前提准备:
1.hadoop安装运行正常。Hadoop安装配置请参考:Ubuntu下 Hadoop 1.2.1 配置安装
2.集成开发环境正常。集成开发环境配置请参考 :Ubuntu 搭建Hadoop源码阅读环境
MapReduce编程实例:
MapReduce编程实例(一),详细介绍在集成环境中运行第一个MapReduce程序 WordCount及代码分析
MapReduce编程实例(五),MapReduce实现单表关联
多表关联
描述:
两张表关联,如下:
左表:
factoryname address
BMW Factory 2
Benz Factory 3
Voivo Factory 4
LG Factory 5
BMW Factory 2
Benz Factory 3
Voivo Factory 4
LG Factory 5
右表:
addressID addressname
2 Beijing
3 Guangzhou
4 Shenzhen
5 Sanya
2 Beijing
3 Guangzhou
4 Shenzhen
5 Sanya
根据addressID关联求出factoryname-address表。很明显,左右关联即可,和单表关联一样。不多作表述,有需要可以查看单表关联的分析。
- package com.t.hadoop;
- import java.io.IOException;
- import java.util.ArrayList;
- import java.util.List;
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.fs.Path;
- import org.apache.hadoop.io.IntWritable;
- 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;
- /**
- * 多表排序
- * @author daT dev.tao@gmail.com
- *
- */
- public class MTJoin {
- public static int times = 1;
- public static class MTMapper extends Mapper<Object, Text, Text, Text>{
- @Override
- protected void map(Object key, Text value, Context context)
- throws IOException, InterruptedException {
- String relation = new String();
- String line = value.toString();
- if(line.contains("factoryname")||line.contains("addressID")) return;
- int i = 0;
- while(line.charAt(i)<'0'||line.charAt(i)>'9'){
- i++;
- }
- if(i>0){//左表
- relation = "1";
- context.write(new Text(String.valueOf(line.charAt(i))),new Text(relation + line.substring(0,i-1)));
- }else{//右表
- relation = "2";
- context.write(new Text(String.valueOf(line.charAt(i))),new Text(relation +line.substring(i+1)));
- }
- }
- }
- public static class MTReducer extends Reducer<Text, Text, Text, Text>{
- @Override
- protected void reduce(Text key, Iterable<Text> value,Context context)
- throws IOException, InterruptedException {
- if(times==1){
- context.write(new Text("factoryName"), new Text("Address"));
- times ++;
- }
- int factoryNum = 0;
- int addressNum = 0;
- String[] factorys = new String[10];
- String[] addresses = new String[10];
- for(Text t:value){
- if(t.charAt(0)=='1'){//左表
- factorys[factoryNum]=t.toString().substring(1);
- factoryNum++;
- }else{//右表
- addresses[addressNum]=t.toString().substring(1);
- addressNum++;
- }
- }
- for(int i = 0;i<factoryNum;i++){
- for(int j=0;j<addressNum;j++){
- context.write(new Text(factorys[i]), new Text(addresses[j]));
- }
- }
- }
- }
- public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
- Configuration conf = new Configuration();
- String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
- if(otherArgs.length<2){
- System.out.println("Parameters error");
- System.exit(2);
- }
- Job job =new Job(conf,"MTjoin");
- job.setJarByClass(MTJoin.class);
- job.setMapperClass(MTMapper.class);
- job.setReducerClass(MTReducer.class);
- job.setOutputKeyClass(Text.class);
- job.setOutputValueClass(Text.class);
- FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
- FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
- System.exit(job.waitForCompletion(true)?0:1);
- }
- }
输出结果:
factoryName Address
BMW Factory Beijing
Benz Factory Guangzhou
Voivo Factory Shenzhen
LG Factory Sanya
BMW Factory Beijing
Benz Factory Guangzhou
Voivo Factory Shenzhen
LG Factory Sanya
欢迎同学们多多交流~