build_sparkr_window.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 / SparkR-only (master, 4.4.2, windows-2022)"

on:
  schedule:
    - cron: '0 17 * * *'
  workflow_dispatch:

jobs:
  build:
    name: "Build module: sparkr"
    runs-on: windows-2022
    timeout-minutes: 300
    if: github.repository == 'apache/spark'
    steps:
    - name: Download winutils Hadoop binary
      uses: actions/checkout@v4
      with:
        repository: cdarlint/winutils
    - name: Move Hadoop winutil into home directory
      run: |
        Move-Item -Path hadoop-3.3.6 -Destination ~\
    - name: Checkout Spark repository
      uses: actions/checkout@v4
    - name: Cache Maven local repository
      uses: actions/cache@v4
      with:
        path: ~/.m2/repository
        key: build-sparkr-windows-maven-${{ hashFiles('**/pom.xml') }}
        restore-keys: |
          build-sparkr-windows-maven-
    - name: Install Java 17
      uses: actions/setup-java@v4
      with:
        distribution: zulu
        java-version: 17
    - name: Install R 4.4.2
      uses: r-lib/actions/setup-r@v2
      with:
        r-version: 4.4.2
    - name: Install R dependencies
      run: |
        Rscript -e "install.packages(c('knitr', 'rmarkdown', 'testthat', 'e1071', 'survival', 'arrow', 'xml2'), repos='https://cloud.r-project.org/')"
        Rscript -e "pkg_list <- as.data.frame(installed.packages()[,c(1, 3:4)]); pkg_list[is.na(pkg_list$Priority), 1:2, drop = FALSE]"
      shell: cmd
    # SparkR build does not need Python. However, it shows warnings when the Python version is too low during
    # the attempt to look up Python Data Sources for session initialization. The Windows 2019 runner
    # includes Python 3.7, which Spark does not support. Therefore, we simply install the proper Python
    # for simplicity, see SPARK-47116.
    - name: Install Python 3.11
      uses: actions/setup-python@v5
      with:
        python-version: '3.11'
        architecture: x64
    - name: Build Spark
      run: |
        rem 1. '-Djna.nosys=true' is required to avoid kernel32.dll load failure.
        rem   See SPARK-28759.
        rem 2. Ideally we should check the tests related to Hive in SparkR as well (SPARK-31745).
        rem 3. setup-java installs Maven 3.8.7 but does not allow changing its version, so overwrite
        rem   Maven version as a workaround.
        mvn -DskipTests -Psparkr -Djna.nosys=true package -Dmaven.version=3.8.7
      shell: cmd
    - name: Run SparkR tests
      run: |
        set HADOOP_HOME=%USERPROFILE%\hadoop-3.3.6
        set PATH=%HADOOP_HOME%\bin;%PATH%
        .\bin\spark-submit2.cmd --driver-java-options "-Dlog4j.configurationFile=file:///%CD:\=/%/R/log4j2.properties" --conf spark.hadoop.fs.defaultFS="file:///" R\pkg\tests\run-all.R
      shell: cmd
      env:
        NOT_CRAN: true
        SPARKR_SUPPRESS_DEPRECATION_WARNING: 1
        # See SPARK-27848. Currently installing some dependent packages causes
        # "(converted from warning) unable to identify current timezone 'C':" for an unknown reason.
        # This environment variable works around to test SparkR against a higher version.
        R_REMOTES_NO_ERRORS_FROM_WARNINGS: true