package com.zhiyou.bd17.mr1014;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.mapred.lib.InputSampler;
import org.apache.hadoop.mapred.lib.TotalOrderPartitioner;
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.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TotalSort {
public static class TotalSortMap extends Mapper<LongWritable, Text, IntWritable, Text> {
private String[] infos;
private IntWritable oKey = new IntWritable();
private Text oValue= new Tex
TotalSort全排序(抽样取中值)
最新推荐文章于 2020-07-21 17:28:25 发布
该博客介绍了一个使用MapReduce实现全排序的Java程序。通过定义`TotalSortMap`和`TotalSortReduce`类,实现了数据的映射和规约。程序使用了`InputSampler.RandomSampler`进行抽样,`TotalOrderPartitioner`进行全排序,并在`main`函数中配置了作业参数,包括设置比较器、分区文件和输入输出格式。
摘要由CSDN通过智能技术生成