spaCy/.github/workflows/tests.yml

name: tests

on:
  push:
    tags-ignore:
      - '**'
    branches-ignore:
      - "spacy.io"
      - "nightly.spacy.io"
      - "v2.spacy.io"
    paths-ignore:
      - "*.md"
      - "*.mdx"
      - "website/**"
  pull_request:
    types: [opened, synchronize, reopened, edited]
    paths-ignore:
      - "*.md"
      - "*.mdx"
      - "website/**"

jobs:
  validate:
    name: Validate
    if: github.repository_owner == 'explosion'
    runs-on: ubuntu-latest
    steps:
      - name: Check out repo
        uses: actions/checkout@v4

      - name: Configure Python version
        uses: actions/setup-python@v4
        with:
          python-version: "3.10"

      - name: black
        run: |
          python -m pip install black -c requirements.txt
          python -m black spacy --check          
      - name: isort
        run: |
          python -m pip install isort -c requirements.txt
          python -m isort spacy --check          
      - name: flake8
        run: |
          python -m pip install flake8==5.0.4
          python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics          
      - name: cython-lint
        run: |
          python -m pip install cython-lint -c requirements.txt
          # E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
          cython-lint spacy --ignore E501,W291,E266          

  tests:
    name: Test
    needs: Validate
    strategy:
      fail-fast: true
      matrix:
        os: [ubuntu-latest, windows-latest, macos-latest]
        python_version: ["3.9", "3.12"]

    runs-on: ${{ matrix.os }}

    steps:
      - name: Check out repo
        uses: actions/checkout@v4

      - name: Configure Python version
        uses: actions/setup-python@v4
        with:
          python-version: ${{ matrix.python_version }}

      - name: Install dependencies
        run: |
          python -m pip install -U build pip setuptools
          python -m pip install -U -r requirements.txt          

      - name: Build sdist
        run: |
          python -m build --sdist          

      - name: Run mypy
        run: |
          python -m mypy spacy          
        if: matrix.python_version != '3.7'

      - name: Delete source directory and .egg-info
        run: |
          rm -rf spacy *.egg-info          
        shell: bash

      - name: Uninstall all packages
        run: |
          python -m pip freeze
          python -m pip freeze --exclude pywin32 > installed.txt
          python -m pip uninstall -y -r installed.txt          

      - name: Install from sdist
        run: |
          SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
          SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST          
        shell: bash

      - name: Test import
        run: python -W error -c "import spacy"

      - name: "Test download CLI"
        run: |
          python -m spacy download ca_core_news_sm
          python -m spacy download ca_core_news_md
          python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"          
        if: matrix.python_version == '3.9'

      - name: "Test download_url in info CLI"
        run: |
          python -W error -m spacy info ca_core_news_sm | grep -q download_url          
        if: matrix.python_version == '3.9'

      - name: "Test no warnings on load (#11713)"
        run: |
          python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"          
        if: matrix.python_version == '3.9'

      - name: "Test convert CLI"
        run: |
          python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .          
        if: matrix.python_version == '3.9'

      - name: "Test debug config CLI"
        run: |
          python -m spacy init config -p ner -l ca ner.cfg
          python -m spacy debug config ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy          
        if: matrix.python_version == '3.9'

      - name: "Test debug data CLI"
        run: |
          # will have errors due to sparse data, check for summary in output
          python -m spacy debug data ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy | grep -q Summary          
        if: matrix.python_version == '3.9'

      - name: "Test train CLI"
        run: |
          python -m spacy train ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy --training.max_steps 10 --gpu-id -1          
        if: matrix.python_version == '3.9'

      - name: "Test assemble CLI"
        run: |
          python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
          python -m spacy assemble ner_source_sm.cfg output_dir          
        env:
          PYTHONWARNINGS: "error,ignore::DeprecationWarning" 
        if: matrix.python_version == '3.9'

      - name: "Test assemble CLI vectors warning"
        run: |
          python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
          python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113          
        if: matrix.python_version == '3.9'

      - name: "Install test requirements"
        run: |
          python -m pip install -U -r requirements.txt          

      - name: "Run CPU tests"
        run: |
          python -m pytest --pyargs spacy -W error          
        if: "!(startsWith(matrix.os, 'macos') && matrix.python_version == '3.11')"

      - name: "Run CPU tests with thinc-apple-ops"
        run: |
          python -m pip install 'spacy[apple]'
          python -m pytest --pyargs spacy          
        if: startsWith(matrix.os, 'macos') && matrix.python_version == '3.11'