mapreduce中最简单的wordcount程序

package com.zhichao.wan.mr.wordcount1;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable>{

@Override
protected void map(LongWritable key, Text value,Context context)
throws IOException, InterruptedException {
//1.获取每一行的字符串
String sting = value.toString();

//2.开始切割字符串，成为一个个的单词
String[] words = StringUtils.split(sting, " ");

for (String word : words) {

context.write(new Text(word), new LongWritable(1));
}

}

}

package com.zhichao.wan.mr.wordcount1;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WCReducer extends Reducer<Text, LongWritable, Text, LongWritable>{

@Override
protected void reduce(Text key, Iterable<LongWritable> values,Context context)
throws IOException, InterruptedException {

long count=0;

for (LongWritable value : values) {

count+=value.get();
}

context.write(key, new LongWritable(count));

}

}

package com.zhichao.wan.mr.wordcount1;

import java.io
4000
.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

public class WCRunner {

/**
* @param args
* @throws Exception
*/
public static void main(String[] args) throws Exception {

Job job=Job.getInstance();

job.setJarByClass(WCRunner.class);

job.setMapperClass(WCMapper.class);
job.setReducerClass(WCReducer.class);

job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

FileInputFormat.setInputPaths(job, new Path("/wc/srcdata/"));

FileOutputFormat.setOutputPath(job, new Path("/wc/output"));

job.waitForCompletion(true);

}

}