需求:
以下是qq的好友列表数据,冒号前是一个用,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
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
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?
第一阶段思路:我们先找出一个人被哪几个人共同拥有
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 ShareFriendsStepOne {
static class ShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text> {
@Override
protected void map(LongWritable key, Text values, Context context) throws IOException, InterruptedException {
// A:B,C,D,F,E,O
String value = values.toString();
String[] person_friends = value.split(":");
String person = person_friends[0];
String friends = person_friends[1];
for (String friend : friends.split(",")) {
//输出(友人)
context.write(new Text(friend), new Text(person));
}
}
}
static class ShareFriendsReduce extends Reducer<Text, Text, Text, Text> {
// (B,A) (C,A) (D,A)(E,A)(F,A)
@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(",");
}
// 输出(友人,人,人,人)
context.write(friend,