hadoop Partition使用实例

1、为何使用Partitioner，主要是想reduce的结果能够根据key再次分类输出到不同的文件夹中。

2、结果能够直观，同时做到对数据结果的简单的统计分析。

1、输入的数据文件内容如下(1条数据内容少，1条数据内容超长，3条数据内容正常)：

kaka    1       28
hua     0       26
chao    1
tao     1       22
mao     0       29      22

2、目的是为了分别输出结果，正确的结果输出到一个文本，太短的数据输出到一个文本，太长的输出到一个文本，共三个文本输出。

代码

    package com.partition;

    import java.io.IOException;
    import java.util.*;

    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.conf.*;
    import org.apache.hadoop.io.*;
    import org.apache.hadoop.mapred.*;
    import org.apache.hadoop.util.*;

    import com.hadoop.mapred.WordCount.Map;
import com.hadoop.mapred.WordCount.Reduce;

    //Partitioner函数的使用

    public class MyPartitioner {
        //Map函数
        public static class MyMap extends MapReduceBase implements Mapper<LongWritable,Text,Text,Text>{
            
            
            public void map(LongWritable key, Text value,
                    OutputCollector<Text, Text> output, Reporter reporter)
                    throws IOException {
                
                String [] arr_value = value.toString().split("\t");
                Text word1 = new Text();
                Text word2 = new Text();
                
                if(arr_value.length > 3){
                    word1.set("long");
                    word2.set(value);
                }else if(arr_value.length < 3){
                    word1.set("short");
                    word2.set(value);
                }else {
                    word1.set("right");
                    word2.set(value);
                }
                
                output.collect(word1, word2);
            }        
        }        
        
        public static class MyPartitionerPar implements Partitioner<Text, Text> {

            @Override
            public int getPartition(Text key, Text value, int numPartitions) {
                int result = 0;
                System.out.println("numPartitions--"+numPartitions);
                if (key.toString().equals("long")) {
                    result = 0 % numPartitions;
                } else if (key.toString().equals("short")) {
                    result = 1 % numPartitions;
                } else if (key.toString().equals("right")) {
                    result = 2 % numPartitions;
                }
                return result;
            }

            @Override
            public void configure(JobConf arg0) {
                // TODO Auto-generated method stub
                
            }

        }
        
        public static class MyReduce extends MapReduceBase implements Reducer<Text, Text, Text, Text> {
             public void reduce(Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter) throws IOException {
               int sum = 0;
               while (values.hasNext()) {
                   output.collect(key, new Text(values.next().getBytes()));
               }               
             }
           }
        
        public static void main(String[] args) throws Exception {
             JobConf conf = new JobConf(MyPartitioner.class);
             conf.setJobName("MyPartitioner");
             conf.setNumReduceTasks(3);
             
             conf.setMapOutputKeyClass(Text.class);
             conf.setMapOutputValueClass(Text.class);
             
             conf.setPartitionerClass(MyPartitionerPar.class);

             conf.setOutputKeyClass(Text.class);
             conf.setOutputValueClass(Text.class);
        
             conf.setMapperClass(MyMap.class);
             conf.setReducerClass(MyReduce.class);
        
             conf.setInputFormat(TextInputFormat.class);
             conf.setOutputFormat(TextOutputFormat.class);
        
             FileInputFormat.setInputPaths(conf, new Path(args[0]));
              FileOutputFormat.setOutputPath(conf, new Path(args[1]));
        
             JobClient.runJob(conf);
        }    
    }
    

转自http://xchunlnei.i.sohu.com/blog/view/160278649.htm