wordcount.java

mapper.java

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 mapper extends Mapper<Object,Text,Text,IntWritable> {

	private final static IntWritable one = new IntWritable(1);
	private 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);
		}
	}

}

reducer.java

import java.io.IOException;
import java.util.Iterator;

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


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

    public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException {
        // replace KeyType with the real type of your key
        int sum = 0;
        for(IntWritable val:values)
        {
            sum += val.get();
        }
        result.set(sum);
        context.write(key,result);
    }

}

WordCount.java

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.mapred.JobClient;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.mapreduce.Job;

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("Uage:wordcount<in><out>");
			System.exit(2);
		}
		
		Job job = new Job(conf,"word count");
		job.setJarByClass(WordCount.class);
		job.setMapperClass(mapper.class);
		job.setCombinerClass(reducer.class);
		job.setReducerClass(reducer.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);
		
	}

}