mapreduce编程：多表关联

package my.hadoopstudy;  

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

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.mapred.TextInputFormat;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;


public class TableConnect {
 
 public static class tableMapper extends Mapper<Text, Text, Text, Text>
 {
  @Override
  public void map(Text key, Text value, Context context) throws IOException, InterruptedException
  {
       context.write(key,value);
  }
 }
 
 
 public static class tableReducer extends Reducer<Text, Text, Text, Text>
 {
  @Override
  public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException
  {
   List<String> gChildren=new ArrayList<String>();
   List<String> gParents =new ArrayList<String>();
   for(Text val : values)
   {
    if(val.toString().charAt(0)  == '1')// the key's child.
    {
       gChildren.add(val.toString().substring(1));
    }
    else//the key's parent.
    {
       gParents.add(val.toString().substring(1));
    }
   }
   for(int i=0; i<gChildren.size(); i++)
    for(int j=0;j<gParents.size();j++)
    {
       context.write(new Text(gChildren.get(i)), new Text(gParents.get(j)));
    }
  } 
 }
 
 public static void main(String[] args) throws Exception
 {
  Configuration conf = new Configuration();
  conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", " ");
  
  Job job = new Job(conf, "tableConnect");
  job.setJarByClass(TableConnect.class);
  
  job.setMapperClass(tableMapper.class);
  job.setReducerClass(tableReducer.class);
  
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(Text.class);
  
  job.setInputFormatClass(KeyValueTextInputFormat.class);
  job.setOutputFormatClass(TextOutputFormat.class);
  
  FileInputFormat.addInputPath(job, new Path(args[0]));
  FileOutputFormat.setOutputPath(job, new Path(args[1]));
  
  System.exit( job.waitForCompletion(true) ? 0 : 1);
 }
}

输入数据，文本1：

代号        公司

a 1Beijing Red Star
c 1Shenzhen Thunder
b 1Guangzhou Honda
a 1Beijing Rising
b 1Guangzhou Development Bank
c 1Tencent
a 1Back of Beijing

输入数据，文本2：

代号       地方

a 2Beijing
b 2Guangzhou
c 2Shenzhen
d 2Xian

输出：