GDPRScanner/.github/workflows/build.yml

name: Build — Windows & Linux

# Trigger on every push to main, on version tags, or manually
on:
  push:
    branches: [main]
    tags:     ['v*']
  workflow_dispatch:

# Only run one build at a time per branch to avoid race conditions
concurrency:
  group: build-${{ github.ref }}
  cancel-in-progress: true

jobs:

  # ── Document Scanner ──────────────────────────────────────────────────────
  build-document-scanner:
    strategy:
      fail-fast: false
      matrix:
        include:
          - os: windows-latest
            name: windows
            artifact_glob: "dist/*.exe"
          - os: ubuntu-22.04
            name: linux
            artifact_glob: "dist/Document Scanner"

    runs-on: ${{ matrix.os }}
    name: Document Scanner / ${{ matrix.name }}

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Set up Python 3.12
        uses: actions/setup-python@v5
        with:
          python-version: "3.12"
          cache: pip

      # Linux: install system libraries required by OpenCV, pdf2image, Tesseract
      - name: Install Linux system dependencies
        if: runner.os == 'Linux'
        run: |
          sudo apt-get update -qq
          sudo apt-get install -y --no-install-recommends \
            tesseract-ocr tesseract-ocr-dan tesseract-ocr-deu \
            poppler-utils \
            libgtk-3-dev libwebkit2gtk-4.0-dev \
            libglib2.0-dev libcairo2-dev pkg-config \
            python3-dev

      - name: Install Python dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      # Download the Danish spaCy model used for NER/anonymisation
      - name: Download spaCy model
        run: python -m spacy download da_core_news_sm

      - name: Build Document Scanner
        run: python build_gdpr.py

      # Zip the Linux binary (no installer on Linux)
      - name: Package Linux binary
        if: runner.os == 'Linux'
        run: |
          cd dist
          zip -r "Document_Scanner_linux_x86_64.zip" "Document Scanner"

      - name: Upload artifact
        uses: actions/upload-artifact@v4
        with:
          name: DocumentScanner-${{ matrix.name }}
          retention-days: 30
          path: |
            dist/*.exe
            dist/Document_Scanner_linux_x86_64.zip

  # ── GDPRScanner ──────────────────────────────────────────────────────────
  build-m365-scanner:
    strategy:
      fail-fast: false
      matrix:
        include:
          - os: windows-latest
            name: windows
            artifact_glob: "dist/*.exe"
          - os: ubuntu-22.04
            name: linux
            artifact_glob: "dist/GDPRScanner"

    runs-on: ${{ matrix.os }}
    name: GDPRScanner / ${{ matrix.name }}

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Set up Python 3.12
        uses: actions/setup-python@v5
        with:
          python-version: "3.12"
          cache: pip

      - name: Install Linux system dependencies
        if: runner.os == 'Linux'
        run: |
          sudo apt-get update -qq
          sudo apt-get install -y --no-install-recommends \
            libgtk-3-dev libwebkit2gtk-4.0-dev \
            libglib2.0-dev libcairo2-dev pkg-config \
            python3-dev

      - name: Install Python dependencies
        run: |
          python -m pip install --upgrade pip
          # GDPRScanner only needs a subset — skip OCR/CV heavy deps
          pip install flask msal requests openpyxl pillow \
                      python-docx \
                      pywebview pystray \
                      pyinstaller pyinstaller-hooks-contrib

      - name: Build GDPRScanner
        run: python build_gdpr.py

      - name: Package Linux binary
        if: runner.os == 'Linux'
        run: |
          cd dist
          zip -r "GDPRScanner_linux_x86_64.zip" "GDPRScanner"

      - name: Upload artifact
        uses: actions/upload-artifact@v4
        with:
          name: M365Scanner-${{ matrix.name }}
          retention-days: 30
          path: |
            dist/*.exe
            dist/GDPRScanner_linux_x86_64.zip

  # ── Release (only on version tags v*) ────────────────────────────────────
  release:
    name: Create GitHub Release
    needs: [build-document-scanner, build-m365-scanner]
    if: startsWith(github.ref, 'refs/tags/v')
    runs-on: ubuntu-latest
    permissions:
      contents: write

    steps:
      - name: Download all artifacts
        uses: actions/download-artifact@v4
        with:
          path: artifacts
          merge-multiple: true

      - name: Create release
        uses: softprops/action-gh-release@v2
        with:
          name: ${{ github.ref_name }}
          draft: false
          prerelease: ${{ contains(github.ref_name, '-beta') || contains(github.ref_name, '-rc') }}
          generate_release_notes: true
          files: artifacts/**