MapReduce实现QQ好友推荐

大家都知道qq用户量上亿，每个用户又有很多的好友，因此，数据量十分的庞大，如何才能实现QQ的好友推荐呢？
下面举一个例子：
A有QQ好友B
B有QQ好友C
则A，C有可能是好友。
当A登录的时候，则会向A推荐C，当C登录的时候，则会向C推荐A。

Demo

输入数据

map阶段
key：主
value：从
key：从
value：主
将一条记录分别作为key，value进行输出。
tom-->jason
jason-->tom
tom-->lgd
lgd-->tom

reduce阶段
将同一个key的values值进行两两组合。

package FriendsRecommended;

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Set;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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 FindFriends {
    private final static String INPUT_PATH = "hdfs://liguodong:8020/liguodong";
    private final static String OUTPUT_PATH = "hdfs://liguodong:8020/liguodong/QQFriendRecommended";


    public static void main(String[] args) throws IOException,
    URISyntaxException, ClassNotFoundException, InterruptedException {

        Configuration conf = new Configuration();
        final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH),conf);
        if(fileSystem.exists(new Path(OUTPUT_PATH)))
        {
            fileSystem.delete(new Path(OUTPUT_PATH),true);
        }
        Job job = Job.getInstance(conf, "qq friend recommended"); 

        job.setJarByClass(FindFriends.class);

        FileInputFormat.addInputPath(job, new Path(INPUT_PATH));  
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReudcer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH));

        //提交作业
        System.exit(job.waitForCompletion(true) ? 0 : 1);


    }

    public static class MyMapper extends Mapper<LongWritable,Text,Text,Text>{
        @Override
        protected void map(LongWritable k1, Text v1, Context context)
                throws IOException, InterruptedException {
            String line = v1.toString();
            String[] ss = line.split("\\s+");

            context.write(new Text(ss[0]), new Text(ss[1]));
            context.write(new Text(ss[1]), new Text(ss[0]));
        }
    }

    public static class MyReudcer extends Reducer<Text, Text, Text, Text>{
        @Override
        protected void reduce(Text k2, Iterable<Text> v2s,Context context)
                throws IOException, InterruptedException {
            Set<String> set = new HashSet<String>();
            for (Text v2:v2s) {
                set.add(v2.toString());
            }
            if (set.size()>1) {
                for (Iterator i = set.iterator();i.hasNext();) {

                    String qqName = (String)i.next();
                    for (Iterator j = set.iterator();j.hasNext();){
                        String otherqqName = (String)j.next();
                        if(!qqName.equals(otherqqName)){
                            context.write(new Text(qqName), new Text(otherqqName));
                        }
                    }
                }
            }
        }

    }
}

输出结果：