Spark之使用idea写scala的worldcount程序打包运行-04

先从官网下载下scala,然后配置环境变量,和配置java环境变量一样

然后打开idea下载这两个插件

创建好普通maven项目后

导入pom依赖,下面的几个plugins是必须的打包时使用的,只需要修改mainclass就可以了

<?xml version="1.0" encoding="UTF-8"?>
<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>

    <groupId>com.buba</groupId>
    <artifactId>scala-helloworld</artifactId>
    <version>1.0-SNAPSHOT</version>

    <packaging>jar</packaging>

    <properties>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.1.1</spark.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
            <scope>provided</scope>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
            <scope>provided</scope>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <archive>
                        <manifest>
                            <mainClass>com.buba.WordCount</mainClass>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

scala类,worldcount 

package com.buba

import org.apache.spark.{SparkConf, SparkContext}


object WordCount extends App {

  val sparkConf = new SparkConf().setAppName("WordCount")

  val sparkContext = new SparkContext(sparkConf)

  val file = sparkContext.textFile("hdfs://hadoop-senior01.buba.com:8020/test.txt")

  val words = file.flatMap(_.split(" "))

  val wordsTuple = words.map((_,1))

  wordsTuple.reduceByKey(_+_).saveAsTextFile("hdfs://hadoop-senior01.buba.com:8020/out1")

  sparkContext.stop()

}

打完包后把这个jar包上传到spark集群上去