Spark第一个应用--WordCount

简介：本篇博客主要数用于Spark安装用来测试用的。

1、创建一个maven工程

详细结构如上图

2、配置pom.xml

本地运行配置

<?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.lqs</groupId>
    <artifactId>WordCount</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
    </dependencies>

    <build>
        <finalName>WordCount</finalName>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.4.6</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

打包给集群运行配置

<?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.lqs</groupId>
    <artifactId>WordCount</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
    </dependencies>

    <build>
        <finalName>WordCount</finalName>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.4.6</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <!-- 打包依赖的插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <!-- 打包依赖插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

        </plugins>
    </build>

</project>

3、本地运行Spark代码

package com.lqs.spark

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

/**
 * @Author lqs
 * @Date 2022年01月24日 10:20:39
 * @Version 1.0.0
 * @ClassName WordCount
 * @Describe
 */
object WordCount {
  def main(args: Array[String]): Unit = {
    //创建SparkConf并设置APP名称
    val conf: SparkConf = new SparkConf().setAppName("WordCount").setMaster("local[*]")

    //2创建SparkContext,该对象是提交Spark APP的人口
    val context: SparkContext = new SparkContext(conf)

    //需要使用行动算子,读取指定位置文件
    val lineRdd: RDD[String] = context.textFile("input")

    //读取的一行一行的数据分解成一个一个的单词（扁平化）
    val wordRdd: RDD[String] = lineRdd.flatMap(line => line.split(" "))

    //将数据转换结构
    val wordToOneRdd: RDD[(String, Int)] = wordRdd.map(word => (word, 1))

    //将转换结构后的数据进行聚合处理
    val wordToSumRdd: RDD[(String, Int)] = wordToOneRdd.reduceByKey((v1, v2) => v1 + v2)

    //将统计结构采集到控制台打印
    val wordToCountArray: Array[(String, Int)] = wordToSumRdd.collect()

    wordToCountArray.foreach(println)

    //一行写完,打包时也用本行代码，把其它一样的注释掉即可
//    context.textFile(args(0)).flatMap(_.split(" ")).map((_,1)).reduceByKey(_ + _).saveAsTextFile(args(1))

    //暂停一段时间，好在http://lqs:4040访问
//    Thread.sleep(1000000)

    //关闭连接
    context.stop()

  }
}

4、集群运行打包代码

package com.lqs.spark

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

/**
 * @Author lqs
 * @Date 2022年01月24日 10:20:39
 * @Version 1.0.0
 * @ClassName WordCount
 * @Describe
 */
object WordCount {
  def main(args: Array[String]): Unit = {
    //创建SparkConf并设置APP名称
    val conf: SparkConf = new SparkConf().setAppName("WordCount").setMaster("local[*]")

    //2创建SparkContext,该对象是提交Spark APP的人口
    val context: SparkContext = new SparkContext(conf)

    //一行写完,打包时也用本行代码，把其它一样的注释掉即可
    context.textFile(args(0)).flatMap(_.split(" ")).map((_,1)).reduceByKey(_ + _).saveAsTextFile(args(1))
    context.stop()

  }
}