name: 'Link Checker: All English'

# **What it does**: Renders the content of every page and check all internal links.
# **Why we have it**: To make sure all links connect correctly.
# **Who does it impact**: Docs content.

on:
  workflow_dispatch:
  merge_group:
  push:
    branches:
      - main
  pull_request:

permissions:
  contents: read
  # Needed for the 'trilom/file-changes-action' action
  pull-requests: read

# This allows a subsequently queued workflow run to interrupt previous runs
concurrency:
  group: '${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}'
  cancel-in-progress: true

jobs:
  check-links:
    runs-on: ${{ fromJSON('["ubuntu-latest", "ubuntu-20.04-xl"]')[github.repository == 'github/docs-internal'] }}
    steps:
      - name: Checkout
        uses: actions/checkout@dcd71f646680f2efd8db4afa5ad64fdcba30e748

      - name: Setup node
        uses: actions/setup-node@17f8bd926464a1afa4c6a11669539e9c1ba77048
        with:
          node-version: '16.15.0'
          cache: npm

      - name: Install
        run: npm ci

      - name: Gather files changed
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          PR: ${{ github.event.pull_request.number }}
          HEAD: ${{ github.event.pull_request.head.ref || github.event.merge_group.head_ref }}
        run: |
          # Find the file diff in the pull request or merge group
          # If its a pull request, use the faster call to the GitHub API
          # For push, workflow_dispatch, and merge_group, use git diff
          if [ -n "$PR" ]
          then
            echo __ running gh pr diff __
            DIFF=`gh pr diff $PR --name-only`
          elif [ -n "$HEAD" ]
          then
            echo __ running git fetch main __
            git fetch origin main --depth 1
            echo __ running git diff __
            DIFF=`git diff --name-only origin/main`
          else
            echo __ no head, empty diff __
            DIFF=''
          fi
          # So we can inspect the output
          echo __ DIFF found __
          echo $DIFF

          # Formats into single line JSON array, removing any empty strings
          echo __ format, write to files.json __
          echo $DIFF | \
            tr ' ' '\n' | \
            jq --raw-input | \
            jq --slurp --compact-output 'map(select(length > 0))' \
            > $HOME/files.json

      - name: Link check (warnings, changed files)
        env:
          # Don't care about CDN caching image URLs
          DISABLE_REWRITE_ASSET_URLS: true
        run: |
          # Note as of Aug 2022, we *don't* check external links
          # on the pages you touched in the PR. We could enable that
          # but it has the added risk of false positives blocking CI.
          # We are using this script for the daily/nightly checker that
          # checks external links too. Once we're confident it really works
          # well, we can consider enabling it here on every content PR too.

          ./script/rendered-content-link-checker.js \
            --language en \
            --max 100 \
            --check-anchors \
            --check-images \
            --verbose \
            --list $HOME/files.json

      - name: Link check (critical, all files)
        env:
          # Don't care about CDN caching image URLs
          DISABLE_REWRITE_ASSET_URLS: true
        run: |
          ./script/rendered-content-link-checker.js \
            --language en \
            --exit \
            --verbose \
            --check-images \
            --level critical