MapReduce编程系列 — 6：多表关联

1、项目名称：

2、程序代码：

版本一（详细版）：

package com.mtjoin;

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 MTjoin {

    public static int time = 0;

    public static class Map extends Mapper<Object, Text, Text, Text>{

        public void map(Object key, Text value, Context context)throws IOException,InterruptedException{

            System.out.println("mapper........................");

            String line = value.toString();

            if(line.contains("factoryname")==true || line.contains("addressID")== true){

                return ;

            }

            int i = 0;

            while(line.charAt(i) >= '9'|| line.charAt(i) <= '0'){

                i++;

            }

            if(line.charAt(0) >= '9'|| line.charAt(0) <= '0'){

                int j = i-1;

                while(line.charAt(j) != ' ') j--;

                System.out.println("key:"+line.substring(i)+"  value:"+line.substring(0,j));

                String values[] = {line.substring(0, j),line.substring(i)};

                context.write(new Text(values[1]), new Text("1+"+values[0]));

            }

            else {

                int j = i + 1;

                while(line.charAt(j)!=' ')  j++;

                System.out.println("key:"+line.substring(0, i+1)+"  value:"+line.substring(j));

                String values[] ={line.substring(0,i+1),line.substring(j)};

                context.write(new Text(values[0]), new Text("2+"+values[1]));

            }

        }

    }

        public static class Reduce extends Reducer<Text, Text, Text, Text>{

            public void reduce(Text key, Iterable<Text> values, Context context)throws IOException,InterruptedException{

                System.out.println("reducer........................");

                if( time == 0){

                    context.write(new Text("factoryname"), new Text("addressname"));

                    time++;

                }

                int factorynum = 0;

                String factory[] = new String[10];

                int addressnum = 0;

                String address[] = new String[10];

                Iterator ite = values.iterator();

                while(ite.hasNext()){

                    String record = ite.next().toString();

                    char type = record.charAt(0);

                    if(type == '1'){

                        factory[factorynum] = record.substring(2);

                        factorynum++;

                    }

                    else{

                        address[addressnum] = record.substring(2);

                        addressnum++;

                    }

                }

                if(factorynum != 0 && addressnum != 0){

                    for(int m = 0 ; m < factorynum ; m++){

                        for(int n = 0; n < addressnum; n++){

                            context.write(new Text(factory[m]), new Text(address[n]));

                            System.out.println("factoryname:"+factory[m]+"  addressname:"+address[n]);

                        }

                    }

                }

            }

        }

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

        Configuration conf = new Configuration();

        String otherArgs[] = new GenericOptionsParser(conf,args).getRemainingArgs();

        if(otherArgs.length != 2){

            System.err.println("Usage:MTjoin<in><out>");

            System.exit(2);

        }

        Job job = new Job(conf,"multiple table join");

        job.setJarByClass(MTjoin.class);

        job.setMapperClass(Map.class);

        job.setReducerClass(Reduce.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);

        }

}

版本二（简化版）：

package com.mtjoin;

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 MTjoin {

    public static int time = 0;

    public static class Map extends Mapper<Object, Text, Text, Text>{

        public void map(Object key, Text value, Context context)throws IOException,InterruptedException{

            System.out.println("mapper........................");

            String line = value.toString();

            if(line.contains("factoryname")==true || line.contains("addressID")== true){

                return ;

            }

            int len = line.length();

            if(line.charAt(0) > '9'|| line.charAt(0) < '0'){

                System.out.println("key:"+line.substring(len-1)+"  value:"+line.substring(0,len-2));

                String values[] = {line.substring(0, len-2),line.substring(len-1)};

                context.write(new Text(values[1]), new Text("1+"+values[0]));

            }

            else {

                System.out.println("key:"+line.substring(0, 1)+"  value:"+line.substring(2));

                String values[] ={line.substring(0,1),line.substring(2)};

                context.write(new Text(values[0]), new Text("2+"+values[1]));

            }

        }

    }

        public static class Reduce extends Reducer<Text, Text, Text, Text>{

            public void reduce(Text key, Iterable<Text> values, Context context)throws IOException,InterruptedException{

                System.out.println("reducer........................");

                if( time == 0){

                    context.write(new Text("factoryname"), new Text("addressname"));

                    time++;

                }

                int factorynum = 0;

                String factory[] = new String[10];

                int addressnum = 0;

                String address[] = new String[10];

                Iterator ite = values.iterator();

                while(ite.hasNext()){

                    String record = ite.next().toString();

                    char type = record.charAt(0);

                    if(type == '1'){

                        factory[factorynum] = record.substring(2);

                        factorynum++;

                    }

                    else{

                        address[addressnum] = record.substring(2);

                        addressnum++;

                    }

                }

                if(factorynum != 0 && addressnum != 0){

                    for(int m = 0 ; m < factorynum ; m++){

                        for(int n = 0; n < addressnum; n++){

                            context.write(new Text(factory[m]), new Text(address[n]));

                            System.out.println("factoryname:"+factory[m]+"  addressname:"+address[n]);

                        }

                    }

                }

            }

        }

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

        Configuration conf = new Configuration();

        String otherArgs[] = new GenericOptionsParser(conf,args).getRemainingArgs();

        if(otherArgs.length != 2){

            System.err.println("Usage:MTjoin<in><out>");

            System.exit(2);

        }

        Job job = new Job(conf,"multiple table join");

        job.setJarByClass(MTjoin.class);

        job.setMapperClass(Map.class);

        job.setReducerClass(Reduce.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);

        }

}

3、测试数据：

address：

addressID addressname
1 Beijing
2 Guangzhou
3 Shenzhen
4 Xian

factory：

factoryname addressname
Beijing Red Star 1
Shenzhen Thunder 3
Guangzhou Honda 2
Beijing Rising 1
Guangzhou Development Bank 2
Tencent 3
Bank of Beijing 1

4、运行过程：

14/09/24 09:39:55 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
14/09/24 09:39:55 WARN mapred.JobClient: No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
14/09/24 09:39:55 INFO input.FileInputFormat: Total input paths to process : 2
14/09/24 09:39:55 WARN snappy.LoadSnappy: Snappy native library not loaded
14/09/24 09:39:55 INFO mapred.JobClient: Running job: job_local_0001
14/09/24 09:39:55 INFO util.ProcessTree: setsid exited with exit code 0
14/09/24 09:39:55 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@e095722
14/09/24 09:39:55 INFO mapred.MapTask: io.sort.mb = 100
14/09/24 09:39:55 INFO mapred.MapTask: data buffer = 79691776/99614720
14/09/24 09:39:55 INFO mapred.MapTask: record buffer = 262144/327680
mapper........................
mapper........................
key:1 value:Beijing Red Star
mapper........................
key:3 value:Shenzhen Thunder
mapper........................
key:2 value:Guangzhou Honda
mapper........................
key:1 value:Beijing Rising
mapper........................
key:2 value:Guangzhou Development Bank
mapper........................
key:3 value:Tencent
mapper........................
key:1 value:Bank of Beijing
14/09/24 09:39:55 INFO mapred.MapTask: Starting flush of map output
14/09/24 09:39:55 INFO mapred.MapTask: Finished spill 0
14/09/24 09:39:55 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
14/09/24 09:39:56 INFO mapred.JobClient: map 0% reduce 0%
14/09/24 09:39:58 INFO mapred.LocalJobRunner:
14/09/24 09:39:58 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
14/09/24 09:39:58 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@7dabd20
14/09/24 09:39:58 INFO mapred.MapTask: io.sort.mb = 100
14/09/24 09:39:58 INFO mapred.MapTask: data buffer = 79691776/99614720
14/09/24 09:39:58 INFO mapred.MapTask: record buffer = 262144/327680
mapper........................
mapper........................
key:1 value:Beijing
mapper........................
key:2 value:Guangzhou
mapper........................
key:3 value:Shenzhen
mapper........................
key:4 value:Xian
14/09/24 09:39:58 INFO mapred.MapTask: Starting flush of map output
14/09/24 09:39:58 INFO mapred.MapTask: Finished spill 0
14/09/24 09:39:58 INFO mapred.Task: Task:attempt_local_0001_m_000001_0 is done. And is in the process of commiting
14/09/24 09:39:59 INFO mapred.JobClient: map 100% reduce 0%
14/09/24 09:40:01 INFO mapred.LocalJobRunner:
14/09/24 09:40:01 INFO mapred.Task: Task 'attempt_local_0001_m_000001_0' done.
14/09/24 09:40:01 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@49fa6f3c
14/09/24 09:40:01 INFO mapred.LocalJobRunner:
14/09/24 09:40:01 INFO mapred.Merger: Merging 2 sorted segments
14/09/24 09:40:01 INFO mapred.Merger: Down to the last merge-pass, with 2 segments left of total size: 218 bytes
14/09/24 09:40:01 INFO mapred.LocalJobRunner:
reducer........................
factoryname:Beijing Red Star addressname:Beijing
factoryname:Beijing Rising addressname:Beijing
factoryname:Bank of Beijing addressname:Beijing
reducer........................
factoryname:Guangzhou Honda addressname:Guangzhou
factoryname:Guangzhou Development Bank addressname:Guangzhou
reducer........................
factoryname:Shenzhen Thunder addressname:Shenzhen
factoryname:Tencent addressname:Shenzhen
reducer........................
14/09/24 09:40:01 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
14/09/24 09:40:01 INFO mapred.LocalJobRunner:
14/09/24 09:40:01 INFO mapred.Task: Task attempt_local_0001_r_000000_0 is allowed to commit now
14/09/24 09:40:01 INFO output.FileOutputCommitter: Saved output of task 'attempt_local_0001_r_000000_0' to hdfs://localhost:9000/user/hadoop/mtjoin_output02
14/09/24 09:40:04 INFO mapred.LocalJobRunner: reduce > reduce
14/09/24 09:40:04 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
14/09/24 09:40:05 INFO mapred.JobClient: map 100% reduce 100%
14/09/24 09:40:05 INFO mapred.JobClient: Job complete: job_local_0001
14/09/24 09:40:05 INFO mapred.JobClient: Counters: 22
14/09/24 09:40:05 INFO mapred.JobClient:   Map-Reduce Framework
14/09/24 09:40:05 INFO mapred.JobClient:     Spilled Records=22
14/09/24 09:40:05 INFO mapred.JobClient:     Map output materialized bytes=226
14/09/24 09:40:05 INFO mapred.JobClient:     Reduce input records=11
14/09/24 09:40:05 INFO mapred.JobClient:     Virtual memory (bytes) snapshot=0
14/09/24 09:40:05 INFO mapred.JobClient:     Map input records=13
14/09/24 09:40:05 INFO mapred.JobClient:     SPLIT_RAW_BYTES=238
14/09/24 09:40:05 INFO mapred.JobClient:     Map output bytes=192
14/09/24 09:40:05 INFO mapred.JobClient:     Reduce shuffle bytes=0
14/09/24 09:40:05 INFO mapred.JobClient:     Physical memory (bytes) snapshot=0
14/09/24 09:40:05 INFO mapred.JobClient:     Reduce input groups=4
14/09/24 09:40:05 INFO mapred.JobClient:     Combine output records=0
14/09/24 09:40:05 INFO mapred.JobClient:     Reduce output records=8
14/09/24 09:40:05 INFO mapred.JobClient:     Map output records=11
14/09/24 09:40:05 INFO mapred.JobClient:     Combine input records=0
14/09/24 09:40:05 INFO mapred.JobClient:     CPU time spent (ms)=0
14/09/24 09:40:05 INFO mapred.JobClient:     Total committed heap usage (bytes)=813170688
14/09/24 09:40:05 INFO mapred.JobClient:   File Input Format Counters
14/09/24 09:40:05 INFO mapred.JobClient:     Bytes Read=216
14/09/24 09:40:05 INFO mapred.JobClient:   FileSystemCounters
14/09/24 09:40:05 INFO mapred.JobClient:     HDFS_BYTES_READ=586
14/09/24 09:40:05 INFO mapred.JobClient:     FILE_BYTES_WRITTEN=122093
14/09/24 09:40:05 INFO mapred.JobClient:     FILE_BYTES_READ=1658
14/09/24 09:40:05 INFO mapred.JobClient:     HDFS_BYTES_WRITTEN=202
14/09/24 09:40:05 INFO mapred.JobClient:   File Output Format Counters
14/09/24 09:40:05 INFO mapred.JobClient:     Bytes Written=202

5、运行结果：

factoryname   addressname
Beijing Red Star   Beijing
Beijing Rising   Beijing
Bank of Beijing   Beijing
Guangzhou Honda   Guangzhou
Guangzhou Development Bank   Guangzhou
Shenzhen Thunder   Shenzhen
Tencent   Shenzhen

MapReduce编程系列 — 6：多表关联的更多相关文章

MapReduce编程系列 — 5：单表关联
1.项目名称: 2.项目数据: chile parentTom LucyTom JackJone LucyJone JackLucy MaryLucy Ben ...
【原创】MapReduce编程系列之表连接
问题描述需要连接的表如下:其中左边是child,右边是parent,我们要做的是找出grandchild和grandparent的对应关系,为此需要进行表的连接. Tom Lucy Tom Jim ...
【原创】MapReduce编程系列之二元排序
普通排序实现普通排序的实现利用了按姓名的排序,调用了默认的对key的HashPartition函数来实现数据的分组.partition操作之后写入磁盘时会对数据进行排序操作(对一个分区内的数据作排序 ...
MapReduce编程系列 — 4：排序
1.项目名称: 2.程序代码: package com.sort; import java.io.IOException; import org.apache.hadoop.conf.Configur ...
MapReduce编程系列 — 3：数据去重
1.项目名称: 2.程序代码: package com.dedup; import java.io.IOException; import org.apache.hadoop.conf.Configu ...
MapReduce编程系列 — 2：计算平均分
1.项目名称: 2.程序代码: package com.averagescorecount; import java.io.IOException; import java.util.Iterator ...
MapReduce编程系列 — 1：计算单词
1.代码: package com.mrdemo; import java.io.IOException; import java.util.StringTokenizer; import org.a ...
MapReduce 编程系列九 Reducer数目
本篇介绍怎样控制reduce的数目.前面观察结果文件,都会发现通常是以part-r-00000 形式出现多个文件,事实上这个reducer的数目有关系.reducer数目多,结果文件数目就多. 在初始 ...
MapReduce 编程系列七 MapReduce程序日志查看
首先,假设须要打印日志,不须要用log4j这些东西,直接用System.out.println就可以,这些输出到stdout的日志信息能够在jobtracker网站终于找到. 其次,假设在main函数 ...

随机推荐

把数组排成最小的数/1038. Recover the Smallest Number
题目描述输入一个正整数数组,把数组里所有数字拼接起来排成一个数,打印能拼接出的所有数字中最小的一个.例如输入数组{3,32,321},则打印出这三个数字能排成的最小数字为321323. Give ...
【python】开始第一个项目
根据这篇文章开始上手 http://www.oschina.net/translate/the-flask-mega-tutorial-part-i-hello-world 再加点东西如果你的环境是 ...
[转]- Winform 用子窗体刷新父窗体,子窗体改变父窗体控件的值
转自:http://heisetoufa.iteye.com/blog/382684 第一种方法: 用委托,Form2和Form3是同一组 Form2 using System; using Sys ...
《自学C语言》初级教程－目录
我现在打算出一个C语言学习教程,目的是为了让初学者能够很容易和更深刻地理解C语言. 你可能有这样的疑问,网上不是有很多的初级教程吗,我需要这个吗?我的回答是:网上的C语言教程讲得不够全面,而且许多的初 ...
sharepoint mysite and upgrade topics
My Sites overview (SharePoint Server 2010)http://technet.microsoft.com/en-us/library/ff382643(v=offi ...
c语言编程之二叉树
利用链表建立二叉树,完成前序遍历.中序遍历.后序遍历. 建立二叉树用的是前序遍历建立二叉树: #include<stdio.h> #include<stdlib.h> #inc ...
(转)assert()函数用法总结
assert宏的原型定义在<assert.h>中,其作用是如果它的条件返回错误,则终止程序执行,原型定义: #include <assert.h>void assert( in ...
.net datatable 添加一列
dt.Columns.Add("image", Type.GetType("System.String")); foreach (DataRow dr in d ...
Enterprise Library 6——Using the Logging Application Block
原文参考 http://msdn.microsoft.com/en-us/library/dn440731(v=pandp.60).aspx 一.简介 .更重要的是用于审计.这种日志可以跟踪用户的行为 ...
IP地址格式控制
/// <summary> /// 验证IP格式是否输入正确 /// </summary> /// <param name="ip"></ ...

MapReduce编程系列 — 6：多表关联

MapReduce编程系列 — 6：多表关联的更多相关文章

随机推荐

热门专题