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(",")) { // output <friend, person> 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> { // The data obtained is the output result of the previous step // A I,K,C,B,G,F,H,O,D, // friend, person, person @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(","); Arrays.sort(persons); for (int i = 0; i < persons.length - 1; i++) { for (int j = i + 1; j < persons.length; j++) { // issue <person-person, friend>, so that all friends of the same "person-person" pair will go to the same reduce 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); } }
Test file:
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 G:A,C,D,E,F H:A,C,D,E,O I:A,O J:B,O K:A,C,D L:D,E,F M:E,F,G O:A,H,I,J
Output result:
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,
A-B C E AC FD AD EF A-E B C D A-F C D B E O AG DEFC AH EOCD AI O A-K D A-L F E BC A BD EA B-E C B-F E A C BG CEA B-H E C A BI A BK A W E C-D F A C-E D C-F D A C-G F A D CH AD CI A C-K D A C-L F D-F E A DG AEF DH AE DI A DK A D-L F E E-F C D B EG DC E-H D C E-K D F-G C E D A FH CADEO FI AO F-K D A FL E G-H D E C A GI A TG AD GL FE HI AO HK AD HL E IK A