IDEA下使用Maven搭建spark开发环境WordCount示例

版权声明：转载附链接并联系 https://blog.csdn.net/BigCabbageFy/article/details/84776836

一、创建Maven项目

二、添加相关依赖（配置pom.xml文件）

<?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.spark</groupId>
    <artifactId>WordCountTest</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <spark.version>2.1.1</spark.version>
        <scala.version>2.11</scala.version>
        <hadoop.version>2.6.5</hadoop.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.39</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
    </dependencies>

    <!-- maven官方 http://repo1.maven.org/maven2/  或 http://repo2.maven.org/maven2/ （延迟低一些） -->
    <repositories>
        <repository>
            <id>central</id>
            <name>Maven Repository Switchboard</name>
            <layout>default</layout>
            <url>http://repo2.maven.org/maven2</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
    </repositories>

    <build>
        //将../src/main/java改成scala即可，下面同理
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
    </build>

</project>

三、编写WordCount

注意：WordCount是 Object 而非 class

package spark

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

object WordCount {
  def main(args: Array[String]): Unit = {
    /**
      * SparkContext 的初始化需要一个SparkConf对象
      * SparkConf包含了Spark集群的配置的各种参数
      */
    val conf=new SparkConf()
      .setMaster("local")//启动本地化计算
      .setAppName("WordCount")//设置本程序名称

    //Spark程序的编写都是从SparkContext开始的
    val sc=new SparkContext(conf)
    //以上的语句等价与val sc=new SparkContext("local","testRdd")
    val data=sc.textFile("F://wordcount.txt")//读取本地文件
    val result = data.flatMap(_.split(" "))//下划线是占位符，flatMap是对行操作的方法，对读入的数据进行分割
      .map((_,1))//将每一项转换为key-value，数据是key，value是1
      .reduceByKey(_+_)//将具有相同key的项相加合并成一个
      .collect()//将分布式的RDD返回一个单机的scala array，在这个数组上运用scala的函数操作，并返回结果到驱动程序
    
    //循环打印
    for (r <- result) {
      print(r)
    }
  }
}

四、打印结果