MinerU/.github/workflows/cli.yml

name: mineru-cli-test

on:
  push:
    branches: [master, dev]
  pull_request:
    branches: [master, dev]
  workflow_dispatch:
  workflow_call:

permissions:
  contents: read

concurrency:
  group: cli-${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' || (github.event_name == 'push' && startsWith(github.ref, 'refs/heads/')) }}

env:
  PYTHONUTF8: '1'

jobs:
  changes:
    # fork 保持跳过；来自 fork 的上游 PR 仍在上游仓库执行只读测试。
    if: github.repository == 'opendatalab/MinerU'
    runs-on: ubuntu-latest
    timeout-minutes: 5
    outputs:
      code: ${{ steps.changes.outputs.code }}
    steps:
      - uses: actions/checkout@v6
        with:
          ref: ${{ github.sha }}
          fetch-depth: 2
          persist-credentials: false
      - uses: actions/setup-python@v6
        with:
          python-version: '3.12'
      - id: changes
        run: python scripts/ci/changes.py

  lint:
    needs: changes
    if: needs.changes.outputs.code == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      - uses: actions/checkout@v6
        with:
          ref: ${{ github.sha }}
          persist-credentials: false
      - uses: actions/setup-python@v6
        with:
          python-version: '3.11'
      - uses: astral-sh/setup-uv@v7
      - name: Install lightweight check tools
        run: |
          uv venv
          uv pip install ruff==0.14.2 pytest packaging
      - name: Check Python and CI helpers
        run: |
          uv run --no-project --no-sync python -m compileall -q mineru scripts tests
          # 存量注解问题分批治理；全仓先阻止语法错误及未定义名称。
          uv run --no-project --no-sync ruff check --select E9,F63,F7,F82 mineru scripts tests
          uv run --no-project --no-sync ruff check scripts/ci tests/ci
          uv run --no-project --no-sync ruff format --check scripts/ci tests/ci
          uv run --no-project --no-sync python -m pytest -o addopts='' --confcutdir=tests/ci tests/ci

  cli-test:
    needs: changes
    if: needs.changes.outputs.code == 'true'
    runs-on: ${{ matrix.os }}
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest, windows-latest, macos-latest]
        python: ['3.11', '3.12', '3.13', '3.14']
    defaults:
      run:
        shell: bash
    steps:
      - uses: actions/checkout@v6
        with:
          ref: ${{ github.sha }}
          persist-credentials: false
      - uses: actions/setup-python@v6
        with:
          python-version: ${{ matrix.python }}
      - uses: astral-sh/setup-uv@v7
      - uses: actions/setup-node@v6
        if: runner.os == 'Linux'
        with:
          node-version: '22'
      - name: Install and check dependencies
        run: |
          uv venv --python "$(python -c 'import sys; print(sys.executable)')"
          uv pip install --only-binary=docvortex '.[test]'
          uv pip check
      - name: Run Linux unit tests
        if: runner.os == 'Linux'
        run: |
          command -v jq >/dev/null || { sudo apt-get update && sudo apt-get install -y --no-install-recommends jq; }
          coverage=()
          if [[ '${{ matrix.python }}' == '3.12' ]]; then
            coverage=(--cov=mineru --cov-report=term:skip-covered --cov-report=xml:build/ci/coverage.xml --cov-precision=2 --cov-fail-under=58)
          fi
          uv run --no-project --no-sync python -m pytest -o addopts='' --strict-markers \
            -m 'not torch' --durations=30 --junitxml=build/ci/tests.xml "${coverage[@]}" tests/unittest
      - name: Run Windows and macOS public contract tests
        if: runner.os != 'Linux'
        run: |
          uv run --no-project --no-sync python -m pytest -o addopts='' --strict-markers \
            --durations=30 --junitxml=build/ci/tests.xml \
            tests/unittest/test_docvortex_import_boundary.py \
            tests/unittest/test_backend_architecture.py \
            tests/unittest/test_docvortex_protocol.py \
            tests/unittest/test_docvortex_routing.py \
            tests/unittest/test_parser_api_contract.py
      - name: Retain test reports
        if: ${{ always() }}
        uses: actions/upload-artifact@v6
        with:
          name: tests-${{ matrix.os }}-py${{ matrix.python }}
          path: build/ci/*.xml
          retention-days: 14
          if-no-files-found: warn

  torch-test:
    needs: changes
    if: needs.changes.outputs.code == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@v6
        with:
          ref: ${{ github.sha }}
          persist-credentials: false
      - uses: actions/setup-python@v6
        with:
          python-version: '3.12'
      - uses: astral-sh/setup-uv@v7
        with:
          cache-suffix: torch-cpu
      - name: Install CPU Torch test dependencies
        run: |
          uv venv
          # 先安装 CPU wheel，宿主求解复用已安装的兼容版本，避免下载 CUDA 运行时。
          uv pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
          uv pip install --only-binary=docvortex '.[test,torch]'
          uv pip check
          uv run --no-project --no-sync python -c 'import torch, torchvision, transformers; assert torch.version.cuda is None'
      - name: Run Torch regressions
        run: |
          uv run --no-project --no-sync python -m pytest -o addopts='' --strict-markers \
            -m 'torch and not accelerator' --durations=30 --junitxml=build/ci/torch.xml tests/unittest
      - name: Retain Torch test report
        if: ${{ always() }}
        uses: actions/upload-artifact@v6
        with:
          name: tests-torch-cpu
          path: build/ci/torch.xml
          retention-days: 14
          if-no-files-found: warn

  ci-result:
    name: CI result
    needs: [changes, lint, cli-test, torch-test]
    if: ${{ always() && github.repository == 'opendatalab/MinerU' }}
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      - name: Require all applicable checks
        env:
          CHANGES_RESULT: ${{ needs.changes.result }}
          CODE_CHANGED: ${{ needs.changes.outputs.code }}
          LINT_RESULT: ${{ needs.lint.result }}
          TEST_RESULT: ${{ needs.cli-test.result }}
          TORCH_RESULT: ${{ needs.torch-test.result }}
        run: |
          test "$CHANGES_RESULT" = success
          if [[ "$CODE_CHANGED" == true ]]; then
            test "$LINT_RESULT" = success
            test "$TEST_RESULT" = success
            test "$TORCH_RESULT" = success
          else
            test "$CODE_CHANGED" = false
          fi