MapReduce输出结果到多个文件

一,简介

    利用MultipleOutputs可以方便的实现将结果按自己的要求输出到不同的文件,方法简单,

    1,直接在map或reduce中加入类似如下的代码,

    2 ,用mos.write替换以前的context.write

    3,在main中利用MultipleOutputs.addNamedOutput(job, "shortkey", TextOutputFormat.class, Text.class, IntWritable.class);添加输出路径。

  private MultipleOutputs mos=null;
    public void setup(Context context) throws IOException
    {
    	mos=new MultipleOutputs(context);
    }
    public void cleanup(Context context)
     {
    	try {
			mos.close();
		} catch (IOException | InterruptedException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
     }

二,示例代码

    还是以wordcount为例


/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.hadoop.examples;

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

import org.apache.hadoop.conf.Configuration;
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.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCount {

  public static class TokenizerMapper 
       extends Mapper{
     
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
      
    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); 
      }
    }
  }
  
  public static class IntSumReducer 
           extends Reducer {
    private IntWritable result = new IntWritable();
    @SuppressWarnings("unused")
   
    private MultipleOutputs mos=null;
    public void setup(Context context) throws IOException
    {
    	mos=new MultipleOutputs(context);
    }
    public void cleanup(Context context)
     {
    	try {
			mos.close();
		} catch (IOException | InterruptedException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
     }
    
    
    public void reduce(Text key, Iterable values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
     result.set(sum);
     
     if (key.getLength()>=3)
       {
    	  mos.write("longkey", key, result);
       }
     else
       {    	  
    	 mos.write("shortkey", key, result);
       }

    }
  }

  public static void main(String[] args) throws Exception {
	  
	  Configuration conf=new Configuration();
	  Job job=new Job(conf);
	  
	  job.setJarByClass(WordCount.class);
	  job.setMapperClass(TokenizerMapper.class);
	  job.setReducerClass(IntSumReducer.class);
	  job.setOutputKeyClass(Text.class);
	  job.setOutputValueClass(IntWritable.class);
	  FileInputFormat.setInputPaths(job, new Path(args[0]));
	  FileOutputFormat.setOutputPath(job,new Path(args[1]));
	  
	  
	  MultipleOutputs.addNamedOutput(job, "shortkey", TextOutputFormat.class, Text.class, IntWritable.class);
	  MultipleOutputs.addNamedOutput(job, "longkey", TextOutputFormat.class, Text.class, IntWritable.class);
	   

	  
	  
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}



你可能感兴趣的:(hadoop)