Hadoop中双表链接

import java.io.IOException;

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 java.util.Iterator;
import java.util.StringTokenizer;

class Map extends Mapper<Object, Text, Text, Text>{
    public void map(Object key, Text value, Context context)
            throws IOException, InterruptedException{
            if ( value.toString().contains("factoryname") || value.toString().contains("addressID") ){
                return;
            }
            String line = value.toString();
            StringTokenizer str = new StringTokenizer(line);
            String flag = new String();
            String firstStr = new String();
            String secondStr = new String();
            
            if ( str.nextToken().length() == 1){
                flag = "2";
                firstStr = line.substring(0, 1);
                secondStr = line.substring(2);
                context.write( new Text(firstStr), new Text(flag+" "+secondStr) );
            }
            else {
                flag = "1";
                firstStr = line.substring(0, line.length()-2);
                secondStr = line.substring(line.length()-1);
                context.write( new Text(secondStr), new Text(flag+" "+firstStr) );
            }
    }
}

    
class Reduce extends Reducer<Text, Text, Text, Text>{
    private static int time = 0;
    public void reduce(Text key, Iterable<Text> values,Context context)
        throws IOException, InterruptedException{
        if (time == 0){
            context.write(new Text("addressID"), new Text("addreddname"));
            time++;
        }
        Iterator<Text> ite = values.iterator();
        int factoryNum = 0;
        int addressNum = 0;
        String[] factory = new String[10];
        String[] address = new String[10];
        while (ite.hasNext()){
            String  str = ite.next().toString();
            if (str.charAt(0) == '2'){

                address[addressNum] = str.substring(2);
                addressNum++;
            }
            else{
                factory[factoryNum] = str.substring(2);
                factoryNum++;
            }
        }
            if(factoryNum != 0 && addressNum != 0){
                 for (int m = 0; m < factoryNum; m++) {
                        for (int n = 0; n < addressNum; n++) {
                            context.write(new Text(factory[m]), new Text(address[n]));
                        }
                 }
            }
    }
}
    
public class MTjoin{
    public static void main(String[] args) throws Exception{
        Job job = new Job();
        job.setJarByClass(MTjoin.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        
        System.exit(job.waitForCompletion(true)?0:1);
        
    }
}