.github/workflows/ci.yml

name: CI/CD Pipeline

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
  #schedule:
  # Run tests daily at 2 AM UTC
  #  - cron: '0 2 * * *'

permissions:
  contents: read
  actions: read
  pull-requests: write
  issues: write

env:
  PYTHON_VERSION: "3.11"

jobs:
  lint:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
    
    - name: Set up Python
      uses: actions/setup-python@v4
      with:
        python-version: ${{ env.PYTHON_VERSION }}
    
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install ruff black
    
    - name: Run Ruff linter
      run: ruff check .
    
    - name: Run Black formatter check
      run: black --check .

  test-unit:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: [3.11, 3.12, 3.13]
    
    steps:
    - uses: actions/checkout@v4
    
    - name: Set up Python ${{ matrix.python-version }}
      uses: actions/setup-python@v4
      with:
        python-version: ${{ matrix.python-version }}
    
    - name: Cache pip dependencies
      uses: actions/cache@v4
      with:
        path: ~/.cache/pip
        key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
        restore-keys: |
          ${{ runner.os }}-pip-
    
    - name: Install system dependencies
      run: |
        sudo apt-get update
        sudo apt-get install -y \
          tesseract-ocr \
          tesseract-ocr-eng \
          poppler-utils \
          libgl1-mesa-dri \
          libglib2.0-0 \
          libsm6 \
          libxext6 \
          libxrender-dev \
          libgomp1
    
    - name: Install Python dependencies
      run: |
        python -m pip install --upgrade pip
        pip install -r requirements_lightweight.txt
        pip install pytest pytest-cov pytest-html pytest-xdist reportlab pillow
    
    - name: Download spaCy model
      run: |
        python -m spacy download en_core_web_lg
    
    - name: Setup test data
      run: |
        python .github/scripts/setup_test_data.py
        echo "Setup script completed. Checking results:"
        ls -la example_data/ || echo "example_data directory not found"
    
    - name: Verify test data files
      run: |
        echo "Checking if critical test files exist:"
        ls -la example_data/
        echo "Checking for specific PDF files:"
        ls -la example_data/*.pdf || echo "No PDF files found"
        echo "Checking file sizes:"
        find example_data -name "*.pdf" -exec ls -lh {} \;
    
    - name: Clean up problematic config files
      run: |
        rm -f config*.py || true
    
    - name: Run CLI tests
      run: |
        cd test
        python test.py
    
    - name: Run tests with pytest
      run: |
        pytest test/test.py -v --tb=short --junitxml=test-results.xml
    
    - name: Run tests with coverage
      run: |
        pytest test/test.py --cov=. --cov-config=.coveragerc --cov-report=xml --cov-report=html --cov-report=term
    
    #- name: Upload coverage to Codecov - not necessary
    #  uses: codecov/codecov-action@v3
    #  if: matrix.python-version == '3.11'
    #  with:
    #    file: ./coverage.xml
    #    flags: unittests
    #    name: codecov-umbrella
    #    fail_ci_if_error: false
    
    - name: Upload test results
      uses: actions/upload-artifact@v4
      if: always()
      with:
        name: test-results-python-${{ matrix.python-version }}
        path: |
          test-results.xml
          htmlcov/
          coverage.xml

  test-integration:
    runs-on: ubuntu-latest
    needs: [lint, test-unit]
    
    steps:
    - uses: actions/checkout@v4
    
    - name: Set up Python
      uses: actions/setup-python@v4
      with:
        python-version: ${{ env.PYTHON_VERSION }}
    
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install -r requirements_lightweight.txt
        pip install pytest pytest-cov reportlab pillow
    
    - name: Install system dependencies
      run: |
        sudo apt-get update
        sudo apt-get install -y \
          tesseract-ocr \
          tesseract-ocr-eng \
          poppler-utils \
          libgl1-mesa-dri \
          libglib2.0-0
    
    - name: Download spaCy model
      run: |
        python -m spacy download en_core_web_lg
    
    - name: Setup test data
      run: |
        python .github/scripts/setup_test_data.py
        echo "Setup script completed. Checking results:"
        ls -la example_data/ || echo "example_data directory not found"
    
    - name: Verify test data files
      run: |
        echo "Checking if critical test files exist:"
        ls -la example_data/
        echo "Checking for specific PDF files:"
        ls -la example_data/*.pdf || echo "No PDF files found"
        echo "Checking file sizes:"
        find example_data -name "*.pdf" -exec ls -lh {} \;
    
    - name: Run integration tests
      run: |
        cd test
        python demo_single_test.py
    
    - name: Test CLI help
      run: |
        python cli_redact.py --help
    
    - name: Test CLI version
      run: |
        python -c "import sys; print(f'Python {sys.version}')"

  security:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
    
    - name: Set up Python
      uses: actions/setup-python@v4
      with:
        python-version: ${{ env.PYTHON_VERSION }}
    
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install safety bandit
    
    #- name: Run safety scan - removed as now requires login
    #  run: |
    #    safety scan -r requirements.txt
    
    - name: Run bandit security check
      run: |
        bandit -r . -f json -o bandit-report.json || true
    
    - name: Upload security report
      uses: actions/upload-artifact@v4
      if: always()
      with:
        name: security-report
        path: bandit-report.json

  build:
    runs-on: ubuntu-latest
    needs: [lint, test-unit]
    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
    
    steps:
    - uses: actions/checkout@v4
    
    - name: Set up Python
      uses: actions/setup-python@v4
      with:
        python-version: ${{ env.PYTHON_VERSION }}
    
    - name: Install build dependencies
      run: |
        python -m pip install --upgrade pip
        pip install build twine
    
    - name: Build package
      run: |
        python -m build
    
    - name: Check package
      run: |
        twine check dist/*
    
    - name: Upload build artifacts
      uses: actions/upload-artifact@v4
      with:
        name: dist
        path: dist/