HADOOP MapReduce WordCount案列

1.安装windows hadoop 运行环境

2.IDEA 创建maven项目

导入依赖

      <dependencies>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-client</artifactId>
                <version>3.1.3</version>
            </dependency>
      </dependencies>

3.创建WordCountMap类继承Mapper

package com.lhh.textlhh;

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;

/**
 * @program: lhh
 * @description:
 * @author: 华仔
 * @create: 2021-04-25 14:50
 */
public class WordCountMap extends Mapper<LongWritable, Text,Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行数据
        String values = value.toString();
        //--\\s+--匹配一个或者多个空格
        String[] split = s1.split("\\s+");
        //循环
        for (String s : split) {
            //写出
            context.write(new Text(s),new IntWritable(1));
        }

    }
}

4.创建WordCountReduce类继承Reducer

package com.lhh.textlhh;

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

import java.io.IOException;


/**
 * @program: lhh
 * @description:
 * @author: 华仔
 * @create: 2021-04-25 14:51
 */
public class WordCountRduce extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //声明变量
        int i = 0;
        for (IntWritable value : values) {
            i += 1; //累加
        }
        //写出数据
        context.write(key, new IntWritable(i));
    }
}

5.创建主启动类

package com.lhh.textlhh;

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;


/**
 * @program: lhh
 * @description:
 * @author: 华仔
 * @create: 2021-04-25 14:51
 */
public class WordCountJob {
    public static void main(String[] args) throws IOException, ClassNotFoundException,  InterruptedException {
          //获取job
        Configuration configured=new Configuration();
        Job job =Job.getInstance(configured);
		//设置map reduce
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountRduce.class);
 		//设置map输出类
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
		//设置最终输出类
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
		//设置输入和输出路径
        FileInputFormat.setInputPaths(job,new Path("D:/test/in/123.txt"));
        FileOutputFormat.setOutputPath(job,new Path("D:/test/out/test123"));
		//等待任务完成
        boolean b = job.waitForCompletion(true);
         if (b){
            System.out.println("程序完成");
        }else{
            System.out.println("程序异常");
        }
        //关闭程序
        System.exit(b ? 0 : 1);
    }
}