MapReduce当中Partitioner的用法

Partitioner的用法：

马克-to-win @ 马克java社区：防盗版实名手机尾号：73203。如果现在我们的需求变成，输出放在两个文件当中，按照关键字的首个字母的26个字母来分，头13个放在一个文件当中，以此类推， 这时我们就要用到partition的技术。

package com;

import java.io.IOException;

import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Partitioner;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

public class WordCountMark_to_win {

public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

private IntWritable one = new IntWritable(1);

private Text word = new Text();

public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

System.out.println("key is 马克-to-win @ 马克java社区："+key.toString()+" value is "+value.toString());

StringTokenizer itr = new StringTokenizer(value.toString());

while (itr.hasMoreTokens()) {

word.set(itr.nextToken());

context.write(word, one);

}

}

}

public static class PartitionClass extends Partitioner<Text, IntWritable> {

public int getPartition(Text key, IntWritable value, int numPartitions)

// numPartitions参数值从主函数中的job.setNumReduceTasks()获得马克-to-win @ 马克java社区：

{

int distancemark_to_win=26/numPartitions;

int result ;

if((key.charAt(0) - 'a')<distancemark_to_win)

result=0;

else

result = 1;

return result;

}

}

更多请见：https://blog.csdn.net/qq_44594249/article/details/97007904