datasets_monthly #3
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
| name: datasets_biweekly | |
| on: | |
| schedule: | |
| - cron: "1 3 12 */1 *" | |
| workflow_dispatch: {} | |
| jobs: | |
| data: | |
| runs-on: ubuntu-latest | |
| container: ghcr.io/dataresearchcenter/datasets:latest | |
| env: | |
| AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| FSSPEC_S3_ENDPOINT_URL: ${{ secrets.FSSPEC_S3_ENDPOINT_URL }} | |
| strategy: | |
| matrix: | |
| dataset: | |
| - us_cpr | |
| steps: | |
| - name: parse and write the dataset | |
| run: "investigraph run -c /datasets/${{ matrix.dataset }}/config.yml --entities-uri s3://data.ftm.store/${{ matrix.dataset }}/entities.ftm.json --index-uri s3://data.ftm.store/${{ matrix.dataset }}/index.json" | |
| catalog: | |
| needs: data | |
| runs-on: ubuntu-latest | |
| container: ghcr.io/dataresearchcenter/datasets:latest | |
| defaults: | |
| run: | |
| working-directory: /datasets | |
| env: | |
| AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| FSSPEC_S3_ENDPOINT_URL: ${{ secrets.FSSPEC_S3_ENDPOINT_URL }} | |
| steps: | |
| - name: Update the catalog | |
| run: "make publish" | |
| - name: Notify success | |
| run: "anystore io -i ${{ secrets.DATASETS_MONTHLY_HEARTBEAT }}" |