Synced repo using 'sync_with_huggingface' Github Action

.editorconfig

@@ -0,0 +1,25 @@
+# see http://editorconfig.org
+
+# Top-level config
+root = true
+
+
+# All files
+[*]
+charset = utf-8
+indent_style = space
+indent_size = 4
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+max_line_length = 100
+
+
+# YAML files
+[*.{yml,yaml}]
+indent_size = 2
+
+
+# Windows scripts
+[*.{bat,cmd,ps1}]
+end_of_line = crlf

app.py

@@ -46,7 +46,7 @@ def generate_iscc(file):
         thumbnail = Image.open(io.BytesIO(data))
     metadata = imeta.dict(exclude_unset=False, by_alias=True)
     if metadata.get("thumbnail"):
-        del metadata['thumbnail']
+        del metadata["thumbnail"]
     return imeta.iscc, thumbnail, metadata
 
 
@@ -72,31 +72,48 @@ def generate_text_code(text, chunk_size):
         end = start + size
         chunks.append(no_nl(cleaned[start:end]))
         start = end
-    result = [(chunk, f"{size}:{feat}") for chunk, size, feat in zip(chunks, sizes, features)]
+    result = [
+        (chunk, f"{size}:{feat}") for chunk, size, feat in zip(chunks, sizes, features)
+    ]
     idk.sdk_opts.text_avg_chunk_size = original_chunk_size
     return result
 
 
-with gr.Blocks(title="ISCC-CODE") as demo_generate:
-    gr.Markdown("""
+####################################################################################################
+# TAB ISCC-CODE                                                                                    #
+####################################################################################################
+
+with gr.Blocks() as demo_generate:
+    gr.Markdown(
+        """
     ## 🌟 ISCC-CODE Generator - The DNA of digital content
-    """)
+    """
+    )
     with gr.Row():
         with gr.Column(scale=2):
             in_file = gr.File(label="Media File")
         with gr.Column(scale=1):
-            out_thumbnail = gr.Image(label="Extracted Thumbnail", elem_classes=["fixed-height"])
+            out_thumbnail = gr.Image(
+                label="Extracted Thumbnail", elem_classes=["fixed-height"]
+            )
     with gr.Row():
         out_iscc = gr.Text(label="ISCC-CODE", show_copy_button=True)
     with gr.Row():
         out_meta = gr.Json(label="Metadata")
-    in_file.change(generate_iscc, inputs=[in_file], outputs=[out_iscc, out_thumbnail, out_meta])
+    in_file.change(
+        generate_iscc, inputs=[in_file], outputs=[out_iscc, out_thumbnail, out_meta]
+    )
 
+####################################################################################################
+# TAB ENCODING                                                                                     #
+####################################################################################################
 
-with gr.Blocks("ENCODING") as demo_decode:
-    gr.Markdown("""
+with gr.Blocks() as demo_decode:
+    gr.Markdown(
+        """
     ## 🌟 A Codec for Self-Describing Compact Binary Codes
-    """)
+    """
+    )
     with gr.Row():
         with gr.Column():
             in_iscc = gr.Text(
@@ -139,40 +156,57 @@ with gr.Blocks("ENCODING") as demo_decode:
                 info="BASE58-BTC",
                 show_copy_button=True,
             )
-    in_iscc.change(explain_iscc, inputs=[in_iscc], outputs=[
-        out_canonical,
-        out_human,
-        out_decomposed,
-        out_multiformat,
-    ])
-
-with gr.Blocks(title="CHUNKING") as demo_text_code:
-    gr.Markdown("""
+    in_iscc.change(
+        explain_iscc,
+        inputs=[in_iscc],
+        outputs=[
+            out_canonical,
+            out_human,
+            out_decomposed,
+            out_multiformat,
+        ],
+    )
+
+####################################################################################################
+# CHUNKING                                                                                         #
+####################################################################################################
+
+with gr.Blocks() as demo_chunking:
+    gr.Markdown(
+        """
     ## 🌟 Content Defined Chunking for Shift-Resistant Text and Data Segmentation
-    """)
+    """
+    )
     with gr.Row():
         with gr.Column():
             in_text = gr.Textbox(label="Text Input", lines=8, autofocus=True)
             in_chunksize = gr.Slider(
                 label="Chunk Size",
                 info="AVERAGE NUMBER OF CHARACTERS PER CHUNK",
-                minimum=32, maximum=2048, step=32,
-                value=64)
+                minimum=32,
+                maximum=2048,
+                step=32,
+                value=64,
+            )
 
         out_text = gr.HighlightedText(
             label="Chunked Text Output",
             interactive=False,
             elem_id="chunked-text",
         )
-    in_text.change(generate_text_code, inputs=[in_text, in_chunksize], outputs=[out_text])
-    in_chunksize.change(generate_text_code, inputs=[in_text, in_chunksize], outputs=[out_text])
+    in_text.change(
+        generate_text_code, inputs=[in_text, in_chunksize], outputs=[out_text]
+    )
+    in_chunksize.change(
+        generate_text_code, inputs=[in_text, in_chunksize], outputs=[out_text]
+    )
 
 demo = gr.TabbedInterface(
     title="▶️ ISCC Playground",
-    interface_list=[demo_generate, demo_decode, demo_text_code],
+    interface_list=[demo_generate, demo_decode, demo_chunking],
     tab_names=["ISCC-CODE", "ENCODING", "CHUNKING"],
     css=custom_css,
 )
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     demo.launch()

poetry.lock

@@ -232,6 +232,52 @@ files = [
     {file = "bitarray-2.9.2.tar.gz", hash = "sha256:a8f286a51a32323715d77755ed959f94bef13972e9a2fe71b609e40e6d27957e"},
 ]
 
+[[package]]
+name = "black"
+version = "23.12.1"
+description = "The uncompromising code formatter."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "black-23.12.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e0aaf6041986767a5e0ce663c7a2f0e9eaf21e6ff87a5f95cbf3675bfd4c41d2"},
+    {file = "black-23.12.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c88b3711d12905b74206227109272673edce0cb29f27e1385f33b0163c414bba"},
+    {file = "black-23.12.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a920b569dc6b3472513ba6ddea21f440d4b4c699494d2e972a1753cdc25df7b0"},
+    {file = "black-23.12.1-cp310-cp310-win_amd64.whl", hash = "sha256:3fa4be75ef2a6b96ea8d92b1587dd8cb3a35c7e3d51f0738ced0781c3aa3a5a3"},
+    {file = "black-23.12.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8d4df77958a622f9b5a4c96edb4b8c0034f8434032ab11077ec6c56ae9f384ba"},
+    {file = "black-23.12.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:602cfb1196dc692424c70b6507593a2b29aac0547c1be9a1d1365f0d964c353b"},
+    {file = "black-23.12.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9c4352800f14be5b4864016882cdba10755bd50805c95f728011bcb47a4afd59"},
+    {file = "black-23.12.1-cp311-cp311-win_amd64.whl", hash = "sha256:0808494f2b2df923ffc5723ed3c7b096bd76341f6213989759287611e9837d50"},
+    {file = "black-23.12.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:25e57fd232a6d6ff3f4478a6fd0580838e47c93c83eaf1ccc92d4faf27112c4e"},
+    {file = "black-23.12.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2d9e13db441c509a3763a7a3d9a49ccc1b4e974a47be4e08ade2a228876500ec"},
+    {file = "black-23.12.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d1bd9c210f8b109b1762ec9fd36592fdd528485aadb3f5849b2740ef17e674e"},
+    {file = "black-23.12.1-cp312-cp312-win_amd64.whl", hash = "sha256:ae76c22bde5cbb6bfd211ec343ded2163bba7883c7bc77f6b756a1049436fbb9"},
+    {file = "black-23.12.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1fa88a0f74e50e4487477bc0bb900c6781dbddfdfa32691e780bf854c3b4a47f"},
+    {file = "black-23.12.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a4d6a9668e45ad99d2f8ec70d5c8c04ef4f32f648ef39048d010b0689832ec6d"},
+    {file = "black-23.12.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b18fb2ae6c4bb63eebe5be6bd869ba2f14fd0259bda7d18a46b764d8fb86298a"},
+    {file = "black-23.12.1-cp38-cp38-win_amd64.whl", hash = "sha256:c04b6d9d20e9c13f43eee8ea87d44156b8505ca8a3c878773f68b4e4812a421e"},
+    {file = "black-23.12.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3e1b38b3135fd4c025c28c55ddfc236b05af657828a8a6abe5deec419a0b7055"},
+    {file = "black-23.12.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4f0031eaa7b921db76decd73636ef3a12c942ed367d8c3841a0739412b260a54"},
+    {file = "black-23.12.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97e56155c6b737854e60a9ab1c598ff2533d57e7506d97af5481141671abf3ea"},
+    {file = "black-23.12.1-cp39-cp39-win_amd64.whl", hash = "sha256:dd15245c8b68fe2b6bd0f32c1556509d11bb33aec9b5d0866dd8e2ed3dba09c2"},
+    {file = "black-23.12.1-py3-none-any.whl", hash = "sha256:78baad24af0f033958cad29731e27363183e140962595def56423e626f4bee3e"},
+    {file = "black-23.12.1.tar.gz", hash = "sha256:4ce3ef14ebe8d9509188014d96af1c456a910d5b5cbf434a09fef7e024b3d0d5"},
+]
+
+[package.dependencies]
+click = ">=8.0.0"
+mypy-extensions = ">=0.4.3"
+packaging = ">=22.0"
+pathspec = ">=0.9.0"
+platformdirs = ">=2"
+tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
+typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+colorama = ["colorama (>=0.4.3)"]
+d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
+jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
+uvloop = ["uvloop (>=0.15.2)"]
+
 [[package]]
 name = "blake3"
 version = "0.3.4"
@@ -1470,6 +1516,17 @@ files = [
     {file = "more_itertools-10.2.0-py3-none-any.whl", hash = "sha256:686b06abe565edfab151cb8fd385a05651e1fdf8f0a14191e4439283421f8684"},
 ]
 
+[[package]]
+name = "mypy-extensions"
+version = "1.0.0"
+description = "Type system extensions for programs checked with the mypy type checker."
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"},
+    {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
+]
+
 [[package]]
 name = "numpy"
 version = "1.26.3"
@@ -1657,6 +1714,17 @@ sql-other = ["SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "adbc-d
 test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)"]
 xml = ["lxml (>=4.9.2)"]
 
+[[package]]
+name = "pathspec"
+version = "0.12.1"
+description = "Utility library for gitignore style pattern matching of file paths."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08"},
+    {file = "pathspec-0.12.1.tar.gz", hash = "sha256:a482d51503a1ab33b1c67a6c3813a26953dbdc71c31dacaef9a838c4e29f5712"},
+]
+
 [[package]]
 name = "pillow"
 version = "10.2.0"
@@ -2688,6 +2756,17 @@ typing-extensions = {version = ">=3.10.0", markers = "python_version < \"3.10\""
 [package.extras]
 full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart", "pyyaml"]
 
+[[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
+    {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
+]
+
 [[package]]
 name = "tomlkit"
 version = "0.12.0"
@@ -3050,4 +3129,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "7c4666b5f04855126c0fbd9dc39c1b52b3ca2551d338100033f52bb811f46ae7"
+content-hash = "003507cb038ece514b8afaf4896b719885450817f0a63852ab74a09357be2894"

pyproject.toml

@@ -11,6 +11,9 @@ python = "^3.9"
 gradio = "^4.12.0"
 iscc-sdk = "^0.6.0"
 
+[tool.poetry.group.dev.dependencies]
+black = "^23.12.1"
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"