validate-sources.yml

name: Validate Data Sources

on:
  pull_request:
    types: [opened, synchronize, ready_for_review, reopened]
    paths:
      - "firstdata/sources/**/*.json"
      - "firstdata/schemas/datasource-schema.json"

jobs:
  protect-schema:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Block schema modifications
        run: |
          if git diff --name-only origin/${{ github.base_ref }}...HEAD | grep -q "firstdata/schemas/datasource-schema.json"; then
            echo "❌ PRs must not modify firstdata/schemas/datasource-schema.json"
            echo "Schema changes require direct commit to main by a maintainer."
            exit 1
          fi

  validate:
    needs: protect-schema
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Install uv
        uses: astral-sh/setup-uv@v5

      - name: Install dependencies
        run: uv sync

      - name: Validate all source JSON files
        run: |
          find firstdata/sources -name "*.json" | xargs uv run check-jsonschema \
            --schemafile firstdata/schemas/datasource-schema.json

      - name: Check for duplicate IDs
        run: uv run python scripts/check_ids.py