MapReduce的Mapper类

一、Mapper类源码

Mapper模板类

Mapper

class Context  -- 保存了作业运行的上下文信息，例如作业配置信息、InputSplit信息、任务ID setup()  -- map前的准备工作（可重写） map()  -- 承担主要的对键值对的处理工作（可重写） cleanup()  -- 收尾工作，例如关闭文件、执行map后的键值对分发（可重写） run()  -- 提供setup-->map-->cleanup的执行模板（可重写）

package org.apache.hadoop.mapreduce;

import java.io.IOException;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.RawComparator;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.mapreduce.task.MapContextImpl;

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

  public abstract class Context
    implements MapContext<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {
  }
  
  /**
   * 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.
   */
  protected void map(KEYIN key, VALUEIN value, 
                     Context context) throws IOException, InterruptedException {
    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);
    try {
      while (context.nextKeyValue()) {
        map(context.getCurrentKey(), context.getCurrentValue(), context);
      }
    } finally {
      cleanup(context);
    }
  }
}

二、Hadoop自带的Mapper实现类

1.InverseMapper类：实现了键值对调换后输出的功能，如下源码：

package org.apache.hadoop.mapreduce.lib.map;

import java.io.IOException;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.mapreduce.Mapper;

public class InverseMapper<K, V> extends Mapper<K,V,V,K> {

  /** The inverse function.  Input keys and values are swapped.*/
  @Override
  public void map(K key, V value, Context context
                  ) throws IOException, InterruptedException {
    context.write(value, key);
  }
  
}

2.TokenCounterMapper类：实现了单词计数的功能，如下源码： 

package org.apache.hadoop.mapreduce.lib.map;

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

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class TokenCounterMapper extends Mapper<Object, Text, Text, IntWritable>{
    
  private final static IntWritable one = new IntWritable(1);
  private Text word = new Text();
  
  @Override
  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());
      context.write(word, one);
    }
  }
}

 三、自定义Mapper类

自定义MyMapper类需要继承Mapper(org.apache.hadoop.mapreduce.Mapper)，重写map函数。

package com.hadoop.hello;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/*
 * MyMapper类
 * LongWritable: map输入键值对的键类型
 * Text: map输入键值对的值类型
 * Text: map输出键值对的键类型
 * IntWritable: map输出键值对的值类型
 */
public class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable>{

	/*
	 * @param key: 输入分块inputsplit的行号
	 * @param value: 摄入分块inputsplit的行内容
	 */
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {

		//自定义map处理逻辑
		//context.write(key, value);
	}
}