dolthub--dolt/.github/workflows/ci-bats-unix.yaml

name: Test Bats Unix

on:
  pull_request:
    branches: [ main ]
    paths:
      - 'go/**'
      - 'integration-tests/**'

concurrency:
  group: ci-bats-unix-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  test:
    name: Bats tests
    defaults:
      run:
        shell: bash
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: true
      matrix:
        os: [ ubuntu-22.04 ]
    env:
      use_credentials: ${{ secrets.AWS_SECRET_ACCESS_KEY != '' && secrets.AWS_ACCESS_KEY_ID != '' }}
    steps:
      # Docker entrypoint and docker tests in general may use more space than is available in the GitHub default runner,
      # so we remove unused pre-installed programs.
      - name: Free disk space
        run: |
          NAME="DISK-CLEANUP"
          echo "[${NAME}] Starting background cleanup..."
          [ -d /usr/share/dotnet ] && sudo rm -rf /usr/share/dotnet &
          [ -d /usr/local/lib/android ] && sudo rm -rf /usr/local/lib/android &
          [ -d /opt/ghc ] && sudo rm -rf /opt/ghc &
          [ -d /usr/local/share/boost ] && sudo rm -rf /usr/local/share/boost &

      - name: Conditionally Set ENV VARS for AWS tests
        run: |
          if [[ $use_credentials == true ]]; then
            echo "AWS_SDK_LOAD_CONFIG=1" >> $GITHUB_ENV
            echo "AWS_REGION=us-west-2" >> $GITHUB_ENV
            echo "DOLT_BATS_AWS_TABLE=dolt-ci-bats-manifests-us-west-2" >> $GITHUB_ENV
            echo "DOLT_BATS_AWS_BUCKET=dolt-ci-bats-chunks-us-west-2" >> $GITHUB_ENV
            echo "DOLT_BATS_AWS_EXISTING_REPO=aws_remote_bats_tests__dolt__" >> $GITHUB_ENV
          fi
      - name: Configure filter tags for lambda bats
        if: ${{ matrix.os == 'ubuntu-22.04' && env.use_credentials == 'true' }}
        run: |
          echo "BATS_FILTER=--filter-tags no_lambda" >> $GITHUB_ENV
      - name: Configure AWS Credentials
        if: ${{ env.use_credentials == 'true' }}
        uses: aws-actions/configure-aws-credentials@v4
        with:
          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
          aws-region: us-west-2
          role-to-assume: ${{ secrets.AWS_ROLE_TO_ASSUME }}
          role-duration-seconds: 10800 # 3 hours D:
      - uses: actions/checkout@v6
      - name: Set up Go toolchain
        uses: ./.github/actions/setup-go-toolchain
      - name: Setup Python 3.x
        uses: actions/setup-python@v5
        with:
          python-version: "3.10"
      - uses: actions/setup-node@v4
        with:
          node-version: ^16
      - name: Build dolt
        uses: ./.github/actions/build-dolt
        with:
          remotesrv: 'true'
          noms: 'true'
      - name: Install Bats
        run: |
          npm i bats
          echo "$(pwd)/node_modules/.bin" >> $GITHUB_PATH
        working-directory: ./.ci_bin
      - name: Install Python Deps
        run: |
          pip install mysql-connector-python
          pip install pandas
          pip install pyarrow
      - name: Setup Dolt Config
        uses: ./.github/actions/setup-dolt-config
      - name: Install expect
        if: matrix.os == 'ubuntu-22.04'
        run: sudo apt-get install -y expect
      - name: Install pcre2grep
        if: matrix.os == 'ubuntu-22.04'
        run: sudo apt-get install -y pcre2-utils
      - name: Install openssh-server
        if: matrix.os == 'ubuntu-22.04'
        run: sudo apt-get install -y openssh-server
      - name: Install Maven
        run: sudo apt-get install -y maven
      - name: Install Hadoop
        working-directory: ./.ci_bin
        run: |
          curl -LO https://downloads.apache.org/hadoop/common/hadoop-3.3.6/hadoop-3.3.6.tar.gz
          tar xvf hadoop-3.3.6.tar.gz
          echo "$(pwd)/hadoop-3.3.6/bin" >> $GITHUB_PATH
      - name: Install parquet-cli
        id: parquet_cli
        working-directory: ./.ci_bin
        run: |
          curl -OL https://github.com/apache/parquet-mr/archive/refs/tags/apache-parquet-1.12.3.tar.gz
          tar zxvf apache-parquet-1.12.3.tar.gz
          cd parquet-java-apache-parquet-1.12.3/parquet-cli
          mvn clean install -DskipTests
          runtime_jar="$(pwd)"/target/parquet-cli-1.12.3-runtime.jar
          echo "runtime_jar=$runtime_jar" >> $GITHUB_OUTPUT
      - name: Check expect
        run: expect -v
      - name: Test all Unix
        env:
          SQL_ENGINE: "local-engine"
          PARQUET_RUNTIME_JAR: ${{ steps.parquet_cli.outputs.runtime_jar }}
          BATS_TEST_RETRIES: "3"
        run: |
          bats --print-output-on-failure --tap $BATS_FILTER .
        working-directory: ./integration-tests/bats
      - name: Test all Unix, SQL_ENGINE=remote-engine
        # If we have AWS credentials, we run these remote-engine tests here instead of in the separate job.
        if: ${{ env.use_credentials == 'true' && matrix.os == 'ubuntu-22.04' }}
        env:
          SQL_ENGINE: "remote-engine"
          PARQUET_RUNTIME_JAR: ${{ steps.parquet_cli.outputs.runtime_jar }}
          BATS_TEST_RETRIES: "3"
        run: |
          bats --print-output-on-failure --tap $BATS_FILTER .
        working-directory: ./integration-tests/bats