core.yml

name: core
on:
  push:
  pull_request:
    branches:
      - master
      - branch-*
    types: [opened, synchronize]

env:
  # Disable keepAlive and pool
  # https://github.com/actions/virtual-environments/issues/1499#issuecomment-689467080
  MAVEN_OPTS: >-
      -Xms1024M -Xmx2048M -XX:MaxMetaspaceSize=1024m -XX:-UseGCOverheadLimit -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn
      -Dhttp.keepAlive=false
      -Dmaven.wagon.http.pool=false
      -Dmaven.wagon.http.retryHandler.count=3
  ZEPPELIN_HELIUM_REGISTRY: helium
  SPARK_PRINT_LAUNCH_COMMAND: "true"
  SPARK_LOCAL_IP: 127.0.0.1
  ZEPPELIN_LOCAL_IP: 127.0.0.1

# Use the bash login, because we are using miniconda
defaults:
  run:
    shell: bash -l {0}

jobs:
  # test on core-modules (zeppelin-interpreter,zeppelin-zengine,zeppelin-server),
  # some interpreters are included, because zeppelin-server test depends on them: spark, shell & markdown
  core-modules:
    runs-on: ubuntu-20.04
    strategy:
      fail-fast: false
      matrix:
        hadoop: [hadoop2, hadoop3]
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install application with some interpreter
        run: ./mvnw install -Pbuild-distr -DskipRat -DskipTests -pl zeppelin-server,zeppelin-web,spark-submit,spark/scala-2.11,spark/scala-2.12,spark/scala-2.13,markdown,angular,shell -am -Phelium-dev -Pexamples -P${{ matrix.hadoop }} -B
      - name: install and test plugins
        run: ./mvnw package -DskipRat -pl zeppelin-plugins -amd -B
      - name: Setup conda environment with python 3.7 and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R
          environment-file: testing/env_python_3.7_with_R.yml
          python-version: 3.7
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: Make IRkernel available to Jupyter
        run: |
          R -e "IRkernel::installspec()"
          conda list
          conda info
      - name: run tests with ${{ matrix.hadoop }} # skip spark test because we would run them in other CI
        run: ./mvnw verify -Pusing-packaged-distr -DskipRat -pl zeppelin-server,zeppelin-web,spark-submit,spark/scala-2.11,spark/scala-2.12,spark/scala-2.13,markdown,angular,shell -am -Phelium-dev -Pexamples -P${{ matrix.hadoop }} -Dtests.to.exclude=**/org/apache/zeppelin/spark/* -DfailIfNoTests=false

  # test interpreter modules except spark, flink, python, rlang, jupyter
  interpreter-test-non-core:
    runs-on: ubuntu-20.04
    env:
      INTERPRETERS: 'beam,hbase,pig,jdbc,file,flink-cmd,ignite,kylin,cassandra,elasticsearch,bigquery,alluxio,scio,livy,groovy,sap,java,geode,neo4j,hazelcastjet,submarine,sparql,mongodb,influxdb,ksql,scalding'
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install environment
        run: ./mvnw install -DskipTests -DskipRat -am -pl .,zeppelin-interpreter,zeppelin-interpreter-shaded,${INTERPRETERS} -Pscala-2.10 -B
      - name: Setup conda environment with python 3.7 and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R_and_tensorflow
          environment-file: testing/env_python_3_with_R_and_tensorflow.yml
          python-version: 3.7
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: verify interpreter
        run: ./mvnw verify -DskipRat -pl ${INTERPRETERS} -Pscala-2.10 -B

  # test interpreter modules for jupyter, python, rlang
  interpreter-test-jupyter-python-rlang:
    runs-on: ubuntu-20.04
    strategy:
      fail-fast: false
      matrix:
        python: [ 3.7, 3.8 ]
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: Setup conda environment with python ${{ matrix.python }} and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R
          environment-file: testing/env_python_${{ matrix.python }}_with_R.yml
          python-version: ${{ matrix.python }}
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: Make IRkernel available to Jupyter
        run: |
          R -e "IRkernel::installspec()"
      - name: install environment
        run: |
          ./mvnw install -DskipTests -DskipRat -pl python,rlang,zeppelin-jupyter-interpreter -am -Phadoop2 -B
      - name: run tests with ${{ matrix.python }}
        run: |
          ./mvnw test -DskipRat -pl python,rlang,zeppelin-jupyter-interpreter -DfailIfNoTests=false -B

  # zeppelin integration test except Spark & Flink
  zeppelin-integration-test:
    runs-on: ubuntu-20.04
    steps:
      # user/password => root/root
      - name: Start mysql
        run: sudo systemctl start mysql.service
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install environment
        run: |
          ./mvnw install -DskipTests -DskipRat -Phadoop2 -Pintegration -pl zeppelin-interpreter-integration,zeppelin-web,spark-submit,spark/scala-2.11,spark/scala-2.12,spark/scala-2.13,markdown,flink-cmd,flink/flink-scala-2.11,flink/flink-scala-2.12,jdbc,shell -am -Pflink-114
          ./mvnw package -DskipRat -pl zeppelin-plugins -amd -DskipTests -B
      - name: Setup conda environment with python 3.7 and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R
          environment-file: testing/env_python_3_with_R.yml
          python-version: 3.7
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: Make IRkernel available to Jupyter
        run: |
          R -e "IRkernel::installspec()"
      - name: run tests
        run: ./mvnw test -DskipRat -pl zeppelin-interpreter-integration -Phadoop2 -Pintegration -DfailIfNoTests=false -Dtest=ZeppelinClientIntegrationTest,ZeppelinClientWithAuthIntegrationTest,ZSessionIntegrationTest,ShellIntegrationTest,JdbcIntegrationTest
      - name: Print zeppelin logs
        if: always()
        run: if [ -d "logs" ]; then cat logs/*; fi
        
  flink-test-and-flink-integration-test:
    runs-on: ubuntu-20.04
    strategy:
      fail-fast: false
      matrix:
        flink: [112, 113, 114, 115]
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install environment for flink before 1.15 (exclusive)
        if: matrix.flink != '115'
        run: |
          ./mvnw install -DskipTests -DskipRat -am -pl flink/flink-scala-2.11,flink/flink-scala-2.12,flink-cmd,zeppelin-interpreter-integration -Pflink-${{ matrix.flink }} -Phadoop2 -Pintegration -B
          ./mvnw clean package -pl zeppelin-plugins -amd -DskipTests -B
      - name: install environment for flink after 1.15 (inclusive)
        if: matrix.flink == '115'
        run: |
          ./mvnw install -DskipTests -DskipRat -am -pl flink/flink-scala-2.12,flink-cmd,zeppelin-interpreter-integration -Pflink-${{ matrix.flink }} -Phadoop2 -Pintegration -B
          ./mvnw clean package -pl zeppelin-plugins -amd -DskipTests -B
      - name: Setup conda environment with python 3.7 and
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_flink
          environment-file: testing/env_python_3_with_flink_${{ matrix.flink }}.yml
          python-version: 3.7
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: run tests for flink before 1.15 (exclusive)
        if: matrix.flink != '115'
        run: ./mvnw test -DskipRat -pl flink/flink-scala-2.11,flink/flink-scala-2.12,flink-cmd,zeppelin-interpreter-integration -Pflink-${{ matrix.flink }} -Phadoop2 -Pintegration -DfailIfNoTests=false -B -Dtest=org.apache.zeppelin.flink.*Test,FlinkIntegrationTest${{ matrix.flink }}
      - name: run tests for flink before 1.15 (inclusive)
        if: matrix.flink == '115'
        run: ./mvnw test -DskipRat -pl flink/flink-scala-2.12,flink-cmd,zeppelin-interpreter-integration -Pflink-${{ matrix.flink }} -Phadoop2 -Pintegration -DfailIfNoTests=false -B -Dtest=org.apache.zeppelin.flink.*Test,FlinkIntegrationTest${{ matrix.flink }}
      - name: Print zeppelin logs
        if: always()
        run: if [ -d "logs" ]; then cat logs/*; fi


  spark-integration-test:
    runs-on: ubuntu-20.04
    strategy:
      fail-fast: false
      matrix:
        hadoop: [ 2, 3 ]
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install environment
        run: |
          ./mvnw install -DskipTests -DskipRat -pl zeppelin-interpreter-integration,zeppelin-web,spark-submit,spark/scala-2.11,spark/scala-2.12,spark/scala-2.13,markdown -am -Phadoop2 -Pintegration -B
          ./mvnw clean package -pl zeppelin-plugins -amd -DskipTests -B
      - name: Setup conda environment with python 3.7 and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R
          environment-file: testing/env_python_3_with_R.yml
          python-version: 3.7
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: Make IRkernel available to Jupyter
        run: |
          R -e "IRkernel::installspec()"
      - name: run tests on hadoop${{ matrix.hadoop }}
        run: ./mvnw test -DskipRat -pl zeppelin-interpreter-integration -Phadoop${{ matrix.hadoop }} -Pintegration -B -Dtest=SparkSubmitIntegrationTest,ZeppelinSparkClusterTest24,SparkIntegrationTest24,ZeppelinSparkClusterTest30,SparkIntegrationTest30,ZeppelinSparkClusterTest31,SparkIntegrationTest31,ZeppelinSparkClusterTest32,SparkIntegrationTest32 -DfailIfNoTests=false

  # test on spark for each spark version & scala version
  spark-test:
    runs-on: ubuntu-20.04
    strategy:
      fail-fast: false
      matrix:
        python: [ 3.7, 3.8 ]
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install environment
        run: ./mvnw install -DskipTests -DskipRat -pl spark-submit,spark/scala-2.11,spark/scala-2.12,spark/scala-2.13 -am -Phadoop2 -B
      - name: Setup conda environment with python ${{ matrix.python }} and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R
          environment-file: testing/env_python_${{ matrix.python }}_with_R.yml
          python-version: ${{ matrix.python }}
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: Make IRkernel available to Jupyter
        run: |
          R -e "IRkernel::installspec()"
      - name: run spark-2.4 tests with scala-2.11 and python-${{ matrix.python }}
        if: matrix.python == '3.7'  # Spark 2.4 doesn't support python 3.8
        run: ./mvnw test -DskipRat -pl spark-submit,spark/interpreter -Pspark-2.4 -Pspark-scala-2.11 -DfailIfNoTests=false -B
      - name: run spark-2.4 tests with scala-2.12 and python-${{ matrix.python }}
        if: matrix.python == '3.7'  # Spark 2.4 doesn't support python 3.8
        run: |
          rm -rf spark/interpreter/metastore_db
          ./mvnw test -DskipRat -pl spark-submit,spark/interpreter -Pspark-2.4 -Pspark-scala-2.12 -Phadoop2 -Pintegration -B -DfailIfNoTests=false
      - name: run spark-3.0 tests with scala-2.12 and python-${{ matrix.python }}
        run: |
          rm -rf spark/interpreter/metastore_db
          ./mvnw test -DskipRat -pl spark-submit,spark/interpreter -Pspark-3.0 -Pspark-scala-2.12 -Phadoop2 -Pintegration -B -DfailIfNoTests=false
      - name: run spark-3.1 tests with scala-2.12 and python-${{ matrix.python }}
        run: |
          rm -rf spark/interpreter/metastore_db
          ./mvnw test -DskipRat -pl spark-submit,spark/interpreter -Pspark-3.1 -Pspark-scala-2.12 -Phadoop2 -Pintegration -B -DfailIfNoTests=false
      - name: run spark-3.2 tests with scala-2.12 and python-${{ matrix.python }}
        run: |
          rm -rf spark/interpreter/metastore_db
          ./mvnw test -DskipRat -pl spark-submit,spark/interpreter -Pspark-3.2 -Pspark-scala-2.12 -Phadoop2 -Pintegration -B -DfailIfNoTests=false
      - name: run spark-3.2 tests with scala-2.13 and python-${{ matrix.python }}
        run: |
          rm -rf spark/interpreter/metastore_db
          ./mvnw test -DskipRat -pl spark-submit,spark/interpreter -Pspark-3.2 -Pspark-scala-2.13 -Phadoop2 -Pintegration -B -DfailIfNoTests=false

  livy-0-5-with-spark-2-2-0-under-python3:
    runs-on: ubuntu-20.04
    steps:
      - name: Checkout
        uses: actions/checkout@v2
      - name: Tune Runner VM
        uses: ./.github/actions/tune-runner-vm
      - name: Set up JDK 8
        uses: actions/setup-java@v2
        with:
          distribution: 'temurin'
          java-version: 8
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: |
            ~/.m2/repository
            !~/.m2/repository/org/apache/zeppelin/
            ~/.spark-dist
            ~/.cache
          key: ${{ runner.os }}-zeppelin-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            ${{ runner.os }}-zeppelin-
      - name: install environment
        run: |
          ./mvnw install -DskipTests -DskipRat -pl livy -am  -B
          ./testing/downloadSpark.sh "2.2.0" "2.6"
          ./testing/downloadLivy.sh "0.5.0-incubating"
      - name: Setup conda environment with python 3.7 and R
        uses: conda-incubator/setup-miniconda@v2
        with:
          activate-environment: python_3_with_R
          environment-file: testing/env_python_3_with_R.yml
          python-version: 3.7
          mamba-version: "*"
          channels: conda-forge,defaults
          channel-priority: true
          auto-activate-base: false
          use-mamba: true
      - name: Make IRkernel available to Jupyter
        run: |
          R -e "IRkernel::installspec()"
      - name: run tests
        run: ./mvnw verify -DskipRat -pl livy -am  -B