4、第一 个mapReduce程序

第一步，map，TokenizerMapper：

package com.Kevin.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());
		while(itr.hasMoreTokens())
		{
			word.set(itr.nextToken());
			context.write(word, one);
		}
	}
}

继承Mapper<Object,Text,Text,IntWritable>，Object输入数据的key，如该行数据的偏移量,Text输入数据的值,Text输出数据的key,IntWritable输出数据的值；

IntWritable one = new IntWritable(1);设置每个key的value都为1

Text word = new Text();创建key对象

StringTokenizer itr = new StringTokenizer(value.toString());java中用来分割字符串的类

context.write(word, one);context保存key-value，留待reduce处理

第二步，reduce，IntSumReducer

package com.Kevin.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);
		
	}

}

for(IntWritable val:values)
{
	sum += val.get();
}

循环读取key对应的所有value，并将其累加，最后将结果写入到context中

第三步，WordCount

package com.Kevin.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(2 != otherArgs.length)
		{
			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);
	}

}

configuration类：读写和保存各种配置资源

job.setMapperClass(TokenizerMapper.class);设置map

job.setReducerClass(IntSumReducer.class);设置reduce

job.setOutputKeyClass(Text.class);设置输出key

job.setOutputValueClass(IntWritable.class);设置输出value

FileInputFormat.addInputPath(job, new Path(otherArgs[0]));设置输入文件路径

FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));设置输出文件路径