仅用一次MapReduce就可以找共同好友！

pom文件

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.hadoop</groupId>
    <artifactId>project</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <hadoopVersion>2.7.2</hadoopVersion>
    </properties>
    <dependencies>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.48</version>
        </dependency>

    </dependencies>

Driver端

package com.mr.serachFriends;


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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;




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

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(MyDriverPro.class);
        job.setMapperClass(MyMappr.class);
        job.setReducerClass(MyReducerPro.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}

Map端

package com.mr.serachFriends;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class MyMappr extends Mapper<LongWritable,Text,Text,Text> {
    Text k =new Text();
    Text v =new Text();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String str = value.toString();
        String[] split = str.split(":");
        String[] friends = split[1].split(",");
        String people = split[0];
        System.out.println(people);
        for(String friend : friends){
            k.set(friend);
            v.set(people);
            context.write(k,v);
        }
    }
}

Reduce端

package com.mr.serachFriends;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

import java.util.*;

public class MyReducerPro extends Reducer<Text,Text,Text,Text> {
    Text k=new Text();
    Text v=new Text();
    Map<String,ArrayList<String>> map= new HashMap<String, ArrayList<String>>();
    Map<String,String> map2=new HashMap<String, String>();
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        ArrayList<String> list =new ArrayList<String >();
        for (Text people: values) {
            list.add(people.toString());
        }
        map.put(key.toString(),list);
    }

    @Override
    protected void cleanup(Context context) throws IOException, InterruptedException {
        Set<String> strings = map.keySet();
        Iterator<String> iterator = strings.iterator();
        while(iterator.hasNext()){
            String next = iterator.next();
            ArrayList<String> list = map.get(next);
            Collections.sort(list);
            for(int i=0;i<list.size()-1;i++){
                for (int j=i+1;j<list.size();j++) {
                    String Peoples=list.get(i)+" "+list.get(j);
                    if(!map2.containsKey(Peoples)){
                        map2.put(Peoples,next);
                    }else{
                        map2.put(Peoples,map2.get(Peoples)+" "+next);
                    }
                }
            }
        }

        Set<String> mapSet = map2.keySet();
        Iterator<String> iter = mapSet.iterator();
        while(iter.hasNext()){
            String ke = iter.next();
            String va = map2.get(ke);
            k.set(ke);
            v.set(va);
            context.write(k,v);
        }
    }
}

通过在Driver端输入参数，即需要处理的文件和输出文件夹，即可以查看结果！

						compiled up by JiaMingcan
						转载请署名：JiaMingcan