mirror of
https://github.com/docling-project/docling.git
synced 2026-03-27 05:11:23 +00:00
1c74a9b9c7
- Implementation of HTML backend that (optionally) uses headless browser (via Playwright) to materialize HTML pages into images, and add provenances with bboxes to all elements in the converted docling document. - Conversion preserves reading order given by HTML DOM tree - Added support for HTML "input" fields: checkboxes, radiobuttons, text inputs, etc. - Added support to Key-Value convention in HTML (i.e. elements with id "key1" and "key1_value1" will be paired as key-values, see test cases as examples) - Heuristic that glues independent inline HTML elements with single-character text in them into larger text blocks - Support for inline styling (bold, italic, etc.) Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
454 lines
16 KiB
YAML
454 lines
16 KiB
YAML
on:
|
|
workflow_call:
|
|
inputs:
|
|
push_coverage:
|
|
type: boolean
|
|
description: "If true, the coverage results are pushed to codecov.io."
|
|
default: true
|
|
secrets:
|
|
CODECOV_TOKEN:
|
|
required: false
|
|
|
|
env:
|
|
HF_HUB_DOWNLOAD_TIMEOUT: "90"
|
|
HF_HUB_ETAG_TIMEOUT: "90"
|
|
UV_FROZEN: "1"
|
|
PYTEST_ML: |-
|
|
tests/test_e2e_conversion.py
|
|
tests/test_e2e_ocr_conversion.py
|
|
tests/test_backend_webp.py
|
|
tests/test_asr_pipeline.py
|
|
tests/test_threaded_pipeline.py
|
|
PYTEST_TO_SKIP: |-
|
|
EXAMPLES_TO_SKIP: '^(batch_convert|compare_vlm_models|minimal|minimal_vlm_pipeline|minimal_asr_pipeline|export_multimodal|custom_convert|develop_picture_enrichment|rapidocr_with_custom_models|suryaocr_with_custom_models|offline_convert|pictures_description|pictures_description_api|vlm_pipeline_api_model|granitedocling_repetition_stopping|mlx_whisper_example|gpu_standard_pipeline|gpu_vlm_pipeline|demo_layout_vlm|post_process_ocr_with_vlm|run_with_formats_html_rendered|run_with_formats_html_rendered_mp)\.py$|xbrl_conversion\.ipynb$'
|
|
|
|
jobs:
|
|
lint:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
python-version: ["3.12"]
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v7
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
enable-cache: true
|
|
|
|
- name: Set pre-commit cache key
|
|
run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> "$GITHUB_ENV"
|
|
|
|
- name: Cache pre-commit environments
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: ~/.cache/pre-commit
|
|
key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
|
|
restore-keys: |
|
|
pre-commit|${{ env.PY }}|
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Check style
|
|
run: |
|
|
echo "--- Running pre-commit style checks ---"
|
|
uv run pre-commit run --all-files
|
|
|
|
run-tests-1:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
|
|
- name: Grant permissions to APT cache directory # allows restore
|
|
run: sudo chown -R $USER:$USER /var/cache/apt/archives
|
|
|
|
- name: Cache APT packages
|
|
id: apt-cache
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: /var/cache/apt/archives
|
|
key: apt-packages-${{ runner.os }}-${{ hashFiles('.github/workflows/checks.yml') }}
|
|
restore-keys: |
|
|
apt-packages-${{ runner.os }}-
|
|
|
|
- name: Install System Dependencies
|
|
run: |
|
|
sudo apt-get -qq update
|
|
sudo apt-get -qq install -y ffmpeg tesseract-ocr tesseract-ocr-eng tesseract-ocr-fra tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-script-latn libleptonica-dev libtesseract-dev libreoffice pkg-config
|
|
|
|
- name: Set TESSDATA_PREFIX
|
|
run: echo "TESSDATA_PREFIX=$(dpkg -L tesseract-ocr-eng | grep tessdata$)" >> "$GITHUB_ENV"
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v7
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Cache Models
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: |
|
|
~/.cache/huggingface
|
|
~/.cache/modelscope
|
|
~/.EasyOCR/
|
|
key: models-cache
|
|
|
|
- name: Pre-download Models
|
|
run: uv run python -c "import easyocr; reader = easyocr.Reader(['en', 'fr', 'de', 'es'])"
|
|
|
|
- name: Run tests for GROUP1
|
|
run: |
|
|
echo "--- Running tests ---"
|
|
GROUP1=$(echo "$PYTEST_ML" | sed -e 's/^/--ignore=/' | tr '\n' ' ')
|
|
echo "Running tests for GROUP1"
|
|
uv run pytest -v --durations=0 --cov=docling --cov-report=xml --cov-context=test $GROUP1
|
|
|
|
- name: Upload coverage to Codecov
|
|
if: inputs.push_coverage
|
|
uses: codecov/codecov-action@v5
|
|
with:
|
|
token: ${{ secrets.CODECOV_TOKEN }}
|
|
files: ./coverage.xml
|
|
flags: run-tests-1
|
|
|
|
- name: Grant permissions to APT cache directory # allows backup
|
|
run: sudo chown -R $USER:$USER /var/cache/apt/archives
|
|
|
|
run-tests-2:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
|
|
- name: Grant permissions to APT cache directory # allows restore
|
|
run: sudo chown -R $USER:$USER /var/cache/apt/archives
|
|
|
|
- name: Cache APT packages
|
|
id: apt-cache
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: /var/cache/apt/archives
|
|
key: apt-packages-${{ runner.os }}-${{ hashFiles('.github/workflows/checks.yml') }}
|
|
restore-keys: |
|
|
apt-packages-${{ runner.os }}-
|
|
|
|
- name: Install System Dependencies
|
|
run: |
|
|
sudo apt-get -qq update
|
|
sudo apt-get -qq install -y ffmpeg tesseract-ocr tesseract-ocr-eng tesseract-ocr-fra tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-script-latn libleptonica-dev libtesseract-dev libreoffice pkg-config
|
|
|
|
- name: Set TESSDATA_PREFIX
|
|
run: echo "TESSDATA_PREFIX=$(dpkg -L tesseract-ocr-eng | grep tessdata$)" >> "$GITHUB_ENV"
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v7
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Cache Models
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: |
|
|
~/.cache/huggingface
|
|
~/.cache/modelscope
|
|
~/.EasyOCR/
|
|
key: models-cache
|
|
|
|
- name: Pre-download Models
|
|
run: uv run python -c "import easyocr; reader = easyocr.Reader(['en', 'fr', 'de', 'es'])"
|
|
|
|
- name: Run tests for GROUP2
|
|
run: |
|
|
echo "--- Running tests ---"
|
|
GROUP2=$(echo "$PYTEST_ML" | tr '\n' ' ')
|
|
echo "Running tests for GROUP2"
|
|
DESELECT_OPT=""
|
|
if [ -n "$PYTEST_TO_SKIP" ]; then
|
|
DESELECT_OPT="--deselect $PYTEST_TO_SKIP"
|
|
fi
|
|
echo "Running tests for GROUP2"
|
|
uv run pytest -v --durations=0 --cov=docling --cov-report=xml --cov-context=test $GROUP2 $DESELECT_OPT
|
|
|
|
- name: Upload coverage to Codecov
|
|
if: inputs.push_coverage
|
|
uses: codecov/codecov-action@v5
|
|
with:
|
|
token: ${{ secrets.CODECOV_TOKEN }}
|
|
files: ./coverage.xml
|
|
flags: run-tests-2
|
|
|
|
- name: Grant permissions to APT cache directory # allows backup
|
|
run: sudo chown -R $USER:$USER /var/cache/apt/archives
|
|
|
|
run-examples:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
|
|
- name: Grant permissions to APT cache directory # allows restore
|
|
run: sudo chown -R $USER:$USER /var/cache/apt/archives
|
|
|
|
- name: Cache APT packages
|
|
id: apt-cache
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: /var/cache/apt/archives
|
|
key: apt-packages-${{ runner.os }}-${{ hashFiles('.github/workflows/checks.yml') }}
|
|
restore-keys: |
|
|
apt-packages-${{ runner.os }}-
|
|
|
|
- name: Install System Dependencies
|
|
run: |
|
|
sudo apt-get -qq update
|
|
sudo apt-get -qq install -y ffmpeg tesseract-ocr tesseract-ocr-eng tesseract-ocr-fra tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-script-latn libleptonica-dev libtesseract-dev libreoffice pkg-config
|
|
|
|
- name: Set TESSDATA_PREFIX
|
|
run: echo "TESSDATA_PREFIX=$(dpkg -L tesseract-ocr-eng | grep tessdata$)" >> "$GITHUB_ENV"
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v7
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Cache Models
|
|
uses: actions/cache@v5
|
|
with:
|
|
path: |
|
|
~/.cache/huggingface
|
|
~/.cache/modelscope
|
|
~/.EasyOCR/
|
|
key: models-cache
|
|
|
|
- name: Free up disk space
|
|
run: |
|
|
df -h
|
|
sudo rm -rf /usr/share/dotnet
|
|
sudo rm -rf /usr/local/lib/android
|
|
sudo rm -rf /opt/ghc
|
|
sudo apt-get clean
|
|
df -h
|
|
|
|
- name: Run examples
|
|
run: |
|
|
echo "--- Creating output directory ---"
|
|
mkdir -p scratch
|
|
|
|
echo "--- Running examples ---"
|
|
|
|
summary_file="runtime_summary.log"
|
|
echo "--- Example Runtimes ---" > "$summary_file"
|
|
|
|
for file in docs/examples/*.py; do
|
|
if [[ "$(basename "$file")" =~ ${EXAMPLES_TO_SKIP} ]]; then
|
|
echo "Skipping example: $(basename "$file")"
|
|
else
|
|
echo "--- Running example $(basename "$file") ---"
|
|
|
|
start_time=$SECONDS
|
|
|
|
uv run --no-sync python "$file" || exit 1
|
|
duration=$((SECONDS - start_time))
|
|
echo "Finished in ${duration}s."
|
|
|
|
echo "$(basename "$file"): ${duration}s" >> "$summary_file"
|
|
fi
|
|
done
|
|
|
|
echo
|
|
echo "==================================="
|
|
echo " Final Runtime Summary "
|
|
echo "==================================="
|
|
cat "$summary_file"
|
|
echo "==================================="
|
|
|
|
- name: Grant permissions to APT cache directory # allows backup
|
|
run: sudo chown -R $USER:$USER /var/cache/apt/archives
|
|
|
|
test-pip-install-no-lock:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- name: Install uv
|
|
uses: astral-sh/setup-uv@v6
|
|
|
|
- name: Test pip install across Python versions
|
|
run: |
|
|
for py_version in 3.10 3.11 3.12 3.13 3.14; do
|
|
echo "=========================================="
|
|
echo "Testing Python $py_version"
|
|
echo "=========================================="
|
|
|
|
# Create virtual environment with uv
|
|
uv venv /tmp/venv-${py_version} --python=${py_version}
|
|
source /tmp/venv-${py_version}/bin/activate
|
|
|
|
# Install package with pip (no lock file)
|
|
uv pip install --torch-backend=cpu -e .[easyocr,tesserocr,vlm,rapidocr,asr]
|
|
|
|
# Run basic import test
|
|
python -c "import docling; from docling.document_converter import DocumentConverter; print('Import successful for Python ${py_version}')"
|
|
|
|
# Cleanup
|
|
deactivate
|
|
rm -rf /tmp/venv-${py_version}
|
|
|
|
echo "Python $py_version: PASSED"
|
|
echo ""
|
|
done
|
|
|
|
test-pip-install-no-dev-headers:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- name: Install uv
|
|
uses: astral-sh/setup-uv@v6
|
|
|
|
- name: Test pip install without dev headers across Python versions
|
|
run: |
|
|
for py_version in 3.10 3.11 3.12 3.13 3.14; do
|
|
echo "=========================================="
|
|
echo "Testing Python $py_version (no dev headers)"
|
|
echo "=========================================="
|
|
|
|
# Create virtual environment with uv
|
|
uv venv /tmp/venv-nodev-${py_version} --python=${py_version}
|
|
source /tmp/venv-nodev-${py_version}/bin/activate
|
|
|
|
# Find and remove Python.h from the Python installation
|
|
echo "Removing Python development headers from Python installation..."
|
|
python_include_dir=$(python -c "import sysconfig; print(sysconfig.get_path('include'))")
|
|
echo "Python include directory: $python_include_dir"
|
|
|
|
if [ -f "$python_include_dir/Python.h" ]; then
|
|
echo "Found Python.h, removing it and other headers..."
|
|
# Use sudo if the directory is system-owned
|
|
if [ -w "$python_include_dir" ]; then
|
|
rm -rf "$python_include_dir"/*
|
|
else
|
|
sudo rm -rf "$python_include_dir"/*
|
|
fi
|
|
echo "✓ Headers removed"
|
|
else
|
|
echo "Warning: Python.h not found at expected location"
|
|
fi
|
|
|
|
# Verify that compilation fails without dev headers
|
|
# Try to install numpy from source (sdist) - this should fail
|
|
echo "Verifying compilation fails without dev headers..."
|
|
set +e # Temporarily allow command to fail
|
|
uv pip install --no-binary=:all: numpy==1.26.4 > /tmp/numpy-install-${py_version}.log 2>&1
|
|
numpy_exit_code=$?
|
|
set -e # Re-enable exit on error
|
|
|
|
if [ $numpy_exit_code -eq 0 ]; then
|
|
echo "ERROR: numpy installation from source succeeded, but it should have failed without dev headers!"
|
|
cat /tmp/numpy-install-${py_version}.log
|
|
exit 1
|
|
else
|
|
echo "✓ Compilation correctly failed without dev headers (expected behavior)"
|
|
# Check that the error mentions missing Python.h or similar
|
|
if grep -qi "Python.h\|fatal error.*\.h" /tmp/numpy-install-${py_version}.log; then
|
|
echo "✓ Error message confirms missing development headers"
|
|
else
|
|
echo "Warning: Error message doesn't explicitly mention missing headers, but compilation failed as expected"
|
|
fi
|
|
fi
|
|
|
|
# Install package with pip (no lock file, no compilation)
|
|
# Install without extras that require compilation (tesserocr requires dev headers)
|
|
# Note: Not using --only-binary since some packages are sdist-only but don't require compilation
|
|
uv pip install --torch-backend=cpu -e .[easyocr,vlm,rapidocr,asr]
|
|
|
|
# Run basic import test
|
|
python -c "import docling; from docling.document_converter import DocumentConverter; print('Import successful for Python ${py_version} without dev headers')"
|
|
|
|
# Cleanup
|
|
deactivate
|
|
rm -rf /tmp/venv-nodev-${py_version}
|
|
|
|
echo "Python $py_version (no dev headers): PASSED"
|
|
echo ""
|
|
done
|
|
|
|
build-package:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
matrix:
|
|
python-version: ["3.12"]
|
|
steps:
|
|
- uses: actions/checkout@v6
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v7
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
enable-cache: true
|
|
|
|
- name: Install dependencies
|
|
run: uv sync --all-extras
|
|
|
|
- name: Build package
|
|
run: uv build
|
|
|
|
- name: Check content of wheel
|
|
run: unzip -l dist/*.whl
|
|
|
|
- name: Store the distribution packages
|
|
uses: actions/upload-artifact@v6
|
|
with:
|
|
name: python-package-distributions
|
|
path: dist/
|
|
|
|
test-package:
|
|
needs:
|
|
- build-package
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
matrix:
|
|
python-version: ["3.12"]
|
|
steps:
|
|
- name: Download all the dists
|
|
uses: actions/download-artifact@v7
|
|
with:
|
|
name: python-package-distributions
|
|
path: dist/
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v7
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
activate-environment: true
|
|
enable-cache: false
|
|
|
|
- name: Install package
|
|
run: |
|
|
uv pip install dist/*.whl
|
|
|
|
- name: Run docling
|
|
run: uv run docling --help
|