MapReduce(五)：表关联

给出：

Tom Lucy

Tom Jack

Jone Lucy

Jone Jack

Lucy Mary

Lucy Ben

Jack Alice

Jack Jesse

输出：

Tom Alice

Tom Jesse

Jone Alice

Jone Jesse

Tom Mary

Tom Ben

Jone Mary

Jone Ben

源代码如下：

import java.io.IOException;

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;


public class SingleTable_Join {

	public static class STMapper extends Mapper<Object,Text,Text,Text>
	{
		private Text k1=new Text();
		private Text v1=new Text();
		private Text k2=new Text();
		private Text v2=new Text();
		@Override
		protected void map(Object key, Text value,Context context)
				throws IOException, InterruptedException {
			String line=value.toString();
			String[]str=line.split("	");
			String a=str[0];
			String b=str[1];
			String relationType=new String();
			//建立左表
			relationType="1";
			k1.set(b);
			v1.set(relationType+" "+a);
			context.write(k1, v1);
			//建立右表
			relationType="2";
			k2.set(a);
			v2.set(relationType+" "+b);
			context.write(k2, v2);
		}
	}
	public static class STReducer extends Reducer<Text,Text,Text,Text>
	{
		private Text k=new Text();
		private Text v=new Text();
		@Override
		protected void reduce(Text key, Iterable<Text> values,Context context)
				throws IOException, InterruptedException {
			String[]grandChild=new String[10];
			String[]grandParent=new String[10];
			int grandChildNum=0;
			int grandParentNum=0;
			for(Text t:values)
			{
				String str=t.toString();
				String[] s=str.split(" ");
				if(s.length==0)
					continue;
				if(s[0].compareTo("1")==0)
					grandChild[grandChildNum++]=s[1];
				else
					grandParent[grandParentNum++]=s[1];
			}
			if(grandChildNum!=0&&grandParentNum!=0)
			{
				for(int i=0;i<grandChildNum;i++)
				{
					k.set(grandChild[i]);
					for(int j=0;j<grandParentNum;j++)
					{
						v.set(grandParent[j]);
						context.write(k,v);
					}
				}
			}
		}
		
	}
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		Configuration conf=new Configuration();
		Job job=Job.getInstance(conf,"SingleTable_Join");
		
		job.setJarByClass(SingleTable_Join.class);
		
		job.setMapperClass(STMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		
		job.setReducerClass(STReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		System.exit(job.waitForCompletion(true)? 0:1);
	}

}

注：多表关联思路也一样！