Hadoop Simple WordCount Example

[Software]
    Hadoop2.4.1

[Reference]
http://azure.microsoft.com/zh-tw/documentation/articles/hdinsight-develop-deploy-java-mapreduce/

1. Open Notepad.
2. Copy WordCount.java and paste the following program into notepad.

package org.apache.hadoop.examples;

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;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

  public static class TokenizerMapper 
       extends Mapper<object intwritable="" text="">{

    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 ext="" ntwritable=""> {
    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();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    Job job = new Job(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(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

3.Make Dir:
$mkdir Word_Count
4.Compile java:
$javac -classpath $HADOOP_INSTALL/share/hadoop/common/hadoop-common-2.4.1.jar:$HADOOP_INSTALL/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.4.1.jar:$HADOOP_INSTALL/share/hadoop/common/lib/commons-cli-1.2.jar:$HADOOP_INSTALL/share/hadoop/common/lib/hadoop-annotations-2.4.1.jar -d Word_Count WordCount.java

5.Create jar file:
$jar -cvf WordCount.jar -C Word_Count/ . 

Then the WordCount.jar will be created at the current DIR.

6.Put input file to HDFS:
$hdfs dfs -put WordCount.java /WordCount/Input/file1

6.Execute the jar
$hadoop jar WordCount.jar org.apache.hadoop.examples.WordCount /WordCount/Input /WordCount/Output

7.Check Result:
$hdfs dfs -cat /WordCount/Output/part-r-00000