Combiner合并的使用案例

Combiner合并案例实操

统计过程中对每一个MapTask的输出进行局部汇总，以减小网络传输量即采用Combiner功能

1)需求

数据输入：hello.txt
期望输出：Combine输入数据多，输出时经过合并，输出数据降低

2)需求分析

3)编程实现

只写出方案一，方案二不用在原基础上增加类，只是加个驱动即可

1.创建Combiner类

package com.yingzi.mapreduce.combiner;

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

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-14-15:03
 **/
public class WordCountCombiner extends Reducer<Text, IntWritable,Text,IntWritable> {

    private IntWritable outV = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {

        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }

        outV.set(sum);

        context.write(key,outV);
    }
}

2.创建Mapper类

package com.yingzi.mapreduce.combiner;

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 影子
 * @create 2022-01-13-14:41
 **/
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 {

        // 1 获取一行
        String line = value.toString();

        // 2 切割
        String[] words = line.split(" ");

        // 3 输出
        for (String word : words) {

            k.set(word);
            context.write(k, v);
        }
    }
}

3.创建Reducer类

同Combiner类完全相同！！！

package com.yingzi.mapreduce.combiner;

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

import java.io.IOException;


/**
 * @author 影子
 * @create 2022-01-13-14:41
 **/
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

    int sum;
    IntWritable v = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {

        // 1 累加求和
        sum = 0;
        for (IntWritable count : values) {
            sum += count.get();
        }

        // 2 输出
        v.set(sum);
        context.write(key,v);
    }
}

4.创建Driver类

package com.yingzi.mapreduce.combiner;

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 影子
 * @create 2022-01-13-14:41
 **/
public class WordCountDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 1 获取配置信息以及获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 关联本Driver程序的jar
        job.setJarByClass(WordCountDriver.class);

        // 3 关联Mapper和Reducer的jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置Mapper输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setCombinerClass(WordCountCombiner.class);

        // 6 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\11_input\\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\output6"));

        // 7 提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

4.查看结果