MapReduce版wordcount

1.创建Mapper类，发送(单词,1)到reduce端。

package com.aura.hadoop.wc;

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 panghu
 * @description wordcount Mapper类，负责把单词拆分为（单词，1）的形式发送给reducer
 * 四个泛型分别表示：输入的key类型，输入的value类型，输出的key类型，输出的value类型
 * @create 2021-02-14-11:58
 */
public class WcMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
    private Text word = new Text();
    private IntWritable one = new IntWritable(1);
    /**
     * map方法每行就会调用一次
     * @param key 偏移量
     * @param value 每一行的数据
     * @param context 上下文对象，任务本身
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 获取每行数据
        String line = value.toString();
        // 切分单词
        String[] words = line.split(" ");
        for (String w : words) {
            // 包装并发送给框架
            this.word.set(w);
            context.write(word,one);
        }
    }
}

2.创建Reducer类，统计单词数量。

package com.aura.hadoop.wc;

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

import java.io.IOException;

/**
 * @author panghu
 * @description wordcount的reducer类，负责接收mapper类的输出，并进行汇总计算
 * 四个泛型类型分别为：map端的输出key类型，map端的输出value类型，reduce端的输出key类型，reduce端的输出value类型
 * @create 2021-02-14-11:58
 */
public class WcReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
    private Text word = new Text();
    private IntWritable cnt = new IntWritable();
    /**
     * 汇总统计map端的输出，接收到的数据类似于 单词：[1,1,1,1...]这种形式
     * reduce方法每组调用一次，即每个不同的key调用一次
     * @param key
     * @param values
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        System.out.println("---------------------------------");
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        // 发送数据
        this.word.set(key);
        this.cnt.set(sum);
        context.write(word,cnt);
    }
}

3.创建Driver类，串联Mapper和Reducer。

package com.aura.hadoop.wc;

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;

/**
 * @author panghu
 * @description wordcount的Driver类，用于串联Mapper类和Reducer类
 * @create 2021-02-14-11:58
 */
public class WcDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1.获取job对象
        Job job = Job.getInstance(new Configuration());
        // 2.设置jar包
        job.setJarByClass(WcDriver.class);
        // 3.设置Mapper类和Reducer类
        job.setMapperClass(WcMapper.class);
        job.setReducerClass(WcReducer.class);
        // 4.设置map端和reduce端输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        // 5.设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 6.提交任务
        boolean res = job.waitForCompletion(true);
        System.exit(res ? 0:1);
    }
}