update_datasets.yml

name: Update Datasets and Create PR

on:
  schedule:
    - cron: '0 2 * * 7' # Runs at 02:00 UTC every Sunday
  workflow_dispatch: # This line enables manual triggering of the workflow

jobs:
  update-datasets:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v3
        with:
          fetch-depth: 0 # Fetches all history for all branches and tags

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.x' # Replace with the version you need

      - name: Install dependencies
        run: pip install requests pyyaml

      - name: Run update_datasets.py
        run: python ./scripts/update_datasets.py

      - name: Check for changes
        id: git-check
        run: |
          git diff
          if [ -n "$(git status -s)" ]; then
            echo "Changes detected"
            echo "changes_detected=true" >> $GITHUB_ENV
          else
            echo "changes_detected=false" >> $GITHUB_ENV

      - name: Commit changes
        if: env.changes_detected == 'true'
        run: |
          git config --global user.name 'github-actions[bot]'
          git config --global user.email 'github-actions[bot]@users.noreply.github.com'
          git add .
          git commit -m "GitHub Action: Update datasets"

      - name: Create Pull Request
        if: env.changes_detected == 'true'
        uses: peter-evans/create-pull-request@v4
        with:
          token: ${{ secrets.PERSONAL_ACCESS_TOKEN }} 
          commit-message: "GitHub Action: Update datasets"
          title: "[AUTO] Update Datasets"
          body: "This is an auto-generated PR with dataset updates."
          branch: "update-datasets-${{ github.run_number }}"
          delete-branch: true

      - name: Install GitHub CLI
        run: |
          if ! command -v gh &> /dev/null
          then
              echo "GitHub CLI not found, installing..."
              curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | sudo dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg
              echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | sudo tee /etc/apt/sources.list.d/github-cli.list > /dev/null
              sudo apt update
              sudo apt install gh -y
          else
              echo "GitHub CLI is already installed."
          fi

      - name: Enable Auto-Merge for the PR
        if: steps.git-check.outputs.changes_detected == 'true'
        run: |
          PR_NUMBER=$(echo ${{ steps.create-pr.outputs.pull-request-number }})
          gh pr merge $PR_NUMBER --auto --squash
        env:
          GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}