Combiner+GroupingComparator+shuffle原理+Reduce原理

1、Combiner

Combiner的输入输出对象必须一样。

2、GroupingComparator

运行代码：

map

package groupcompartor;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;


import java.io.IOException;

public class OrderMapper extends Mapper<LongWritable, Text,OrderBean, NullWritable> {

    private OrderBean orderbean=new OrderBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fieds=value.toString().split("\t");
        orderbean.setOrderId(fieds[0]);
        orderbean.setProductId(fieds[1]);
        orderbean.setPrice(Double.parseDouble(fieds[2]));
        context.write(orderbean,NullWritable.get());
    }
}

　　reduce

package groupcompartor;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class OrderReducer extends Reducer<OrderBean, NullWritable,OrderBean, NullWritable> {

    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

　　driver

package groupcompartor;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.logging.log4j.core.config.OrderComparator;

import java.io.IOException;

public class OrderDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance(new Configuration());
        job.setJarByClass(OrderDriver.class);
        job. setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);
        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(OrderBean.class);
        job.setGroupingComparatorClass(OderCompartor.class);
        job.setOutputValueClass(NullWritable.class);
        FileInputFormat.setInputPaths(job,new Path("d:\\linput"));
        FileOutputFormat.setOutputPath(job,new Path("d:\\loutput"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

　　comparator

package groupcompartor;

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;

public class OderCompartor extends WritableComparator {
    protected OderCompartor() {
        super(OrderBean.class,true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        OrderBean oa=(OrderBean)a;
        OrderBean ob=(OrderBean)b;
        return oa.getOrderId().compareTo(ob.getOrderId());
    }
}

原本结果：