Skip to content

chore: remove repetitive words #31755

chore: remove repetitive words

chore: remove repetitive words #31755

Workflow file for this run

name: Java CI
on:
push:
branches:
- master
- 'release-*'
- branch-0.x
pull_request:
paths-ignore:
- '**.bmp'
- '**.gif'
- '**.jpg'
- '**.jpeg'
- '**.md'
- '**.pdf'
- '**.png'
- '**.svg'
- '**.yaml'
- '.gitignore'
branches:
- master
- 'release-*'
- branch-0.x
concurrency:
group: ${{ github.ref }}
cancel-in-progress: ${{ !contains(github.ref, 'master') && !contains(github.ref, 'branch-0.x') }}
env:
MVN_ARGS: -e -ntp -B -V -Dgpg.skip -Djacoco.skip -Pwarn-log -Dorg.slf4j.simpleLogger.log.org.apache.maven.plugins.shade=warn -Dorg.slf4j.simpleLogger.log.org.apache.maven.plugins.dependency=warn -Dmaven.wagon.httpconnectionManager.ttlSeconds=25 -Dmaven.wagon.http.retryHandler.count=5
SPARK_COMMON_MODULES: hudi-spark-datasource/hudi-spark,hudi-spark-datasource/hudi-spark-common
jobs:
validate-source:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Check Binary Files
run: ./scripts/release/validate_source_binary_files.sh
- name: Check Copyright
run: |
./scripts/release/create_source_directory.sh hudi-tmp-repo
cd hudi-tmp-repo
./scripts/release/validate_source_copyright.sh
- name: RAT check
run: ./scripts/release/validate_source_rat.sh
test-spark-java-tests:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- scalaProfile: "scala-2.11"
sparkProfile: "spark2.4"
sparkModules: "hudi-spark-datasource/hudi-spark2"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.0"
sparkModules: "hudi-spark-datasource/hudi-spark3.0.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.1"
sparkModules: "hudi-spark-datasource/hudi-spark3.1.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.2"
sparkModules: "hudi-spark-datasource/hudi-spark3.2.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.3"
sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.4"
sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.5"
sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
run:
mvn clean install -T 2 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DskipTests=true $MVN_ARGS -am -pl "hudi-examples/hudi-examples-spark,$SPARK_COMMON_MODULES,$SPARK_MODULES"
- name: Quickstart Test
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
run:
mvn test -Punit-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -pl hudi-examples/hudi-examples-spark $MVN_ARGS
- name: Java UT - Common & Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Punit-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DwildcardSuites=skipScalaTests -DfailIfNoTests=false -pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
- name: Java FT - Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Pfunctional-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DwildcardSuites=skipScalaTests -DfailIfNoTests=false -pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
test-spark-scala-tests:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- scalaProfile: "scala-2.11"
sparkProfile: "spark2.4"
sparkModules: "hudi-spark-datasource/hudi-spark2"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.0"
sparkModules: "hudi-spark-datasource/hudi-spark3.0.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.1"
sparkModules: "hudi-spark-datasource/hudi-spark3.1.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.2"
sparkModules: "hudi-spark-datasource/hudi-spark3.2.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.3"
sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.4"
sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.5"
sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
run:
mvn clean install -T 2 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DskipTests=true $MVN_ARGS -am -pl "hudi-examples/hudi-examples-spark,$SPARK_COMMON_MODULES,$SPARK_MODULES"
- name: Scala UT - Common & Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Punit-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -Dtest=skipJavaTests -DfailIfNoTests=false -pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
- name: Scala FT - Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Pfunctional-tests -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -Dtest=skipJavaTests -DfailIfNoTests=false -pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
test-hudi-hadoop-mr-and-hudi-java-client:
runs-on: ubuntu-latest
timeout-minutes: 40
strategy:
matrix:
include:
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.2"
flinkProfile: "flink1.18"
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Generate Maven Wrapper
run:
mvn -N io.takari:maven:wrapper
- name: Build Project
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
FLINK_PROFILE: ${{ matrix.flinkProfile }}
run:
./mvnw clean install -T 2 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -D"FLINK_PROFILE" -DskipTests=true -Phudi-platform-service $MVN_ARGS -am -pl hudi-hadoop-mr,hudi-client/hudi-java-client
- name: UT - hudi-hadoop-mr and hudi-client/hudi-java-client
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
FLINK_PROFILE: ${{ matrix.flinkProfile }}
run:
./mvnw test -Punit-tests -fae -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -D"FLINK_PROFILE" -pl hudi-hadoop-mr,hudi-client/hudi-java-client $MVN_ARGS
test-spark-java17-java-tests:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.3"
sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.4"
sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.5"
sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
run:
mvn clean install -T 2 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DskipTests=true $MVN_ARGS -am -pl "hudi-examples/hudi-examples-spark,hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES"
- name: Set up JDK 17
uses: actions/setup-java@v3
with:
java-version: '17'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Quickstart Test
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
run:
mvn test -Punit-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DwildcardSuites=skipScalaTests -DfailIfNoTests=false -pl hudi-examples/hudi-examples-spark $MVN_ARGS
- name: Java UT - Common & Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Punit-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DwildcardSuites=skipScalaTests -DfailIfNoTests=false -pl "hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
- name: Java FT - Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Pfunctional-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
test-spark-java17-scala-tests:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.3"
sparkModules: "hudi-spark-datasource/hudi-spark3.3.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.4"
sparkModules: "hudi-spark-datasource/hudi-spark3.4.x"
- scalaProfile: "scala-2.12"
sparkProfile: "spark3.5"
sparkModules: "hudi-spark-datasource/hudi-spark3.5.x"
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
run:
mvn clean install -T 2 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DskipTests=true $MVN_ARGS -am -pl "hudi-examples/hudi-examples-spark,hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES"
- name: Set up JDK 17
uses: actions/setup-java@v3
with:
java-version: '17'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Scala UT - Common & Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Punit-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -Dtest=skipJavaTests -DfailIfNoTests=false -pl "hudi-common,$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
- name: Scala FT - Spark
env:
SCALA_PROFILE: ${{ matrix.scalaProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_MODULES: ${{ matrix.sparkModules }}
if: ${{ !endsWith(env.SPARK_PROFILE, '3.2') }} # skip test spark 3.2 as it's covered by Azure CI
run:
mvn test -Pfunctional-tests -Pjava17 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -Dtest=skipJavaTests -DfailIfNoTests=false -pl "$SPARK_COMMON_MODULES,$SPARK_MODULES" $MVN_ARGS
test-flink:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- flinkProfile: "flink1.14"
- flinkProfile: "flink1.15"
- flinkProfile: "flink1.16"
- flinkProfile: "flink1.17"
- flinkProfile: "flink1.18"
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
SCALA_PROFILE: 'scala-2.12'
FLINK_PROFILE: ${{ matrix.flinkProfile }}
run:
mvn clean install -T 2 -D"$SCALA_PROFILE" -D"$FLINK_PROFILE" -pl hudi-examples/hudi-examples-flink -am -Davro.version=1.10.0 -DskipTests=true $MVN_ARGS
- name: Quickstart Test
env:
SCALA_PROFILE: 'scala-2.12'
FLINK_PROFILE: ${{ matrix.flinkProfile }}
run:
mvn test -Punit-tests -D"$SCALA_PROFILE" -D"$FLINK_PROFILE" -pl hudi-examples/hudi-examples-flink $MVN_ARGS
- name: Integration Test
env:
SCALA_PROFILE: 'scala-2.12'
FLINK_PROFILE: ${{ matrix.flinkProfile }}
if: ${{ endsWith(env.FLINK_PROFILE, '1.18') }}
run: |
mvn clean install -T 2 -Pintegration-tests -D"$SCALA_PROFILE" -D"$FLINK_PROFILE" -pl hudi-flink-datasource/hudi-flink -am -Davro.version=1.10.0 -DskipTests=true $MVN_ARGS
mvn verify -Pintegration-tests -D"$SCALA_PROFILE" -D"$FLINK_PROFILE" -pl hudi-flink-datasource/hudi-flink $MVN_ARGS
docker-java17-test:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- flinkProfile: 'flink1.18'
sparkProfile: 'spark3.5'
sparkRuntime: 'spark3.5.0'
- flinkProfile: 'flink1.18'
sparkProfile: 'spark3.4'
sparkRuntime: 'spark3.4.0'
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: UT/FT - Docker Test - OpenJDK 17
env:
FLINK_PROFILE: ${{ matrix.flinkProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_RUNTIME: ${{ matrix.sparkRuntime }}
SCALA_PROFILE: 'scala-2.12'
if: ${{ env.SPARK_PROFILE >= 'spark3.4' }} # Only support Spark 3.4 for now
run: |
HUDI_VERSION=$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout)
./packaging/bundle-validation/run_docker_java17.sh
validate-bundles:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- flinkProfile: 'flink1.18'
sparkProfile: 'spark3.5'
sparkRuntime: 'spark3.5.0'
- flinkProfile: 'flink1.18'
sparkProfile: 'spark3.4'
sparkRuntime: 'spark3.4.0'
- flinkProfile: 'flink1.17'
sparkProfile: 'spark3.3'
sparkRuntime: 'spark3.3.2'
- flinkProfile: 'flink1.16'
sparkProfile: 'spark3.3'
sparkRuntime: 'spark3.3.1'
- flinkProfile: 'flink1.15'
sparkProfile: 'spark3.2'
sparkRuntime: 'spark3.2.3'
- flinkProfile: 'flink1.14'
sparkProfile: 'spark3.1'
sparkRuntime: 'spark3.1.3'
- flinkProfile: 'flink1.14'
sparkProfile: 'spark3.0'
sparkRuntime: 'spark3.0.2'
- flinkProfile: 'flink1.14'
sparkProfile: 'spark2.4'
sparkRuntime: 'spark2.4.8'
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
FLINK_PROFILE: ${{ matrix.flinkProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SCALA_PROFILE: 'scala-2.12'
run: |
mvn clean package -T 2 -D"$SCALA_PROFILE" -D"$SPARK_PROFILE" -DdeployArtifacts=true -DskipTests=true $MVN_ARGS
# TODO remove the sudo below. It's a needed workaround as detailed in HUDI-5708.
sudo chown -R "$USER:$(id -g -n)" hudi-platform-service/hudi-metaserver/target/generated-sources
mvn clean package -T 2 -D"$SCALA_PROFILE" -D"$FLINK_PROFILE" -DdeployArtifacts=true -DskipTests=true $MVN_ARGS -pl packaging/hudi-flink-bundle -am -Davro.version=1.10.0
- name: IT - Bundle Validation - OpenJDK 8
env:
FLINK_PROFILE: ${{ matrix.flinkProfile }}
SPARK_RUNTIME: ${{ matrix.sparkRuntime }}
SCALA_PROFILE: 'scala-2.12'
if: ${{ env.SPARK_PROFILE >= 'spark3' }} # Only run validation on Spark 3
run: |
HUDI_VERSION=$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout)
./packaging/bundle-validation/ci_run.sh $HUDI_VERSION openjdk8
- name: IT - Bundle Validation - OpenJDK 11
env:
FLINK_PROFILE: ${{ matrix.flinkProfile }}
SPARK_RUNTIME: ${{ matrix.sparkRuntime }}
SCALA_PROFILE: 'scala-2.12'
if: ${{ env.SPARK_PROFILE >= 'spark3' }} # Only run validation on Spark 3
run: |
HUDI_VERSION=$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout)
./packaging/bundle-validation/ci_run.sh $HUDI_VERSION openjdk11
- name: IT - Bundle Validation - OpenJDK 17
env:
FLINK_PROFILE: ${{ matrix.flinkProfile }}
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_RUNTIME: ${{ matrix.sparkRuntime }}
SCALA_PROFILE: 'scala-2.12'
if: ${{ env.SPARK_PROFILE >= 'spark3.3' }} # Only Spark 3.3 and above support Java 17
run: |
HUDI_VERSION=$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout)
./packaging/bundle-validation/ci_run.sh $HUDI_VERSION openjdk17
integration-tests:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- sparkProfile: 'spark2.4'
sparkArchive: 'spark-2.4.4/spark-2.4.4-bin-hadoop2.7.tgz'
steps:
- uses: actions/checkout@v3
- name: Set up JDK 8
uses: actions/setup-java@v3
with:
java-version: '8'
distribution: 'adopt'
architecture: x64
cache: maven
- name: Build Project
env:
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SCALA_PROFILE: '-Dscala-2.11 -Dscala.binary.version=2.11'
run:
mvn clean install -T 2 $SCALA_PROFILE -D"$SPARK_PROFILE" -Pintegration-tests -DskipTests=true $MVN_ARGS
- name: 'UT integ-test'
env:
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SCALA_PROFILE: '-Dscala-2.11 -Dscala.binary.version=2.11'
run:
mvn test $SCALA_PROFILE -D"$SPARK_PROFILE" -Pintegration-tests -DskipUTs=false -DskipITs=true -pl hudi-integ-test $MVN_ARGS
- name: 'IT'
env:
SPARK_PROFILE: ${{ matrix.sparkProfile }}
SPARK_ARCHIVE: ${{ matrix.sparkArchive }}
SCALA_PROFILE: '-Dscala-2.11 -Dscala.binary.version=2.11'
run: |
echo "Downloading $SPARK_ARCHIVE"
curl https://archive.apache.org/dist/spark/$SPARK_ARCHIVE --create-dirs -o $GITHUB_WORKSPACE/$SPARK_ARCHIVE
tar -xvf $GITHUB_WORKSPACE/$SPARK_ARCHIVE -C $GITHUB_WORKSPACE/
mkdir /tmp/spark-events/
SPARK_ARCHIVE_BASENAME=$(basename $SPARK_ARCHIVE)
export SPARK_HOME=$GITHUB_WORKSPACE/${SPARK_ARCHIVE_BASENAME%.*}
rm -f $GITHUB_WORKSPACE/$SPARK_ARCHIVE
docker system prune --all --force
mvn verify $SCALA_PROFILE -D"$SPARK_PROFILE" -Pintegration-tests -pl !hudi-flink-datasource/hudi-flink $MVN_ARGS