mapreduce系列（8）--自定义GroupingComparator

一、概述

GroupingComparator是在reduce阶段分组来使用的，由于reduce阶段，如果key相同的一组，只取第一个key作为key，迭代所有的values。
如果reduce的key是自定义的bean，我们只需要bean里面的某个属性相同就认为这样的key是相同的，这是我们就需要之定义GroupCoparator来“欺骗”reduce了。
    我们需要理清楚的还有map阶段你的几个自定义：
parttioner中的getPartition（）这个是map阶段自定义分区，
bean中定义CopmareTo()是在溢出和merge时用来来排序的。

二、代码

自定义OrderBean.java

package groupingcomparator;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;

/**
 * 自定义bean
 * @author tianjun
 */
public class OrderBean implements WritableComparable<OrderBean>{

    private Text itemid;
    private DoubleWritable amount;

    public OrderBean() {
    }

    public OrderBean(Text itemid, DoubleWritable amount) {
        set(itemid, amount);

    }

    public void set(Text itemid, DoubleWritable amount) {

        this.itemid = itemid;
        this.amount = amount;

    }



    public Text getItemid() {
        return itemid;
    }

    public DoubleWritable getAmount() {
        return amount;
    }



    @Override
    public int compareTo(OrderBean o) {
        int cmp = this.itemid.compareTo(o.getItemid());
        if (cmp == 0) {
            cmp = -this.amount.compareTo(o.getAmount());
        }
        return cmp;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(itemid.toString());
        out.writeDouble(amount.get());

    }

    @Override
    public void readFields(DataInput in) throws IOException {
        String readUTF = in.readUTF();
        double readDouble = in.readDouble();

        this.itemid = new Text(readUTF);
        this.amount= new DoubleWritable(readDouble);
    }


    @Override
    public String toString() {

        return itemid.toString() + "\t" + amount.get();

    }

}

自定义分区ItemIdPartitioner.java

package groupingcomparator;

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


public class ItemIdPartitioner extends Partitioner<OrderBean, NullWritable>{

    @Override
    public int getPartition(OrderBean bean, NullWritable value, int numReduceTasks) {
        //相同id的订单bean，会发往相同的partition
        //而且，产生的分区数，是会跟用户设置的reduce task数保持一致
        return (bean.getItemid().hashCode() & Integer.MAX_VALUE) % numReduceTasks;

    }

}

欺骗reduce的分组ItemidGroupingComparator.java

package groupingcomparator;

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

/**
 * 利用reduce端的GroupingComparator来实现将一组bean看成相同的key
 * @author tianjun
 *
 */
public class ItemidGroupingComparator extends WritableComparator {

    //传入作为key的bean的class类型，以及制定需要让框架做反射获取实例对象
    protected ItemidGroupingComparator() {
        super(OrderBean.class, true);
    }


    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        OrderBean abean = (OrderBean) a;
        OrderBean bbean = (OrderBean) b;

        //比较两个bean时，指定只比较bean中的orderid
        return abean.getItemid().compareTo(bbean.getItemid());

    }

}

mr程序SecondarySort.java

package groupingcomparator;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


/**
 * 
 * @author tianjun
 *
 */
public class SecondarySort {

    static class SecondarySortMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable>{

        OrderBean bean = new OrderBean();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            String line = value.toString();
            String[] fields = StringUtils.split(line, ",");

            bean.set(new Text(fields[0]), new DoubleWritable(Double.parseDouble(fields[2])));

            context.write(bean, NullWritable.get());

        }

    }

    static class SecondarySortReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable>{


        //到达reduce时，相同id的所有bean已经被看成一组，且金额最大的那个一排在第一位
        @Override
        protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
            context.write(key, NullWritable.get());
        }
    }


    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(SecondarySort.class);

        job.setMapperClass(SecondarySortMapper.class);
        job.setReducerClass(SecondarySortReducer.class);


        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job, new Path("F:\\myWorkPlace\\java\\dubbo\\demo\\dubbo-demo\\mr-demo1\\src\\main\\java\\groupingcomparator\\orders.txt"));
        FileOutputFormat.setOutputPath(job, new Path("c:/wordcount/gpoutput"));

        //在此设置自定义的Groupingcomparator类 
        job.setGroupingComparatorClass(ItemidGroupingComparator.class);
        //在此设置自定义的partitioner类
        job.setPartitionerClass(ItemIdPartitioner.class);

        job.setNumReduceTasks(2);

        job.waitForCompletion(true);

    }

}

还有数据如下：

Order_0000001,Pdt_01,222.8
Order_0000001,Pdt_05,25.8
Order_0000002,Pdt_05,325.8
Order_0000002,Pdt_03,522.8
Order_0000002,Pdt_04,122.4
Order_0000003,Pdt_05,222.8
Order_0000003,Pdt_07,932.8
Order_0000003,Pdt_06,132.8

local形式跑出来的结果如下：
part-r-00000:

Order_0000002   522.8

part-r-00001

Order_0000001   222.8
Order_0000003   932.8