name: "S3 Spark Integration Tests"

on:
  pull_request:
    paths:
      - 'weed/s3api/**'
      - 'test/s3/spark/**'
      - 'test/s3tables/testutil/**'
      - '.github/workflows/s3-spark-tests.yml'
  workflow_dispatch:

concurrency:
  group: ${{ github.head_ref }}/s3-spark-tests
  cancel-in-progress: true

permissions:
  contents: read

jobs:
  s3-spark-issue-repro-tests:
    name: S3 Spark Issue Reproduction Tests
    runs-on: ubuntu-22.04
    timeout-minutes: 45

    steps:
      - name: Check out code
        uses: actions/checkout@v6

      - name: Set up Go
        uses: actions/setup-go@v6
        with:
          go-version-file: 'go.mod'
        id: go

      - name: Set up Docker
        uses: docker/setup-buildx-action@v3

      - name: Install SeaweedFS
        run: |
          go install -buildvcs=false ./weed

      - name: Pre-pull Spark image
        run: docker pull apache/spark:3.5.8

      - name: Run S3 Spark integration tests
        working-directory: test/s3/spark
        timeout-minutes: 35
        run: |
          set -x
          set -o pipefail
          echo "=== System Information ==="
          uname -a
          free -h
          df -h
          echo "=== Starting S3 Spark Integration Tests ==="

          go test -v -timeout 30m . 2>&1 | tee test-output.log || {
            echo "S3 Spark integration tests failed"
            exit 1
          }

      - name: Show test output on failure
        if: failure()
        working-directory: test/s3/spark
        run: |
          echo "=== Test Output ==="
          if [ -f test-output.log ]; then
            tail -200 test-output.log
          fi

          echo "=== Process information ==="
          ps aux | grep -E "(weed|test|docker|spark)" || true

      - name: Upload test logs on failure
        if: failure()
        uses: actions/upload-artifact@v6
        with:
          name: s3-spark-test-logs
          path: test/s3/spark/test-output.log
          retention-days: 3