datatools-dev/.github/workflows/build.yml

name: Build installers

# Triggers:
#   * Tag push (v*) → produces installers, attaches them to a GitHub Release.
#   * Manual dispatch → uploads the installers as workflow artifacts only.
#
# Outputs per platform (downloadable by buyers):
#   * macOS:    .dmg installer
#   * Windows:  .exe installer
#   * Linux:    .AppImage (already portable; no separate installer step)
#
# Self-contained: every artifact ships its own Python interpreter + every
# runtime dep (including bundled Tesseract OCR) through PyInstaller. No
# pre/post install steps on the buyer's machine.
#
# What this workflow doesn't do (yet):
#   * Code signing (Mac Developer ID, Windows code-signing cert).
#     Those need GitHub Secrets the owner sets up first. See
#     build/README.md "Signing" for the secret names this workflow
#     will read once they exist.
#   * Auto-update endpoint generation. v1 distributes via Gumroad;
#     buyers re-download for updates.

on:
  workflow_dispatch:
  push:
    tags:
      - 'v*'

permissions:
  contents: write   # needed to create the release on tag push

jobs:
  build:
    name: Build (${{ matrix.os }})
    strategy:
      fail-fast: false
      matrix:
        include:
          - os: macos-latest
            platform: mac
            artifact_name: DataTools-mac.dmg
            artifact_path: dist/DataTools-*-mac.dmg
          - os: windows-latest
            platform: win
            artifact_name: DataTools-win.exe
            artifact_path: dist/DataTools-*-win-setup.exe
          - os: ubuntu-latest
            platform: linux
            artifact_name: DataTools-linux.AppImage
            artifact_path: dist/DataTools-*-linux-x86_64.AppImage
    runs-on: ${{ matrix.os }}
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'
          cache: pip

      - name: Install build deps
        run: |
          pip install --upgrade pip
          pip install -r requirements.txt
          pip install pyinstaller pillow

      # ---- Tesseract bundling cache --------------------------------
      # The fetch logic inside build/tesseract.py downloads:
      #   * build/vendor/tessdata/eng.traineddata (~16 MB, shared)
      #   * build/_tesseract/<platform>/  (binary + libs, 30-120 MB)
      # Cache both so iterative CI runs don't re-download. The
      # cache key bakes in the pinned Tesseract version + tessdata
      # URL so a version bump invalidates automatically.
      - name: Cache Tesseract bundle inputs
        uses: actions/cache@v4
        with:
          path: |
            build/_tesseract
            build/vendor/tessdata
          key: tesseract-${{ runner.os }}-5.5.0-tessdata_best-v1

      # ---- Linux: install patchelf so tesseract.py can rewrite
      # RPATH on the bundled tesseract binary. apt-get install
      # tesseract-ocr is handled inside tesseract.py itself. --------
      - name: Install Linux build prereqs for Tesseract bundling
        if: matrix.os == 'ubuntu-latest'
        run: |
          sudo apt-get update
          sudo apt-get install -y patchelf

      - name: Read version
        id: version
        shell: bash
        run: |
          VER=$(python -c "import re; print(re.search(r'__version__\s*=\s*\"([^\"]+)\"', open('src/__init__.py').read()).group(1))")
          echo "version=$VER" >> "$GITHUB_OUTPUT"

      - name: Generate platform icons
        run: python build/generate_icons.py

      # Stage Tesseract before PyInstaller. The tesseract.py helpers
      # handle the per-platform fetch (UB-Mannheim on Win, brew on
      # Mac, apt on Linux) and stage the binary + libs into
      # build/_tesseract/<platform>/ where the spec picks them up.
      # We invoke a tiny inline Python so the workflow doesn't have
      # to know the per-platform target string.
      - name: Stage Tesseract binary + tessdata
        shell: bash
        env:
          DATATOOLS_PLATFORM: ${{ matrix.platform }}
        run: |
          python - <<'PY'
          import os, sys
          sys.path.insert(0, "build")
          from tesseract import fetch_tessdata, fetch_tesseract_for_platform
          target = os.environ["DATATOOLS_PLATFORM"]
          fetch_tessdata()
          fetch_tesseract_for_platform(target)
          PY

      - name: Build PyInstaller bundle
        shell: bash
        env:
          # The spec reads this to find the per-platform staging dir;
          # see build/datatools.spec for the contract.
          DATATOOLS_TESS_STAGING: build/_tesseract/${{ matrix.platform }}
        run: pyinstaller build/datatools.spec --clean --noconfirm

      # ---- Per-platform installer packaging ------------------------

      - name: Package macOS DMG (installer)
        if: matrix.os == 'macos-latest'
        run: bash build/macos/build_dmg.sh "${{ steps.version.outputs.version }}"

      - name: Install Inno Setup (Windows)
        if: matrix.os == 'windows-latest'
        run: choco install innosetup --no-progress -y

      - name: Package Windows installer
        if: matrix.os == 'windows-latest'
        shell: cmd
        run: |
          iscc /DAppVersion=${{ steps.version.outputs.version }} build\installer.iss

      - name: Install AppImage tooling (Linux)
        if: matrix.os == 'ubuntu-latest'
        run: |
          sudo apt-get update
          sudo apt-get install -y libfuse2 wget
          wget -q https://github.com/AppImage/AppImageKit/releases/download/continuous/appimagetool-x86_64.AppImage -O /usr/local/bin/appimagetool
          sudo chmod +x /usr/local/bin/appimagetool

      - name: Package Linux AppImage
        if: matrix.os == 'ubuntu-latest'
        run: bash build/appimage/build.sh "${{ steps.version.outputs.version }}"

      # ---- Upload + release ----------------------------------------

      - name: Upload installer artifact
        uses: actions/upload-artifact@v4
        with:
          name: ${{ matrix.artifact_name }}
          path: ${{ matrix.artifact_path }}
          if-no-files-found: error

      - name: Attach to Release (tag push only)
        if: startsWith(github.ref, 'refs/tags/v')
        uses: softprops/action-gh-release@v2
        with:
          files: ${{ matrix.artifact_path }}
          fail_on_unmatched_files: true
          generate_release_notes: true