Merge pull request #197 from rocky-linux/feature/url-check

Downloads URL Checker

Author: NebraskaCoder

.devcontainer/devcontainer.json

@@ -0,0 +1,65 @@
+# GitHub Actions Workflows
+
+This directory contains GitHub Actions workflows for the Rocky Linux website.
+
+## Workflows
+
+### check-download-urls.yml
+
+This workflow automatically checks all URLs in the `data/downloads.json` file to ensure they are accessible.
+
+#### When it runs:
+
+- **On push/PR**: When `data/downloads.json` is modified
+- **Daily**: At 2 AM UTC (scheduled check)
+- **Manual**: Can be triggered manually from the Actions tab
+
+#### What it does:
+
+1. Extracts all URLs from the nested JSON structure
+2. Checks each URL using HTTP HEAD requests
+3. Reports any URLs that return errors or non-success status codes
+4. Creates issues or PR comments when failures are detected
+
+#### Local testing:
+
+You can test the URL checker locally using the standalone script:
+
+```bash
+# Run the URL checker
+node scripts/check-download-urls.js
+
+# Or make it executable and run directly
+chmod +x scripts/check-download-urls.js
+./scripts/check-download-urls.js
+```
+
+#### Features:
+
+- **Batch processing**: Checks URLs in batches to avoid overwhelming servers
+- **Progress indicator**: Shows real-time progress when run locally
+- **Detailed reporting**: Shows the JSON path and error details for each failed URL
+- **GitHub integration**: Automatically comments on PRs and creates issues for scheduled runs
+
+#### Expected behavior:
+
+- URLs returning 2xx or 3xx status codes are considered successful
+- 4xx or 5xx status codes are reported as failures
+- Network errors and timeouts are also reported
+- All URLs, including Docker Hub, are checked using HTTP HEAD requests. Some services (like Docker Hub) may not support HEAD requests, which can result in false negatives.
+
+### Other Workflows
+
+- **playwright.yml**: Runs Playwright end-to-end tests
+- **validate_markdown_filenames.yml**: Ensures markdown files follow naming conventions
+- **Validate.yml**: General validation workflow
+
+## Adding New Workflows
+
+When adding new workflows:
+
+1. Place the workflow file in this directory
+2. Use descriptive names ending with `.yml`
+3. Document the workflow purpose and triggers
+4. Consider adding manual trigger option (`workflow_dispatch`)
+5. Add appropriate error handling and notifications

.github/workflows/README.md

@@ -0,0 +1,74 @@
+name: Check Download URLs
+
+on:
+  push:
+    branches: [ main, develop ]
+    paths:
+      - 'data/downloads.json'
+  pull_request:
+    branches: [ main, develop ]
+    paths:
+      - 'data/downloads.json'
+  schedule:
+    # Run daily at 2 AM UTC to catch broken links
+    - cron: '0 2 * * *'
+  workflow_dispatch:
+    # Allow manual triggering
+
+jobs:
+  check-urls:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+    
+    - name: Set up Node.js
+      uses: actions/setup-node@v4
+      with:
+        node-version: '20'
+    
+    - name: Extract and check URLs
+      run: node scripts/check-download-urls.js
+      env:
+        GITHUB_ACTIONS: true
+    
+    - name: Comment PR on failure
+      if: failure() && github.event_name == 'pull_request'
+      uses: actions/github-script@v7
+      with:
+        script: |
+          const fs = require('fs');
+          if (fs.existsSync('url-check-summary.md')) {
+            const summary = fs.readFileSync('url-check-summary.md', 'utf8');
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: summary
+            });
+          }
+    
+    - name: Create issue on scheduled run failure
+      if: failure() && github.event_name == 'schedule'
+      uses: actions/github-script@v7
+      with:
+        script: |
+          const fs = require('fs');
+          let body = '## 🚨 Daily URL Check Failed\n\n';
+          
+          if (fs.existsSync('url-check-summary.md')) {
+            body += fs.readFileSync('url-check-summary.md', 'utf8');
+          } else {
+            body += 'The URL checker found broken links in downloads.json. Please check the workflow logs for details.';
+          }
+          
+          body += '\n\n[View workflow run](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})';
+          
+          github.rest.issues.create({
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            title: 'Broken download URLs detected',
+            body: body,
+            labels: ['bug', 'downloads']
+          });

.github/workflows/check-download-urls.yml

@@ -13,7 +13,8 @@
     "e2e:dev": "playwright test --ui",
     "e2e:install": "playwright install",
     "test": "jest",
-    "test:coverage": "jest --coverage"
+    "test:coverage": "jest --coverage",
+    "check:downloads": "node scripts/check-download-urls.js"
   },
   "dependencies": {
     "@headlessui/react": "^2.2.2",