Broken Link Check (full) #10
This file contains hidden or 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: Broken Link Check (full) | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: '0 0 * * 1' | |
| jobs: | |
| link-checker: | |
| runs-on: ubuntu-latest | |
| if: github.repository == 'hashicorp/web-unified-docs' | |
| steps: | |
| - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4.1.4 | |
| - name: Run lychee link checker | |
| id: lychee | |
| uses: lycheeverse/lychee-action@f613c4a64e50d792e0b31ec34bbcbba12263c6a6 # v2.3.0 | |
| with: | |
| args: >- | |
| ./content/ | |
| -b https://developer.hashicorp.com/ | |
| --exclude-all-private | |
| --exclude '\.(svg|gif|jpg|png)' | |
| --exclude 'gnu\.org' | |
| --accept 200,408,429 | |
| --timeout=60 | |
| --max-concurrency 24 | |
| --no-progress | |
| --verbose | |
| fail: false | |
| failIfEmpty: false | |
| env: | |
| GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}} | |
| - name: Close Previous Link Checker Report GitHub Issue with label 'link-checker-report' | |
| uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9.1.0 | |
| with: | |
| # Only issues with ALL these labels are checked | |
| only-issue-labels: link-checker-report | |
| # Idle number of days before marking issues stale | |
| # Issues must be marked stale before it can be closed | |
| days-before-issue-stale: 0 | |
| # Idle number of days before closing old issues | |
| days-before-issue-close: 0 | |
| close-issue-message: 'This issue was closed because an updated Link Checker Report has been generated.' | |
| repo-token: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Generate enhanced issue content with categorization | |
| if: steps.lychee.outputs.exit_code != 0 | |
| run: | | |
| # Count different types of broken links | |
| TOTAL_COUNT=$(grep -c "✗" ./lychee/out.md || echo "0") | |
| # Define HashiCorp domains (easily maintainable list) | |
| HASHICORP_DOMAINS="hashicorp\.com|hashicorp\.io|terraform\.io|consul\.io|vault\.io|nomad\.io|packer\.io|vagrant\.io|waypoint\.io|boundary\.io|hcp\.io" | |
| # Count internal HashiCorp links using the dynamic list | |
| INTERNAL_COUNT=$(grep -E "✗.*($HASHICORP_DOMAINS)" ./lychee/out.md | wc -l || echo "0") | |
| EXTERNAL_COUNT=$((TOTAL_COUNT - INTERNAL_COUNT)) | |
| # Create enhanced issue content | |
| cat > ./issue-content.md << EOF | |
| # 🔗 Weekly Link Checker Report - $(date '+%B %Y') | |
| ## 📊 Summary | |
| - **Total broken links**: $TOTAL_COUNT | |
| - **Internal HashiCorp links**: $INTERNAL_COUNT 🚨 | |
| - **External links**: $EXTERNAL_COUNT ⚠️ | |
| - **Scan date**: $(date '+%Y-%m-%d') | |
| - **Content scanned**: All \`/content/\` directories | |
| ## 🎯 Prioritization Guide | |
| When reviewing broken links, prioritize fixes in this order: | |
| 1. **🚨 High Priority**: Internal HashiCorp links (developer.hashicorp.com, etc.) | |
| 2. **⚠️ Medium Priority**: External documentation/API references users rely on | |
| 3. **ℹ️ Low Priority**: External blog posts, news articles, or optional resources | |
| ## 📋 Action Items | |
| - [ ] Review high-priority internal links ($INTERNAL_COUNT found) | |
| - [ ] Check if external links have moved to new URLs | |
| - [ ] Update or remove links that are permanently broken | |
| - [ ] Consider adding warnings for unreliable external sources | |
| ## 🔍 Link Details | |
| EOF | |
| # Add the actual lychee output | |
| cat ./lychee/out.md >> ./issue-content.md | |
| # Add footer | |
| cat >> ./issue-content.md << EOF | |
| --- | |
| **Note**: This issue is automatically updated weekly. Previous reports are closed when new ones are generated. | |
| For more information, see our [Broken Link Monitoring documentation](.github/BROKEN_LINK_MONITORING.md). | |
| EOF | |
| - name: Create automated GitHub issue with broken link report | |
| id: create_issue | |
| if: steps.lychee.outputs.exit_code != 0 | |
| uses: peter-evans/create-issue-from-file@e8ef132d6df98ed982188e460ebb3b5d4ef3a9cd # v5.0.1 | |
| with: | |
| title: 'Link Checker Report - $(date +"%B %Y")' | |
| content-filepath: ./issue-content.md | |
| labels: | | |
| link-checker-report | |
| content-quality | |
| - name: Log production broken links to Datadog | |
| if: steps.lychee.outputs.exit_code != 0 | |
| run: | | |
| BROKEN_COUNT=$(grep -c "✗" ./lychee/out.md || echo "0") | |
| echo "::error::PRODUCTION broken links detected: $BROKEN_COUNT issues affecting end users" | |
| echo "GitHub issue: https://github.com/${{ github.repository }}/issues/${{ steps.create_issue.outputs.issue-number }}" | |
| # Send structured alert to Datadog for production monitoring | |
| curl -X POST "https://http-intake.logs.datadoghq.com/v1/input/${{ secrets.DD_API_KEY }}" \ | |
| -H "Content-Type: application/json" \ | |
| -d '{ | |
| "ddsource": "github-actions", | |
| "ddtags": "environment:production,service:web-unified-docs,alert_type:broken_links_production", | |
| "hostname": "github-actions", | |
| "message": "Production broken links detected: '"$BROKEN_COUNT"' issues affecting end users", | |
| "level": "error", | |
| "broken_link_count": '"$BROKEN_COUNT"', | |
| "issue_url": "https://github.com/${{ github.repository }}/issues/${{ steps.create_issue.outputs.issue-number }}" | |
| }' || echo "Failed to send Datadog alert" | |
| - name: Report success in GitHub Step Summary | |
| if: steps.lychee.outputs.exit_code == 0 | |
| run: | | |
| echo "## Link Health Report - Success!" >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| echo " **No broken links found in production content**" >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| echo "- **Scan date**: $(date '+%Y-%m-%d %H:%M:%S UTC')" >> $GITHUB_STEP_SUMMARY | |
| echo "- **Content scanned**: All \`/content/\` directories" >> $GITHUB_STEP_SUMMARY | |
| echo "- **Status**: All links are healthy " >> $GITHUB_STEP_SUMMARY | |
| echo "" >> $GITHUB_STEP_SUMMARY | |
| echo "Great work maintaining high content quality!" >> $GITHUB_STEP_SUMMARY | |
| # Log success to Datadog for trend tracking | |
| curl -X POST "https://http-intake.logs.datadoghq.com/v1/input/${{ secrets.DD_API_KEY }}" \ | |
| -H "Content-Type: application/json" \ | |
| -d '{ | |
| "ddsource": "github-actions", | |
| "ddtags": "environment:production,service:web-unified-docs,alert_type:link_health_success", | |
| "hostname": "github-actions", | |
| "message": "Production link check passed - no broken links found", | |
| "level": "info", | |
| "broken_link_count": 0, | |
| "scan_status": "success" | |
| }' || echo "Failed to send Datadog success metric" | |
| - name: Report failure in GitHub Step Summary | |
| if: steps.lychee.outputs.exit_code != 0 | |
| run: | | |
| echo "Broken links found, [check the following Github issue for more information.](https://github.com/${{ github.repository }}/issues/${{ steps.create_issue.outputs.issue-number }})" >> $GITHUB_STEP_SUMMARY |