data-integrity.yml

name: Data integrity

# Verifies the published OpenSAK-Data boundary release (issue #60): checksums
# match, boundaries.db is structurally sound, every GeoJSON pack is valid,
# and the resolver actually returns a result for known real-world coordinates.
on:
  schedule:
    # every 2 days, 06:00 UTC (cron has no exact "every N days" — day-of-month
    # */2 drifts by a day across some month boundaries, close enough here)
    - cron: '0 6 */2 * *'
  workflow_dispatch:

jobs:
  verify:
    runs-on: ubuntu-latest
    permissions:
      issues: write
    steps:
      - uses: actions/checkout@v7
      - uses: actions/setup-python@v7
        with:
          python-version: "3.12"
          cache: pip
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -e ".[dev]"
      - name: Verify release data
        run: python tools/boundaries/verify_release.py
      - name: File an issue on failure
        if: failure()
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          open_count=$(gh issue list --label data-integrity --state open --json number --jq 'length')
          if [ "$open_count" -eq 0 ]; then
            gh issue create \
              --label data-integrity \
              --title "Data integrity check failed ($(date -u +%F))" \
              --body "The scheduled data-integrity workflow failed. See the run: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
          else
            echo "An open data-integrity issue already exists, skipping."
          fi