8.Combiner合并案例

• 需求：统计过程中对每个MapTask的输出进行局部汇总，以减小网络传输量即采用Combiner功能
• 期望输出数据：Comnine输入数据多，输出是经过合并，输出数据降低

程序源码

Map类

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

import java.io.IOException;

public class Map extends Mapper<Object, Text,Text, IntWritable> {

    private Text result = new Text();
    private IntWritable one  = new IntWritable(1);

    @Override
    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        String[] array  =value.toString().trim().split(" ");
        for (String s : array) {
            context.write(new Text(s),one);
        }
    }
}

Reduce类

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

import java.io.IOException;

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

Combiner类

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

import java.io.IOException;

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

Driver类

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

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration, "combine");
        job.setJarByClass(Driver.class);

        job.setMapperClass(Map.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setCombinerClass(Combiner.class);

        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

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

    }
}