pyprocessors-metadata_from_categories 1.6.1__tar.gz

pyprocessors_metadata_from_categories-1.6.1/.gitignore

@@ -0,0 +1,137 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+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
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+results.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+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
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Specific
+.idea/
+.groovylintrc.json
+.emailNotif
+uv.lock
+
+# SBOMs
+**/sbom*.json
+**/trivy*.html
+**/audit*.json

pyprocessors_metadata_from_categories-1.6.1/AUTHORS.md

@@ -0,0 +1,5 @@
+# Authors
+
+Contributors to pyprocessors_metadata_from_categories include:
+
++ [Olivier Terrier](mailto:olivier.terrier@kairntech.com)

pyprocessors_metadata_from_categories-1.6.1/CHANGELOG.md

@@ -0,0 +1,7 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [unreleased]

pyprocessors_metadata_from_categories-1.6.1/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2021 Olivier Terrier
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

pyprocessors_metadata_from_categories-1.6.1/PKG-INFO

@@ -0,0 +1,173 @@
+Metadata-Version: 2.4
+Name: pyprocessors-metadata_from_categories
+Version: 1.6.1
+Summary: Sherpa transform annotations to categories processor
+Project-URL: Homepage, https://github.com/oterrier/pyprocessors_metadata_from_categories/
+Author-email: Olivier Terrier <olivier.terrier@kairntech.com>
+License: The MIT License (MIT)
+        
+        Copyright (c) 2021 Olivier Terrier
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in
+        all copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+        THE SOFTWARE.
+License-File: AUTHORS.md
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: System Administrators
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.12
+Requires-Dist: collections-extended
+Requires-Dist: log-with-context
+Requires-Dist: openpyxl
+Requires-Dist: pandas
+Requires-Dist: pymultirole-plugins<1.7.0,>=1.6.0
+Provides-Extra: dev
+Requires-Dist: bump2version; extra == 'dev'
+Requires-Dist: pre-commit; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: lxml-html-clean; extra == 'docs'
+Requires-Dist: m2r2; 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: test
+Requires-Dist: dirty-equals; extra == 'test'
+Requires-Dist: pip; extra == 'test'
+Requires-Dist: pytest; extra == 'test'
+Requires-Dist: pytest-cov; extra == 'test'
+Requires-Dist: ruff; extra == 'test'
+Description-Content-Type: text/markdown
+
+# pyprocessors_metadata_from_categories
+
+[![license](https://img.shields.io/github/license/oterrier/pyprocessors_metadata_from_categories)](https://github.com/oterrier/pyprocessors_metadata_from_categories/blob/master/LICENSE)
+[![tests](https://github.com/oterrier/pyprocessors_metadata_from_categories/workflows/tests/badge.svg)](https://github.com/oterrier/pyprocessors_metadata_from_categories/actions?query=workflow%3Atests)
+[![codecov](https://img.shields.io/codecov/c/github/oterrier/pyprocessors_metadata_from_categories)](https://codecov.io/gh/oterrier/pyprocessors_metadata_from_categories)
+[![docs](https://img.shields.io/readthedocs/pyprocessors_metadata_from_categories)](https://pyprocessors_metadata_from_categories.readthedocs.io)
+[![version](https://img.shields.io/pypi/v/pyprocessors_metadata_from_categories)](https://pypi.org/project/pyprocessors_metadata_from_categories/)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/pyprocessors_metadata_from_categories)](https://pypi.org/project/pyprocessors_metadata_from_categories/)
+
+Turn the categories carried by a document into a metadata value.
+
+## How it works
+
+For every input document the processor converts its categories into a metadata
+entry and then clears the categories. Conversion happens **systematically at both
+levels**:
+
+- **Document level** — the document's categories are turned into
+  `document.metadata[metadata_name]`, then `document.categories` is cleared.
+- **Segment level** — the same conversion is applied to each sentence: its
+  categories become `sentence.metadata[metadata_name]`, then the sentence's
+  categories are cleared.
+
+For a given set of categories, only those whose `score` is greater than or equal
+to `multi_label_threshold` are kept, and the resulting metadata value is:
+
+- `None` (the metadata key is removed) when no category passes the threshold,
+- a single value when exactly one category passes,
+- a list of values when several categories pass.
+
+### Parameters
+
+| Parameter               | Default | Description                                                                 |
+| ----------------------- | ------- | --------------------------------------------------------------------------- |
+| `metadata_name`         | `None`  | Name of the generated metadata key.                                         |
+| `multi_label_threshold` | `0.0`   | Only categories with a score greater than or equal to this value are kept.  |
+
+## Installation
+
+You can simply `pip install pyprocessors_metadata_from_categories`.
+
+## Developing
+
+### Pre-requesites
+
+You will need to install `uv` (for managing the virtual environment and running tests):
+
+```
+pip install uv
+```
+
+Clone the repository:
+
+```
+git clone https://github.com/oterrier/pyprocessors_metadata_from_categories
+```
+
+### Running the test suite
+
+You can run the full test suite with:
+
+```
+uv run pytest
+```
+
+### Linting
+
+```
+uv run ruff check .
+uv run ruff format --check .
+```
+
+### Building the documentation
+
+You can build the HTML documentation with:
+
+```
+uv run --extra docs sphinx-build docs docs/_build
+```
+
+The built documentation is available at `docs/_build/index.html`.
+
+## 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
+```

pyprocessors_metadata_from_categories-1.6.1/README.md

@@ -0,0 +1,107 @@
+# pyprocessors_metadata_from_categories
+
+[![license](https://img.shields.io/github/license/oterrier/pyprocessors_metadata_from_categories)](https://github.com/oterrier/pyprocessors_metadata_from_categories/blob/master/LICENSE)
+[![tests](https://github.com/oterrier/pyprocessors_metadata_from_categories/workflows/tests/badge.svg)](https://github.com/oterrier/pyprocessors_metadata_from_categories/actions?query=workflow%3Atests)
+[![codecov](https://img.shields.io/codecov/c/github/oterrier/pyprocessors_metadata_from_categories)](https://codecov.io/gh/oterrier/pyprocessors_metadata_from_categories)
+[![docs](https://img.shields.io/readthedocs/pyprocessors_metadata_from_categories)](https://pyprocessors_metadata_from_categories.readthedocs.io)
+[![version](https://img.shields.io/pypi/v/pyprocessors_metadata_from_categories)](https://pypi.org/project/pyprocessors_metadata_from_categories/)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/pyprocessors_metadata_from_categories)](https://pypi.org/project/pyprocessors_metadata_from_categories/)
+
+Turn the categories carried by a document into a metadata value.
+
+## How it works
+
+For every input document the processor converts its categories into a metadata
+entry and then clears the categories. Conversion happens **systematically at both
+levels**:
+
+- **Document level** — the document's categories are turned into
+  `document.metadata[metadata_name]`, then `document.categories` is cleared.
+- **Segment level** — the same conversion is applied to each sentence: its
+  categories become `sentence.metadata[metadata_name]`, then the sentence's
+  categories are cleared.
+
+For a given set of categories, only those whose `score` is greater than or equal
+to `multi_label_threshold` are kept, and the resulting metadata value is:
+
+- `None` (the metadata key is removed) when no category passes the threshold,
+- a single value when exactly one category passes,
+- a list of values when several categories pass.
+
+### Parameters
+
+| Parameter               | Default | Description                                                                 |
+| ----------------------- | ------- | --------------------------------------------------------------------------- |
+| `metadata_name`         | `None`  | Name of the generated metadata key.                                         |
+| `multi_label_threshold` | `0.0`   | Only categories with a score greater than or equal to this value are kept.  |
+
+## Installation
+
+You can simply `pip install pyprocessors_metadata_from_categories`.
+
+## Developing
+
+### Pre-requesites
+
+You will need to install `uv` (for managing the virtual environment and running tests):
+
+```
+pip install uv
+```
+
+Clone the repository:
+
+```
+git clone https://github.com/oterrier/pyprocessors_metadata_from_categories
+```
+
+### Running the test suite
+
+You can run the full test suite with:
+
+```
+uv run pytest
+```
+
+### Linting
+
+```
+uv run ruff check .
+uv run ruff format --check .
+```
+
+### Building the documentation
+
+You can build the HTML documentation with:
+
+```
+uv run --extra docs sphinx-build docs docs/_build
+```
+
+The built documentation is available at `docs/_build/index.html`.
+
+## 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
+```

pyprocessors_metadata_from_categories-1.6.1/RELEASE.md

@@ -0,0 +1,39 @@
+# Release Instructions
+
+This document guides a contributor through creating a release of pyprocessors_metadata_from_categories.
+
+## Preflight checks
+
+### Ensure all tests pass
+
+Locally you can run `tox` to check that all tests pass, and check that tests
+against all supported environments are passing also by checking qsim's
+[GitHub actions](https://github.com/oterrier/pyprocessors_metadata_from_categories/actions?query=branch%3Amaster+workflow%3Atests).
+
+#### Verify that `AUTHORS.md` is up-to-date
+
+The following command shows the number of commits per author since the last
+annotated tag:
+```
+t=$(git describe --abbrev=0); echo Commits since $t; git shortlog -s $t..
+```
+
+## Make the release
+
+Run
+
+```
+bumpversion release  # bump version from .devX to release version
+git push --tags      # push tagged release to upstream
+flit publish         # publish to PyPI
+```
+
+## Start work on the next release
+
+Run
+
+```
+bumpversion minor
+```
+
+To start work on the next release

pyprocessors_metadata_from_categories-1.6.1/pyproject.toml

@@ -0,0 +1,100 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "pyprocessors-metadata_from_categories"
+dynamic = ["version"]
+description = "Sherpa transform annotations to categories processor"
+readme = "README.md"
+license = {file = "LICENSE"}
+authors = [
+    {name = "Olivier Terrier", email = "olivier.terrier@kairntech.com"},
+]
+keywords = []
+classifiers = [
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Developers",
+    "Intended Audience :: System Administrators",
+    "Operating System :: OS Independent",
+    "Topic :: Software Development :: Libraries :: Application Frameworks",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Software Development",
+    "License :: OSI Approved :: MIT License",
+    "Development Status :: 4 - Beta",
+    "Programming Language :: Python :: 3.12",
+]
+requires-python = ">=3.12"
+dependencies = [
+    "pymultirole-plugins>=1.6.0,<1.7.0",
+    "collections-extended",
+    "pandas",
+    "openpyxl",
+    "log-with-context",
+]
+
+[project.urls]
+Homepage = "https://github.com/oterrier/pyprocessors_metadata_from_categories/"
+
+[project.entry-points."pyprocessors.plugins"]
+metadata_from_categories = "pyprocessors_metadata_from_categories.metadata_from_categories:MetadataFromCategoriesProcessor"
+
+[project.optional-dependencies]
+test = [
+    "pytest",
+    "pytest-cov",
+    "ruff",
+    "pip",
+    "dirty-equals",
+]
+docs = [
+    "sphinx",
+    "sphinx-rtd-theme",
+    "m2r2",
+    "sphinxcontrib.apidoc",
+    "lxml_html_clean",
+]
+dev = [
+    "pre-commit",
+    "bump2version",
+]
+
+sbom = ["cyclonedx-bom", "pip-audit"]
+
+[tool.hatch.version]
+path = "src/pyprocessors_metadata_from_categories/__init__.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/pyprocessors_metadata_from_categories"]
+
+[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"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "W", "F", "I", "B", "C4", "UP", "ARG", "SIM"]
+ignore = ["E501"]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"

pyprocessors_metadata_from_categories-1.6.1/src/pyprocessors_metadata_from_categories/__init__.py

@@ -0,0 +1,3 @@
+"""Sherpa transform labels to metadata"""
+
+__version__ = "1.6.1"

pyprocessors_metadata_from_categories-1.6.1/src/pyprocessors_metadata_from_categories/metadata_from_categories.py

@@ -0,0 +1,56 @@
+from typing import cast
+
+from log_with_context import Logger, add_logging_context
+from pydantic import BaseModel, Field
+from pymultirole_plugins.v1.processor import ProcessorBase, ProcessorParameters
+from pymultirole_plugins.v1.schema import Document
+
+logger = Logger("pymultirole")
+
+
+class MetadataFromCategoriesParameters(ProcessorParameters):
+    metadata_name: str = Field(None, description="Name of the generated metadata")
+    multi_label_threshold: float = Field(
+        0.0, description="only categories with a score greater than threshold are kept"
+    )
+
+
+class MetadataFromCategoriesProcessor(ProcessorBase):
+    """Create categories from annotations"""
+
+    def process(self, documents: list[Document], parameters: ProcessorParameters) -> list[Document]:
+        params: MetadataFromCategoriesParameters = cast(MetadataFromCategoriesParameters, parameters)
+        for document in documents:
+            with add_logging_context(docid=document.identifier):
+                # Document level
+                mvals = create_metadata_from_categories(document.categories, params.multi_label_threshold)
+                if mvals is None:
+                    if params.metadata_name in document.metadata:
+                        del document.metadata[params.metadata_name]
+                else:
+                    document.metadata[params.metadata_name] = mvals
+                document.categories = None
+
+                # Segment level
+                for sent in document.sentences or []:
+                    mvals = create_metadata_from_categories(sent.categories, params.multi_label_threshold)
+                    if mvals is None:
+                        if params.metadata_name in sent.metadata:
+                            del sent.metadata[params.metadata_name]
+                    else:
+                        sent.metadata[params.metadata_name] = mvals
+                    sent.categories = None
+        return documents
+
+    @classmethod
+    def get_model(cls) -> type[BaseModel]:
+        return MetadataFromCategoriesParameters
+
+
+def create_metadata_from_categories(categories, threshold=0.0):
+    values = []
+    if categories:
+        for c in categories:
+            if c.score and c.score >= threshold:
+                values.append(c.label or c.labelName)
+    return values if len(values) > 1 else (values[0] if len(values) == 1 else None)