Hadoop map reduce new API

Hadoop map reduce API changed starting from Hadoop 0.20.x

Older API: - org.apache.hadoop.hbase.mapred  
 Newer API- org.apache.hadoop.hbase.mapreduce

The package org.apache.hadoop.mapred.* have been deprecated.
The current Map Reduce tutorial on the apache Hadoop page is written for the old API.

WordCount program with new API

import java.io.IOException;
import java.lang.InterruptedException;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
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 WordCount {
/**
 * The map class of WordCount.
 */
public static class TokenCounterMapper     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);
        }
    }
}
/**
 * The reducer class of WordCount
 */
public static class TokenCounterReducer extends Reducer<Text, IntWritable, Text, IntWritable>
{
    public void reduce(Text key, Iterable<IntWritable> values, Context context)
        throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        context.write(key, new IntWritable(sum));
    }
}
/**
 * The main entry point.
 */
public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = new Job(conf, "Example Hadoop 0.20.1 WordCount");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenCounterMapper.class);
    job.setReducerClass(TokenCounterReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}


Compile WordCount.java:
mkdir wordcount_classes
$ javac -cp classpath -d wordcount_classes WordCount.java

 where classpath is: CDH4 -/usr/lib/hadoop/*:/usr/lib/hadoop/client-0.20/*
In apache hadoop:     ${HADOOP_HOME}/hadoop-core-1.1.2.jar

 Create a JAR
$jar -cvf wordcount.jar -C wordcount_classes/ .



Execute program:
$hadoop jar wordcount.jar WordCount /wordcount/input /wordcount/output