Friends-of-friends-Map Reduce program

Program to illustrate FOF Map Reduce:

import java.io.IOException;
import java.util.*;
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 FriendCommon {
    public static class FriendMapper extends Mapper<Object, Text, Text, Text> {
        private Text pair = new Text();
        private Text user = new Text();
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] line = value.toString().split(" -> ");
            if (line.length == 2) {
                String[] friends = line[1].split(" ");
                for (int i = 0; i < friends.length; i++) {
                    for (int j = i + 1; j < friends.length; j++) {
                        String friendPair = friends[i].trim() + "," + friends[j].trim();
                        pair.set(friendPair);
                        user.set(line[0].trim());
                        context.write(pair, user);
                    }
                }
            }
        }
    }
    public static class FriendReducer extends Reducer<Text, Text, Text, Text> {
        private Text commonFriends = new Text();
        public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            Set<String> userList = new HashSet<>();
            for (Text value : values) {
                userList.add(value.toString());
            }
            if (userList.size() > 1) {
                List<String> sortedUsers = new ArrayList<>(userList);
                Collections.sort(sortedUsers);
                commonFriends.set(String.join(" ", sortedUsers));
                context.write(key, commonFriends);
            }
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "FriendCommon");
        job.setJarByClass(FriendCommon.class);
        job.setMapperClass(FriendMapper.class);
        job.setReducerClass(FriendReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

Step  to run Map Reduce program :

Input File:

A -> B C D

B -> A C D E

C -> A B D E

D -> A B C E 

E -> B C D

 

hduser@ubuntu:~/fof$ ls

FriendCommon.java  in.txt

hduser@ubuntu:~/fof$ export CLASSPATH=`hadoop classpath`

hduser@ubuntu:~/fof$ echo $CLASSPATH

hduser@ubuntu:~/fof$ javac -d . FriendCommon.java 

hduser@ubuntu:~/fof$ ls

'FriendCommon$FriendMapper.class'  'FriendCommon$FriendReducer.class'   FriendCommon.class   FriendCommon.java   in.txt

hduser@ubuntu:~/fof$ jar -cvf fmr.jar -C /home/hduser/fof .

hduser@ubuntu:~/fof$ ls

 fmr.jar  'FriendCommon$FriendMapper.class'  'FriendCommon$FriendReducer.class'   FriendCommon.class   FriendCommon.java   in.txt

hduser@ubuntu:~/fof$ hadoop fs -mkdir  /fofrk

hduser@ubuntu:~/fof$ hadoop fs -put /home/hduser/fof/in.txt  /fofrk

hduser@ubuntu:~/fof$ hadoop fs -lsr /fofrk

lsr: DEPRECATED: Please use 'ls -R' instead.

-rw-r--r--   1 hduser supergroup         62 2024-03-21 11:36 /fofrk/in.txt

hduser@ubuntu:~/fof$ hadoop fs -cat /fofrk/in.txt

A -> B C D

B -> A C D E

C -> A B D E

D -> A B C E 

E -> B C D

hduser@ubuntu:~/fof$ hadoop jar fmr.jar FriendCommon /fofrk/in.txt /fofrk/out

hduser@ubuntu:~/fof$ hadoop fs -lsr /fofrk

lsr: DEPRECATED: Please use 'ls -R' instead.

-rw-r--r--   1 hduser supergroup         62 2024-03-21 11:36 /fofrk/in.txt

drwxr-xr-x   - hduser supergroup          0 2024-03-21 11:40 /fofrk/out

-rw-r--r--   1 hduser supergroup          0 2024-03-21 11:40 /fofrk/out/_SUCCESS

-rw-r--r--   1 hduser supergroup         88 2024-03-21 11:40 /fofrk/out/part-r-00000

hduser@ubuntu:~/fof$ hadoop fs -cat /fofrk/in.txt

A -> B C D

B -> A C D E

C -> A B D E

D -> A B C E 

E -> B C D

hduser@ubuntu:~/fof$ hadoop fs -cat /fofrk/out/part-r-00000

A,B C D

A,C B D

A,D B C

A,E B C D

B,C A D E

B,D A C E

B,E C D

C,D A B E

C,E B D

D,E B C

 

Output: