data-pipeline.yml

name: Data Pipeline

on:
  pull_request:
    branches: [ master ]

jobs:
  data-pipeline:
    runs-on: ubuntu-latest
    defaults:
      run:
        shell: bash -l {0}
    steps:
    - uses: actions/checkout@v2
      with:
        ref: ${{ github.event.pull_request.head.ref }}
    - name: Setup environment
      uses: mamba-org/setup-micromamba@v1
      with:
        environment-file: environment-dev.yml
        environment-name: landcover-mapping
        cache-environment: true
    - uses: google-github-actions/auth@v0
      with:
        credentials_json: ${{ secrets.GCP_SA_KEY }}
    - uses: google-github-actions/setup-gcloud@v0

    - name: Run data pipeline
      env:
        GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
      run: |
        dvc pull -f
        openmapflow create-datasets --non-interactive
        dvc commit -f
        dvc push
    - name: Push automated dataset updates
      run: |
        git config --global user.name 'Dataset bot'
        git config --global user.email 'dataset-bot@users.noreply.github.com'
        git pull
        git add data
        git commit -m "Automated dataset updates" || echo "No updates to commit"
        git push