mapreduce多表关联

在Hadoop实战多表关联的例子上做了修改，感觉Hadoop实战上的例子限制性较大。
使用了两个数据文件，一个文件是factory.txt，数据如下：
factoryName addressId
Beijing Red Star 1
Shenzhen Thunder 3
Guangzhou Honda 2
Beijing Rising 1
Guangzhou Development Bank 2
Tencent 3
Bank of Beijing 1

另一个是address.txt，数据如下：
addressId addressName
1 Beijing
2 Guangzhou
3 Shenzhen
4 Xian

最终结果：
factoryName    addreddName
Bank of Beijing      Beijing
Beijing Rising      Beijing
Beijing Red Star      Beijing
Guangzhou Development Bank      Guangzhou
Guangzhou Honda      Guangzhou
Tencent      Shenzhen
Shenzhen Thunder      Shenzhen

package com.more.table;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.util.GenericOptionsParser;

public class STjoin {
	public static int time = 0;
	
	// Beijing Red Star 1
	// 1 Beijing
	public static class SMap extends Mapper{
		public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
			
			
			String line = value.toString();
			// 输入文件首行不做处理
			if(line.contains("factoryName") || line.contains("addressId")){
				return;
			}
			String[] values = line.split(" ");
			
			// 第一个数据
			String firstVal = values[0];
			// 数组最后一个数据
			String lastVal = values[values.length-1];
			
			Pattern pattern = Pattern.compile("^[1-9]d*$"); 
			Matcher isNum = pattern.matcher(lastVal);
			
			// 判断开头/结束是否为数字，对字段进行分割
			// 对如果数据的第一个为数字的话则第一个是addressId
			// 否则最后一个是addressId
			if(isNum.matches()){
				// 
				// 左表     aaa 11  substring包头不包尾
				context.write(new Text(lastVal), new Text("1+" + line.substring(0, line.length() - lastVal.length())));
			}else{
				// 11 aaa
				context.write(new Text(values[0]), new Text("2+" + line.substring(firstVal.length())));
			}
		}
	}
	
	// reduce
	public static class SReduce extends Reducer{
		public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException{
			// <1,1+Beijing Red Star><1,1+Bank of Beijing><1,2+Beijing>
			// shuffle后的值：<1,<1+Beijing Red Star><1+Bank of Beijing><2+Beijing>>
			if(time == 0){
				// 输出表头
				context.write(new Text("factoryName"), new Text("addreddName"));
				time++;
			}
			
			// 工厂名称list
			List factoryList = new ArrayList();
			// 地址list
			List addressList = new ArrayList();
			Iterator ite = values.iterator();
			while(ite.hasNext()){
				String record = ite.next().toString();
				char type = record.charAt(0);
				
				if(type == '1'){
					// 左表
					factoryList.add(record.substring(2));
				}else{
					// 右表
					addressList.add(record.substring(2));
				}
			}
			
			// 求笛卡尔积
			if(factoryList.size() > 0 && addressList.size() > 0){
				for (String factory : factoryList) {
					for (String address : addressList) {
						// 输出结果
						context.write(new Text(factory), new Text(address));
					}
				}
			}
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		if(otherArgs.length != 2){
			System.err.println("Usage: join ");
			System.exit(2);
		}
		
		@SuppressWarnings("deprecation")
		Job job = new Job(conf, "Join job");
		job.setNumReduceTasks(1);
		job.setJarByClass(STjoin.class);
		job.setMapperClass(SMap.class);
		job.setReducerClass(SReduce.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}