Hadoop-Mapreduce(共同好友案例)

共同好友案例

• 需求

  以下是博客的好友列表数据，冒号前是一个用户，冒号后是该用户的所有好友（数据中的好友关系是单向的）

  求出哪些人两两之间有共同好友，及他俩的共同好友都有谁？

• 需求分析

  先求出A、B、C、….等是谁的好友

  • 第一次输出结果

A	I,K,C,B,G,F,H,O,D,
B	A,F,J,E,
C	A,E,B,H,F,G,K,
D	G,C,K,A,L,F,E,H,
E	G,M,L,H,A,F,B,D,
F	L,M,D,C,G,A,
G	M,
H	O,
I	O,C,
J	O,
K	B,
L	D,E,
M	E,F,
O	A,H,I,J,F,

第二次输出结果

A-B	E C 
A-C	D F 
A-D	E F 
A-E	D B C 
A-F	O B C D E 
A-G	F E C D 
….

代码实现：

• 第一次Mapper

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class OneShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text>{
	
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
			throws IOException, InterruptedException {
		// 1 获取一行 A:B,C,D,F,E,O
		String line = value.toString();
		
		// 2 切割
		String[] fields = line.split(":");
		
		// 3 获取person和好友
		String person = fields[0];
		String[] friends = fields[1].split(",");
		
		// 4写出去
		for(String friend: friends){
			// 输出 <好友，人>
			context.write(new Text(friend), new Text(person));
		}
	}
}

第一次Reducer

import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class OneShareFriendsReducer extends Reducer<Text, Text, Text, Text>{
	
	@Override
	protected void reduce(Text key, Iterable<Text> values, Context context)
			throws IOException, InterruptedException {
		
		StringBuffer sb = new StringBuffer();
		//1 拼接
		for(Text person: values){
			sb.append(person).append(",");
		}
		
		//2 写出
		context.write(key, new Text(sb.toString()));
	}
}

第一次Driver

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class OneShareFriendsDriver {

	public static void main(String[] args) throws Exception {
		// 1 获取job对象
		Configuration configuration = new Configuration();
		Job job = Job.getInstance(configuration);
		
		// 2 指定jar包运行的路径
		job.setJarByClass(OneShareFriendsDriver.class);

		// 3 指定map/reduce使用的类
		job.setMapperClass(OneShareFriendsMapper.class);
		job.setReducerClass(OneShareFriendsReducer.class);
		
		// 4 指定map输出的数据类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		
		// 5 指定最终输出的数据类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		// 6 指定job的输入原始所在目录
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		// 7 提交
		boolean result = job.waitForCompletion(true);
		
		System.exit(result?0:1);
	}
}

第二次Mapper

import java.io.IOException;
import java.util.Arrays;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class TwoShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text>{
	
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		// A I,K,C,B,G,F,H,O,D,
		// 友 人，人，人
		String line = value.toString();
		String[] friend_persons = line.split("\t");

		String friend = friend_persons[0];
		String[] persons = friend_persons[1].split(",");

		Arrays.sort(persons);

		for (int i = 0; i < persons.length - 1; i++) {
			
			for (int j = i + 1; j < persons.length; j++) {
				// 发出 <人-人，好友> ，这样，相同的“人-人”对的所有好友就会到同1个reduce中去
				context.write(new Text(persons[i] + "-" + persons[j]), new Text(friend));
			}
		}
	}
}

第二次Reducer

import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class TwoShareFriendsReducer extends Reducer<Text, Text, Text, Text>{
	
	@Override
	protected void reduce(Text key, Iterable<Text> values, Context context)
			throws IOException, InterruptedException {
		
		StringBuffer sb = new StringBuffer();

		for (Text friend : values) {
			sb.append(friend).append(" ");
		}
		
		context.write(key, new Text(sb.toString()));
	}
}

第二次Driver

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class TwoShareFriendsDriver {

	public static void main(String[] args) throws Exception {
		// 1 获取job对象
		Configuration configuration = new Configuration();
		Job job = Job.getInstance(configuration);
		
		// 2 指定jar包运行的路径
		job.setJarByClass(TwoShareFriendsDriver.class);

		// 3 指定map/reduce使用的类
		job.setMapperClass(TwoShareFriendsMapper.class);
		job.setReducerClass(TwoShareFriendsReducer.class);
		
		// 4 指定map输出的数据类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		
		// 5 指定最终输出的数据类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		// 6 指定job的输入原始所在目录
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		// 7 提交
		boolean result = job.waitForCompletion(true);
		System.exit(result?0:1);
	}
}

一个Driver串联

public class AllShareFriendsReducer {
    public static void main(String[] args) throws IOException {
        args = new String[]{"F:\\date\\A\\friends.txt","F:\\date\\A\\FA1","F:\\date\\A\\FA11"};

        Configuration conf = new Configuration();
        Job job1 = Job.getInstance(conf);

        job1.setMapperClass(OneShareFriendsMapper.class);
        job1.setReducerClass(OneShareFriendsReducer.class);

        job1.setMapOutputKeyClass(Text.class);
        job1.setMapOutputValueClass(Text.class);
        job1.setOutputKeyClass(Text.class);
        job1.setOutputValueClass(Text.class);

        FileInputFormat.setInputPaths(job1, new Path(args[0]));
        FileOutputFormat.setOutputPath(job1, new Path(args[1]));

        Job job2 = Job.getInstance(conf);

        job2.setMapperClass(TwoShareFriendsMapper.class);
        job2.setReducerClass(TwoShareFriendsReducer.class);

        job2.setMapOutputKeyClass(Text.class);
        job2.setMapOutputValueClass(Text.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);

        FileInputFormat.setInputPaths(job2, new Path(args[1]));
        FileOutputFormat.setOutputPath(job2, new Path(args[2]));

        JobControl control = new JobControl("Andy");
        ControlledJob ajob = new ControlledJob(job1.getConfiguration());
        ControlledJob bjob = new ControlledJob(job2.getConfiguration());
        bjob.addDependingJob(ajob);
        control.addJob(ajob);
        control.addJob(bjob);
        Thread thread = new Thread(control);
        thread.start();
    }
}