Link Checker: Daily #118
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: 'Link Checker: Daily' | |
| # **What it does**: This script once a day checks all English links and reports in issue if any are broken. | |
| # **Why we have it**: We want to know if any links break internally or externally. | |
| # **Who does it impact**: Docs content. | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: '20 16 * * *' # Run every day at 16:20 UTC / 8:20 PST | |
| permissions: | |
| contents: read | |
| issues: write | |
| jobs: | |
| check_all_english_links: | |
| name: Check all links | |
| if: github.repository == 'github/docs-internal' | |
| runs-on: ubuntu-20.04-xl | |
| steps: | |
| - name: Check that gh CLI is installed | |
| run: gh --version | |
| - name: Check out repo's default branch | |
| uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1 | |
| - uses: ./.github/actions/node-npm-setup | |
| - name: Figure out which docs-early-access branch to checkout, if internal repo | |
| if: ${{ github.repository == 'github/docs-internal' }} | |
| id: check-early-access | |
| env: | |
| BRANCH_NAME: ${{ github.head_ref || github.ref_name }} | |
| GITHUB_TOKEN: ${{ secrets.DOCS_BOT_PAT_READPUBLICKEY }} | |
| run: node src/early-access/scripts/what-docs-early-access-branch.js | |
| - name: Check out docs-early-access too, if internal repo | |
| if: ${{ github.repository == 'github/docs-internal' }} | |
| uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1 | |
| with: | |
| repository: github/docs-early-access | |
| token: ${{ secrets.DOCS_BOT_PAT_READPUBLICKEY }} | |
| path: docs-early-access | |
| ref: ${{ steps.check-early-access.outputs.branch }} | |
| - name: Merge docs-early-access repo's folders | |
| if: ${{ github.repository == 'github/docs-internal' }} | |
| run: src/early-access/scripts/merge-early-access.sh | |
| - name: Restore disk-cache file for external link checking | |
| uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # v4.0.0 | |
| with: | |
| path: external-link-checker-db.json | |
| key: external-link-checker-${{ hashFiles('src/links/scripts/rendered-content-link-checker.ts') }} | |
| - name: Insight into external link checker DB json file (before) | |
| run: | | |
| if [ -f external-link-checker-db.json ]; then | |
| echo "external-link-checker-db.json exists" | |
| echo -n "Number of URLs in cache: " | |
| jq '.urls | keys_unsorted' external-link-checker-db.json | wc -l | |
| else | |
| echo "external-link-checker-db.json does not exist" | |
| fi | |
| - name: Run link checker | |
| env: | |
| DISABLE_REWRITE_ASSET_URLS: true | |
| LEVEL: 'critical' | |
| # Set this to true in repo scope to enable debug logs | |
| # ACTIONS_RUNNER_DEBUG = true | |
| ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} | |
| GITHUB_TOKEN: ${{ secrets.DOCS_BOT_PAT_WRITEORG_PROJECT }} | |
| REPORT_AUTHOR: docs-bot | |
| REPORT_LABEL: broken link report | |
| REPORT_REPOSITORY: github/docs-content | |
| CREATE_REPORT: true | |
| CHECK_EXTERNAL_LINKS: true | |
| PATIENT: true | |
| # This means that we'll *re-check* external URLs once a week. | |
| # But mind you that the number has a 10% chance of "jitter" | |
| # to avoid a stampeding herd when they all expire some day. | |
| EXTERNAL_LINK_CHECKER_MAX_AGE_DAYS: 7 | |
| # If we're unable to connect or the server returns a 50x error, | |
| # treat it as a warning and not as a broken link. | |
| EXTERNAL_SERVER_ERRORS_AS_WARNINGS: true | |
| FAIL_ON_FLAW: false | |
| timeout-minutes: 30 | |
| run: npm run rendered-content-link-checker | |
| - name: Insight into external link checker DB json file (after) | |
| run: | | |
| if [ -f external-link-checker-db.json ]; then | |
| echo "external-link-checker-db.json exists" | |
| echo -n "Number of URLs in cache: " | |
| jq '.urls | keys_unsorted' external-link-checker-db.json | wc -l | |
| else | |
| echo "external-link-checker-db.json does not exist" | |
| fi | |
| - uses: ./.github/actions/slack-alert | |
| if: ${{ failure() && github.event_name != 'workflow_dispatch' }} | |
| with: | |
| slack_channel_id: ${{ secrets.DOCS_ALERTS_SLACK_CHANNEL_ID }} | |
| slack_token: ${{ secrets.SLACK_DOCS_BOT_TOKEN }} |