githubmirror/spark

assembly/pom.xml
375 строк13 KB
Huaxin Gao
Preparing Spark release v4.2.0-rc6
11 июл 2026, 18:18
11 июл 2026, 18:1832f7299
<?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_2.13</artifactId>
    <version>4.2.0</version>
    <relativePath>../pom.xml</relativePath>
  </parent>

  <artifactId>spark-assembly_2.13</artifactId>
  <name>Spark Project Assembly</name>
  <url>https://spark.apache.org/</url>
  <packaging>pom</packaging>

  <properties>
    <sbt.project.name>assembly</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>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-connect_${scala.binary.version}</artifactId>
      <version>${project.version}</version>
      <exclusions>
        <exclusion>
          <groupId>org.apache.spark</groupId>
          <artifactId>spark-connect-common_${scala.binary.version}</artifactId>
        </exclusion>
        <exclusion>
          <groupId>io.grpc</groupId>
          <artifactId>*</artifactId>
        </exclusion>
        <exclusion>
          <groupId>com.google.code.gson</groupId>
          <artifactId>gson</artifactId>
        </exclusion>
        <exclusion>
          <groupId>com.google.guava</groupId>
          <artifactId>failureaccess</artifactId>
        </exclusion>
      </exclusions>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-avro_${scala.binary.version}</artifactId>
      <version>${project.version}</version>
      <scope>provided</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-protobuf_${scala.binary.version}</artifactId>
      <version>${project.version}</version>
      <scope>provided</scope>
    </dependency>
    <!--
      Included so Spark Connect client was compiled before triggering assembly.
      See 'get-connect-client-jar' below. This will not be included in the packaging output.
    -->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-connect-client-jvm_${scala.binary.version}</artifactId>
      <version>${project.version}</version>
      <exclusions>
        <exclusion>
          <groupId>org.apache.spark</groupId>
          <artifactId>spark-connect-shims_${scala.binary.version}</artifactId>
        </exclusion>
      </exclusions>
      <scope>provided</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-connect-client-jdbc_${scala.binary.version}</artifactId>
      <version>${project.version}</version>
      <exclusions>
        <exclusion>
          <groupId>org.apache.spark</groupId>
          <artifactId>spark-connect-shims_${scala.binary.version}</artifactId>
        </exclusion>
      </exclusions>
      <scope>provided</scope>
    </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 which is not the same as Hadoop dependencies, but works.
      As mentioned in https://github.com/google/guava/wiki/UseGuavaInYourBuild
      Guava has one dependency that is needed for linkage at runtime:
      com.google.guava:failureaccess:<version>
    -->
    <dependency>
      <groupId>com.google.guava</groupId>
      <artifactId>guava</artifactId>
      <scope>${hadoop.deps.scope}</scope>
      <exclusions>
        <exclusion>
          <groupId>*</groupId>
          <artifactId>*</artifactId>
        </exclusion>
      </exclusions>
    </dependency>
    <dependency>
      <groupId>com.google.guava</groupId>
      <artifactId>failureaccess</artifactId>
      <scope>${hadoop.deps.scope}</scope>
    </dependency>
  </dependencies>

  <build>
    <plugins>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-deploy-plugin</artifactId>
        <configuration>
          <skip>true</skip>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-install-plugin</artifactId>
        <configuration>
          <skip>true</skip>
        </configuration>
      </plugin>
      <!-- zip pyspark archives to run python application on yarn mode -->
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
          <artifactId>maven-antrun-plugin</artifactId>
          <executions>
            <execution>
              <phase>package</phase>
                <goals>
                  <goal>run</goal>
                </goals>
            </execution>
          </executions>
          <configuration>
            <target>
              <delete file="${basedir}/../python/lib/pyspark.zip"/>
              <zip destfile="${basedir}/../python/lib/pyspark.zip">
                <fileset dir="${basedir}/../python/" includes="pyspark/**/*"/>
              </zip>
            </target>
          </configuration>
      </plugin>
      <plugin>
        <!--
          Copy Spark Connect client jar and its dependencies for Spark Connect REPL.
        -->
        <groupId>org.codehaus.mojo</groupId>
        <artifactId>exec-maven-plugin</artifactId>
        <executions>
          <execution>
            <id>copy-connect-client-repl-jars</id>
            <phase>package</phase>
            <goals>
              <goal>exec</goal>
            </goals>
            <configuration>
              <executable>cp</executable>
              <arguments>
                <argument>-r</argument>
                <argument>${basedir}/../sql/connect/client/jvm/target/connect-repl</argument>
                <argument>${basedir}/target/scala-${scala.binary.version}/jars/</argument>
              </arguments>
            </configuration>
          </execution>
          <execution>
            <id>copy-connect-client-jar</id>
            <phase>package</phase>
            <goals>
              <goal>exec</goal>
            </goals>
            <configuration>
              <executable>cp</executable>
              <arguments>
                <argument>${basedir}/../sql/connect/client/jvm/target/spark-connect-client-jvm_${scala.binary.version}-${project.version}.jar</argument>
                <argument>${basedir}/target/scala-${scala.binary.version}/jars/connect-repl</argument>
              </arguments>
            </configuration>
          </execution>
          <execution>
            <id>copy-connect-client-jdbc-jar</id>
            <phase>package</phase>
            <goals>
              <goal>exec</goal>
            </goals>
            <configuration>
              <executable>cp</executable>
              <arguments>
                <argument>${basedir}/../sql/connect/client/jdbc/target/spark-connect-client-jdbc_${scala.binary.version}-${project.version}.jar</argument>
                <argument>${basedir}/target/scala-${scala.binary.version}/jars/connect-repl</argument>
              </arguments>
            </configuration>
          </execution>
        </executions>
      </plugin>
    </plugins>
  </build>

  <profiles>
    <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>kubernetes</id>
      <dependencies>
        <dependency>
          <groupId>org.apache.spark</groupId>
          <artifactId>spark-kubernetes_${scala.binary.version}</artifactId>
          <version>${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>
      </dependencies>
    </profile>
    <profile>
      <id>hive-thriftserver</id>
      <dependencies>
        <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>jvm-profiler</id>
      <dependencies>
        <dependency>
          <groupId>org.apache.spark</groupId>
          <artifactId>spark-profiler_${scala.binary.version}</artifactId>
          <version>${project.version}</version>
        </dependency>
      </dependencies>
    </profile>

    <!-- Profiles that disable inclusion of certain dependencies. -->
    <profile>
      <id>derby-provided</id>
      <properties>
        <derby.deps.scope>provided</derby.deps.scope>
      </properties>
    </profile>
    <profile>
      <id>hadoop-provided</id>
      <properties>
        <hadoop.deps.scope>provided</hadoop.deps.scope>
      </properties>
    </profile>
    <profile>
      <id>hive-provided</id>
      <properties>
        <hive.deps.scope>provided</hive.deps.scope>
        <hive.llap.scope>provided</hive.llap.scope>
      </properties>
    </profile>
    <profile>
      <id>orc-provided</id>
      <properties>
        <orc.deps.scope>provided</orc.deps.scope>
      </properties>
    </profile>
    <profile>
      <id>parquet-provided</id>
      <properties>
        <parquet.deps.scope>provided</parquet.deps.scope>
      </properties>
    </profile>

    <profile>
      <id>jjwt-provided</id>
      <properties>
        <jjwt.deps.scope>provided</jjwt.deps.scope>
      </properties>
    </profile>

    <!--
     Pull in spark-hadoop-cloud and its associated JARs,
    -->
    <profile>
      <id>hadoop-cloud</id>
      <dependencies>
        <dependency>
          <groupId>org.apache.spark</groupId>
          <artifactId>spark-hadoop-cloud_${scala.binary.version}</artifactId>
          <version>${project.version}</version>
        </dependency>
      </dependencies>
    </profile>
  </profiles>
</project>