MR基础案例（六）TOP N

任务需求

需要求出wordcount的前3名 的数据
TopN.java

package MR;

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.TreeSet;

public class TopN {
   
    //自定义的mapper类
    public static class MyMapper extends Mapper<Object, Text, Text, LongWritable> {
   
        Text k = new Text();
        LongWritable v = new LongWritable(1L);
        /**
         * 抽象map函数   (map阶段的核心业务逻辑)
         */
        @Override
        protected void map(Object key, Text value,Context context) throws IOException, InterruptedException {
   
            //获取行值
            String row = value.toString();
            /**
             * 
             */
            //拆分行值
            String [] words = row.split(" ");
            for