mr求TOPN

需求：求一个文件中金额前三的数据
分析：首先实现序列化，重写cpmpareto方法，再根据TOPN再reduce中实现
求TOPN的文件：

AA,5
BB,10
CC,20
DD,20
EE,15

package com.ruozedata.bigdata.hadoop.mapreduce.TopN;

import com.ruozedata.bigdata.hadoop.utils.FileUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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;

import java.io.IOException;
import java.util.TreeMap;

public class TopNAppV2 {

    public static void main(String[] args) throws Exception{
        //获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        String input="data/top.data";
        String output="out/";
        FileUtils.deleteTarget(output,configuration);

        //设置jar相关信息
        job.setJarByClass(TopNAppV2.class);

        //设置自定义的mapper跟Reducer
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

        //设置mapper阶段输出的key跟value类型
        job.setMapOutputKeyClass(RuozedataInt.class);
        job.setMapOutputValueClass(Text.class);

        //设置reducer阶段输出的key跟vlaue类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(RuozedataInt.class);

        //设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(input));
        FileOutputFormat.setOutputPath(job,new Path(output));

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

    public static final int topn=3;

    public static class RuozedataInt extends  IntWritable{
        public RuozedataInt(){}
        public RuozedataInt(int vlaue){
            super(vlaue);
        }

        @Override
        public int compareTo(IntWritable o) {
            return -super.compareTo(o);
        }
    }

    public static class MyMapper extends Mapper<LongWritable, Text,RuozedataInt,Text >{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
             String[] splits = value.toString().split(",");
             int price = Integer.parseInt(splits[1]);
            String produce = splits[0];
            context.write(new RuozedataInt(price),new Text(produce));
            }
    }
    public static class MyReducer extends Reducer<RuozedataInt,Text,Text,RuozedataInt>{
        int index = 0;
        @Override
        protected void reduce(RuozedataInt key, Iterable<Text> values, Context context) throws IOException, InterruptedException {

            for(Text vlaue:values){
                if (index < topn){
                    context.write(vlaue,key);
                }
                index ++;
            }
        }
    }
}