AggregateWordHistogram源代码注释

package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Map.Entry;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorBaseDescriptor;
import org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJob;

/**
 hadoop的map/reduce例子，求的是单词在文本中的直方图，本人不解其意。
执行的命令也是需要-libjars参数：
hadoop jar hadoop-example.jar -libjars hadoop-example.jar shakepoems.text out_aggregate_his 3 textinputformat
利用系统已经实现的算法来写map/reduce程序简化开发，算法类型如下：
UniqValueCount
LongValueSum
DoubleValueSum
ValueHistogram
LongValueMax
LongValueMin
StringValueMax
StringValueMin
运行的结果是：
WORD_HISTOGRAM  11247   1       1       1710    4.4786165199608785      32.29810604730843
这个和直方图有啥关系？希望高人指点迷津。
 * This is an example Aggregated Hadoop Map/Reduce application. Computes the
 * histogram of the words in the input texts.
 * 
 * To run: bin/hadoop jar hadoop-*-examples.jar aggregatewordhist <i>in-dir</i>
 * <i>out-dir</i> <i>numOfReducers</i> textinputformat
 * 
 */
public class AggregateWordHistogram {

  public static class AggregateWordHistogramPlugin 
    extends ValueAggregatorBaseDescriptor {
    
    /**指定算法类型是VALUE_HISTOGRAM
     * Parse the given value, generate an aggregation-id/value pair per word.
     * The ID is of type VALUE_HISTOGRAM, with WORD_HISTOGRAM as the real id.
     * The value is WORD\t1.
     *
     * @return a list of the generated pairs.
     */
    @Override
    public ArrayList<Entry<Text, Text>> generateKeyValPairs(Object key, Object val) {
      String words[] = val.toString().split(" |\t");
      ArrayList<Entry<Text, Text>> retv = new ArrayList<Entry<Text, Text>>();
      for (int i = 0; i < words.length; i++) {
        Text valCount = new Text(words[i] + "\t" + "1");
        Entry<Text, Text> en = generateEntry(VALUE_HISTOGRAM, "WORD_HISTOGRAM",
                                 valCount);
        retv.add(en);
      }
      return retv;
    }
    
  }
  
  /**
   * The main driver for word count map/reduce program. Invoke this method to
   * submit the map/reduce job.
   * 
   * @throws IOException
   *           When there is communication problems with the job tracker.
   */
  @SuppressWarnings("unchecked")
  public static void main(String[] args) throws IOException {
    JobConf conf = ValueAggregatorJob.createValueAggregatorJob(args
        , new Class[] {AggregateWordHistogramPlugin.class});
    
    JobClient.runJob(conf);
  }
  
}