<dependencies>        <dependency>            <groupId>org.apache.hadoop</groupId>            <artifactId>hadoop-common</artifactId>            <version>2.4.1</version>        </dependency>        <dependency>            <groupId>org.apache.hadoop</groupId>            <artifactId>hadoop-mapreduce-client-core</artifactId>            <version>2.4.1</version>        </dependency>    </dependencies>

import java.io.IOException;import java.util.StringTokenizer;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.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;public class WordCount {  public static class TokenizerMapper       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);      }    }  }  public static class IntSumReducer       extends Reducer<Text,IntWritable,Text,IntWritable> {    private 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);    }  }  public static void main(String[] args) throws Exception {    Configuration conf = new Configuration();    Job job = Job.getInstance(conf, "word count");    job.setJarByClass(WordCount.class);    job.setMapperClass(TokenizerMapper.class);    job.setCombinerClass(IntSumReducer.class);    job.setReducerClass(IntSumReducer.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);  }}

export JAVA_HOME=/usr/java/defaultexport PATH=$JAVA_HOME/bin:$PATHexport HADOOP_CLASSPATH=$JAVA_HOME/lib/tools.jar

$ bin/hadoop com.sun.tools.javac.Main WordCount.java$ jar cf wc.jar WordCount*.clas

    /user/joe/wordcount/input - input directory in HDFS    /user/joe/wordcount/output - output directory in HDFS

$ bin/hdfs dfs -ls /user/joe/wordcount/input//user/joe/wordcount/input/file01/user/joe/wordcount/input/file02

$ bin/hdfs dfs -cat /user/joe/wordcount/input/file01Hello World Bye World$ bin/hdfs dfs -cat /user/joe/wordcount/input/file02Hello Hadoop Goodbye Hadoop

$ bin/hadoop jar wc.jar WordCount /user/joe/wordcount/input /user/joe/wordcount/output

$ bin/hdfs dfs -cat /user/joe/wordcount/output/part-r-00000Bye 1Goodbye 1Hadoop 2Hello 2World 2