minor/bugfix '\n 'elements from name.'),\n max_length=9,\n null=False,\n blank=True,\n unique=False)\n\n approved = models.BooleanField(\n help_text=(\n 'Whether this version has been approved for use by the '\n 'project owner.'),\n default=False)\n\n image_file = models.ImageField(\n help_text=(\n 'An optional image for this version e.g. a splashscreen. '\n 'Most browsers support dragging the image directly on to the '\n '\"Choose File\" button above.'),\n upload_to=os.path.join(MEDIA_ROOT, 'images/projects'),\n blank=True)\n\n description = models.TextField(\n null=True,\n blank=True,\n help_text='Describe the new version. Markdown is supported.')\n\n release_date = models.DateField(\n _('Release date (yyyy-mm-dd)'),\n help_text='Date of official release',\n null=True,\n blank=True)\n\n author = models.ForeignKey(User)\n slug = models.SlugField()\n project = models.ForeignKey('base.Project')\n objects = models.Manager()\n approved_objects = ApprovedVersionManager()\n unapproved_objects = UnapprovedVersionManager()\n\n # noinspection PyClassicStyleClass\n class Meta:\n \"\"\"Meta options for the version class.\"\"\"\n unique_together = (\n ('name', 'project'),\n ('slug', 'project'),\n )\n app_label = 'changes'\n # ordering = ['-datetime_created']\n\n def save(self, *args, **kwargs):\n if not self.pk:\n words = self.name.split()\n filtered_words = [t for t in words if t.lower() not in STOP_WORDS]\n new_list = ' '.join(filtered_words)\n self.slug = version_slugify(new_list)[:50]\n self.padded_version = self.pad_name(self.name)\n super(Version, self).save(*args, **kwargs)\n\n def pad_name(self, version):\n \"\"\"Create a 0 padded version of the version name.\n\n e.g. input: 2.10.1\n e.g. output: 002010100\n\n This will ensure we have sortable version names.\n\n :param version: A text version in the form 0.0.0 - if the version is\n not in this form, we return the version unaltered.\n :type version: str\n\n :returns: Zero padded representation of the version e.g. 001010100\n :rtype: str\n\n \"\"\"\n tokens = version.split('.')\n if len(tokens) != 3:\n return version\n result = ''\n for token in tokens:\n result += token.zfill(3)\n return result\n\n def __unicode__(self):\n return u'%s : %s' % (self.project.name, self.name)\n\n def get_absolute_url(self):\n return reverse('version-detail', kwargs={\n 'slug': self.slug,\n 'project_slug': self.project.slug\n })\n\n def entries(self):\n \"\"\"Get the entries for this version.\"\"\"\n qs = Entry.objects.filter(version=self).order_by('category')\n return qs\n\n def _entries_for_category(self, category):\n \"\"\"All entries for this version and filtered by the given category.\n\n :param category: Category to filter by.\n :type category: Category\n\n .. note:: only approved entries returned.\n \"\"\"\n qs = Entry.objects.filter(version=self,\n category=category,\n approved=True)\n return qs\n\n def categories(self):\n \"\"\"Get a list of categories where there are one or more entries.\n\n Example use in template::\n {% for row in version.categories %}\n <h2 class=\"text-muted\">{{ row.category.name }}</h2>\n <ul>\n {% for entry in row.entries %}\n <li>{{ entry.name }}</li>\n {% endfor %}\n </ul>\n {% endfor %}\n \"\"\"\n qs = self.entries()\n used = []\n categories = []\n for entry in qs:\n category = entry.category\n if category not in used:\n row = {\n 'category': category,\n 'entries': self._entries_for_category(category)\n }\n categories.append(row)\n used.append(category)\n return categories\n\n def sponsors(self):\n \"\"\"Return a list of sponsors current at time of this version release.\n\n :returns: A list of SponsorPeriod objects whose release date coincides\n with the version release date. Only approved sponsors are returned.\n Returns None if the release date (which is optional) is not set.\n :rtype: Queryset, None\n \"\"\"\n if self.release_date is None:\n return None\n sponsors = SponsorshipPeriod.approved_objects.filter(\n end_date__gte=self.release_date).filter(\n start_date__lte=self.release_date).order_by(\n 'start_date').order_by(\n '-sponsorship_level__value')\n return sponsors\n", "path": "django_project/changes/models/version.py"}], "after_files": [{"content": "# coding=utf-8\nfrom django.core.urlresolvers import reverse\n# from django.utils.text import slugify\nfrom common.utilities import version_slugify\nimport os\nimport logging\nfrom core.settings.contrib import STOP_WORDS\nfrom django.conf.global_settings import MEDIA_ROOT\nfrom django.db import models\nfrom .entry import Entry\nfrom .sponsorship_period import SponsorshipPeriod\nfrom django.contrib.auth.models import User\nfrom django.utils.translation import ugettext_lazy as _\n\nlogger = logging.getLogger(__name__)\n\n\nclass ApprovedVersionManager(models.Manager):\n \"\"\"Custom version manager that shows only approved records.\"\"\"\n\n def get_queryset(self):\n \"\"\"Query set generator\"\"\"\n return super(\n ApprovedVersionManager, self).get_queryset().filter(\n approved=True)\n\n\nclass UnapprovedVersionManager(models.Manager):\n \"\"\"Custom version manager that shows only unapproved records.\"\"\"\n\n def get_queryset(self):\n \"\"\"Query set generator\"\"\"\n return super(\n UnapprovedVersionManager, self).get_queryset().filter(\n approved=False)\n\n\n# noinspection PyUnresolvedReferences\nclass Version(models.Model):\n \"\"\"A version model that the changelog is associated with..\"\"\"\n\n name = models.CharField(\n help_text='Name of this release e.g. 1.0.1.',\n max_length=255,\n null=False,\n blank=False,\n unique=False)\n\n padded_version = models.CharField(\n help_text=(\n 'Numeric version for this release e.g. 001000001 for 1.0.1 '\n 'calculated by zero padding each component of maj/minor/bugfix '\n 'elements from name.'),\n max_length=9,\n null=False,\n blank=True,\n unique=False)\n\n approved = models.BooleanField(\n help_text=(\n 'Whether this version has been approved for use by the '\n 'project owner.'),\n default=False)\n\n image_file = models.ImageField(\n help_text=(\n 'An optional image for this version e.g. a splashscreen. '\n 'Most browsers support dragging the image directly on to the '\n '\"Choose File\" button above.'),\n upload_to=os.path.join(MEDIA_ROOT, 'images/projects'),\n blank=True)\n\n description = models.TextField(\n null=True,\n blank=True,\n help_text='Describe the new version. Markdown is supported.')\n\n release_date = models.DateField(\n _('Release date (yyyy-mm-dd)'),\n help_text='Date of official release',\n null=True,\n blank=True)\n\n author = models.ForeignKey(User)\n slug = models.SlugField()\n project = models.ForeignKey('base.Project')\n objects = models.Manager()\n approved_objects = ApprovedVersionManager()\n unapproved_objects = UnapprovedVersionManager()\n\n # noinspection PyClassicStyleClass\n class Meta:\n \"\"\"Meta options for the version class.\"\"\"\n unique_together = (\n ('name', 'project'),\n ('slug', 'project'),\n )\n app_label = 'changes'\n # ordering = ['-datetime_created']\n\n def save(self, *args, **kwargs):\n if not self.pk:\n words = self.name.split()\n filtered_words = [t for t in words if t.lower() not in STOP_WORDS]\n new_list = ' '.join(filtered_words)\n self.slug = version_slugify(new_list)[:50]\n self.padded_version = self.pad_name(self.name)\n super(Version, self).save(*args, **kwargs)\n\n def pad_name(self, version):\n \"\"\"Create a 0 padded version of the version name.\n\n e.g. input: 2.10.1\n e.g. output: 002010100\n\n This will ensure we have sortable version names.\n\n :param version: A text version in the form 0.0.0 - if the version is\n not in this form, we return the version unaltered.\n :type version: str\n\n :returns: Zero padded representation of the version e.g. 001010100\n :rtype: str\n\n \"\"\"\n tokens = version.split('.')\n if len(tokens) != 3:\n return version\n result = ''\n for token in tokens:\n result += token.zfill(3)\n return result\n\n def __unicode__(self):\n return u'%s : %s' % (self.project.name, self.name)\n\n def get_absolute_url(self):\n return reverse('version-detail', kwargs={\n 'slug': self.slug,\n 'project_slug': self.project.slug\n })\n\n def entries(self):\n \"\"\"Get the entries for this version.\"\"\"\n qs = Entry.objects.filter(version=self).order_by('category')\n return qs\n\n def _entries_for_category(self, category):\n \"\"\"All entries for this version and filtered by the given category.\n\n :param category: Category to filter by.\n :type category: Category\n\n .. note:: only approved entries returned.\n \"\"\"\n qs = Entry.objects.filter(version=self,\n category=category,\n approved=True)\n return qs\n\n def categories(self):\n \"\"\"Get a list of categories where there are one or more entries.\n\n Example use in template::\n {% for row in version.categories %}\n <h2 class=\"text-muted\">{{ row.category.name }}</h2>\n <ul>\n {% for entry in row.entries %}\n <li>{{ entry.name }}</li>\n {% endfor %}\n </ul>\n {% endfor %}\n \"\"\"\n qs = self.entries()\n used = []\n categories = []\n for entry in qs:\n category = entry.category\n if category not in used:\n row = {\n 'category': category,\n 'entries': self._entries_for_category(category)\n }\n categories.append(row)\n used.append(category)\n return categories\n\n def sponsors(self):\n \"\"\"Return a list of sponsors current at time of this version release.\n\n :returns: A list of SponsorPeriod objects for current project\n whose release date coincides with the version release date.\n Only approved sponsors are returned.\n Returns None if the release date (which is optional) is not set.\n :rtype: Queryset, None\n \"\"\"\n if self.release_date is None:\n return None\n sponsors = SponsorshipPeriod.approved_objects.filter(\n end_date__gte=self.release_date).filter(\n start_date__lte=self.release_date).filter(\n project=self.project).order_by(\n 'start_date').order_by(\n '-sponsorship_level__value')\n return sponsors\n", "path": "django_project/changes/models/version.py"}]}
| 2,412 | 268 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.