Skip to content

datasets_biweekly

datasets_biweekly #27

Workflow file for this run

name: datasets_biweekly
on:
schedule:
- cron: "0 0 3/17 * *"
workflow_dispatch: {}
push:
paths:
- gb/gb_ocod
- gb/gb_ccod
- gb/gb_pricepaid
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 }}
GB_OCOD_KEY: ${{ secrets.GB_OCOD_KEY }}
strategy:
fail-fast: false
matrix:
dataset:
- gb_ocod
- gb_ccod
- gb_pricepaid
steps:
- name: parse and write the dataset
run: make investigraph dataset=${{ matrix.dataset }} DATASETS_DIR=.
working-directory: /datasets
catalog:
needs: data
if: always()
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_BIWEEKLY_HEARTBEAT }}"