srowen closed pull request #22997: SPARK-25999: make-distribution.sh failure with --r and -Phadoop-provided URL: https://github.com/apache/spark/pull/22997
This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is a foreign pull request (from a fork), the diff is supplied below (as it won't show otherwise due to GitHub magic): diff --git a/R/rjarsdep/pom.xml b/R/rjarsdep/pom.xml new file mode 100644 index 0000000000000..a9c88a10b1d94 --- /dev/null +++ b/R/rjarsdep/pom.xml @@ -0,0 +1,89 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ 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. + --> + +<project xmlns="http://maven.apache.org/POM/4.0.0"; xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd";> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>spark-parent_2.11</artifactId> + <version>2.3.3-SNAPSHOT</version> + <relativePath>../../pom.xml</relativePath> + </parent> + + <artifactId>r-jars-dep</artifactId> + <name>Spark Project Dependency for R</name> + <url>http://spark.apache.org/</url> + <packaging>pom</packaging> + + <properties> + <sbt.project.name>rjarsdep</sbt.project.name> + <build.testJarPhase>none</build.testJarPhase> + <build.copyDependenciesPhase>package</build.copyDependenciesPhase> + </properties> + + <dependencies> + <!-- Prevent our dummy JAR from being included in Spark distributions or uploaded to YARN --> + <dependency> + <groupId>org.spark-project.spark</groupId> + <artifactId>unused</artifactId> + <version>1.0.0</version> + <scope>provided</scope> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-core_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-mllib_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-graphx_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-sql_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-repl_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + + <!-- + Because we don't shade dependencies anymore, we need to restore Guava to compile scope so + that the libraries Spark depend on have it available. We'll package the version that Spark + uses (14.0.1) which is not the same as Hadoop dependencies, but works. + --> + <dependency> + <groupId>com.google.guava</groupId> + <artifactId>guava</artifactId> + <scope>${hadoop.deps.scope}</scope> + </dependency> + </dependencies> +</project> diff --git a/dev/make-distribution.sh b/dev/make-distribution.sh index 84f4ae9a64ff8..7348b5b3847f5 100755 --- a/dev/make-distribution.sh +++ b/dev/make-distribution.sh @@ -241,6 +241,10 @@ fi # Make R package - this is used for both CRAN release and packing R layout into distribution if [ "$MAKE_R" == "true" ]; then + echo "Make sure Spark jars folder contains all hadoop dependencies" + SPARK_JARS_DIR="$SPARK_HOME/assembly/target/scala-${SCALA_VERSION}/jars" + cp -n ${SPARK_HOME}/R/rjarsdep/target/scala-${SCALA_VERSION}/jars/* $SPARK_JARS_DIR + echo "Building R source package" R_PACKAGE_VERSION=`grep Version "$SPARK_HOME/R/pkg/DESCRIPTION" | awk '{print $NF}'` pushd "$SPARK_HOME/R" > /dev/null diff --git a/pom.xml b/pom.xml index a08b7fda33387..0eaf79c1d7b3c 100644 --- a/pom.xml +++ b/pom.xml @@ -2797,6 +2797,9 @@ </profile> <profile> <id>sparkr</id> + <modules> + <module>R/rjarsdep</module> + </modules> </profile> </profiles> </project> ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
