acecalisto3 commited on
Commit
1538970
·
verified ·
1 Parent(s): 5fad07a

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +8 -8
app.py CHANGED
@@ -181,10 +181,10 @@ class EnhancedURLProcessor:
181
  class EnhancedFileProcessor:
182
  """Advanced file processing with complete content extraction"""
183
 
184
- def __init__(self, max_file_size: int = 5 * 1024 * 1024 * 1024): # 5GB default
185
  self.max_file_size = max_file_size
186
  self.supported_extensions = {
187
- '.txt', '.md', '.csv', '.json', '.xml', '.html', '.htm',
188
  '.log', '.yml', '.yaml', '.ini', '.conf', '.cfg',
189
  '.zip', '.tar', '.gz', '.bz2', '.7z', '.rar',
190
  '.pdf', '.doc', '.docx', '.rtf', '.odt'
@@ -199,7 +199,7 @@ class EnhancedFileProcessor:
199
  try:
200
  file_size = os.path.getsize(file.name)
201
  if file_size > self.max_file_size:
202
- logger.warning(f"File size ({file_size} bytes) exceeds maximum allowed size")
203
  return []
204
 
205
  with tempfile.TemporaryDirectory() as temp_dir:
@@ -212,7 +212,7 @@ class EnhancedFileProcessor:
212
  dataset.extend(self._process_single_file(file))
213
 
214
  except Exception as e:
215
- logger.error(f"Error processing file: {str(e)}")
216
  return []
217
 
218
  return dataset
@@ -263,7 +263,7 @@ class EnhancedFileProcessor:
263
  'timestamp': datetime.now().isoformat()
264
  }]
265
  except Exception as e:
266
- logger.error(f"File processing error: {e}")
267
  return []
268
 
269
  def _process_archive(self, archive_path: str, extract_to: Path) -> List[Dict]:
@@ -284,7 +284,7 @@ class EnhancedFileProcessor:
284
  # TODO: Add support for other archive types (tar, 7z, etc.)
285
 
286
  except Exception as e:
287
- logger.error(f"Archive processing error: {e}")
288
 
289
  return dataset
290
 
@@ -332,7 +332,7 @@ class EnhancedFileProcessor:
332
 
333
  return chunks
334
  except Exception as e:
335
- logger.error(f"Error chunking data: {e}")
336
  return []
337
 
338
  # Calculate number of chunks needed
@@ -357,7 +357,7 @@ class EnhancedFileProcessor:
357
  return chunks
358
 
359
  except Exception as e:
360
- logger.error(f"Error chunking data: {e}")
361
  return []
362
 
363
  def generate_stylish_qr(data: Union[str, Dict],
 
181
  class EnhancedFileProcessor:
182
  """Advanced file processing with complete content extraction"""
183
 
184
+ def __init__(self, max_file_size: int = 5 * 1024 * 1024 * 1024 * 1024 *1024):
185
  self.max_file_size = max_file_size
186
  self.supported_extensions = {
187
+ '.txt', '.md', '.csv', '.json', '.xml', '.html', '.html',
188
  '.log', '.yml', '.yaml', '.ini', '.conf', '.cfg',
189
  '.zip', '.tar', '.gz', '.bz2', '.7z', '.rar',
190
  '.pdf', '.doc', '.docx', '.rtf', '.odt'
 
199
  try:
200
  file_size = os.path.getsize(file.name)
201
  if file_size > self.max_file_size:
202
+ logger.warning(f"File size ({{file_size}} bytes) exceeds maximum allowed size")
203
  return []
204
 
205
  with tempfile.TemporaryDirectory() as temp_dir:
 
212
  dataset.extend(self._process_single_file(file))
213
 
214
  except Exception as e:
215
+ logger.error(f"Error processing file: {{str(e)}}")
216
  return []
217
 
218
  return dataset
 
263
  'timestamp': datetime.now().isoformat()
264
  }]
265
  except Exception as e:
266
+ logger.error(f"File processing error: {{e}}")
267
  return []
268
 
269
  def _process_archive(self, archive_path: str, extract_to: Path) -> List[Dict]:
 
284
  # TODO: Add support for other archive types (tar, 7z, etc.)
285
 
286
  except Exception as e:
287
+ logger.error(f"Archive processing error: {{e}}")
288
 
289
  return dataset
290
 
 
332
 
333
  return chunks
334
  except Exception as e:
335
+ logger.error(f"Error chunking data: {{e}}")
336
  return []
337
 
338
  # Calculate number of chunks needed
 
357
  return chunks
358
 
359
  except Exception as e:
360
+ logger.error(f"Error chunking data: {{e}}")
361
  return []
362
 
363
  def generate_stylish_qr(data: Union[str, Dict],