xinmi/.github/workflows/docreader.yml

name: DocReader

on:
  push:
    branches: [main]
    paths:
      - "docreader/**"
      - "go.mod"
      - "go.sum"
      - "testdata/**"
      - "docker/Dockerfile.docreader"
      - "docker/Dockerfile.odl-hybrid"
      - ".github/workflows/docreader.yml"
  pull_request:
    paths:
      - "docreader/**"
      - "go.mod"
      - "go.sum"
      - "testdata/**"
      - "docker/Dockerfile.docreader"
      - "docker/Dockerfile.odl-hybrid"
      - ".github/workflows/docreader.yml"
  workflow_dispatch:

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

env:
  PYTHON_VERSION: "3.10.18"
  GO_VERSION: "1.26"
  GOPROXY: https://proxy.golang.org,direct

jobs:
  verify:
    name: Python tests and Go client tests
    runs-on: ubuntu-latest
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@v6

      - uses: actions/setup-python@v6
        with:
          python-version: ${{ env.PYTHON_VERSION }}

      - name: Install uv
        uses: astral-sh/setup-uv@v4
        with:
          enable-cache: true
          cache-dependency-glob: docreader/uv.lock

      - name: Install Python dependencies
        run: uv sync --project docreader --locked --no-dev --python ${{ env.PYTHON_VERSION }}

      - name: Compile Python sources
        run: uv run --project docreader --python ${{ env.PYTHON_VERSION }} python -m compileall -q docreader

      - name: Run Python tests
        run: uv run --project docreader --python ${{ env.PYTHON_VERSION }} python -m unittest discover -s docreader/tests -p "test_*.py" -v

      - uses: actions/setup-go@v6
        with:
          go-version: ${{ env.GO_VERSION }}
          cache: true

      - name: Download Go modules
        run: go mod download

      # TestReadURL drives the live WebParser (Playwright WebKit). Without the
      # browser binary, scrape used to return "Error parsing web page: …" as
      # markdown and the Go client treated that as success. After #2883 the
      # parser raises, so CI must install WebKit the same way the image does.
      - name: Cache Playwright browsers
        uses: actions/cache@v4
        with:
          path: ~/.cache/ms-playwright
          key: ${{ runner.os }}-playwright-webkit-${{ hashFiles('docreader/uv.lock') }}

      - name: Install Playwright WebKit
        run: uv run --project docreader --python ${{ env.PYTHON_VERSION }} python -m playwright install --with-deps webkit

      - name: Start DocReader gRPC server
        run: |
          uv run --project docreader --python ${{ env.PYTHON_VERSION }} python -m docreader.main &
          echo $! > /tmp/docreader.pid
          for i in $(seq 1 30); do
            if nc -z 127.0.0.1 50051 2>/dev/null; then
              echo "DocReader gRPC server is ready"
              exit 0
            fi
            sleep 1
          done
          echo "DocReader gRPC server failed to start"
          exit 1

      - name: Run Go client tests
        run: go test ./docreader/client ./docreader/proto

      - name: Stop DocReader gRPC server
        if: always()
        run: |
          if [ -f /tmp/docreader.pid ]; then
            kill "$(cat /tmp/docreader.pid)" 2>/dev/null || true
          fi