单词计数

一、项目总体架构

二、项目的pom.xml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>org.example</groupId>
  <artifactId>MyMapRrduce</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>MyMapRrduce</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.11</version>
      <scope>test</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>2.10.0</version>
    </dependency>
  </dependencies>

  <build>
    <pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
      <plugins>
        <!-- clean lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#clean_Lifecycle -->
        <plugin>
          <artifactId>maven-clean-plugin</artifactId>
          <version>3.1.0</version>
        </plugin>
        <!-- default lifecycle, jar packaging: see https://maven.apache.org/ref/current/maven-core/default-bindings.html#Plugin_bindings_for_jar_packaging -->
        <plugin>
          <artifactId>maven-resources-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-compiler-plugin</artifactId>
          <version>3.8.0</version>
        </plugin>
        <plugin>
          <artifactId>maven-surefire-plugin</artifactId>
          <version>2.22.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-jar-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-install-plugin</artifactId>
          <version>2.5.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-deploy-plugin</artifactId>
          <version>2.8.2</version>
        </plugin>
        <!-- site lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#site_Lifecycle -->
        <plugin>
          <artifactId>maven-site-plugin</artifactId>
          <version>3.7.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-project-info-reports-plugin</artifactId>
          <version>3.0.0</version>
        </plugin>
      </plugins>
    </pluginManagement>
  </build>
</project>

三、每个类的代码

WordCount类

package org.example;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount
{
    public static void main( String[] args ) throws IOException, ClassNotFoundException, InterruptedException
    {
        //初始化Configuration类
        Configuration conf = new Configuration();
        //构建任务对象
        Job wordCountJob = Job.getInstance(conf,WordCount.class.getName());
        wordCountJob.setJarByClass(WordCount.class);
        wordCountJob.setMapperClass(WordCountMapper.class);
        wordCountJob.setReducerClass(WordCountReducer.class);

        //设置输出结果的数据类型
        wordCountJob.setMapOutputKeyClass(Text.class);
        wordCountJob.setMapOutputValueClass(IntWritable.class);
        wordCountJob.setOutputKeyClass(Text.class);
        wordCountJob.setOutputValueClass(IntWritable.class);
        //设置输入路径
        FileInputFormat.addInputPath(wordCountJob,new Path("/wc/input") );
        //设置输出路径
        FileOutputFormat.setOutputPath(wordCountJob, new Path("/output"));
        //提交任务给Hadoop集群
        wordCountJob.waitForCompletion(true);
    }
}

WordCountMapper类

package org.example;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.*;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
    protected void map(LongWritable key, Text value,Context context) throws IOException, InterruptedException {
        String line = value.toString();
        //根据空格分割字符串
        String[] words=line.split(" ");
        //循环输入单词作为key，每个value都为1
        for(String word:words){
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

WordCountReducer类

package org.example;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.*;
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
    protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
        int count = 0;
        //统计单词总数
        for(IntWritable value:values){
            count+=value.get();
        }
        //输出统计结果
        context.write(key, new IntWritable(count));
    }
}

打包成jar,在hadoop运行

hadoop jar XXX.jar org.example.MyWordCount WordCount（主类的类目）