Java+Scala混合开发Spark应用

Java+Scala混合开发Spark应用

我主要使用Spark GraphX 的api，但是使用Scala对项目的成员不是很友好，考虑到Scala在市场上的用户没有Java的多，就打算使用Java+Scala混合开发Spark GraphX应用，

环境：

Java8

Scala 2.12.*

pom.xml

需要修改一下

<groupId>xxx</groupId>
<artifactId>xxx</artifactId>

<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/maven-v4_0_0.xsd">

    <modelVersion>4.0.0</modelVersion>
    <groupId>xxx</groupId>
    <artifactId>xxx</artifactId>
    <inceptionYear>2008</inceptionYear>

    <parent>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-parent_2.12</artifactId>
        <version>3.0.1</version>
    </parent>

    <properties>
        <sbt.project.name>examples</sbt.project.name>
        <build.testJarPhase>none</build.testJarPhase>
        <build.copyDependenciesPhase>package</build.copyDependenciesPhase>
        <!--        <hadoop.deps.scope>provided</hadoop.deps.scope>-->
        <!--        <hive.deps.scope>provided</hive.deps.scope>-->
        <!--        <parquet.deps.scope>provided</parquet.deps.scope>-->
        <scala.version>2.12.12</scala.version>
        <scala.binary.version>2.12</scala.binary.version>
    </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>
        </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-streaming_${scala.binary.version}</artifactId>
            <version>${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-hive_${scala.binary.version}</artifactId>
            <version>${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-streaming-kafka-0-10_${scala.binary.version}</artifactId>
            <version>${project.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql-kafka-0-10_${scala.binary.version}</artifactId>
            <version>${project.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-math3</artifactId>
        </dependency>
        <dependency>
            <groupId>org.scalacheck</groupId>
            <artifactId>scalacheck_${scala.binary.version}</artifactId>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>

        </dependency>
        <dependency>
            <groupId>com.github.scopt</groupId>
            <artifactId>scopt_${scala.binary.version}</artifactId>
            <version>3.7.1</version>
        </dependency>

        <dependency>
            <groupId>com.google.guava</groupId>
            <artifactId>guava</artifactId>
            <version>${guava.version}</version>
            <scope>compile</scope>
        </dependency>

    </dependencies>

    <build>
        <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
        <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory>
        <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>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <configuration>
                    <outputDirectory>${jars.target.dir}</outputDirectory>
                </configuration>
            </plugin>

        </plugins>


    </build>


    <profiles>
        <profile>
            <id>kinesis-asl</id>
            <dependencies>
                <dependency>
                    <groupId>org.apache.spark</groupId>
                    <artifactId>spark-streaming-kinesis-asl_${scala.binary.version}</artifactId>
                    <version>${project.version}</version>
                    <scope>provided</scope>
                </dependency>
            </dependencies>
        </profile>
    </profiles>
</project>

等待依赖下载

速度可能有点慢，可以设置maven的代理

修改maven settings.xml文件，在settings 里面添加 

   <proxies>
        <proxy>
            <id>optional</id>
            <active>true</active>
            <protocol>http</protocol>
            <host>127.0.0.1</host>
            <port>1081</port>
        </proxy>
    </proxies>

然后打开命令行窗口 执行

mvn compile

这样就能够通过代理下载依赖了