mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
16829939cf
* Export of DrawingML figures into docling document
* Adding libreoffice env var and libreoffice to checks image
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* DCO Remediation Commit for Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
I, Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>, hereby add my Signed-off-by to this commit: 9518fffcad
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Enforcing apt get update
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* Only display drawingml warning once per document
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
* add util to test libreoffice and exclude files from test when not found
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* check libreoffice only once
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
* Only initialise converter if needed
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
---------
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
340 lines
11 KiB
YAML
340 lines
11 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|offline_convert|pictures_description|pictures_description_api|vlm_pipeline_api_model|granitedocling_repetition_stopping)\.py$'
|
|
|
|
jobs:
|
|
lint:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
python-version: ['3.12']
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v6
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
enable-cache: true
|
|
|
|
- name: Set pre-commit cache key
|
|
run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> "$GITHUB_ENV"
|
|
|
|
- name: Cache pre-commit environments
|
|
uses: actions/cache@v4
|
|
with:
|
|
path: ~/.cache/pre-commit
|
|
key: pre-commit|${{ 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: ['3.9', '3.10', '3.11', '3.12', '3.13']
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- 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@v4
|
|
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@v6
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Cache Models
|
|
uses: actions/cache@v4
|
|
with:
|
|
path: |
|
|
~/.cache/huggingface
|
|
~/.cache/modelscope
|
|
~/.EasyOCR/
|
|
key: models-cache
|
|
|
|
- name: Pre-download Models
|
|
run: uv run python -c "import easyocr; reader = easyocr.Reader(['en', 'fr', 'de', 'es'])"
|
|
|
|
- name: Run tests for GROUP1
|
|
run: |
|
|
echo "--- Running tests ---"
|
|
GROUP1=$(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: ['3.9', '3.10', '3.11', '3.12', '3.13']
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- 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@v4
|
|
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@v6
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Cache Models
|
|
uses: actions/cache@v4
|
|
with:
|
|
path: |
|
|
~/.cache/huggingface
|
|
~/.cache/modelscope
|
|
~/.EasyOCR/
|
|
key: models-cache
|
|
|
|
- name: Pre-download Models
|
|
run: uv run python -c "import easyocr; reader = easyocr.Reader(['en', 'fr', 'de', 'es'])"
|
|
|
|
- name: Run tests for GROUP2
|
|
run: |
|
|
echo "--- Running tests ---"
|
|
GROUP2=$(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: ['3.9', '3.10', '3.11', '3.12', '3.13']
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- 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@v4
|
|
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@v6
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Install Python Dependencies
|
|
run: uv sync --frozen --all-extras
|
|
|
|
- name: Cache Models
|
|
uses: actions/cache@v4
|
|
with:
|
|
path: |
|
|
~/.cache/huggingface
|
|
~/.cache/modelscope
|
|
~/.EasyOCR/
|
|
key: models-cache
|
|
|
|
- name: Pre-download Models
|
|
run: uv run python -c "import easyocr; reader = easyocr.Reader(['en', 'fr', 'de', 'es'])"
|
|
|
|
- name: Run examples
|
|
run: |
|
|
echo "--- Creating output directory ---"
|
|
mkdir -p scratch
|
|
|
|
echo "--- Running examples ---"
|
|
|
|
summary_file="runtime_summary.log"
|
|
echo "--- Example Runtimes ---" > "$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
|
|
|
|
build-package:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
matrix:
|
|
python-version: ['3.12']
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v6
|
|
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@v4
|
|
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@v4
|
|
with:
|
|
name: python-package-distributions
|
|
path: dist/
|
|
|
|
- name: Install uv and set the python version
|
|
uses: astral-sh/setup-uv@v6
|
|
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
|