detect-new-data.yml

# This workflow automatically detects new data items (feeds, smart data, and streams) and data deprecation changes
# It runs weekly on Sunday at 9 PM UTC and can also be triggered manually
name: Detect Data Changes (Feeds/SmartData/Streams/Deprecations)

on:
  schedule:
    - cron: '0 21 * * 0'  # Sunday 9 PM UTC
  workflow_dispatch: # Allow manual triggering

# Prevent multiple workflow runs from executing simultaneously
# If a new workflow is triggered, any in-progress runs will be cancelled
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

# Define required permissions for the workflow
permissions:
  contents: write      # needed to commit changes
  pull-requests: write # needed to open PR
  issues: write       # needed to create issues

# Set environment variables used across jobs
env:
  NODE_VERSION: '24'

jobs:
  # First job: Sets up the environment and installs dependencies
  setup:
    name: Setup Dependencies
    runs-on: ubuntu-latest
    steps:
      # Step 1: Check out the repository code
      - name: Checkout Repo
        uses: actions/checkout@v6
        with:
          fetch-depth: 0  # Fetch all history for git operations

      # Step 2: Set up Node.js environment
      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version: ${{ env.NODE_VERSION }}
          cache: 'npm'
          cache-dependency-path: '**/package-lock.json'

      # Step 3: Cache node_modules for faster future runs
      - name: Cache node_modules
        uses: actions/cache@v4
        id: cache-node-modules
        with:
          path: |
            node_modules
          key: ${{ runner.os }}-node-modules-${{ hashFiles('**/package-lock.json') }}

      # Step 4: Install dependencies if cache miss occurs
      - name: Install Dependencies
        if: steps.cache-node-modules.outputs.cache-hit != 'true'
        run: |
          echo "Cache miss, installing dependencies..."
          npm ci --prefer-offline --no-audit

  # Second job: Main job to detect new data items/deprecation changes and validate URLs
  detect-new-data:
    needs: setup
    name: Check for Data Changes
    runs-on: ubuntu-latest
    steps:
      # Step 1: Check out repository code
      - name: Checkout Repo
        uses: actions/checkout@v6
        with:
          fetch-depth: 0  # Fetch all history for git operations

      # Step 2: Set up Node.js environment
      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version: ${{ env.NODE_VERSION }}
          cache: 'npm'
          cache-dependency-path: '**/package-lock.json'

      # Step 3: Restore cached node_modules from setup job
      - name: Restore node_modules
        uses: actions/cache@v4
        with:
          path: |
            node_modules
          key: ${{ runner.os }}-node-modules-${{ hashFiles('**/package-lock.json') }}
          restore-keys: |
            ${{ runner.os }}-node-modules-

      # Step 4: Make the detection script executable
      - name: Ensure detect-data.sh is executable
        run: chmod +x .github/scripts/data/detect-data.sh

      # Step 5: Make the validate-urls.sh script executable
      - name: Ensure validate-urls.sh is executable
        run: chmod +x .github/scripts/data/validate-urls.sh

      # Step 6: Run the data detection script to check for new data items/deprecation changes
      - name: Run data detection
        id: detect_data
        run: |
          .github/scripts/data/detect-data.sh check-data
          
          # If we see temp/NEW_DATA_FOUND.json afterwards, we know data changes were found:
          if [ -f temp/NEW_DATA_FOUND.json ]; then
            echo "data_changes_found=true" >> $GITHUB_OUTPUT
          else
            echo "data_changes_found=false" >> $GITHUB_OUTPUT
          fi
        continue-on-error: true

      # Step 7: Validate all URLs in the data
      - name: Validate URLs
        id: validate_urls
        run: .github/scripts/data/validate-urls.sh

      # Step 8: Clean up temporary files
      - name: Cleanup NEW_DATA_FOUND
        run: rm -f temp/NEW_DATA_FOUND.json

      # Step 8b: Format generated files so the PR passes Prettier checks in test.yml
      - name: Format generated files
        if: steps.detect_data.outputs.data_changes_found == 'true'
        run: npx prettier --write public/changelog.json .github/scripts/data/baseline.json

      # Step 9: Create an issue if any invalid URLs are detected
      - name: Create Issue for Broken URLs
        if: steps.validate_urls.outputs.url_validation_failed == 'true'
        uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v6.0.0
        with:
          title: "GHA-data-validate-urls: Invalid URLs Detected"
          content-filepath: "temp/url_validation_report.md"
          labels: |
            bug
            gh-action-data
          assignees: khadni

      # Step 10: Create a pull request if new data items or deprecation changes were found
      - name: Commit & Create Pull Request
        if: steps.detect_data.outputs.data_changes_found == 'true'
        uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          commit-message: "Data: Update changelog for data changes"
          branch: "data-update-${{ github.run_id }}"
          title: "Changelog Update: Data changes found"
          body: "This PR was automatically created."
          add-paths: |
            .github/scripts/data/baseline.json
            public/changelog.json
          labels: |
            automation
          assignees: khadni

      # Step 11: Upload artifacts for debugging and record-keeping
      - name: Capture output artifacts
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: data-detection-${{ github.run_id }}
          path: |
            temp/*.json
            temp/*.md
            public/changelog.json
          retention-days: 14
          if-no-files-found: ignore