test_iasworld_data.yaml

name: test-iasworld-data

# This workflow is not configured to run on PRs, because PRs have their own CI
# process defined by the `build-and-test-dbt` workflow. Instead, the Data
# Department's Spark data extraction process dispatches it via API once per
# day after finishing the daily ingest of iasWorld data. For more detail, see:
#
# https://github.com/ccao-data/service-spark-iasworld
on:
  workflow_dispatch:
    inputs:
      select:
        description: >
          Optional space-separated list of tests to run (defaults to all
          iasWorld data tests)
        required: false
        type: string
      selector:
        description: >
          Optional dbt selector representing tests to run (takes precedence
          over the above list of tests if both are present)
        required: false
        type: string
      upload_test_results:
        description: Upload test results to S3
        required: false
        default: false
        type: boolean

env:
  PYTHONUNBUFFERED: "1"
  UV_SYSTEM_PYTHON: 1

jobs:
  test-iasworld-data:
    runs-on: ubuntu-latest
    # These permissions are needed to interact with GitHub's OIDC Token endpoint
    # so that we can authenticate with AWS
    permissions:
      id-token: write
      contents: read
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Validate and parse input variables
        id: parse-inputs
        run: |
          # Default to no select option, which will fall back to the default
          # behavior of the underlying Python script
          SELECT_OPTION=""
          if [[ -n "$SELECTOR" ]]; then
            SELECT_OPTION="--selector $SELECTOR"
          elif [[ -n "$SELECT" ]]; then
            SELECT_OPTION="--select $SELECT"
          fi
          echo "Setting select option to '$SELECT_OPTION'"
          echo "select-option=$SELECT_OPTION" >> "$GITHUB_OUTPUT"
        shell: bash
        env:
          SELECT: ${{ inputs.select }}
          SELECTOR: ${{ inputs.selector }}

      - name: Setup dbt
        uses: ./.github/actions/setup_dbt
        with:
          role-to-assume: ${{ secrets.AWS_IAM_ROLE_TO_ASSUME_ARN }}

      - name: Restore dbt state cache
        id: cache
        uses: ./.github/actions/restore_dbt_cache
        with:
          path: ${{ env.PROJECT_DIR }}/${{ env.STATE_DIR }}
          key: ${{ env.CACHE_KEY }}

      - name: Install Python dependencies
        working-directory: ${{ env.PROJECT_DIR }}
        shell: bash
        run: uv pip install ".[dbt_tests]"

      - name: Run tests
        run: |
          DEFER_OPTION=""
          if [[ "$CACHE_HIT" == 'true' ]]; then
            DEFER_OPTION="--defer --state $STATE_DIR"
          fi
          # shellcheck disable=SC2086
          python scripts/run_iasworld_data_tests.py \
            --target "$TARGET" \
            --output-dir ./qc_test_results/ \
            $SELECT_OPTION \
            $SKIP_ARTIFACTS_OPTION \
            $DEFER_OPTION
        working-directory: ${{ env.PROJECT_DIR }}
        shell: bash
        env:
          USER: ${{ github.triggering_actor }}
          GIT_SHA: ${{ github.sha }}
          GIT_REF: ${{ github.ref_name }}
          GIT_AUTHOR: ${{ github.event.commits[0].author.name }}
          CACHE_HIT: ${{ steps.cache.outputs.cache-hit }}
          SELECT_OPTION: ${{ steps.parse-inputs.outputs.select-option }}
          SKIP_ARTIFACTS_OPTION: ${{ inputs.upload_test_results && '--no-skip-artifacts' || '--skip-artifacts' }}

      - name: Save test results to S3
        if: inputs.upload_test_results
        run: |
          s3_prefix="s3://ccao-data-warehouse-us-east-1/qc"
          local_prefix="qc_test_results/metadata"
          for dir in "test_run" "test_run_result" "test_run_failing_row"; do
            dirpath="${local_prefix}/${dir}"
            if [ -e "$dirpath" ]; then
              echo "Copying ${dirpath} metadata to S3"
              aws s3 sync "$dirpath" "${s3_prefix}/${dir}"
            fi
          done

          crawler_name="ccao-data-warehouse-qc-crawler"
          aws glue start-crawler --name "$crawler_name"
          echo "Triggered Glue crawler $crawler_name"
        working-directory: ${{ env.PROJECT_DIR }}
        shell: bash

      - name: Get current time
        if: failure()
        run: echo "TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%S")" >> "$GITHUB_ENV"
        shell: bash

      # Only triggered when run on a schedule. Otherwise, whoever dispatched the
      # workflow is notified via GitHub (instead of SNS)
      - name: Send failure notification
        if: github.event_name == 'workflow_dispatch' && github.triggering_actor == 'sqoop-bot[bot]' && failure()
        uses: ./.github/actions/publish_sns_topic
        with:
          sns_topic_arn: ${{ secrets.AWS_SNS_NOTIFICATION_TOPIC_ARN }}
          subject: "iasWorld tests errored for workflow run: ${{ github.run_id }}"
          body: |
            iasWorld tests raised an error for workflow ${{ github.run_id }}, run on ${{ env.TIMESTAMP }} UTC

            Link to failing workflow:
            https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}