Hadoop WordCount Example For Mapper Reducer

Pom文件添加：

    <dependencies>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-simple</artifactId>
            <version>1.7.25</version>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>jdk.tools</groupId>
            <artifactId>jdk.tools</artifactId>
            <version>1.8</version>
            <scope>system</scope>
            <systemPath>C:/Java/jdk1.8/lib/tools.jar</systemPath>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>compile</scope>
        </dependency>
    </dependencies>

Mapper 类：

package com.kpwong.mr;


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;

//Map 阶段
//KEYIN 输入数据 KEY
//VALUEIN输入数据value
//KEYOUT输出数据类型
//VALUEOUT 输出数据Value类型
public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    Text k = new Text();
    IntWritable v = new IntWritable(1);
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行数据
        String line = value.toString();
        //切割单词
        String[] words = line.split(" ");
        for(String word : words)
        {
            /* Text k = new Text(); */
            k.set(word);
/*
            IntWritable v = new IntWritable();
            v.set(1);
*/
            context.write(k,v);
        }

    }
}

Reducer类:

package com.kpwong.mr;

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

import java.io.IOException;

public class WordCountReducer  extends Reducer<Text, IntWritable, Text,IntWritable> {
    IntWritable v = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
    //累加求和
        int sum = 0;
        for(IntWritable value:values)
        {
            sum += value.get();
        }
        //写出
        v.set(sum);
        context.write(key,v);

    }
}

Driver类:(注意：Driver,Mapper,Reducer写法格式都是固定的。)

package com.kpwong.mr;

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;
import java.io.IOException;


public class WordCountDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1获取Job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2设置Jar存储位置
        job.setJarByClass(WordCountDriver.class);
        //3关联Map和Reduce类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //4设置Mapper阶段的输出数据的key value 类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //5设置最终数据的key value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //6设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //7提交Job

        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);


    }
}

添加运行参数args[0],args[1]:

 把要统计的txt文件放入input1文件夹。注意output1文件夹不能新建。系统会自己去创建output1文件夹.