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

Oracle数据库的创建、数据导入导出
如何结合Sql脚本和PL/SQL Developer工具来实现创建表空间.创建数据库.备份数据库.还原数据库等操作,然后实现Oracle对象创建.导入数据等操作,方便我们快速了解.创建所需要的部署Sq ...
安装mysql 5.5.14 报错
提示cmake nod foundyum install cmake 原因是曾经服务器安装过mysql数据库Installing MySQL system tables...101223 14:28: ...
Visual Assist X破解方法
VC2008的破解方法:使用2008的朋友我就不多说了,直接拷贝到你选择的那个安装目录去,例如 C:\Program Files\Visual Assist\ ,直接运覆盖VA_X.dll 即可VC2 ...
【rest】深入理解rest
起因是想搞明白 ajax.rest风格和http请求数据会有什么区别再来回顾一下概念: REST即表述性状态传递满足这些约束条件和原则的应用程序或设计就是RESTful.需要注意的是,REST ...
jQuery 操作Cookie 存储读取删除等
<script type="text/javascript" src="/UI.Web.CRM.Main/js/jquery-2.1.1.min.js"& ...
Python - python不是内部或外部命令
[方法一]我的电脑->属性->高级->环境变量->系统变量在系统变量里找到PATH,双击PATH,在结尾加上 ";C:\Python26"(不要引号) ...
在一个Activity里面的TextView上面添加网页链接，启动后到另一个Activity里面！
可以添加很多的属性,样式或者是什么的,目前要完成的功能是点击TextView里面的某个文字链接,进入另外一个Activity里面!例如你可以做微博里面的 @XXX: 点击后进入他的个人主页! 下面都 ...
.Xresources 配置文件
安装rxvt-unicode-256color,如果不是这个版本的话VIM配色会显示不正常. ~/.Xresources配置文件如下 !urxvt color scheme: URxvt*backgr ...
[转载]WebBrowser控件表单（form）的自动填写和提交
话说有了WebBrowser类,终于不用自己手动封装SHDocVw的AxWebBrowser这个ActiveX控件了.这个类如果仅仅作为一个和IE一模一样浏览器,那就太没意思了(还不如直接用IE呢). ...
JavaScript高级---门面模式设计
门面模式两个作用: 1.简化类的接口 2.消除类与使用它的客户代码之间的耦合门面模式常常是开发人员最亲密的朋友.它几乎是所有javascript库的核心原则门面模式的目的是为了让开发人员用更简单 ...

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