用Mapreduce求共同好友

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 SharedFriendsStepOne {

	static class SharedFriendsStepOneMapper extends Mapper<LongWritable, Text, Text, Text> {

		@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<Text, Text, Text, Text> {

		@Override
		protected void reduce(Text friend, Iterable<Text> 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);

	}

}

　　

import java.io.IOException;
import java.util.Arrays;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 SharedFriendsStepTwo {

	static class SharedFriendsStepTwoMapper extends Mapper<LongWritable, Text, Text, Text> {

		// 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("	");

			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));
				}

			}

		}

	}

	static class SharedFriendsStepTwoReducer extends Reducer<Text, Text, Text, Text> {

		@Override
		protected void reduce(Text person_person, Iterable<Text> 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);

	}

}