Catalog #56
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Catalog automation for production (Railway Postgres). | |
| # Secrets: DATABASE_URL (Railway DATABASE_PUBLIC_URL), FRED_API_KEY | |
| name: Catalog | |
| on: | |
| schedule: | |
| - cron: "0 3 * * 0" # weekly metadata sync (Sun 03:00 UTC) | |
| - cron: "0 4 * * *" # daily grow (04:00 UTC) | |
| workflow_dispatch: | |
| inputs: | |
| job: | |
| description: Which job to run | |
| required: true | |
| default: sync | |
| type: choice | |
| options: | |
| - sync | |
| - sync-nyc | |
| - grow | |
| - both | |
| concurrency: | |
| group: catalog-${{ github.event.schedule || github.event.inputs.job || 'manual' }} | |
| cancel-in-progress: false | |
| env: | |
| # Prod-sized caps (Hobby / ~$5 budget). Override via repo variables if needed. | |
| CKAN_SYNC_MAX_INDEXED: "3000" | |
| CKAN_SYNC_MAX_PACKAGES: "300" | |
| CKAN_SYNC_ROWS: "100" | |
| CKAN_SYNC_MAX_PAGES: "20" | |
| WB_SYNC_MAX_INDEXED: "5000" | |
| WB_SYNC_MAX_INDICATORS: "2000" | |
| WB_SYNC_MAX_PER_FAMILY: "2" | |
| WB_SYNC_MAX_PER_TOPIC: "250" | |
| FRED_SYNC_MAX_INDEXED: "500" | |
| FRED_SYNC_MAX_SERIES: "200" | |
| CATALOG_PROBE_ENABLED: "true" | |
| CATALOG_SYNC_PRUNE_ENABLED: "false" | |
| CATALOG_PROBE_BATCH_SIZE: "100" | |
| CATALOG_SYNC_INTERVAL_HOURS: "0" | |
| CATALOG_PROBE_INTERVAL_HOURS: "0" | |
| NYC_SYNC_MAX_INGESTIBLE: "50" | |
| NYC_SYNC_MAX_INDEXED: "150" | |
| jobs: | |
| sync: | |
| if: >- | |
| github.event.schedule == '0 3 * * 0' || | |
| (github.event_name == 'workflow_dispatch' && | |
| (github.event.inputs.job == 'sync' || github.event.inputs.job == 'both')) | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 180 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| cache-dependency-path: apps/api/pyproject.toml | |
| - name: Install API | |
| run: pip install ./apps/api | |
| - name: Full catalog sync | |
| env: | |
| DATABASE_URL: ${{ secrets.DATABASE_URL }} | |
| FRED_API_KEY: ${{ secrets.FRED_API_KEY }} | |
| run: python -m findings_api.catalog.cli sync | |
| sync-nyc: | |
| if: >- | |
| github.event_name == 'workflow_dispatch' && | |
| github.event.inputs.job == 'sync-nyc' | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 45 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| cache-dependency-path: apps/api/pyproject.toml | |
| - name: Install API | |
| run: pip install ./apps/api | |
| - name: NYC Open Data catalog sync | |
| env: | |
| DATABASE_URL: ${{ secrets.DATABASE_URL }} | |
| run: python -m findings_api.catalog.cli sync-nyc | |
| grow: | |
| if: >- | |
| github.event.schedule == '0 4 * * *' || | |
| (github.event_name == 'workflow_dispatch' && | |
| (github.event.inputs.job == 'grow' || github.event.inputs.job == 'both')) | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 30 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.12" | |
| cache: pip | |
| cache-dependency-path: apps/api/pyproject.toml | |
| - name: Install API | |
| run: pip install ./apps/api | |
| - name: Daily catalog grow | |
| env: | |
| DATABASE_URL: ${{ secrets.DATABASE_URL }} | |
| FRED_API_KEY: ${{ secrets.FRED_API_KEY }} | |
| run: python -m findings_api.catalog.cli grow |