fix for word_tokenize() Failing to Split English Contractions When Followed by [\t\n\f\r] #814
Workflow file for this run
This file contains 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: ci-workflow | |
| # run workflow for these events | |
| on: [push, pull_request, workflow_dispatch] | |
| env: | |
| CORENLP: /home/runner/third/stanford-corenlp | |
| CORENLP_MODELS: /home/runner/third/stanford-corenlp | |
| STANFORD_PARSER: /home/runner/third/stanford-parser | |
| STANFORD_MODELS: /home/runner/third/stanford-postagger | |
| STANFORD_POSTAGGER: /home/runner/third/stanford-postagger | |
| SENNA: /home/runner/third/senna | |
| PROVER9: /home/runner/third/prover9/bin | |
| MEGAM: /home/runner/third/megam | |
| # TADM requires `libtaopetsc.so` from PETSc v2.3.3, and likely has more | |
| # tricky to install requirements, so we don't run tests for it. | |
| # TADM: /home/runner/third/tadm/bin | |
| MALT_PARSER: /home/runner/third/maltparser | |
| jobs: | |
| pre-commit: | |
| name: Run pre-commit | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.x' # run with latest python version | |
| - run: | | |
| pip install pre-commit | |
| pre-commit run --all-files | |
| cache_nltk_data: | |
| name: Cache nltk_data | |
| needs: pre-commit | |
| strategy: | |
| matrix: | |
| os: [ubuntu-latest, windows-latest] | |
| runs-on: ${{ matrix.os }} | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Cache nltk data | |
| uses: actions/cache@v3 | |
| id: restore-cache | |
| with: | |
| path: ~/nltk_data | |
| key: nltk_data_${{ secrets.CACHE_VERSION }} | |
| - name: Download nltk data packages on cache miss | |
| run: | | |
| pip install regex # dependencies needed to download nltk data | |
| python -c "import nltk; from pathlib import Path; path = Path('~/nltk_data').expanduser(); path.mkdir(exist_ok=True); nltk.download('all', download_dir=path)" | |
| shell: bash | |
| if: steps.restore-cache.outputs.cache-hit != 'true' | |
| cache_third_party: | |
| name: Cache third party tools | |
| needs: pre-commit | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Cache third party tools | |
| uses: actions/cache@v3 | |
| id: restore-cache | |
| with: | |
| path: ~/third | |
| key: third_${{ hashFiles('tools/github_actions/third-party.sh') }}_${{ secrets.CACHE_VERSION }} | |
| - name: Download third party data | |
| run: | | |
| chmod +x ./tools/github_actions/third-party.sh | |
| ./tools/github_actions/third-party.sh | |
| if: steps.restore-cache.outputs.cache-hit != 'true' | |
| test: | |
| name: Python ${{ matrix.python-version }} on ${{ matrix.os }} | |
| needs: [cache_nltk_data, cache_third_party] | |
| strategy: | |
| matrix: | |
| python-version: ['3.8', '3.9', '3.10', '3.11', '3.12'] | |
| os: [ubuntu-latest, macos-latest, windows-latest] | |
| fail-fast: false | |
| runs-on: ${{ matrix.os }} | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Setup python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Restore cached dependencies | |
| uses: actions/cache@v3 | |
| id: restore-cache | |
| with: | |
| path: ${{ env.pythonLocation }} | |
| key: python-dependencies-${{ matrix.os }}-${{ matrix.python-version }}-${{ hashFiles('requirements-ci.txt') }}-${{ env.pythonLocation }} | |
| - name: Install dependencies | |
| run: | | |
| pip install --upgrade pip | |
| pip install --upgrade --requirement requirements-ci.txt | |
| #if: steps.restore-cache.outputs.cache-hit != 'true' # disabled due to a persistent issue with restoring cache on macos runner | |
| - name: Use cached nltk data | |
| uses: actions/cache@v3 | |
| with: | |
| path: ~/nltk_data | |
| key: nltk_data_${{ secrets.CACHE_VERSION }} | |
| - name: Use cached third party tools | |
| uses: actions/cache@v3 | |
| with: | |
| path: ~/third | |
| key: third_${{ hashFiles('tools/github_actions/third-party.sh') }}_${{ secrets.CACHE_VERSION }} | |
| if: runner.os == 'Linux' | |
| - name: Set up JDK 16 | |
| uses: actions/setup-java@v4 | |
| with: | |
| distribution: 'zulu' | |
| java-version: '16' | |
| if: runner.os == 'Linux' | |
| - name: Run pytest | |
| shell: bash | |
| run: | | |
| pytest --numprocesses auto -rsx --doctest-modules nltk |