通过MapReduce寻找好友列表数据中的共同好友

以下是qq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）

A:B,C,D,F,E,O

B:A,C,E,K

C:F,A,D,I

D:A,E,F,L

E:B,C,D,M,L

F:A,B,C,D,E,O,M

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？

解题思路： 用两个步骤解决

第一步：找出每一个人，是哪些人的共同好友 map 读一行   A:B,C,D,F,E,O 输出    在读一行   B:A,C,E,K 输出   reduce 拿到的数据比如...... 输出：  .....

第二步：将共同好友两两配对，作为key，发出去 map 读入一行 直接输出 reduce 读入数据  ....... 输出： A-B  C,F,G,.....

以下是代码实现：

public class SharedFriendsStepOne {

	static class SharedFriendsStepOneMapper extends Mapper {
		@Override
		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			// A:B,C,D,F,E,O
			String line = value.toString();
			String[] person_friends = line.split(":");
			String person = person_friends[0];
			String friends = person_friends[1];
			for (String friend : friends.split(",")) {
				// 输出<好友，人>
				context.write(new Text(friend), new Text(person));
			}
		}
	}

	static class SharedFriendsStepOneReducer extends Reducer {
		@Override
		protected void reduce(Text friend, Iterable persons, Context context) throws IOException, InterruptedException {
			StringBuffer sb = new StringBuffer();
			for (Text person : persons) {
				sb.append(person).append(",");
			}
			context.write(friend, new Text(sb.toString()));
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();

		Job job = Job.getInstance(conf);
		job.setJarByClass(SharedFriendsStepOne.class);

		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		job.setMapperClass(SharedFriendsStepOneMapper.class);
		job.setReducerClass(SharedFriendsStepOneReducer.class);

		FileInputFormat.setInputPaths(job, new Path("D:/srcdata/friends"));
		FileOutputFormat.setOutputPath(job, new Path("D:/temp/out"));

		job.waitForCompletion(true);
	}
}

public class SharedFriendsStepTwo {

	static class SharedFriendsStepTwoMapper extends Mapper {
		// 拿到的数据是上一个步骤的输出结果
		// A I,K,C,B,G,F,H,O,D,
		// 友 人，人，人
		@Override
		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			String line = value.toString();
			String[] friend_persons = line.split("\t");
			String friend = friend_persons[0];
			String[] persons = friend_persons[1].split(",");
			//排序，防止C-B和B-C被当成两种情况发往reduce
			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));
				}
			}
		}
	}

	static class SharedFriendsStepTwoReducer extends Reducer {
		@Override
		protected void reduce(Text person_person, Iterable friends, Context context) throws IOException, InterruptedException {
			StringBuffer sb = new StringBuffer();
			for (Text friend : friends) {
				sb.append(friend).append(" ");
			}
			context.write(person_person, new Text(sb.toString()));
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();

		Job job = Job.getInstance(conf);
		job.setJarByClass(SharedFriendsStepTwo.class);

		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);

		job.setMapperClass(SharedFriendsStepTwoMapper.class);
		job.setReducerClass(SharedFriendsStepTwoReducer.class);

		FileInputFormat.setInputPaths(job, new Path("D:/temp/out/part-r-00000"));
		FileOutputFormat.setOutputPath(job, new Path("D:/temp/out2"));

		job.waitForCompletion(true);
	}
}