pyannotators-entityfishing 1.6.28__tar.gz → 1.6.34__tar.gz

{pyannotators_entityfishing-1.6.28 → pyannotators_entityfishing-1.6.34}/.gitignore

@@ -28,6 +28,8 @@ share/python-wheels/
 MANIFEST
 
 # PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
 *.spec
 
@@ -83,6 +85,13 @@ ipython_config.py
 # pyenv
 .python-version
 
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
 # celery beat schedule file
 celerybeat-schedule
 

{pyannotators_entityfishing-1.6.28 → pyannotators_entityfishing-1.6.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyannotators-entityfishing
-Version: 1.6.28
+Version: 1.6.34
 Summary: Annotator based on entity-fishing
 Project-URL: Homepage, https://github.com/oterrier/pyannotators_entityfishing/
 Author-email: Olivier Terrier <olivier.terrier@kairntech.com>
@@ -20,7 +20,7 @@ Requires-Python: >=3.12
 Requires-Dist: collections-extended
 Requires-Dist: mongoquery
 Requires-Dist: pydantic<3.0,>=2.0
-Requires-Dist: pymultirole-plugins<0.7.0,>=0.6.0
+Requires-Dist: pymultirole-plugins<1.7.0,>=1.6.0
 Requires-Dist: python-singleton-metaclasses
 Requires-Dist: requests
 Requires-Dist: requests-cache
@@ -29,13 +29,14 @@ Provides-Extra: dev
 Requires-Dist: bump2version; extra == 'dev'
 Requires-Dist: pre-commit; extra == 'dev'
 Provides-Extra: docs
-Requires-Dist: jupyter-sphinx; extra == 'docs'
 Requires-Dist: lxml-html-clean; extra == 'docs'
 Requires-Dist: m2r2; extra == 'docs'
-Requires-Dist: nbconvert>=7.17.0; extra == 'docs'
 Requires-Dist: sphinx; extra == 'docs'
 Requires-Dist: sphinx-rtd-theme; extra == 'docs'
 Requires-Dist: sphinxcontrib-apidoc; extra == 'docs'
+Provides-Extra: sbom
+Requires-Dist: cyclonedx-bom; extra == 'sbom'
+Requires-Dist: pip-audit; extra == 'sbom'
 Provides-Extra: spacy
 Requires-Dist: spacy>=3.0; extra == 'spacy'
 Provides-Extra: test
@@ -109,3 +110,29 @@ uv run pytest
 ```bash
 uv run pytest --cov=src --cov-report=term-missing
 ```
+
+## SBOM & vulnerability check
+
+Install the SBOM dependencies:
+
+```
+uv sync --extra sbom
+```
+
+Generate a CycloneDX SBOM from the current environment:
+
+```
+uv run cyclonedx-py environment -o sbom.cdx.json --output-format json
+```
+
+Audit dependencies for known vulnerabilities:
+
+```
+uv run pip-audit --format json --output audit-report.json
+```
+
+To fail on any known vulnerability (useful in CI):
+
+```
+uv run pip-audit --strict
+```

{pyannotators_entityfishing-1.6.28 → pyannotators_entityfishing-1.6.34}/README.md

@@ -62,3 +62,29 @@ uv run pytest
 ```bash
 uv run pytest --cov=src --cov-report=term-missing
 ```
+
+## SBOM & vulnerability check
+
+Install the SBOM dependencies:
+
+```
+uv sync --extra sbom
+```
+
+Generate a CycloneDX SBOM from the current environment:
+
+```
+uv run cyclonedx-py environment -o sbom.cdx.json --output-format json
+```
+
+Audit dependencies for known vulnerabilities:
+
+```
+uv run pip-audit --format json --output audit-report.json
+```
+
+To fail on any known vulnerability (useful in CI):
+
+```
+uv run pip-audit --strict
+```

{pyannotators_entityfishing-1.6.28 → pyannotators_entityfishing-1.6.34}/pyproject.toml

@@ -28,7 +28,7 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
 ]
 dependencies = [
-    "pymultirole-plugins>=0.6.0,<0.7.0",
+    "pymultirole-plugins>=1.6.0,<1.7.0",
     "pydantic>=2.0,<3.0",
     "requests",
     "requests-cache",
@@ -59,8 +59,6 @@ docs = [
     "sphinx-rtd-theme",
     "m2r2",
     "sphinxcontrib.apidoc",
-    "jupyter_sphinx",
-    "nbconvert>=7.17.0",
     "lxml_html_clean",
 ]
 dev = [
@@ -68,12 +66,29 @@ dev = [
     "bump2version",
 ]
 
+sbom = ["cyclonedx-bom", "pip-audit"]
+
 [tool.hatch.version]
 path = "src/pyannotators_entityfishing/__init__.py"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/pyannotators_entityfishing"]
 
+[tool.hatch.build]
+exclude = [
+  "/tests",
+  "/docs",
+  "Jenkinsfile",
+  "Dockerfile",
+  "bumpversion.py",
+  "mypy.ini",
+  "hgnc_cache.sqlite",
+  "trivy-html-template.tpl",
+  "MIGRATION.md",
+  ".gitignore",
+  ".dockerignore"
+]
+
 [tool.pytest.ini_options]
 addopts = "--durations=5"
 norecursedirs = ["docs"]

{pyannotators_entityfishing-1.6.28 → pyannotators_entityfishing-1.6.34}/src/pyannotators_entityfishing/__init__.py

@@ -1,3 +1,3 @@
 """Annotator based on entity-fishing"""
 
-__version__ = "1.6.28"
+__version__ = "1.6.34"

{pyannotators_entityfishing-1.6.28 → pyannotators_entityfishing-1.6.34}/src/pyannotators_entityfishing/entityfishing.py

@@ -148,12 +148,12 @@ def _enrich_concepts_with_properties(concepts: dict, wiki_props: list[str], mult
     """Enrich concept dicts with extracted wikidata_properties."""
     for concept in concepts.values():
         if concept is not None and "statements" in concept:
-            fingerprint = defaultdict(list)
+            fingerprint = defaultdict(set)
             for wp in wiki_props:
-                fingerprint[wp] = []
+                fingerprint[wp] = set()
             for st in concept["statements"]:
                 if st["propertyId"] in wiki_props:
-                    fingerprint[st["propertyId"]].append(st["value"])
+                    fingerprint[st["propertyId"]].add(st["value"])
             if sum(len(v) for v in fingerprint.values()) > 0:
                 concept["wikidata_properties"] = dict(fingerprint)
 
@@ -184,7 +184,7 @@ def _build_annotation(entity: dict, label: str, concept: dict | None, lang: str,
         if fingerprints:
             fp_parts = []
             for f in fingerprints:
-                fvals = concept["wikidata_properties"].get(f, [])
+                fvals = list(concept["wikidata_properties"].get(f, []))
                 if fvals:
                     fingers = [f"{f}:{v}" for v in sorted(fvals) if isinstance(v, str)]
                     if multivalued_props:
@@ -194,7 +194,7 @@ def _build_annotation(entity: dict, label: str, concept: dict | None, lang: str,
             ann_term.properties["fingerprint"] = ",".join(fp_parts)
         if wikidata_properties:
             for wp in wikidata_properties:
-                fvals = concept["wikidata_properties"].get(wp, [])
+                fvals = list(concept["wikidata_properties"].get(wp, []))
                 if len(fvals) == 1:
                     ann_term.properties[wp] = fvals[0]
                 elif len(fvals) > 1:

pyannotators_entityfishing-1.6.28/Dockerfile

@@ -1,18 +0,0 @@
-FROM python:3.12-slim-bookworm
-# Install prerequisites
-RUN apt-get update -y && \
-    apt-get install -y \
-    gcc && \
-    apt-get install -y --no-install-recommends \
-    g++ \
-    git && \
-# Final upgrade + clean
-    apt-get update -y && \
-    apt-get clean all -y
-
-# Install uv
-RUN pip install uv
-
-# Add pyproject.toml + README.md for uv install
-ADD pyproject.toml pyproject.toml
-ADD README.md README.md