chore: update Hugging Face sync action and add line ending conversion…

… script

.github/workflows/huggingface.yml

@@ -1,4 +1,4 @@
-name: Publish on Hugging Face Hub
+name: Sync with Hugging Face Space
 on:
   push:
     branches:
@@ -7,12 +7,12 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - name: Sync with Hugging Face
-      uses: nateraw/huggingface-sync-action@v0.0.5
+    - name: Sync with HF
+      uses: alex-bene/huggingface-space-sync-action@v0.1
       with:
-        github_repo_id: iscc/iscc-sct
-        huggingface_repo_id: iscc/iscc-sct
-        repo_type: space
-        space_sdk: gradio
-        private: false
+        github_repo_id: 'iscc/iscc-sct'
+        github_branch: 'huggingface'
+        yaml_header_path: 'space.yml'
+        huggingface_repo_id: 'iscc/iscc-sct'
+        hf_username: 'titusz'
         hf_token: ${{ secrets.HF_TOKEN }}

README.md

@@ -1,15 +1,3 @@
----
-title: ISCC-LAB - Semantic-Code Text
-emoji: ▶️
-colorFrom: red
-colorTo: blue
-sdk: gradio
-sdk_version: 4.41.0
-pinned: true
-license: CC-BY-NC-SA-4.0
-short_description: Cross Lingual Similarity Preserving Text Simprints
----
-
 # ISCC - Semantic Text-Code
 
 [![Tests](https://github.com/iscc/iscc-sct/actions/workflows/tests.yml/badge.svg)](https://github.com/iscc/iscc-core/actions/workflows/tests.yml)
@@ -188,9 +176,5 @@ simprints based on larger chunks of text.
 ## Acknowledgements
 
 - Text Chunking: [text-splitter](https://github.com/benbrandt/text-splitter)
-- Text Embedding:
-  [Sentence-Transformer](https://www.sbert.net/docs/sentence_transformer/pretrained_models.html#original-models)
-
-## License
-
-This project is licensed under the CC-BY-NC-SA-4.0 International License.
+- Text Embeddings:
+  [Sentence-Transformers](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)

iscc_sct/dev.py

@@ -0,0 +1,22 @@
+import pathlib
+
+
+HERE = pathlib.Path(__file__).parent.absolute()
+
+
+def convert_lf():  # pragma: no cover
+    """Convert line endings to LF"""
+    crlf = b"\r\n"
+    lf = b"\n"
+    extensions = {".py", ".toml", ".lock", ".txt", ".yml", ".sh", ".md"}
+    n = 0
+    for fp in HERE.parent.glob("**/*"):
+        if fp.suffix in extensions:
+            with open(fp, "rb") as infile:
+                content = infile.read()
+            if crlf in content:
+                content = content.replace(crlf, lf)
+                with open(fp, "wb") as outfile:
+                    outfile.write(content)
+                n += 1
+    print(f"{n} files converted to LF")

pyproject.toml

@@ -84,11 +84,17 @@ line-length = 119
 [tool.ruff.format]
 line-ending = "lf"
 
+[tool.coverage.run]
+omit = ["iscc_sct/dev.py", "tests/"]
+
 [tool.poe.tasks]
 format-code = { cmd = "ruff format", help = "Code style formating with ruff" }
 format-markdown = { cmd = "mdformat --wrap 119 --end-of-line lf README.md", help = "Markdown formating with mdformat" }
-test = { cmd = "pytest --cov=iscc_sct --cov-fail-under=100 --cov-report=term-missing --color=yes", help = "Run tests with coverage" }
-all = ["format-code", "format-markdown", "test"]
+convert-lf = { script = "iscc_sct.dev:convert_lf", help = "Convert line endings to LF"}
+test = { cmd = "pytest --cov=iscc_sct --cov-fail-under=100", help = "Run tests with coverage" }
+update-dependencies = { cmd = "poetry update", help = "Update dependencies" }
+all = ["format-code", "format-markdown", "convert-lf", "test"]
+update = ["update-dependencies", "all"]
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

space.yml

@@ -0,0 +1,9 @@
+title: ISCC-LAB - Semantic-Code Text
+emoji: ▶️
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 4.41.0
+pinned: true
+license: CC-BY-NC-SA-4.0
+short_description: Cross Lingual Similarity Preserving Text Simprints