实现一个 WordCount 程序 —— MapReduce

需要导入的依赖如下：

<?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.qjl</groupId>
    <artifactId>mapreduce</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <hadoop.version>2.7.3</hadoop.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>3.8.1</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
    </dependencies>
</project>

Mapper

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * @author 曲健磊
 * @date 2018-11-27 16:15:49
 * @description 词频统计的Mapper
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        /**
         * context 表示Mapper的上下文
         * 上文：HDFS
         * 下文：Mapper
         */
        // 数据： I love Beijing
        String data = value.toString();

        // 分词
        String[] words = data.split(" ");

        // 输出 k2 v2
        for (String word : words) {
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

Reducer

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * @author 曲健磊
 * @date 2018-11-27 16:20:38
 * @description 词频统计的Reducer
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        /**
         * context 是reducer上下文
         * 上文：Mapper
         * 下文：HDFS
         */
        // 对v3求和
        int total = 0;
        for (IntWritable value : values) {
            total += value.get();
        }
        context.write(key, new IntWritable(total));
    }
}

Job

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;

/**
 * @author 曲健磊
 * @date 2018-11-27 16:24:58
 * @description 词频统计任务的执行的入口
 */
public class WordCountMain {

    public static void main(String[] args) throws Exception {
        // 1.创建一个job指定任务入口
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(WordCountMain.class);

        // 2.指定job的mapper和输出类型
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 3.指定job的reducer和输出类型
        job.setReducerClass(WordCountReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 4.指定job的输入和输出
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 5.执行job,true表示打印日志
        job.waitForCompletion(true);
    }
}

执行 Job 的流程基本是固定的：

1. 创建一个job指定任务入口

2. 指定job的mapper和输出类型

3. 指定job的reducer和输出类型

4. 指定job的输入和输出

5. 执行job

之后将项目打成 jar 包，上传到 Linux 服务器，提交到 Yarn 上执行：hadoop jar xxx.jar /data.txt /output，如果是本地模式后面跟的两个路径是本地 Linux 的路径，伪分布模式或者全分布模式则表示 HDFS 的路径，第一个表示数据的输入路径，第二个表示数据的输出位置。