hadoop编程:词频排序

hadoop编程:词频排序

本文博客链接:http://blog.csdn.net/jdh99,作者:jdh,转载请注明.

环境：

主机:Ubuntu10.04

hadoop版本:1.2.1

开发工具:gedit

说明:

在词频排序的例子上增加

教程中词频排序不能识别，；等符号，造成“soft”和“soft，”被识别为两个词，所以进行修改。

源代码:

TokenizerMapper.java:

package com.bazhangkeji.hadoop;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>
{
	IntWritable one = new IntWritable(1);
  	Text word = new Text();

  	public void map(Object key, Text value, Context context) throws IOException, InterruptedException 
	{
    		StringTokenizer itr = new StringTokenizer(value.toString());
		StringBuffer str_temp = new StringBuffer();
		StringBuffer str_out = new StringBuffer();
		int i = 0;

    		while (itr.hasMoreTokens())
		{
			str_temp.setLength(0);
			str_out.setLength(0);
			str_temp.append(itr.nextToken());
			
			for (i = 0;i < str_temp.length();i++)
			{
				if ((str_temp.charAt(i) >= 'a' && str_temp.charAt(i) <= 'z') || 
				    (str_temp.charAt(i) >= 'A' && str_temp.charAt(i) <= 'Z') || 
			   	    (str_temp.charAt(i) >= '0' && str_temp.charAt(i) <= '9'))
				{
					str_out.append(str_temp.charAt(i));
				}
			}			

      			word.set(str_out.toString());
      			context.write(word, one);
    		}
  	}
}

IntSumReducer.java：

package com.bazhangkeji.hadoop;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> 
{
  	IntWritable result = new IntWritable();

  	public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException 
	{
    		int sum = 0;
    		for (IntWritable val : values) 
		{
      			sum += val.get();
    		}
    		result.set(sum);
    		context.write(key, result);
  	}
}

WordCount.java：

package com.bazhangkeji.hadoop;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount 
{
  	public static void main(String[] args) throws Exception 
	{
    		Configuration conf = new Configuration();
    		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    		if (otherArgs.length != 2) 
		{
      			System.err.println("Usage: wordcount <in> <out>");
      			System.exit(2);
    		}
		Job job = new Job(conf, "wordcount");
		job.setJarByClass(WordCount.class);
		job.setMapperClass(TokenizerMapper.class);
		job.setReducerClass(IntSumReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
  	}
}

参考资料:

1.《从0开始学习hadoop》

2.《hadoop实战》