spark-instrumented-optimizer/sql/hive/pom.xml
Herman van Hovell 970635a9f8 [SPARK-12362][SQL][WIP] Inline Hive Parser
This PR inlines the Hive SQL parser in Spark SQL.

The previous (merged) incarnation of this PR passed all tests, but had and still has problems with the build. These problems are caused by a the fact that - for some reason - in some cases the ANTLR generated code is not included in the compilation fase.

This PR is a WIP and should not be merged until we have sorted out the build issues.

Author: Herman van Hovell <hvanhovell@questtec.nl>
Author: Nong Li <nong@databricks.com>
Author: Nong Li <nongli@gmail.com>

Closes #10525 from hvanhovell/SPARK-12362.
2016-01-01 23:22:50 -08:00

288 lines
9.6 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_2.10</artifactId>
<version>2.0.0-SNAPSHOT</version>
<relativePath>../../pom.xml</relativePath>
</parent>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.10</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>${hive.group}</groupId>
<artifactId>hive-common</artifactId>
</dependency>
-->
<dependency>
<groupId>${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>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>build-helper-maven-plugin</artifactId>
<executions>
<execution>
<id>add-default-sources</id>
<phase>generate-sources</phase>
<goals>
<goal>add-source</goal>
</goals>
<configuration>
<sources>
<source>v${hive.version.short}/src/main/scala</source>
<source>${project.build.directory/generated-sources/antlr</source>
</sources>
</configuration>
</execution>
</executions>
</plugin>
<!-- Deploy datanucleus jars to the spark/lib_managed/jars directory -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-dependency-plugin</artifactId>
<executions>
<execution>
<id>copy-dependencies</id>
<phase>package</phase>
<goals>
<goal>copy-dependencies</goal>
</goals>
<configuration>
<!-- basedir is spark/sql/hive/ -->
<outputDirectory>${basedir}/../../lib_managed/jars</outputDirectory>
<overWriteReleases>false</overWriteReleases>
<overWriteSnapshots>false</overWriteSnapshots>
<overWriteIfNewer>true</overWriteIfNewer>
<includeGroupIds>org.datanucleus</includeGroupIds>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.antlr</groupId>
<artifactId>antlr3-maven-plugin</artifactId>
<executions>
<execution>
<goals>
<goal>antlr</goal>
</goals>
</execution>
</executions>
<configuration>
<sourceDirectory>${basedir}/src/main/antlr3</sourceDirectory>
<includes>
<include>**/SparkSqlLexer.g</include>
<include>**/SparkSqlParser.g</include>
</includes>
</configuration>
</plugin>
</plugins>
</build>
</project>