chore: import upstream snapshot with attribution

.github/workflows/release-python.yml

@@ -0,0 +1,392 @@
+name: Release - Python
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to release (e.g. 2.1.0)"
+        required: true
+        type: string
+      dry-run:
+        description: "Dry run (build but do not publish)"
+        type: boolean
+        default: false
+
+permissions:
+  contents: write
+  id-token: write
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Validate version
+        run: |
+          PYPROJECT_VERSION=$(python3 -c "
+          import re
+          with open('packages/python/pyproject.toml') as f:
+              match = re.search(r'^version\s*=\s*\"(.+?)\"', f.read(), re.MULTILINE)
+              print(match.group(1))
+          ")
+          if [ "$PYPROJECT_VERSION" != "${{ inputs.version }}" ]; then
+            echo "::error::Version mismatch: pyproject.toml has $PYPROJECT_VERSION, expected ${{ inputs.version }}"
+            exit 1
+          fi
+          echo "Version validated: ${{ inputs.version }}"
+
+  build-wheels:
+    needs: validate
+    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
+            ${{ runner.os == 'Windows' && format('{0}\pdfium-rs', env.LOCALAPPDATA) || '' }}
+            target
+          key: ${{ runner.os }}-${{ matrix.target }}-cargo-python-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Stage pdfium for wheel inclusion
+        if: ${{ !matrix.musl }}
+        shell: bash
+        # Pre-download pdfium and place it at packages/python/liteparse/<dylib>
+        # so the `[tool.maturin] include` rule packs it into the wheel during
+        # the build below. This is what gets the dylib listed in the wheel's
+        # RECORD manifest — appending it after the build leaves RECORD out of
+        # sync, which Poetry warns about.
+        run: bash packages/python/scripts/download-pdfium.sh ${{ matrix.target }}
+
+      - 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 "$HOME/.cache/pdfium-rs":/root/.cache/pdfium-rs \
+            -w /work \
+            python:3.12-alpine \
+            /work/scripts/build-musl-py.sh
+          # The container runs as root; fix perms so subsequent steps can
+          # read/upload the produced wheel.
+          sudo chmod -R a+rw packages/python/dist/ || true
+
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-${{ matrix.target }}
+          path: packages/python/dist/*.whl
+          if-no-files-found: error
+
+  build-sdist:
+    needs: validate
+    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-wheels:
+    needs: build-wheels
+    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: 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
+        run: pip install --no-index --find-links dist liteparse
+
+      - name: Smoke test
+        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
+        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')
+          "
+
+      - name: Bytes parse test
+        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
+        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')
+          "
+
+      - name: CLI test
+        run: |
+          lit --version
+          lit parse demo/docs/apple-10k-2024.pdf --no-ocr --max-pages 1 -q | head -5
+          echo "CLI test passed"
+
+  build-cli:
+    needs: validate
+    strategy:
+      matrix:
+        include:
+          - target: x86_64-unknown-linux-gnu
+            os: ubuntu-22.04
+            artifact: lit-linux-x64
+          - target: aarch64-unknown-linux-gnu
+            os: ubuntu-22.04-arm
+            artifact: lit-linux-arm64
+          - target: aarch64-apple-darwin
+            os: macos-latest
+            artifact: lit-darwin-arm64
+          - target: x86_64-apple-darwin
+            os: macos-26-intel
+            artifact: lit-darwin-x64
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: dtolnay/rust-toolchain@1.95.0
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Install system dependencies (Linux)
+        if: runner.os == 'Linux'
+        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
+
+      - uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            ~/.cache/pdfium-rs
+            ~/Library/Caches/pdfium-rs
+            target
+          key: ${{ runner.os }}-${{ matrix.target }}-cargo-cli-${{ hashFiles('**/Cargo.lock') }}
+
+      - name: Build
+        run: cargo build --release --target ${{ matrix.target }} -p liteparse
+
+      - name: Package binary
+        run: |
+          mkdir -p dist
+          cp target/${{ matrix.target }}/release/lit dist/${{ matrix.artifact }}
+          chmod +x dist/${{ matrix.artifact }}
+          tar -czf dist/${{ matrix.artifact }}.tar.gz -C dist ${{ matrix.artifact }}
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.artifact }}
+          path: dist/${{ matrix.artifact }}.tar.gz
+
+  publish:
+    needs: [test-wheels, build-sdist, build-cli]
+    runs-on: ubuntu-latest
+    name: Publish & Release
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Download all wheels
+        uses: actions/download-artifact@v4
+        with:
+          pattern: wheels-*
+          path: dist
+          merge-multiple: true
+
+      - name: Download sdist
+        uses: actions/download-artifact@v4
+        with:
+          name: sdist
+          path: dist
+
+      - name: Download CLI artifacts
+        uses: actions/download-artifact@v4
+        with:
+          pattern: lit-*
+          path: cli-artifacts
+
+      - name: Publish to PyPI
+        if: ${{ !inputs.dry-run }}
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/
+          password: ${{ secrets.PYPI_TOKEN }}
+          skip-existing: true
+
+      - name: Create git tag
+        if: ${{ !inputs.dry-run }}
+        run: |
+          git tag "python-v${{ inputs.version }}"
+          git push origin "python-v${{ inputs.version }}"
+
+      - name: Create GitHub Release
+        if: ${{ !inputs.dry-run }}
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: python-v${{ inputs.version }}
+          name: "Python v${{ inputs.version }}"
+          generate_release_notes: true
+          files: cli-artifacts/**/*.tar.gz
+
+      - name: Summary (dry run)
+        if: ${{ inputs.dry-run }}
+        run: |
+          echo "## Dry Run Summary" >> $GITHUB_STEP_SUMMARY
+          echo "Would release python-v${{ inputs.version }}" >> $GITHUB_STEP_SUMMARY
+          echo "### Wheels:" >> $GITHUB_STEP_SUMMARY
+          find dist -name "*.whl" -exec echo "- {}" \; >> $GITHUB_STEP_SUMMARY
+          echo "### CLI artifacts:" >> $GITHUB_STEP_SUMMARY
+          find cli-artifacts -name "*.tar.gz" -exec echo "- {}" \; >> $GITHUB_STEP_SUMMARY