mapreduce 二次排序 Partitioner/SortComparator/GroupingComparator

翻了以前代码看了下15年时候写的二次排序 哈哈 怀念

 

实现hadoop自带WritableComparable 序列化排序接口

package com.lei.sort;

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

import org.apache.hadoop.io.WritableComparable;

public class StrWritable implements WritableComparable<StrWritable>{
    private  String strName;
    private  String strValue;
    public void setstrName(String strName) {
        this.strName = strName;
    }
    public void setstrValue(String strValue) {
        this.strValue = strValue;
    }
    public String getstrName() {
        return strName;
    }
    public String getstrValue() {
        return strValue;
    }
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(strName);
        out.writeUTF(strValue);
    }
    @Override
    public void readFields(DataInput in) throws IOException {
        strName =in.readUTF();
        strValue =in.readUTF();
    }
    @Override
    public int compareTo(StrWritable o) {
        //这里只对StrName进行比较，在Job中在没有分组函数情况下，默认是这个排序，也可以重新定 义
        int  i= o.getstrName().compareTo(this.strName);
        //if(i!=0)
            return i;
        //return o.getstrName().compareTo(this.strName);

    }
}

 

Main函数

package com.lei.sort;

import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.