MapReduce—案例（六）求互粉好友对

题目：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,K

A-B 就是一对互粉好友对

标准： 最终的所有结果集中必须包含 一组数据 X-Y 必须有 Y-X
那么我们就认为 X-Y 就是最终的结果--- 互粉好友对

A-B
B-A

A-C

A-D
D-A

B-E
解题思路：
将数据按照从小到大的顺序形成好友对，作为key值，在reduce里面统计key的值，如果key数目为2，即认为是互为好友对。
package practice1;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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;
/**
* 求互粉好友对
* @author potter
*/
public class Practice5 {

public static void main(String[] args) throws Exception {

Configuration conf = new Configuration();
// conf.set("fs.defaultFS", "hdfs://potter2:9000");
// System.setProperty("HADOOP_USER_NAME", "potter");
FileSystem fs = FileSystem.get(conf);

Job job = Job.getInstance();
job.setJarByClass(Practice5.class);
job.setMapperClass(Practice5Mapper.class);
job.setReducerClass(Practice5Reducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);

Path input = new Path("D:\\practice\\input5\\work5.txt");
Path output = new Path("D:\\practice\\input5\\output1");

FileInputFormat.setInputPaths(job, input);
FileOutputFormat.setOutputPath(job, output);

if (fs.exists(output)) {
fs.delete(output,true);
}
boolean isdone = job.waitForCompletion(true);
System.exit(isdone ? 0 :1);

}

public static class Practice5Mapper extends Mapper<LongWritable, Text, Text, NullWritable>{
Text text1 = new Text();
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
/**
* A:B,C,D,F,E,O
* B:A,C,E,K
* C:F,A,D,I
*/
String[] split1 = value.toString().trim().split(":");
String cc = split1[0];
String[] split2 = split1[1].split(",");
//用来判断好友对的个数，如果个数等于2，则两个互粉
for (int i = 0; i < split2.length; i++) {
String xx = split2[i];
if (cc.compareTo(xx) < 0) {
text1.set(cc+"-"+xx);
}else {
text1.set(xx+"-"+cc);
}
context.write(text1, NullWritable.get());
}
}
}

public static class Practice5Reducer extends Reducer<Text, NullWritable, Text, NullWritable>{
@Override
protected void reduce(Text key, Iterable<NullWritable> values, Context context)
throws IOException, InterruptedException {
//用来记录好友互粉的个数
int count = 0;
for(NullWritable dd : values){
count++;
}

if (count == 2) {
context.write(key, NullWritable.get());
}

}
}
}
结果：共16对A-B
A-C
A-D
A-F
A-O
B-E
C-F
D-E
D-F
D-L
E-L
E-M
F-M
H-O
I-O
J-O