Test

Document missing setup prerequisites and env vars in README #14

	name: Test
	on:
	pull_request:
	paths:
	- "**"

	permissions:
	contents: read

	jobs:
	build:
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix:
	python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]

	steps:
	- name: Check out the code
	uses: actions/checkout@v4

	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v5
	with:
	python-version: ${{ matrix.python-version }}

	- name: Set up uv
	uses: astral-sh/setup-uv@v8.2.0

	- name: Install system dependencies
	run: \|
	sudo apt-get update
	sudo apt-get install -y --no-install-recommends libgomp1 libmagic1

	- name: Install dependencies
	run: uv sync --python ${{ matrix.python-version }} --group dev --extra ocr --frozen

	- name: Download NLTK data
	# nltk.download returns False on a failed download instead of raising,
	# which used to surface later as a baffling punkt_tab LookupError at
	# test collection. Retry transient failures and fail this step loudly.
	run: \|
	uv run python -c "
	import sys, time, nltk
	for pkg in ('punkt', 'punkt_tab', 'stopwords'):
	for attempt in range(5):
	if nltk.download(pkg):
	break
	time.sleep(10)
	else:
	sys.exit(f'failed to download nltk package {pkg!r}')
	"

	- name: Run tests (pure Python, no Java/Tika)
	run: \|
	uv run pytest -vv tests/ --runslow

Navigation Menu