WordCount Version Two

package org.myorg;

import java.io.IOException;
import java.util.StringTokenizer;
// Import the Configuration class for WordCount version 2
import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;

public class WordCount extends Configured implements Tool {

  private static final Logger LOG = Logger.getLogger(WordCount.class);

  public static void main(String[] args) throws Exception {
    int res = ToolRunner.run(new WordCount(), args);
    System.exit(res);
  }

  public int run(String[] args) throws Exception {
	  
    Job job = Job.getInstance(getConf(), "wordcount");

    job.setJarByClass(this.getClass());    
    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    return job.waitForCompletion(true) ? 0 : 1;
  }

  public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

// Add this boolean variable for the caseSensitive setting.
    private boolean caseSensitive = false;
   
// Add the setup() method for WordCount2. This will capture the value
// of the caseSensitive argument from the command line. Going forward, case sensitivity
// is disabled by default.

    protected void setup(Mapper.Context context)
        throws IOException,
        InterruptedException 
    {
      Configuration config = context.getConfiguration();
      this.caseSensitive = config.getBoolean("wordcount.case.sensitive", false);
    }
    
// End of the setup() method for WordCount2.

    public void map(LongWritable offset, Text lineText, Context context)
        throws IOException, InterruptedException {

      String line = lineText.toString();

// Add this if statement for WordCount2. If case sensitivity is false,
// change each line to lowercase before running it through the
// StringTokenizer.

      if (!caseSensitive) {
        line = line.toLowerCase();
      }
      
// End of update for WordCount2

      StringTokenizer tokenizer = new StringTokenizer(line);
      while (tokenizer.hasMoreTokens()) {
        word.set(tokenizer.nextToken());
        context.write(word, one);
        context.getCounter(Counters.INPUT_WORDS).increment(1);
      }
    }

    private enum Counters {INPUT_WORDS}
  }

  public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    public void reduce(Text word, Iterable<IntWritable> counts, Context context)
        throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable count : counts) {
        sum += count.get();
      }
      context.write(word, new IntWritable(sum));
    }
  }
}