update_unicode_data.yml

name: Update Unicode Data

on:
  workflow_dispatch:  # Can be triggered manually
  schedule:
    - cron: '0 0 1 */3 *'  # Run at midnight on the 1st of every 3rd month

permissions:
  contents: write
  pull-requests: write

jobs:
  update-unicode-data:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - name: Setup mise
        uses: jdx/mise-action@dba19683ed58901619b14f395a24841710cb4925 # v4.1.0

      - name: Install dependencies
        run: dart pub get

      - name: Generate GitHub App token
        id: generate-token
        uses: actions/create-github-app-token@bcd2ba49218906704ab6c1aa796996da409d3eb1 # v3.2.0
        with:
          app-id: ${{ secrets.UNICODE_UPDATE_APP_ID }}
          private-key: ${{ secrets.UNICODE_UPDATE_PRIVATE_KEY }}

      - name: Run Unicode Data Updater
        run: dart run tools/unicode_data_updater.dart

      - name: Run Normalizer Generator
        run: dart run tools/normalizer_gen.dart

      - name: Check for changes
        id: git-check
        run: |
          if [[ -n $(git status --porcelain) ]]; then
            echo "changes=true" >> $GITHUB_OUTPUT
          else
            echo "changes=false" >> $GITHUB_OUTPUT
          fi

      - name: Create branch and commit changes
        if: steps.git-check.outputs.changes == 'true'
        run: |
          # Generate branch name
          BRANCH_NAME="unicode-data-update-$(date +'%Y-%m-%d')"
          echo "BRANCH_NAME=$BRANCH_NAME" >> $GITHUB_ENV

          # Configure git
          git config --global user.name "GitHub Actions Bot"
          git config --global user.email "actions@github.com"

          # Create a branch
          git checkout -b $BRANCH_NAME

          # Add and commit changes
          git add .
          git commit -m "Update Unicode data and normalization files"

          # Push branch
          git push origin $BRANCH_NAME

      - name: Create Pull Request
        if: steps.git-check.outputs.changes == 'true'
        env:
          GH_TOKEN: ${{ steps.generate-token.outputs.token }}
          BRANCH_NAME: ${{ env.BRANCH_NAME }}
        run: |
          gh pr create \
            --title "Update Unicode Data and Normalization Files" \
            --body "This PR updates the Unicode data files and regenerates normalization data. Updated data files in data/ directory and regenerated normalization data. This PR was automatically created by GitHub Actions." \
            --base master \
            --head "$BRANCH_NAME"