frequencies.java

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();
    
     /*
      * Mapper: takes lines of text, breaks them down into lowercase words and 
      *         emits a (key,value) pair for each word, key being the word and
      *         value being `1`. For example, `one two two three three three` will emit:
      * (one, 1)
      * (two, 1)
      * (two, 1)
      */
    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().toLowerCase());
        context.write(word, one);
      }
    }
  }


  public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();
  /*
   * Reducer: takes a word (key) and a list of int's (`1`'s) and returns 
   *          a pair of (word, sum), with sum being the sum of all the list's values
   *          -- hence, the frequency. For example, (`two`, [1,1]) from above will emit
   * (`two`, 2)
   */
    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);
    }
  }
  
  /*
   * Main driver: Creates a hadoop job, configures mapper, reducer, 
   *              output types, files for input and output and
   *              runs the task.
   */
  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);
  }
}