run-llama--liteparse/.github/workflows/ci-python.yml

name: CI - Python Bindings

on:
  push:
    branches: [main]
    paths:
      - "crates/**"
      - "packages/python/**"
      - ".github/workflows/ci-python.yml"
  pull_request:
    branches: [main]
    paths:
      - "crates/**"
      - "packages/python/**"
      - ".github/workflows/ci-python.yml"

env:
  CARGO_TERM_COLOR: always

jobs:
  build:
    strategy:
      fail-fast: false
      matrix:
        include:
          - os: macos-latest
            target: aarch64-apple-darwin

          - os: macos-26-intel
            target: x86_64-apple-darwin

          - os: ubuntu-latest
            target: x86_64-unknown-linux-gnu

          - os: ubuntu-24.04-arm
            target: aarch64-unknown-linux-gnu

          - os: ubuntu-latest
            target: x86_64-unknown-linux-musl
            musl: true

          - os: windows-latest
            target: x86_64-pc-windows-msvc

          - os: windows-11-arm
            target: aarch64-pc-windows-msvc

    runs-on: ${{ matrix.os }}
    name: Build ${{ matrix.target }}

    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"

      - uses: dtolnay/rust-toolchain@1.95.0
        with:
          targets: ${{ matrix.target }}

      - name: Install system dependencies (Linux)
        if: runner.os == 'Linux' && !matrix.musl
        run: |
          sudo apt-get update
          sudo apt-get install -y libtesseract-dev libleptonica-dev

      - name: Install system dependencies (macOS)
        if: runner.os == 'macOS'
        run: brew install tesseract leptonica

      - name: Force Ninja generator (Windows)
        if: runner.os == 'Windows'
        run: echo "CMAKE_GENERATOR=Ninja" >> $GITHUB_ENV
        shell: bash

      - uses: actions/cache@v4
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            ~/.cache/pdfium-rs
            ~/Library/Caches/pdfium-rs
            target
          key: ${{ runner.os }}-${{ matrix.target }}-cargo-python-${{ hashFiles('**/Cargo.lock') }}

      - name: Build wheels (glibc)
        if: ${{ !matrix.musl }}
        uses: PyO3/maturin-action@v1
        with:
          target: ${{ matrix.target }}
          args: --release --out dist --find-interpreter
          manylinux: 2_28
          working-directory: packages/python
          before-script-linux: |
            if command -v yum &> /dev/null; then
              yum install -y tesseract-devel leptonica-devel openssl-devel pkgconfig perl-IPC-Cmd || true
            elif command -v apt-get &> /dev/null; then
              apt-get update && apt-get install -y libtesseract-dev libleptonica-dev libssl-dev pkg-config || true
            elif command -v apk &> /dev/null; then
              apk add tesseract-ocr-dev leptonica-dev openssl-dev pkgconf || true
            fi

      - name: Build wheels (musl container)
        if: ${{ matrix.musl }}
        # Same pattern as the node musl build: run inside a vanilla
        # python:3-alpine with clang+libc++ from apk. Bypasses maturin-action's
        # musllinux_1_2 cross image, which causes FORTIFY_SOURCE issues with
        # tesseract's C++ build and broken host-openssl for build-deps.
        run: |
          chmod +x scripts/build-musl-py.sh
          docker run --rm \
            -v "$GITHUB_WORKSPACE":/work \
            -v "$HOME/.cargo/registry":/root/.cargo/registry \
            -v "$HOME/.cargo/git":/root/.cargo/git \
            -v "$HOME/.cache/pdfium-rs":/root/.cache/pdfium-rs \
            -w /work \
            python:3.12-alpine \
            /work/scripts/build-musl-py.sh
          # The container runs as root; fix perms so subsequent steps can
          # read/upload the produced wheel.
          sudo chmod -R a+rw packages/python/dist/ || true

      - name: Copy pdfium dylib into wheel (Unix)
        if: runner.os != 'Windows' && !matrix.musl
        working-directory: packages/python
        run: |
          # Fix permissions from Docker/maturin build
          sudo chmod -R a+rw dist/ || true
          # Find pdfium in target/ (mounted from Docker) or cache
          PDFIUM_LIB=$(find ../../target -name "libpdfium.so" -type f 2>/dev/null | head -1 || true)
          if [ -z "$PDFIUM_LIB" ]; then
            PDFIUM_LIB=$(find ~/.cache/pdfium-rs -name "libpdfium.so" -type f 2>/dev/null | head -1 || true)
          fi
          if [ -n "$PDFIUM_LIB" ]; then
            export PDFIUM_LIB_PATH="$(dirname "$PDFIUM_LIB")"
          fi
          bash scripts/copy-pdfium.sh
          for whl in dist/*.whl; do
            python -c "
          import zipfile, os, sys
          whl = sys.argv[1]
          if sys.platform == 'darwin':
              dylib = 'libpdfium.dylib'
          else:
              dylib = 'libpdfium.so'
          dylib_path = os.path.join('liteparse', dylib)
          if not os.path.exists(dylib_path):
              print(f'Warning: {dylib_path} not found, skipping')
              sys.exit(0)
          with zipfile.ZipFile(whl, 'a') as z:
              z.write(dylib_path, f'liteparse/{dylib}')
          print(f'Added {dylib} to {whl}')
          " "$whl"
          done

      - name: Copy pdfium dylib into wheel (Windows)
        if: runner.os == 'Windows'
        working-directory: packages/python
        shell: pwsh
        run: |
          $cacheBase = "$env:LOCALAPPDATA\pdfium-rs"
          if (-not (Test-Path $cacheBase)) {
            $cacheBase = "$env:USERPROFILE\.cache\pdfium-rs"
          }
          $dll = Get-ChildItem -Path $cacheBase -Recurse -Filter "pdfium.dll" | Select-Object -First 1
          if (-not $dll) {
            $dll = Get-ChildItem -Path "..\..\target" -Recurse -Filter "pdfium.dll" | Select-Object -First 1
          }
          if ($dll) {
            Copy-Item $dll.FullName -Destination "liteparse\pdfium.dll"
            Write-Host "Copied $($dll.FullName) -> liteparse\pdfium.dll"
            foreach ($whl in Get-ChildItem dist\*.whl) {
              python -c @"
          import zipfile, sys, os
          whl = sys.argv[1]
          dll = os.path.join('liteparse', 'pdfium.dll')
          if os.path.exists(dll):
              with zipfile.ZipFile(whl, 'a') as z:
                  z.write(dll, 'liteparse/pdfium.dll')
              print(f'Added pdfium.dll to {whl}')
          "@ $whl.FullName
            }
          } else {
            Write-Error "Could not find pdfium.dll"
            exit 1
          }

      - name: Upload wheels
        uses: actions/upload-artifact@v4
        with:
          name: wheels-${{ matrix.target }}
          path: packages/python/dist/*.whl
          if-no-files-found: error

  sdist:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Build sdist
        uses: PyO3/maturin-action@v1
        with:
          command: sdist
          args: --out dist
          working-directory: packages/python

      - name: Upload sdist
        uses: actions/upload-artifact@v4
        with:
          name: sdist
          path: packages/python/dist/*.tar.gz
          if-no-files-found: error

  test:
    needs: build
    strategy:
      fail-fast: false
      matrix:
        include:
          - os: macos-latest
            target: aarch64-apple-darwin
          - os: macos-26-intel
            target: x86_64-apple-darwin
          - os: ubuntu-latest
            target: x86_64-unknown-linux-gnu
          - os: ubuntu-latest
            target: x86_64-unknown-linux-musl
            use-container: true
          - os: windows-latest
            target: x86_64-pc-windows-msvc
          - os: windows-11-arm
            target: aarch64-pc-windows-msvc
    runs-on: ${{ matrix.os }}
    name: Test ${{ matrix.target }}

    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"

      - name: Download wheels
        uses: actions/download-artifact@v4
        with:
          name: wheels-${{ matrix.target }}
          path: dist

      - name: Install wheel
        if: ${{ !matrix.use-container }}
        run: pip install --no-index --find-links dist liteparse

      - name: Smoke test
        if: ${{ !matrix.use-container }}
        run: |
          python -c "
          from liteparse import LiteParse, ParseResult, ParsedPage, TextItem, ScreenshotResult
          parser = LiteParse(ocr_enabled=False, quiet=True)
          print('LiteParse loaded successfully')
          print(repr(parser))
          "

      - name: Parse test
        if: ${{ !matrix.use-container }}
        run: |
          python -c "
          from liteparse import LiteParse
          parser = LiteParse(ocr_enabled=False, quiet=True, max_pages=2)
          result = parser.parse('demo/docs/apple-10k-2024.pdf')
          assert result.num_pages == 2, f'Expected 2 pages, got {result.num_pages}'
          assert len(result.text) > 0, 'Expected non-empty text'
          page = result.get_page(1)
          assert page is not None, 'Expected page 1'
          assert len(page.text_items) > 0, 'Expected text items'
          print(f'Parsed {result.num_pages} pages, {len(result.text)} chars')
          print('Parse test passed')
          "

      - name: Bytes parse test
        if: ${{ !matrix.use-container }}
        run: |
          python -c "
          from liteparse import LiteParse
          parser = LiteParse(ocr_enabled=False, quiet=True, max_pages=1)
          with open('demo/docs/apple-10k-2024.pdf', 'rb') as f:
              data = f.read()
          result = parser.parse(data)
          assert result.num_pages == 1
          assert len(result.text) > 0
          print('Bytes parse test passed')
          "

      - name: Screenshot test
        if: ${{ !matrix.use-container }}
        run: |
          python -c "
          from liteparse import LiteParse
          parser = LiteParse(ocr_enabled=False, quiet=True)
          screenshots = parser.screenshot('demo/docs/apple-10k-2024.pdf', page_numbers=[1])
          assert len(screenshots) == 1
          assert screenshots[0].page_num == 1
          assert len(screenshots[0].image_bytes) > 0
          print(f'Screenshot: {screenshots[0].width}x{screenshots[0].height}, {len(screenshots[0].image_bytes)} bytes')
          print('Screenshot test passed')
          "

      - name: CLI test
        if: ${{ !matrix.use-container }}
        run: |
          lit --version
          lit parse demo/docs/apple-10k-2024.pdf --no-ocr --max-pages 1 -q | head -5
          echo "CLI test passed"

      - name: Test in musl container
        if: ${{ matrix.use-container }}
        run: |
          docker run --rm \
            -v "$GITHUB_WORKSPACE":/work \
            -w /work \
            python:3.12-alpine \
            sh -c '
              pip install --no-index --find-links dist liteparse
              python -c "
          from liteparse import LiteParse, ParseResult, ParsedPage, TextItem, ScreenshotResult
          parser = LiteParse(ocr_enabled=False, quiet=True)
          print(repr(parser))
          print(\"LiteParse loaded successfully\")
          "
              python -c "
          from liteparse import LiteParse
          parser = LiteParse(ocr_enabled=False, quiet=True, max_pages=2)
          result = parser.parse(\"demo/docs/apple-10k-2024.pdf\")
          assert result.num_pages == 2, f\"Expected 2 pages, got {result.num_pages}\"
          assert len(result.text) > 0, \"Expected non-empty text\"
          print(f\"Parsed {result.num_pages} pages, {len(result.text)} chars\")
          print(\"Parse test passed\")
          "
              lit --version
              lit parse demo/docs/apple-10k-2024.pdf --no-ocr --max-pages 1 -q | head -5
              echo "CLI test passed"
            '