.github/workflows/build_python_connect40.yml

#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
#

name: Build / Python-only, Connect-only (master-server, branch-4.0-client, Python 3.11)

on:
  schedule:
    - cron: '0 20 * * *'
  workflow_dispatch:

jobs:
  # Build: build Spark and run the tests for specified modules using SBT
  build:
    name: "Build modules: pyspark-connect"
    runs-on: ubuntu-latest
    timeout-minutes: 100
    if: github.repository == 'apache/spark'
    steps:
      - name: Checkout Spark repository
        uses: actions/checkout@v6
        with:
          fetch-depth: 0
      - name: Cache SBT and Maven
        uses: actions/cache@v5
        with:
          path: |
            build/apache-maven-*
            build/*.jar
            ~/.sbt
          key: build-spark-connect-python-only-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
          restore-keys: |
            build-spark-connect-python-only-
      - name: Cache Coursier local repository
        uses: actions/cache@v5
        with:
          path: ~/.cache/coursier
          key: coursier-build-spark-connect-python-only-${{ hashFiles('**/pom.xml') }}
          restore-keys: |
            coursier-build-spark-connect-python-only-
      - name: Install Java 17
        uses: actions/setup-java@v5
        with:
          distribution: zulu
          java-version: 17
      - name: Install Python 3.11
        uses: actions/setup-python@v6
        with:
          python-version: '3.11'
          architecture: x64
      - name: Build Spark
        run: |
          ./build/sbt -Phive Test/package
      - name: Install Python dependencies
        run: |
          pip install 'numpy' 'pyarrow>=18.0.0' 'pandas==2.2.3' scipy unittest-xml-reporting 'plotly<6.0.0' 'mlflow>=2.8.1' coverage 'matplotlib' openpyxl 'memory-profiler==0.61.0' 'scikit-learn>=1.3.2'

          # Add Python deps for Spark Connect.
          pip install 'grpcio==1.76.0' 'grpcio-status==1.76.0' 'protobuf==6.33.5' 'googleapis-common-protos==1.71.0' 'graphviz==0.20.3' 'zstandard==0.25.0'

          # Add torch as a testing dependency for TorchDistributor
          pip install 'torch==2.0.1' 'torchvision==0.15.2' torcheval
      - name: List Python packages
        run: python -m pip list
      - name: Run tests
        env:
          SPARK_TESTING: 1
          SPARK_SKIP_CONNECT_COMPAT_TESTS: 1
          SPARK_CONNECT_TESTING_REMOTE: sc://localhost
        run: |
          # Make less noisy
          cp conf/log4j2.properties.template conf/log4j2.properties
          sed -i 's/rootLogger.level = info/rootLogger.level = warn/g' conf/log4j2.properties

          # Start a Spark Connect server for local
          PYTHONPATH="python/lib/pyspark.zip:python/lib/py4j-0.10.9.9-src.zip:$PYTHONPATH" ./sbin/start-connect-server.sh \
            --driver-java-options "-Dlog4j.configurationFile=file:$GITHUB_WORKSPACE/conf/log4j2.properties" \
            --jars "`find connector/protobuf/target -name spark-protobuf-*SNAPSHOT.jar`,`find connector/avro/target -name spark-avro*SNAPSHOT.jar`" \
            --conf spark.sql.execution.arrow.pyspark.validateSchema.enabled=false \
            --conf spark.sql.execution.pandas.convertToArrowArraySafely=false

          # Checkout to branch-4.0 to use the tests in branch-4.0.
          cd ..
          git clone --single-branch --branch branch-4.0 $GITHUB_SERVER_URL/$GITHUB_REPOSITORY spark-4.0
          cd spark-4.0

          # Several tests related to catalog requires to run them sequencially, e.g., writing a table in a listener.
          # Run branch-4.0 tests
          ./python/run-tests --parallelism=1 --python-executables=python3 --modules pyspark-connect
          # None of tests are dependent on each other in Pandas API on Spark so run them in parallel
          ./python/run-tests --parallelism=1 --python-executables=python3 --modules pyspark-pandas-connect,pyspark-pandas-slow-connect
      - name: Upload test results to report
        if: always()
        uses: actions/upload-artifact@v6
        with:
          name: test-results-spark-connect-python-only
          path: |
            **/target/test-reports/*.xml
            **/target/surefire-reports/*.xml
      - name: Upload Spark Connect server log file
        if: ${{ !success() }}
        uses: actions/upload-artifact@v6
        with:
          name: unit-tests-log-spark-connect-python-only
          path: logs/*.out