CI workflow (Unstructured-IO/unstructured-api)

name: CI
 
on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
 
env:
  PIPELINE_FAMILY: "general"
 
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true
 
jobs:
  lint:
    timeout-minutes: 30
    runs-on: opensource-linux-8core
    steps:
    - uses: actions/checkout@v5
    - name: Read Python version from .python-version
      run: echo "PYTHON_VERSION=$(cat .python-version)" >> $GITHUB_ENV
    - name: Install uv
      uses: astral-sh/setup-uv@v7
      with:
        enable-cache: true
        cache-dependency-glob: "uv.lock"
    - name: Set up Python ${{ env.PYTHON_VERSION }}
      run: uv python install ${{ env.PYTHON_VERSION }}
    - name: Install lint dependencies
      run: uv sync --only-group lint --locked
    - name: Lint
      run: make check
 
  shellcheck:
    timeout-minutes: 30
    runs-on: opensource-linux-8core
    steps:
      - uses: actions/checkout@v5
      - name: ShellCheck
        uses: ludeeus/action-shellcheck@master
 
  test:
    timeout-minutes: 30
    runs-on: opensource-linux-8core
    needs: lint
    steps:
    - uses: actions/checkout@v5
    - name: Read Python version from .python-version
      run: echo "PYTHON_VERSION=$(cat .python-version)" >> $GITHUB_ENV
    - name: Install uv
      uses: astral-sh/setup-uv@v7
      with:
        enable-cache: true
        cache-dependency-glob: "uv.lock"
    - name: Set up Python ${{ env.PYTHON_VERSION }}
      run: uv python install ${{ env.PYTHON_VERSION }}
    - name: Install dependencies and run core tests
      run: |
        sudo apt-get update && sudo apt-get install --yes poppler-utils libreoffice
        uv sync --group test --locked
        make install-pandoc
        make install-nlp-models
        sudo add-apt-repository -y ppa:alex-p/tesseract-ocr5
        sudo apt-get install -y tesseract-ocr tesseract-ocr-kor
        tesseract --version
        make test
        make check-coverage
 
  changelog:
    timeout-minutes: 30
    runs-on: opensource-linux-8core
    steps:
    - uses: actions/checkout@v5
    - if: github.ref != 'refs/heads/main'
      uses: dorny/paths-filter@v3
      id: changes
      with:
        filters: |
          src:
            - 'doc_recipe/**'
            - 'recipe-notebooks/**'
 
    - if: steps.changes.outputs.src == 'true' && github.ref != 'refs/heads/main'
      uses: dangoslen/changelog-enforcer@v3
 
  # TODO - figure out best practice for caching docker images
  test_dockerfile:
    timeout-minutes: 30
    runs-on: opensource-linux-8core
    needs: lint
    steps:
    - uses: actions/checkout@v5
    - name: Read Python version from .python-version
      run: echo "PYTHON_VERSION=$(cat .python-version)" >> $GITHUB_ENV
    - name: Install uv
      uses: astral-sh/setup-uv@v7
      with:
        enable-cache: true
        cache-dependency-glob: "uv.lock"
    - name: Set up Python ${{ env.PYTHON_VERSION }}
      run: uv python install ${{ env.PYTHON_VERSION }}
    - name: Free up disk space
      run: |
        # Clear some space (https://github.com/actions/runner-images/issues/2840)
        echo "Disk usage before cleanup:"
        df -h
 
        # Remove unnecessary pre-installed software
        sudo rm -rf /usr/share/dotnet
        sudo rm -rf /opt/ghc
        sudo rm -rf /usr/local/share/boost
        sudo rm -rf /usr/local/lib/android
        sudo rm -rf /opt/hostedtoolcache/CodeQL
        sudo rm -rf /usr/local/.ghcup
        sudo rm -rf /usr/share/swift
 
        # Clean up docker to ensure we start fresh
        docker system prune -af --volumes
 
        echo "Disk usage after cleanup:"
        df -h
    - name: Test Dockerfile
      run: |
        uv sync --group test --locked
        make docker-build
        make docker-test