.github/workflows/superset-docs-verify.yml

name: Docs Testing

on:
  pull_request:
    paths:
      - "docs/**"
      - "superset/db_engine_specs/**"
      - ".github/workflows/superset-docs-verify.yml"
    types: [synchronize, opened, reopened, ready_for_review]
  # zizmor: ignore[dangerous-triggers] - runs in base-branch context and only consumes artifacts from the trusted upstream workflow
  workflow_run:
    workflows: ["Python-Integration"]
    types: [completed]

# cancel previous workflow jobs for PRs
concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.workflow_run.head_sha || github.run_id }}
  cancel-in-progress: true

permissions:
  contents: read

jobs:
  linkinator:
    # See docs here: https://github.com/marketplace/actions/linkinator
    # Only run on pull_request, not workflow_run
    if: github.event_name == 'pull_request'
    name: Link Checking
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      # Do not bump this linkinator-action version without opening
      # an ASF Infra ticket to allow the new version first!
      - uses: JustinBeckwith/linkinator-action@af984b9f30f63e796ae2ea5be5e07cb587f1bbd9 # v2.3
        continue-on-error: true # This will make the job advisory (non-blocking, no red X)
        with:
          paths: "**/*.md, **/*.mdx"
          linksToSkip: >-
            ^https://github.com/apache/(superset|incubator-superset)/(pull|issues)/\d+,
            ^https://github.com/apache/(superset|incubator-superset)/commit/[a-f0-9]+,
            superset-frontend/.*CHANGELOG\.md,
            http://localhost:8088/,
            http://127.0.0.1:3000/,
            http://localhost:9001/,
            https://charts.bitnami.com/bitnami,
            https://www.li.me/,
            https://www.fanatics.com/,
            https://tails.com/gb/,
            https://www.techaudit.info/,
            https://avetilearning.com/,
            https://www.udemy.com/,
            https://trustmedis.com/,
            http://theiconic.com.au/,
            https://dev.mysql.com/doc/refman/5.7/en/innodb-limits.html,
            ^https://img\.shields\.io/.*,
            https://vkusvill.ru/,
            https://www.linkedin.com/in/mark-thomas-b16751158/,
            https://theiconic.com.au/,
            https://wattbewerb.de/,
            https://timbr.ai/,
            https://opensource.org/license/apache-2-0,
            https://www.plaidcloud.com/

  build-on-pr:
    # Build docs when PR changes docs/** (uses committed databases.json)
    if: github.event_name == 'pull_request'
    name: Build (PR trigger)
    runs-on: ubuntu-24.04
    defaults:
      run:
        working-directory: docs
    steps:
      - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
          submodules: recursive
      - name: Set up Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
        with:
          node-version-file: "./docs/.nvmrc"
      - name: yarn install
        run: |
          yarn install --check-cache
      - name: Lint docs links
        # Fast source-level check for bare relative internal links
        # like `[Foo](../foo)` that Docusaurus's onBrokenLinks
        # setting can't catch. Runs in seconds; fails fast before
        # the expensive build step.
        run: |
          yarn lint:docs-links
      - name: yarn typecheck
        run: |
          yarn typecheck
      - name: yarn build
        run: |
          yarn build

  build-after-tests:
    # Build docs after integration tests complete (uses fresh diagnostics)
    # Only runs if integration tests succeeded
    if: >
      github.event_name == 'workflow_run' &&
      github.event.workflow_run.conclusion == 'success' &&
      github.event.workflow_run.head_repository.full_name == github.repository
    name: Build (after integration tests)
    runs-on: ubuntu-24.04
    defaults:
      run:
        working-directory: docs
    steps:
      - name: "Checkout PR head: ${{ github.event.workflow_run.head_sha }}"
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          ref: ${{ github.event.workflow_run.head_sha }}
          persist-credentials: false
          submodules: recursive
      - name: Set up Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
        with:
          node-version-file: "./docs/.nvmrc"
      - name: yarn install
        run: |
          yarn install --check-cache
      - name: Download database diagnostics from integration tests
        uses: dawidd6/action-download-artifact@b6e2e70617bc3265edd6dab6c906732b2f1ae151 # v21
        with:
          workflow: superset-python-integrationtest.yml
          run_id: ${{ github.event.workflow_run.id }}
          name: database-diagnostics
          path: docs/src/data/
          if_no_artifact_found: "warning"
      - name: Use fresh diagnostics
        run: |
          if [ -f "src/data/databases-diagnostics.json" ]; then
            echo "Using fresh diagnostics from integration tests"
            mv src/data/databases-diagnostics.json src/data/databases.json
          else
            echo "Warning: No diagnostics artifact found, using committed data"
          fi
      - name: yarn typecheck
        run: |
          yarn typecheck
      - name: yarn build
        run: |
          yarn build