spark-instrumented-optimizer/sql/hive/pom.xml
Marcelo Vanzin 24d7d2e453 [SPARK-13579][BUILD] Stop building the main Spark assembly.
This change modifies the "assembly/" module to just copy needed
dependencies to its build directory, and modifies the packaging
script to pick those up (and remove duplicate jars packages in the
examples module).

I also made some minor adjustments to dependencies to remove some
test jars from the final packaging, and remove jars that conflict with each
other when packaged separately (e.g. servlet api).

Also note that this change restores guava in applications' classpaths, even
though it's still shaded inside Spark. This is now needed for the Hadoop
libraries that are packaged with Spark, which now are not processed by
the shade plugin.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #11796 from vanzin/SPARK-13579.
2016-04-04 16:52:22 -07:00

231 lines
7.6 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_2.11</artifactId>
<version>2.0.0-SNAPSHOT</version>
<relativePath>../../pom.xml</relativePath>
</parent>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<packaging>jar</packaging>
<name>Spark Project Hive</name>
<url>http://spark.apache.org/</url>
<properties>
<sbt.project.name>hive</sbt.project.name>
</properties>
<dependencies>
<!-- Added for Hive Parquet SerDe -->
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-hadoop-bundle</artifactId>
</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-core_${scala.binary.version}</artifactId>
<version>${project.version}</version>
<type>test-jar</type>
<scope>test</scope>
</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-test-tags_${scala.binary.version}</artifactId>
</dependency>
<!--
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>com.google.protobuf</groupId>
<artifactId>protobuf-java</artifactId>
<version>${protobuf.version}</version>
</dependency>
-->
<dependency>
<groupId>${hive.group}</groupId>
<artifactId>hive-cli</artifactId>
</dependency>
<!--
<dependency>
<groupId>${hive.group}</groupId>
<artifactId>hive-common</artifactId>
</dependency>
-->
<dependency>
<groupId>${hive.group}</groupId>
<artifactId>hive-exec</artifactId>
<!--
<classifier>core</classifier>
-->
</dependency>
<dependency>
<groupId>${hive.group}</groupId>
<artifactId>hive-metastore</artifactId>
</dependency>
<!--
<dependency>
<groupId>${hive.group}</groupId>
<artifactId>hive-serde</artifactId>
</dependency>
<dependency>
<groupId>${hive.group}</groupId>
<artifactId>hive-shims</artifactId>
</dependency>
-->
<!-- hive-serde already depends on avro, but this brings in customized config of avro deps from parent -->
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<!-- use the build matching the hadoop api of avro-mapred (i.e. no classifier for hadoop 1 API,
hadoop2 classifier for hadoop 2 API. avro-mapred is a dependency of org.spark-project.hive:hive-serde -->
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro-mapred</artifactId>
<classifier>${avro.mapred.classifier}</classifier>
</dependency>
<dependency>
<groupId>commons-httpclient</groupId>
<artifactId>commons-httpclient</artifactId>
</dependency>
<dependency>
<groupId>org.apache.calcite</groupId>
<artifactId>calcite-avatica</artifactId>
</dependency>
<dependency>
<groupId>org.apache.calcite</groupId>
<artifactId>calcite-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</dependency>
<dependency>
<groupId>org.codehaus.jackson</groupId>
<artifactId>jackson-mapper-asl</artifactId>
</dependency>
<!-- transitive dependencies of hive-exec-core doesn't declare -->
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<dependency>
<groupId>org.jodd</groupId>
<artifactId>jodd-core</artifactId>
</dependency>
<dependency>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
</dependency>
<dependency>
<groupId>org.datanucleus</groupId>
<artifactId>datanucleus-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libfb303</artifactId>
</dependency>
<dependency>
<groupId>org.scalacheck</groupId>
<artifactId>scalacheck_${scala.binary.version}</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.binary.version}</artifactId>
<type>test-jar</type>
<version>${project.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-catalyst_${scala.binary.version}</artifactId>
<type>test-jar</type>
<version>${project.version}</version>
<scope>test</scope>
</dependency>
</dependencies>
<profiles>
<profile>
<id>hive</id>
<build>
<plugins>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>build-helper-maven-plugin</artifactId>
<executions>
<execution>
<id>add-scala-test-sources</id>
<phase>generate-test-sources</phase>
<goals>
<goal>add-test-source</goal>
</goals>
<configuration>
<sources>
<source>compatibility/src/test/scala</source>
</sources>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</profile>
</profiles>
<build>
<outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
<testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory>
<plugins>
<plugin>
<groupId>org.scalatest</groupId>
<artifactId>scalatest-maven-plugin</artifactId>
<configuration>
<!-- Specially disable assertions since some Hive tests fail them -->
<argLine>-da -Xmx3g -XX:MaxPermSize=${MaxPermGen} -XX:ReservedCodeCacheSize=512m</argLine>
</configuration>
</plugin>
</plugins>
</build>
</project>