spark-instrumented-optimizer/assembly/pom.xml
Marcelo Vanzin c9f743957f [SPARK-2848] Shade Guava in uber-jars.
For further discussion, please check the JIRA entry.

This change moves Guava classes to a different package so that they don't conflict with the user-provided Guava (or the Hadoop-provided one). Since one class (Optional) was exposed through Spark's public API, that class was forked from Guava at the current dependency version (14.0.1) so that it can be kept going forward (until the API is cleaned).

Note this change has a few implications:
- *all* classes in the final jars will reference the relocated classes. If Hadoop classes are included (i.e. "-Phadoop-provided" is not activated), those will also reference the Guava 14 classes (instead of the Guava 11 classes from the Hadoop classpath).
- if the Guava version in Spark is ever changed, the new Guava will still reference the forked Optional class; this may or may not be a problem, but in the long term it's better to think about removing Optional from the public API.

For the end user, there are two visible implications:

- Guava is not provided as a transitive dependency anymore (since it's "provided" in Spark)
- At runtime, unless they provide their own, they'll either have no Guava or Hadoop's version of Guava (11), depending on how they set up their classpath.

Note that this patch does not change the sbt deliverables; those will still contain guava in its original package, and provide guava as a compile-time dependency. This assumes that maven is the canonical build, and sbt-built artifacts are not (officially) published.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #1813 from vanzin/SPARK-2848 and squashes the following commits:

9bdffb0 [Marcelo Vanzin] Undo sbt build changes.
819b445 [Marcelo Vanzin] Review feedback.
05e0a3d [Marcelo Vanzin] Merge branch 'master' into SPARK-2848
fef4370 [Marcelo Vanzin] Unfork Optional.java.
d3ea8e1 [Marcelo Vanzin] Exclude asm classes from final jar.
637189b [Marcelo Vanzin] Add hacky filter to prefer Spark's copy of Optional.
2fec990 [Marcelo Vanzin] Shade Guava in the sbt build.
616998e [Marcelo Vanzin] Shade Guava in the maven build, fork Guava's Optional.java.
2014-08-20 16:23:10 -07:00

338 lines
13 KiB
XML

<?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</artifactId>
<version>1.1.0-SNAPSHOT</version>
<relativePath>../pom.xml</relativePath>
</parent>
<groupId>org.apache.spark</groupId>
<artifactId>spark-assembly_2.10</artifactId>
<name>Spark Project Assembly</name>
<url>http://spark.apache.org/</url>
<packaging>pom</packaging>
<properties>
<sbt.project.name>assembly</sbt.project.name>
<spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
<spark.jar.basename>spark-assembly-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
<spark.jar>${project.build.directory}/${spark.jar.dir}/${spark.jar.basename}</spark.jar>
<deb.pkg.name>spark</deb.pkg.name>
<deb.install.path>/usr/share/spark</deb.install.path>
<deb.user>root</deb.user>
<deb.bin.filemode>744</deb.bin.filemode>
</properties>
<dependencies>
<!-- Promote Guava to compile scope in this module so it's included while shading. -->
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<scope>compile</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-bagel_${scala.binary.version}</artifactId>
<version>${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-repl_${scala.binary.version}</artifactId>
<version>${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>
</dependencies>
<build>
<plugins>
<!-- Use the shade plugin to create a big JAR with all the dependencies -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<configuration>
<shadedArtifactAttached>false</shadedArtifactAttached>
<outputFile>${spark.jar}</outputFile>
<artifactSet>
<includes>
<include>*:*</include>
</includes>
</artifactSet>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>org/datanucleus/**</exclude>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
</configuration>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<relocations>
<relocation>
<pattern>com.google</pattern>
<shadedPattern>org.spark-project.guava</shadedPattern>
<includes>
<include>com.google.common.**</include>
</includes>
<excludes>
<exclude>com.google.common.base.Optional**</exclude>
</excludes>
</relocation>
</relocations>
<transformers>
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
<transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
<resource>META-INF/services/org.apache.hadoop.fs.FileSystem</resource>
</transformer>
<transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
<resource>reference.conf</resource>
</transformer>
<transformer implementation="org.apache.maven.plugins.shade.resource.DontIncludeResourceTransformer">
<resource>log4j.properties</resource>
</transformer>
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer"/>
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer"/>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
<profiles>
<profile>
<id>yarn-alpha</id>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-yarn-alpha_${scala.binary.version}</artifactId>
<version>${project.version}</version>
</dependency>
</dependencies>
</profile>
<profile>
<id>yarn</id>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-yarn_${scala.binary.version}</artifactId>
<version>${project.version}</version>
</dependency>
</dependencies>
</profile>
<profile>
<id>hive</id>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_${scala.binary.version}</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
<version>${project.version}</version>
</dependency>
</dependencies>
</profile>
<profile>
<id>spark-ganglia-lgpl</id>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-ganglia-lgpl_${scala.binary.version}</artifactId>
<version>${project.version}</version>
</dependency>
</dependencies>
</profile>
<profile>
<id>bigtop-dist</id>
<!-- This profile uses the assembly plugin to create a special "dist" package for BigTop
that contains Spark but not the Hadoop JARs it depends on. -->
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-assembly-plugin</artifactId>
<version>2.4</version>
<executions>
<execution>
<id>dist</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
<configuration>
<descriptors>
<descriptor>src/main/assembly/assembly.xml</descriptor>
</descriptors>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</profile>
<profile>
<id>deb</id>
<build>
<plugins>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>buildnumber-maven-plugin</artifactId>
<version>1.2</version>
<executions>
<execution>
<phase>validate</phase>
<goals>
<goal>create</goal>
</goals>
<configuration>
<shortRevisionLength>8</shortRevisionLength>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.vafer</groupId>
<artifactId>jdeb</artifactId>
<version>0.11</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>jdeb</goal>
</goals>
<configuration>
<deb>${project.build.directory}/${deb.pkg.name}_${project.version}-${buildNumber}_all.deb</deb>
<attach>false</attach>
<compression>gzip</compression>
<dataSet>
<data>
<src>${spark.jar}</src>
<type>file</type>
<mapper>
<type>perm</type>
<user>${deb.user}</user>
<group>${deb.user}</group>
<prefix>${deb.install.path}/jars</prefix>
</mapper>
</data>
<data>
<src>${basedir}/src/deb/RELEASE</src>
<type>file</type>
<mapper>
<type>perm</type>
<user>${deb.user}</user>
<group>${deb.user}</group>
<prefix>${deb.install.path}</prefix>
</mapper>
</data>
<data>
<src>${basedir}/../conf</src>
<type>directory</type>
<mapper>
<type>perm</type>
<user>${deb.user}</user>
<group>${deb.user}</group>
<prefix>${deb.install.path}/conf</prefix>
<filemode>744</filemode>
</mapper>
</data>
<data>
<src>${basedir}/../bin</src>
<type>directory</type>
<mapper>
<type>perm</type>
<user>${deb.user}</user>
<group>${deb.user}</group>
<prefix>${deb.install.path}/bin</prefix>
<filemode>${deb.bin.filemode}</filemode>
</mapper>
</data>
<data>
<src>${basedir}/../sbin</src>
<type>directory</type>
<mapper>
<type>perm</type>
<user>${deb.user}</user>
<group>${deb.user}</group>
<prefix>${deb.install.path}/sbin</prefix>
<filemode>744</filemode>
</mapper>
</data>
<data>
<src>${basedir}/../python</src>
<type>directory</type>
<mapper>
<type>perm</type>
<user>${deb.user}</user>
<group>${deb.user}</group>
<prefix>${deb.install.path}/python</prefix>
<filemode>744</filemode>
</mapper>
</data>
</dataSet>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</profile>
</profiles>
</project>