MapReduce实现之 查找共同好友

输入：邻接表

100, 200 300 400 500 600
200, 100 300 400
300, 100 200 400 500
400, 100 200 300
500, 100 300
600, 100第一列表示用户，后面的表示用户的好友。
需求：查找两两用户的共同好友。

思路：1、key为两两用户，value为其中一个用户的所有好友

            2、求两个用户所有好友的交集

步骤：1、map：取每一行，组合user和其任一好友为key（key中的两个字段按字典序排列），user的所有好友为value

            2、reduce：求两个用户之间好友的交集

package dabook;

import hadoop.FriendRecom;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Set;
import java.util.TreeSet;

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.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;
import org.apache.hadoop.util.GenericOptionsParser;

public class CommFriend {

public static Set<String> intersect(Set<String> set1, Set<String> set2){
if(set1==null || set2 == null){
return null;
}

Set<String> result = new TreeSet<String>();

Set<String> small = null;
Set<String> big = null;
if(set1.size() < set2.size()){
small = set1;
big = set2;
}
else {
small = set2;
big = set1;
}

for (String String : small) {
if(big.contains(String)){
result.add(String);
}
}
return result;
}

static class MyMapper extends Mapper<LongWritable, Text, Text, Text>{

private static Text outKey = new Text();
private static Text outValue = new Text();

@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String [] input = value.toString().split(",");
if(input.length != 2){
return;
}

outValue.set(input[1]);
String [] sz = input[1].split(" ");
for (String string : sz) {
if(input[0].compareTo(string) < 0){
outKey.set("[" + input[0] + ", " + string + "]");
}
else {
outKey.set("[" + string + ", " + input[0] + "]");
}
context.write(outKey, outValue);
}
}

}

static class MyReducer extends Reducer<Text, Text, Text, Text>{

private Text outKey = new Text();
private Text outValue = new Text();

@Override
protected void reduce(Text key, Iterable<Text> value, Context context)
throws IOException, InterruptedException {

int len = 0;
Set<String> set1 = new TreeSet<String>();
Set<String> set2 = new TreeSet<String>();
ArrayList<String> arrayList = new ArrayList<String>();
for (Text text : value) {
arrayList.add(text.toString());
len++;
}

if(len != 2){
return;
}

String [] sz = arrayList.get(0).split(" ");
for (String s : sz) {
set1.add(s);
}

sz = arrayList.get(1).trim().split(" ");
for (String s : sz) {
set2.add(s);
}

Set<String> res = intersect(set1, set2);
if(res == null){
return;
}
StringBuilder sb = new StringBuilder();
for (String s : res) {
sb.append(s + ", ");
}

String substring = null;
if(sb.length() > 1){
substring = sb.substring(0, sb.length()-2);
}

if(substring != null){
this.outValue.set(substring);
context.write(key, outValue);
}
}
}

private static String inputPath = "dabook/commfriend";
private static String outputPath = "dabook/commfriend-out";

public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
Job job = new Job(conf, "common friend");
job.setJarByClass(CommFriend.class);
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);

job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileSystem fs = FileSystem.get(conf);
Path inPath = new Path(inputPath);
if (fs.exists(inPath)) {
FileInputFormat.addInputPath(job, inPath);
}

Path outPath = new Path(outputPath);
fs.delete(outPath, true);
FileOutputFormat.setOutputPath(job, outPath);

System.exit(job.waitForCompletion(true) ? 0 : 1);

}

private void test(){
Set<String> set1 = new TreeSet<String>();
Set<String> set2 = new TreeSet<String>();

set2.add("2");
set2.add("3");
set2.add("4");
set2.add("5");

set1.add("3");
set1.add("4");
set1.add("6");

Set<String> res = intersect(set1, set2);

for (String string : res) {
System.out.println(string);
}

}

}
输出：
[100, 200] 300, 400
[100, 300] 200, 400, 500
[100, 400] 200, 300
[100, 500] 300
[200, 300] 100, 400
[200, 400] 100, 300
[300, 400] 100, 200
[300, 500] 100