seaweedfs/.github/workflows/s3-parquet-tests.yml

name: "S3 PyArrow Parquet Tests"

on:
  push:
    branches: [master]
    paths:
      - 'weed/s3api/**'
      - 'weed/filer/**'
      - 'test/s3/parquet/**'
      - '.github/workflows/s3-parquet-tests.yml'
  pull_request:
    branches: [master]
    paths:
      - 'weed/s3api/**'
      - 'weed/filer/**'
      - 'test/s3/parquet/**'
      - '.github/workflows/s3-parquet-tests.yml'
  workflow_dispatch:

env:
  S3_ACCESS_KEY: some_access_key1
  S3_SECRET_KEY: some_secret_key1
  S3_ENDPOINT_URL: http://localhost:8333
  BUCKET_NAME: test-parquet-bucket

jobs:
  parquet-integration-tests:
    name: PyArrow Parquet Tests (Python ${{ matrix.python-version }})
    runs-on: ubuntu-latest
    timeout-minutes: 20
    
    strategy:
      fail-fast: false
      matrix:
        python-version: ['3.9', '3.11', '3.12']
    
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
      
      - name: Set up Go
        uses: actions/setup-go@v5
        with:
          go-version: ^1.24
          cache: true
      
      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}
          cache: 'pip'
          cache-dependency-path: 'test/s3/parquet/requirements.txt'
      
      - name: Install system dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y lsof netcat-openbsd
      
      - name: Build SeaweedFS
        run: |
          cd weed
          go build -v
          sudo cp weed /usr/local/bin/
          weed version
      
      - name: Run PyArrow Parquet integration tests
        run: |
          cd test/s3/parquet
          make test-with-server
        env:
          SEAWEEDFS_BINARY: weed
          S3_PORT: 8333
          FILER_PORT: 8888
          VOLUME_PORT: 8080
          MASTER_PORT: 9333
          VOLUME_MAX_SIZE_MB: 50
      
      - name: Run implicit directory fix tests
        run: |
          cd test/s3/parquet
          make test-implicit-dir-with-server
        env:
          SEAWEEDFS_BINARY: weed
          S3_PORT: 8333
          FILER_PORT: 8888
          VOLUME_PORT: 8080
          MASTER_PORT: 9333
      
      - name: Run PyArrow native S3 filesystem tests
        run: |
          cd test/s3/parquet
          make test-native-s3-with-server
        env:
          SEAWEEDFS_BINARY: weed
          S3_PORT: 8333
          FILER_PORT: 8888
          VOLUME_PORT: 8080
          MASTER_PORT: 9333
      
      - name: Run SSE-S3 encryption compatibility tests
        run: |
          cd test/s3/parquet
          make test-sse-s3-compat
        env:
          SEAWEEDFS_BINARY: weed
          S3_PORT: 8333
          FILER_PORT: 8888
          VOLUME_PORT: 8080
          MASTER_PORT: 9333
      
      - name: Upload test logs on failure
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: test-logs-python-${{ matrix.python-version }}
          path: |
            /tmp/seaweedfs-parquet-*.log
            test/s3/parquet/*.log
          retention-days: 7
      
      - name: Cleanup
        if: always()
        run: |
          cd test/s3/parquet
          make stop-seaweedfs-safe || true
          make clean || true

  unit-tests:
    name: Go Unit Tests (Implicit Directory)
    runs-on: ubuntu-latest
    timeout-minutes: 10
    
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
      
      - name: Set up Go
        uses: actions/setup-go@v5
        with:
          go-version: ^1.24
          cache: true
      
      - name: Run Go unit tests
        run: |
          cd weed/s3api
          go test -v -run TestImplicitDirectory
      
      - name: Run all S3 API tests
        run: |
          cd weed/s3api
          go test -v -timeout 5m