regression.yml

on:
  workflow_call:

concurrency:
  group: regression-${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-${{ github.run_id }}
  cancel-in-progress: true

env:
  CMAKE_BUILD_TYPE: Debug

jobs:
  run-regression:
    runs-on: ubuntu-24.04
    steps:
      - uses: actions/checkout@v4
      - name: Install system fonts
        # See checks.yml for why these packages are pinned.
        run: |
          sudo apt-get update
          sudo apt-get install -y --no-install-recommends \
            fonts-dejavu-core \
            fonts-liberation2 \
            fonts-freefont-ttf \
            fonts-urw-base35 \
            fonts-noto-core \
            fonts-noto-cjk
          fc-cache -f
          fc-list :lang=ko file
          if [ ! -f /usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc ]; then
            echo "NotoSansCJK-Regular.ttc is not where DOCLING_PARSE_CJK_FALLBACK_FONT expects it:"
            dpkg -L fonts-noto-cjk | grep -E '\.(ttc|otf|ttf)$' || true
            exit 1
          fi
          test -n "$(fc-list :lang=ko file)"
      - name: Install uv and set the python version
        uses: astral-sh/setup-uv@v5
        with:
          python-version: '3.13'
      - name: Cache HF regression corpus
        # HF_DATASET_REVISION in tests/constants.py is a pinned commit hash, so
        # hashing that file gives us automatic invalidation on bumps.
        uses: actions/cache@v4
        with:
          path: tests/data
          key: hf-regression-${{ hashFiles('tests/constants.py') }}
      - name: Sync and install with uv
        run: |
          uv sync --frozen --all-extras
          ls docling_parse/pdf_parsers*.so
      - name: Regression tests
        env:
          DOCLING_PARSE_CJK_FALLBACK_FONT: /usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc
        run: |
          uv run pytest -v tests/test_regression_*.py