source: sample/hadoop-0.16/tw/org/nchc/demo/DemoWordCount.java @ 243

/**
 * Program: HBaseRecordPro.java
 * Editor: Waue Chen 
 * From :  NCHC. Taiwn
 * Last Update Date: 07/02/2008
 */
/*
 * Cloud9: A MapReduce Library for Hadoop
 */

package tw.org.nchc.demo;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.fs.FileSystem;
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.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

/**
 * <p>Simple word count demo. Counts words in the Bible+Shakespeare sample
 * collection. Expected trace of MapReduce operation:</p>
 * 
 * <pre>
 * Map input records=156215
 * Map output records=1734298
 * Map input bytes=9068074
 * Map output bytes=15919397
 * Combine input records=1734298
 * Combine output records=135372
 * Reduce input groups=41788
 * Reduce input records=135372
 * Reduce output records=41788
 * </pre>
 *
 */
public class DemoWordCount {

  // mapper: emits (token, 1) for every word occurrence
  private static class MapClass extends MapReduceBase implements
      Mapper<LongWritable, Text, Text, IntWritable> {

    // reuse objects to save overhead of object creation
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(LongWritable key, Text value,
        OutputCollector<Text, IntWritable> output, Reporter reporter)
        throws IOException {
      String line = ((Text) value).toString();
      StringTokenizer itr = new StringTokenizer(line);
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        output.collect(word, one);
      }
    }
  }

  // reducer: sums up all the counts
  private static class ReduceClass extends MapReduceBase implements
      Reducer<Text, IntWritable, Text, IntWritable> {

    // reuse objects
    private final static IntWritable SumValue = new IntWritable();

    public void reduce(Text key, Iterator<IntWritable> values,
        OutputCollector<Text, IntWritable> output, Reporter reporter)
        throws IOException {
      // sum up values
      int sum = 0;
      while (values.hasNext()) {
        sum += values.next().get();
      }
      SumValue.set(sum);
      output.collect(key, SumValue);
    }
  }

  private DemoWordCount() {
  }
  
  /**
   * Runs the demo.
   */
  public static void main(String[] args) throws IOException {
    String filename = "/user/waue/test/132.txt";
    String outputPath = "sample-counts";
    int mapTasks = 20;
    int reduceTasks = 1;

    JobConf conf = new JobConf(DemoWordCount.class);
    conf.setJobName("wordcount");

    conf.setNumMapTasks(mapTasks);
    conf.setNumReduceTasks(reduceTasks);

    conf.setInputPath(new Path(filename));

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setOutputPath(new Path(outputPath));
    conf.setMapperClass(MapClass.class);
    conf.setCombinerClass(ReduceClass.class);
    conf.setReducerClass(ReduceClass.class);
    
    // Delete the output directory if it exists already
    Path outputDir = new Path(outputPath);
    FileSystem.get(conf).delete(outputDir);
    JobClient.runJob(conf);
  }
}