MapReduce练习-----互粉好友对

数据：

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

求哪些人两两之间是互粉好友，形如：A的好友有B，B的好友有A 。 那么A和B就是互粉好友。

思路：

对每一行数据进行组合输出 （person-person，1），

然后再Reducer阶段进行统计，等于2的就是互粉好友对；

问题：将B-A转换成A-B这种形式；

方案：比较两个字符之间的大小，小的在前；

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;

public class EachOtherFriend {

	public static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
		@Override
		protected void map(LongWritable key, Text value,Context context) throws IOException, InterruptedException {
			String[] lines = value.toString().split(":");
			char person = lines[0].charAt(0); 
			for (String str : lines[1].split(",")) {
				char friend = str.charAt(0);
				String per_per = "";
				if(person > friend){
					per_per += friend+"-"+person;
				}else{
					per_per += person+"-"+friend;
				}
				context.write(new Text(per_per), new IntWritable(1));
				
			}
		}
	}
	
	
	public static class MyReducer extends Reducer<Text, IntWritable, Text, NullWritable>{
		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,Context context)
				throws IOException, InterruptedException {
			
			int num = 0;
			for (IntWritable it : values) {
				num++;
			}
			if(num > 1){
				context.write(key, null);
			}
		}
	}
	
	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		
		Job job = Job.getInstance(conf);
		
		job.setJarByClass(EachOtherFriend.class);
		job.setMapperClass(MyMapper.class);
		job.setReducerClass(MyReducer.class);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(NullWritable.class);
		
		FileInputFormat.setInputPaths(job, new Path("G:/files/input"));
		FileOutputFormat.setOutputPath(job, new Path("G:/files/output"));
		
		boolean isDone = job.waitForCompletion(true);
		System.exit(isDone ? 0:1);
		
	}
}

结果如下：

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