标签：key view auth interrupt jar hdf print nmap har
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（二），计算学生平均成绩
MapReduce编程实例（三），数据去重
MapReduce编程实例（四），排序
MapReduce编程实例（五），MapReduce实现单表关联
单表关联：
描述：
单表的自连接求解问题。如下表，根据child-parent表列出grandchild-grandparent表的值。
child parent
Tom Lucy
Tom Jim
Lucy David
Lucy Lili
Jim Lilei
Jim SuSan
Lily Green
Lily Bians
Green Well
Green MillShell
Havid James
James LiT
Richard Cheng
Cheng LiHua
问题分析：
显然需要分解为左右两张表来进行自连接，而左右两张表其实都是child-parent表，通过parent字段做key值进行连接。结合MapReduce的特性，MapReduce会在shuffle过程把相同的key放在一起传到Reduce进行处理。OK，这下有思路了，将左表的parent作为key输出，将右表的child做为key输出，这样shuffle之后很自然的，左右就连接在一起了，有木有！然后通过对左右表进行求迪卡尔积便得到所需的数据。
- package com.t.hadoop;
-
- import java.io.IOException;
- import java.util.Iterator;
-
- 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.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 STJoin {
- public static int time = 0;
-
- public static class STJoinMapper extends Mapper<Object, Text, Text, Text>{
-
- @Override
- protected void map(Object key, Text value, Context context)
- throws IOException, InterruptedException {
- String childName = new String();
- String parentName = new String();
- String relation = new String();
- String line = value.toString();
- int i =0;
- while(line.charAt(i)!=‘ ‘){
- i++;
- }
- String[] values = {line.substring(0,i),line.substring(i+1)};
- if(values[0].compareTo("child") != 0){
- childName = values[0];
- parentName = values[1];
- relation = "1";
- context.write(new Text(parentName),new Text(relation+"+"+childName));
- relation = "2";
- context.write(new Text(childName), new Text(relation+"+"+parentName));
- }
- }
- }
-
- public static class STJoinReduce extends Reducer<Text, Text, Text, Text>{
-
- @Override
- protected void reduce(Text key, Iterable<Text> values,Context context)
- throws IOException, InterruptedException {
- if(time ==0){
- context.write(new Text("grandChild"), new Text("grandParent"));
- time ++;
- }
- int grandChildNum = 0;
- String[] grandChild = new String[10];
- int grandParentNum = 0;
- String[] grandParent = new String[10];
- Iterator<Text> ite = values.iterator();
- while(ite.hasNext()){
- String record = ite.next().toString();
- int len = record.length();
- int i = 2;
- if(len ==0) continue;
- char relation = record.charAt(0);
-
- if(relation == ‘1‘){
- String childName = new String();
- while(i < len){
- childName = childName + record.charAt(i);
- i++;
- }
- grandChild[grandChildNum] = childName;
- grandChildNum++;
- }else{
- String parentName = new String();
- while(i < len){
- parentName = parentName + record.charAt(i);
- i++;
- }
- grandParent[grandParentNum] = parentName;
- grandParentNum++;
- }
- }
-
- if(grandChildNum!=0&&grandParentNum!=0){
- for(int m=0;m<grandChildNum;m++){
- for(int n=0;n<grandParentNum;n++){
- System.out.println("grandChild "+grandChild[m] +" grandParent "+ grandParent[n]);
- context.write(new Text(grandChild[m]),new Text(grandParent[n]));
- }
- }
- }
- }
- }
-
- 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("parameter error");
- System.exit(2);
- }
-
- Job job = new Job(conf);
- job.setJarByClass(STJoin.class);
- job.setMapperClass(STJoinMapper.class);
- job.setReducerClass(STJoinReduce.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);
- }
- }
传入参数：
hdfs://localhost:9000/user/dat/stjon_input hdfs://localhost:9000/user/dat/stjon_output
输出结果：
grandChild grandParent
Richard LiHua
Lily Well
Lily MillShell
Havid LiT
Tom Lilei
Tom SuSan
Tom Lili
Tom David
OK~!欢迎同学们多多交流～～
MapReduce编程实例5
标签：key view auth interrupt jar hdf print nmap har
原文地址：http://www.cnblogs.com/gaochsh/p/7802892.html
