Check all English links #61
Workflow file for this run
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: Check all English links | |
| # **What it does**: This script once a day checks all English links and reports in issues. | |
| # **Why we have it**: We want to know if any links break. | |
| # **Who does it impact**: Docs content. | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: '40 19 * * *' # once a day at 19:40 UTC / 11:40 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 | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.DOCUBOT_READORG_REPO_WORKFLOW_SCOPES }} | |
| FIRST_RESPONDER_PROJECT: Docs content first responder | |
| REPORT_AUTHOR: docubot | |
| REPORT_LABEL: broken link report | |
| REPORT_REPOSITORY: github/docs-content | |
| steps: | |
| - name: Check that gh CLI is installed | |
| run: gh --version | |
| - name: Check out repo's default branch | |
| uses: actions/checkout@dcd71f646680f2efd8db4afa5ad64fdcba30e748 | |
| - name: Setup Node | |
| uses: actions/setup-node@17f8bd926464a1afa4c6a11669539e9c1ba77048 | |
| with: | |
| node-version: '16.15.0' | |
| cache: npm | |
| - name: Install dependencies | |
| run: npm ci | |
| - name: Cache nextjs build | |
| uses: actions/cache@48af2dc4a9e8278b89d7fa154b955c30c6aaab09 | |
| with: | |
| path: .next/cache | |
| key: ${{ runner.os }}-nextjs-${{ hashFiles('package*.json') }} | |
| - name: Build server | |
| run: npm run build | |
| - name: Start server in the background | |
| env: | |
| NODE_ENV: production | |
| PORT: 4000 | |
| # We don't want or need the changelog entries in this context. | |
| CHANGELOG_DISABLED: true | |
| # The default is 10s. But because this runs overnight, we can | |
| # be a lot more patient. | |
| REQUEST_TIMEOUT: 20000 | |
| # Don't care about CDN caching image URLs | |
| DISABLE_REWRITE_ASSET_URLS: true | |
| run: | | |
| node server.js > /tmp/stdout.log 2> /tmp/stderr.log & | |
| sleep 6 | |
| curl --retry-connrefused --retry 5 -I http://localhost:4000/ | |
| - if: ${{ failure() }} | |
| name: Debug server outputs on errors | |
| run: | | |
| echo "____STDOUT____" | |
| cat /tmp/stdout.log | |
| echo "____STDERR____" | |
| cat /tmp/stderr.log | |
| - name: Run script | |
| timeout-minutes: 120 | |
| env: | |
| # The default is 300 which works OK on a fast macbook pro | |
| # but not so well in Actions. | |
| LINKINATOR_CONCURRENCY: 100 | |
| LINKINATOR_LOG_FILE_PATH: linkinator.log | |
| run: | | |
| script/check-english-links.js > broken_links.md | |
| # check-english-links.js returns 0 if no links are broken, and 1 if any links | |
| # are broken. When an Actions step's exit code is 1, the action run's job status | |
| # is failure and the run ends. The following steps create an issue for the | |
| # broken link report only if any links are broken, so `if: ${{ failure() }}` | |
| # ensures the steps run despite the previous step's failure of the job. | |
| # | |
| # https://docs.github.com/actions/reference/context-and-expression-syntax-for-github-actions#job-status-check-functions | |
| - uses: actions/upload-artifact@6673cd052c4cd6fcf4b4e6e60ea986c889389535 | |
| with: | |
| name: linkinator_log | |
| path: linkinator.log | |
| - uses: actions/upload-artifact@6673cd052c4cd6fcf4b4e6e60ea986c889389535 | |
| if: ${{ failure() }} | |
| with: | |
| name: broken_links | |
| path: ./broken_links.md | |
| - if: ${{ failure() }} | |
| name: Get title for issue | |
| id: check | |
| run: echo "::set-output name=title::$(head -1 broken_links.md)" | |
| - if: ${{ failure() }} | |
| name: Create issue from file | |
| id: broken-link-report | |
| uses: peter-evans/create-issue-from-file@b4f9ee0a9d4abbfc6986601d9b1a4f8f8e74c77e | |
| with: | |
| token: ${{ env.GITHUB_TOKEN }} | |
| title: ${{ steps.check.outputs.title }} | |
| content-filepath: ./broken_links.md | |
| repository: ${{ env.REPORT_REPOSITORY }} | |
| labels: ${{ env.REPORT_LABEL }} | |
| - if: ${{ failure() }} | |
| name: Close and/or comment on old issues | |
| env: | |
| NEW_REPORT_URL: 'https://github.com/${{ env.REPORT_REPOSITORY }}/issues/${{ steps.broken-link-report.outputs.issue-number }}' | |
| run: | | |
| gh alias set list-reports "issue list \ | |
| --repo ${{ env.REPORT_REPOSITORY }} \ | |
| --author ${{ env.REPORT_AUTHOR }} \ | |
| --label '${{ env.REPORT_LABEL }}'" | |
| # Link to the previous report from the new report that triggered this | |
| # workflow run. | |
| previous_report_url=$(gh list-reports \ | |
| --state all \ | |
| --limit 2 \ | |
| --json url \ | |
| --jq '.[].url' \ | |
| | grep -v ${{ env.NEW_REPORT_URL }} | head -1) | |
| gh issue comment ${{ env.NEW_REPORT_URL }} --body "⬅️ [Previous report]($previous_report_url)" | |
| # If an old report is open and assigned to someone, link to the newer | |
| # report without closing the old report. | |
| for issue_url in $(gh list-reports \ | |
| --json assignees,url \ | |
| --jq '.[] | select (.assignees != []) | .url'); do | |
| if [ "$issue_url" != "${{ env.NEW_REPORT_URL }}" ]; then | |
| gh issue comment $issue_url --body "➡️ [Newer report](${{ env.NEW_REPORT_URL }})" | |
| fi | |
| done | |
| # Link to the newer report from any older report that is still open, | |
| # then close the older report and remove it from the first responder's | |
| # project board. | |
| for issue_url in $(gh list-reports \ | |
| --search 'no:assignee' \ | |
| --json url \ | |
| --jq '.[].url'); do | |
| if [ "$issue_url" != "${{ env.NEW_REPORT_URL }}" ]; then | |
| gh issue comment $issue_url --body "➡️ [Newer report](${{ env.NEW_REPORT_URL }})" | |
| gh issue close $issue_url | |
| gh issue edit $issue_url --remove-project "${{ env.FIRST_RESPONDER_PROJECT }}" | |
| fi | |
| done |