feat: HTML downloader fix & text segmentation pipeline #48
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Build, Test, Lint & Upload to TestPyPI and PyPI for ECHR-extractor | |
| on: | |
| push: | |
| branches: [ main ] | |
| tags: | |
| - 'v*' | |
| pull_request: | |
| branches: [ main ] | |
| jobs: | |
| lint: | |
| if: github.event_name == 'pull_request' | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Check out the repository | |
| uses: actions/checkout@v4 | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.9' | |
| - name: Lint with super linter | |
| uses: github/super-linter@v4 | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| DEFAULT_BRANCH: 'main' | |
| VALIDATE_PYTHON_BLACK: true | |
| IGNORE_GITIGNORED_FILES: true | |
| VALIDATE_ALL_CODEBASE: false | |
| test: | |
| needs: lint | |
| if: github.event_name == 'pull_request' | |
| name: Test on ${{ matrix.os }} | |
| runs-on: ${{ matrix.os }} | |
| strategy: | |
| matrix: | |
| os: [ubuntu-latest, windows-latest, macos-latest] | |
| python-version: ['3.9', '3.10', '3.11', '3.12'] | |
| steps: | |
| - name: Check out the repository | |
| uses: actions/checkout@v4 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install setuptools wheel pytest pytest-cov | |
| pip install -r requirements.txt | |
| - name: Install package for testing | |
| run: | | |
| pip install -e . | |
| - name: Run tests with pytest | |
| run: | | |
| mkdir -p junit | |
| pytest tests/ --doctest-modules --junitxml=junit/test-results.xml --cov=src/echr_extractor --cov-report=xml --cov-report=html | |
| build: | |
| name: Build Python package | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 # Required for setuptools_scm to get version from git tags | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.9' | |
| - name: Install build dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install setuptools wheel build setuptools_scm | |
| - name: Show version to be built | |
| run: | | |
| python -c "import setuptools_scm; print(f'Version: {setuptools_scm.get_version()}')" | |
| - name: Build package | |
| run: | | |
| python -m build | |
| - name: Upload build artifacts | |
| if: startsWith(github.ref, 'refs/tags/') | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: python-package-distributions | |
| path: dist/ | |
| pypi-publish: | |
| if: startsWith(github.ref, 'refs/tags/') | |
| name: Publish to PyPI | |
| needs: build | |
| runs-on: ubuntu-latest | |
| environment: | |
| name: pypi | |
| url: https://pypi.org/project/echr-extractor/ | |
| permissions: | |
| id-token: write | |
| steps: | |
| - name: Download all the artifacts | |
| uses: actions/download-artifact@v4 | |
| with: | |
| name: python-package-distributions | |
| path: dist/ | |
| - name: Publish distribution to PyPI | |
| uses: pypa/gh-action-pypi-publish@release/v1 | |
| github-release: | |
| if: startsWith(github.ref, 'refs/tags/') | |
| name: Sign the Python distribution with Sigstore and upload them to GitHub Releases | |
| needs: | |
| - pypi-publish | |
| runs-on: ubuntu-latest | |
| permissions: | |
| id-token: write | |
| contents: write | |
| steps: | |
| - name: Download all the artifacts | |
| uses: actions/download-artifact@v4 | |
| with: | |
| name: python-package-distributions | |
| path: dist/ | |
| - name: Sign the Python distribution with Sigstore | |
| uses: sigstore/gh-action-sigstore-python@v3.0.0 | |
| with: | |
| inputs: >- | |
| ./dist/*.tar.gz | |
| ./dist/*.whl | |
| - name: Extract version from tag | |
| id: get_version | |
| run: echo "VERSION=${GITHUB_REF#refs/tags/v}" >> $GITHUB_OUTPUT | |
| - name: Create Github release | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| run: | | |
| gh release create \ | |
| '${{ github.ref_name }}' \ | |
| --repo '${{ github.repository }}' \ | |
| --title "echr-extractor ${{ steps.get_version.outputs.VERSION }}" \ | |
| --notes "" | |
| - name: Upload artifact signatures to Github release | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| run: | | |
| gh release upload \ | |
| '${{ github.ref_name }}' ./dist/*.tar.gz ./dist/*.whl \ | |
| --repo '${{ github.repository }}' |