Synced repo using 'sync_with_huggingface' Github Action

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

@@ -4,40 +4,6 @@ colorFrom: red
 colorTo: blue
 sdk: gradio
 sdk_version: 4.41.0
-app_file: ./iscc_sct/demo.py
 pinned: true
 license: CC-BY-NC-SA-4.0
 short_description: Cross Lingual Similarity Preserving Text Simprints
-description: >
-  # ISCC-LAB - Semantic-Code Text
-
-  `iscc-sct` is a **proof of concept implementation** of a semantic Text-Code for the
-  [ISCC](https://core.iscc.codes) (*International Standard Content Code*). Semantic Text-Codes are
-  short identifiers created from text documents that preserve similarity (in hamming distance)
-  for semantically similar cross-lingual text inputs.
-
-  ## What is the ISCC
-
-  The ISCC is a combination of various similarity preserving fingerprints and an identifier for
-  digital media content.
-
-  ISCCs are generated algorithmically from digital content, just like cryptographic hashes. However,
-  instead of using a single cryptographic hash function to identify data only, the ISCC uses various
-  algorithms to create a composite identifier that exhibits similarity-preserving properties (soft
-  hash or Simprint).
-
-  The component-based structure of the ISCC identifies content at multiple levels of abstraction. Each
-  component is self-describing, modular, and can be used separately or with others to aid in various
-  content identification tasks. The algorithmic design supports content deduplication, database
-  synchronization, indexing, integrity verification, timestamping, versioning, data provenance,
-  similarity clustering, anomaly detection, usage tracking, allocation of royalties, fact-checking and
-  general digital asset management use-cases.
-
-
-  ## ISCC Status
-
-  The [ISCC](https://iscc.codes) is an ISO Standrad published under
-  [ISO 24138:2024](https://www.iso.org/standard/77899.html) - International Standard Content Code
-  within [ISO/TC 46/SC 9/WG 18](https://www.iso.org/committee/48836.html).
-
-  The algorithms of this `iscc-sct` are experimental and not (yet) part of the official standard.