ChainMapper的实际使用

Question

我已经在一个程序中实现了ChainMapper，其中有两个映射器和一个reducer。以下是ChainMapper实现方式的代码：

该代码旨在计算出现的单词，即WordCount。
1st Mapper将从输入文本文件中读取文件并拆分每个文本并将其存储在Context中。 第二个Mapper将获得1stMapper的输出并将所有关键文本数据转换为小写关键文本数据。 小写键文本数据将存储在Context中。 Reducer将从2ndMapper获取值，相同的键相关值将转到一个reducer任务。 在Reducer中，我们只是使用给定的键进行字数统计操作。

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

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.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.chain.ChainMapper;
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;

//implementing CHAIN MAPREDUCE without using custom format




//SPLIT MAPPER
class SplitMapper extends Mapper<Object,Text,Text,IntWritable>
{
    StringTokenizer xs;
    private IntWritable dummyValue=new IntWritable(1);
    //private String content;
    private String tokens[];
    @Override
    public void map(Object key,Text value,Context context)throws IOException,InterruptedException{
//      xs=new StringTokenizer(value.toString()," ");
//      while(xs.hasMoreTokens())
//      {
//          content=(String)xs.nextToken();
//      }
        tokens=value.toString().split(" ");
        for(String x:tokens)
        {
        context.write(new Text(x), dummyValue);
        }
    }   
}




//UPPER CASE MAPPER
class UpperCaseMapper extends Mapper<Text,IntWritable,Text,IntWritable>
{
    @Override
    public void map(Text key,IntWritable value,Context context)throws IOException,InterruptedException{
        String val=key.toString().toUpperCase();
        Text newKey=new Text(val);
        context.write(newKey, value);
    }
}



//ChainMapReducer
class ChainMapReducer extends Reducer<Text,IntWritable,Text,IntWritable>
{
    private int sum=0;
    @Override
    public void reduce(Text key,Iterable<IntWritable>values,Context context)throws IOException,InterruptedException{
        for(IntWritable value:values)
        {
            sum+=value.get();
        }
        context.write(key, new IntWritable(sum));
    }
}
public class FirstClass extends Configured implements Tool{
    static Configuration cf;
    public int run (String args[])throws IOException,InterruptedException,ClassNotFoundException{
        cf=new Configuration();

        //bypassing the GenericOptionsParser part and directly running into job declaration part
        Job j=Job.getInstance(cf);

        /**************CHAIN MAPPER AREA STARTS********************************/
        Configuration splitMapConfig=new Configuration(false);
        //below we add the 1st mapper class under ChainMapper Class
        ChainMapper.addMapper(j, SplitMapper.class, Object.class, Text.class, Text.class, IntWritable.class, splitMapConfig);

        //configuration for second mapper
        Configuration upperCaseConfig=new Configuration(false);
        //below we add the 2nd mapper that is the lower case mapper to the Chain Mapper class
        ChainMapper.addMapper(j, UpperCaseMapper.class, Text.class, IntWritable.class, Text.class, IntWritable.class, upperCaseConfig);
        /**************CHAIN MAPPER AREA FINISHES********************************/

        //now proceeding with the normal delivery
        j.setJarByClass(FirstClass.class);
        j.setCombinerClass(ChainMapReducer.class);
        j.setOutputKeyClass(Text.class);
        j.setOutputValueClass(IntWritable.class);
        Path p=new Path(args[1]);

        //set the input and output URI
        FileInputFormat.addInputPath(j, new Path(args[0]));
        FileOutputFormat.setOutputPath(j, p);
        p.getFileSystem(cf).delete(p, true);
        return j.waitForCompletion(true)?0:1;
    }
    public static void main(String args[])throws Exception{
        int res=ToolRunner.run(cf, new FirstClass(), args);
        System.exit(res);
    }
}

现在，我有一个问题。 ChainMapper能否真正减轻多个MR工作的负担，或者任何人都拥有ChainMapper实际使用的概念和知识？

谢谢你：）