매퍼(Mapper) 와 리듀서(Reducer) 클래스

1. Mapper.java

public class Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT> {  
//<입력키 유형, 입력값 유형, 출력키 유형, 출력값 유형>을 의미
  public class Context 
    extends MapContext<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {
    public Context(Configuration conf, TaskAttemptID taskid,
                   RecordReader<KEYIN,VALUEIN> reader,
                   RecordWriter<KEYOUT,VALUEOUT> writer,
                   OutputCommitter committer,
                   StatusReporter reporter,
                   InputSplit split) throws IOException, InterruptedException {
      super(conf, taskid, reader, writer, committer, reporter, split);
    }
  }
  
  /**
   * Called once at the beginning of the task.
   */
  protected void setup(Context context
                       ) throws IOException, InterruptedException {
    // NOTHING
  }

  /**
   * Called once for each key/value pair in the input split. Most applications
   * should override this, but the default is the identity function.
   */
  @SuppressWarnings("unchecked")
  protected void map(KEYIN key, VALUEIN value, 
                     Context context) throws IOException, InterruptedException {  
  //맵 메서드, 맵리듀스 프로그램을 개발할 때 이 메서드를 재정의한다.
    context.write((KEYOUT) key, (VALUEOUT) value);
  }

  /**
   * Called once at the end of the task.
   */
  protected void cleanup(Context context
                         ) throws IOException, InterruptedException {
    // NOTHING
  }
  
  /**
   * Expert users can override this method for more complete control over the
   * execution of the Mapper.
   * @param context
   * @throws IOException
   */
  public void run(Context context) throws IOException, InterruptedException {
    setup(context);
    while (context.nextKeyValue()) {
      map(context.getCurrentKey(), context.getCurrentValue(), context);
    }
    cleanup(context);
  }
}

2. Reducer.java

public class Reducer<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {

  public class Context 
    extends ReduceContext<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {
    public Context(Configuration conf, TaskAttemptID taskid,
                   RawKeyValueIterator input, 
                   Counter inputKeyCounter,
                   Counter inputValueCounter,
                   RecordWriter<KEYOUT,VALUEOUT> output,
                   OutputCommitter committer,
                   StatusReporter reporter,
                   RawComparator<KEYIN> comparator,
                   Class<KEYIN> keyClass,
                   Class<VALUEIN> valueClass
                   ) throws IOException, InterruptedException {
      super(conf, taskid, input, inputKeyCounter, inputValueCounter,
            output, committer, reporter, 
            comparator, keyClass, valueClass);
    }
  }

  /**
   * Called once at the start of the task.
   */
  protected void setup(Context context
                       ) throws IOException, InterruptedException {
    // NOTHING
  }

  /**
   * This method is called once for each key. Most applications will define
   * their reduce class by overriding this method. The default implementation
   * is an identity function.
   */
  @SuppressWarnings("unchecked")
  protected void reduce(KEYIN key, Iterable<VALUEIN> values, Context context //이 메서드를 재정의한다.
                        ) throws IOException, InterruptedException {
    for(VALUEIN value: values) {
      context.write((KEYOUT) key, (VALUEOUT) value);
    }
  }

  /**
   * Called once at the end of the task.
   */
  protected void cleanup(Context context
                         ) throws IOException, InterruptedException {
    // NOTHING
  }

  /**
   * Advanced application writers can use the 
   * {@link #run(org.apache.hadoop.mapreduce.Reducer.Context)} method to
   * control how the reduce task works.
   */
  public void run(Context context) throws IOException, InterruptedException {
    setup(context);
    while (context.nextKey()) {
      context.progress();
      reduce(context.getCurrentKey(), context.getValues(), context);
    }
    cleanup(context);
  }
}