Tom Lucy
Tom Jack
Jone Lucy
Jone Jack
Lucy Mary
Lucy Ben
Jack Alice
Jack Jesse
Terry Alice
Terry Jesse
Philip Terry
Philip Alma
Mark Terry
Mark Alma

package com;import java.io.IOException;
import java.util.ArrayList;
import java.util.List;import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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 TestParents {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {Configuration config = new  Configuration();config.set("fs.defaultFS", "hdfs://192.168.0.100:9000");config.set("yarn.resourcemanager.hostname", "192.168.0.100");FileSystem fs = FileSystem.get(config);Job job = Job.getInstance(config);job.setJarByClass(TestParents.class);//设置所用到的map类job.setMapperClass(myMapper.class);job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(Text.class);//设置用到的reducer类job.setReducerClass(myReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(Text.class);//设置输入输出地址FileInputFormat.addInputPath(job, new Path("/input/parent.txt"));Path path = new Path("/output3/");if(fs.exists(path)){fs.delete(path, true);}//指定文件的输出地址
        FileOutputFormat.setOutputPath(job, path);//启动处理任务jobboolean completion = job.waitForCompletion(true);if(completion){System.out.println("Job Success!");}}public static class myMapper extends Mapper<Object, Text, Text, Text> {// 实现map函数public void map(Object key, Text value, Context context) throws IOException, InterruptedException {String temp=new String();// 左右表标识
                String values=value.toString();String words[]=values.split(" ");//Tom    Lucy// 输出左表temp = "1";context.write(new Text(words[1]), new Text(temp +"+"+ words[0] + "+" + words[1]));//(Lucy,1+Tom+Lucy)// 输出右表temp = "2";context.write(new Text(words[0]), new Text(temp +"+"+ words[0] + "+" + words[1]));//(Tom,2+Tom+Lucy)
            }}public static class myReducer extends Reducer<Text, Text, Text, Text> {// 实现reducer函数public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {List<String> grandchild = new ArrayList<String>();List<String> grandparent = new ArrayList<String>();for (Text value : values) {char temp=(char) value.charAt(0);String words[]=value.toString().split("[+]");  //1,Tom+Lucy// +、*、|、/等符号在正则表达示中有相应的不同意义,一般来讲只需要加[]、或是\\即可if(temp == '1'){grandchild.add(words[1]);}if(temp == '2'){grandparent.add(words[2]);}}//求笛卡尔儿积for (String gc : grandchild) {for (String gp : grandparent) {context.write(new Text(gc),new Text(gp));}}}}
}

    Tom        Lucy                    map输出：               <Lucy，1+Tom+Lucy><Tom，2+Tom+Lucy >Tom        Jack                    map输出：                <Jack，1+Tom+Jack><Tom，2+Tom+Jack>Jone        Lucy                   map输出：                <Lucy，1+Jone+Lucy><Jone，2+Jone+Lucy>Jone        Jack                   map输出：                <Jack，1+Jone+Jack><Jone，2+Jone+Jack>Lucy        Mary                   map输出：                <Mary，1+Lucy+Mary><Lucy，2+Lucy+Mary>Lucy        Ben                    map输出：                <Ben，1+Lucy+Ben><Lucy，2+Lucy+Ben>Jack        Alice                  map输出：                <Alice，1+Jack+Alice><Jack，2+Jack+Alice>Jack        Jesse                  map输出：                <Jesse，1+Jack+Jesse><Jack，2+Jack+Jesse>Terry        Alice                 map输出：               <Alice，1+Terry+Alice><Terry，2+Terry+Alice>Terry        Jesse                 map输出：                <Jesse，1+Terry+Jesse><Terry，2+Terry+Jesse>Philip        Terry                map输出：               <Terry，1+Philip+Terry><Philip，2+Philip+Terry>Philip        Alma                 map输出：                <Alma，1+Philip+Alma><Philip，2+Philip+Alma>Mark        Terry                  map输出：                <Terry，1+Mark+Terry><Mark，2+Mark+Terry>Mark        Alma                   map输出：                <Alma，1+Mark+Alma><Mark，2+Mark+Alma>