raincloud-conformance.yml

name: Raincloud conformance

# Real-world cross-implementation conformance (issue #205): hydrates the Raincloud
# corpus (Vortex files written by the Python bindings + Parquet oracles) and runs
# RaincloudConformanceIntegrationTest against everything hydrated. Scheduled, not on
# the PR path: hydration depends on upstream dataset URLs that rot independently of
# our code, so a failure here is a finding to triage, not a broken build.

on:
  schedule:
    - cron: '0 5 * * 1'   # Mondays 05:00 UTC
  workflow_dispatch:
    inputs:
      max-mb:
        description: 'Per-slug artifact size cap in MB (0 = uncapped)'
        default: '200'

jobs:
  conformance:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7

      - name: Set up Azul Zulu JDK 25
        uses: actions/setup-java@v5
        with:
          distribution: zulu
          java-version: '25'

      - name: Cache Maven repository
        uses: actions/cache@v6
        with:
          path: ~/.m2/repository
          key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-maven-

      - uses: actions/setup-python@v6
        with:
          python-version: '3.12'

      # keyed on the matrix + pinned tag: a corpus change rebuilds, otherwise
      # weekly runs reuse artifacts instead of re-fetching upstream sources
      - name: Cache Raincloud corpus
        uses: actions/cache@v6
        with:
          path: ~/.cache/raincloud
          key: raincloud-corpus-${{ hashFiles('scripts/hydrate-raincloud-corpus.sh', 'integration/src/test/resources/raincloud/expected-status.csv') }}

      - name: Hydrate corpus
        run: scripts/hydrate-raincloud-corpus.sh --max-mb "${{ github.event.inputs.max-mb || '200' }}"

      - name: Run conformance suite
        run: ./mvnw verify -pl integration -am -Dit.test=RaincloudConformanceIntegrationTest

      - name: Publish per-slug results to job summary
        if: always()
        run: |
          {
            echo '## Raincloud conformance'
            echo '```'
            grep -hE "Tests run|slug" integration/target/failsafe-reports/*.txt || true
            echo '```'
          } >> "$GITHUB_STEP_SUMMARY"