hadoop2.2.0 MapReduce的序列化
package com.my.hadoop.mapreduce.dataformat;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
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;
import com.my.hadoop.common.Configs;
/**
* hadoop的序列化
* @author yao
*
*/
public class DataCount {
static class DTMap extends Mapper<LongWritable, Text, Text, DataBean>{
DataBean dataBean = null;
@Override
public void map(LongWritable key, Text value, Context context) throws IOException ,InterruptedException {
String[] fields = value.toString().split("\t");
String telNo = fields[1];
long upPayLoad = Long.parseLong(fields[8]);
long downPayLoad = Long.parseLong(fields[9]);
dataBean = new DataBean(telNo, upPayLoad, downPayLoad);
context.write(new Text(telNo), dataBean);
}
}
static class DTReduce extends Reducer<Text, DataBean, Text, DataBean>{
@Override
public void reduce(Text key, Iterable<DataBean> dataBeans, Context context) throws IOException ,InterruptedException {
long upPayLoad = 0;
long downPayLoad = 0;
for (DataBean dataBean : dataBeans) {
upPayLoad += dataBean.getUpPayLoad();
downPayLoad += dataBean.getDownPayLoad();
}
DataBean dataBean = new DataBean("", upPayLoad, downPayLoad);
context.write(key, dataBean);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = Configs.getConfigInstance();
String[] paths = new GenericOptionsParser(conf, args).getRemainingArgs();
if (paths.length != 2) {
System.err.println("Usage: " + DataCount.class.getName() + " <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, DataCount.class.getSimpleName());
job.setJarByClass(DataCount.class); //设置main函数所在的类
FileInputFormat.setInputPaths(job, new Path(args[0]));
job.setMapperClass(DTMap.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(DataBean.class);
job.setReducerClass(DTReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(DataBean.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1); //等待MapReduce执行完成并打印作业进度详情
}
}
/**
* 实现Writable接口,重写Write方法和readFields方法,严格按字段顺序进行写入写出
* @author yao
*
*/
class DataBean implements Writable {
private String telNo;
private long upPayLoad;
private long downPayLoad;
private long totalPayLoad;
public DataBean(){
}
public DataBean(String telNo, long upPayLoad, long downPayLoad) {
super();
this.telNo = telNo;
this.upPayLoad = upPayLoad;
this.downPayLoad = downPayLoad;
this.totalPayLoad = upPayLoad + downPayLoad;
}
@Override
public void readFields(DataInput in) throws IOException {
this.telNo = in.readUTF();
this.upPayLoad = in.readLong();
this.downPayLoad = in.readLong();
this.totalPayLoad = in.readLong();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(telNo);
out.writeLong(upPayLoad);
out.writeLong(downPayLoad);
out.writeLong(totalPayLoad);
}
@Override
public String toString() {
return this.telNo+"\t"+this.upPayLoad+"\t"+this.downPayLoad+"\t"+this.totalPayLoad;
}
public String getTelNo() {
return telNo;
}
public void setTelNo(String telNo) {
this.telNo = telNo;
}
public long getUpPayLoad() {
return upPayLoad;
}
public void setUpPayLoad(long upPayLoad) {
this.upPayLoad = upPayLoad;
}
public long getDownPayLoad() {
return downPayLoad;
}
public void setDownPayLoad(long downPayLoad) {
this.downPayLoad = downPayLoad;
}
public long getTotalPayLoad() {
return totalPayLoad;
}
public void setTotalPayLoad(long totalPayLoad) {
this.totalPayLoad = totalPayLoad;
}
}
hadoop2.2.0 MapReduce的序列化的更多相关文章
- hadoop2.2.0 MapReduce求和并排序
javabean必须实现WritableComparable接口,并实现该接口的序列化,反序列话和比较方法 package com.my.hadoop.mapreduce.sort; import j ...
- hadoop2.2.0 MapReduce分区
package com.my.hadoop.mapreduce.partition; import java.util.HashMap;import java.util.Map; import org ...
- 国内最全最详细的hadoop2.2.0集群的MapReduce的最简单配置
简介 hadoop2的中的MapReduce不再是hadoop1中的结构已经没有了JobTracker,而是分解成ResourceManager和ApplicationMaster.这次大变革被称为M ...
- 编写简单的Mapreduce程序并部署在Hadoop2.2.0上运行
今天主要来说说怎么在Hadoop2.2.0分布式上面运行写好的 Mapreduce 程序. 可以在eclipse写好程序,export或用fatjar打包成jar文件. 先给出这个程序所依赖的Mave ...
- Hadoop2.2.0 第一步完成MapReduce wordcount计算文本数量
1.完成Hadoop2.2.0单机版环境搭建之后需要利用一个例子程序来检验hadoop2 的mapreduce的功能 //启动hdfs和yarn sbin/start-dfs.sh sbin/star ...
- 【hadoop2.6.0】用C++ 编写mapreduce
hadoop通过hadoop streaming 来实现用非Java语言写的mapreduce代码. 对于一个一点Java都不会的我来说,这真是个天大的好消息. 官网上hadoop streaming ...
- 使用命令行编译打包运行自己的MapReduce程序 Hadoop2.6.0
使用命令行编译打包运行自己的MapReduce程序 Hadoop2.6.0 网上的 MapReduce WordCount 教程对于如何编译 WordCount.java 几乎是一笔带过… 而有写到的 ...
- Hadoop-2.2.0 (传 hadoop-2.2.0.tar.gz)
配置hadoop 2.1 上传hadoop包 2.2 解压hadoop包 首先在根目录下创建一个cloud目录 mkdir /cloud tar -zxvf hadoop-2.2.0.tar.gz - ...
- Hadoop2.2.0安装过程记录
1 安装环境1.1 客户端1.2 服务端1.3 安装准备 2 操作系统安装2.1.1 BIOS打开虚拟化支持2.1.2 关闭防火墙2.1.3 安装 ...
随机推荐
- Android消息机制(2)
在Android 中,线程内部或者线程之间进行信息交互时经常会使用消息,这些基础的东西如果我们熟悉其内部的原理,将会使我们容易.更好地架构系统,避免一些低级的错误. 下面我们分析下程序的运行过程: 1 ...
- mysql将一个库中表的某几个字段插入到另一个库中的表
insert into dbname1.tablename1(filed1,filed2,filed3) select filed1,filed2,filed3from dbname2.tablena ...
- tomcat配置文件server.xml详解 转载http://blog.csdn.net/yuanxuegui2008/article/details/6056754
元素名 属性 解释 server port 指定一个端口,这个端口负责监听关闭tomcat 的请求 shutdown 指定向端口发送的命令字符串 service name 指定service 的名字 ...
- Creating Lists and Cards 创建列表和卡片
To create complex lists and cards with material design styles in your apps, you can use the Recycler ...
- Bzoj3990 [SDOI2015]排序
Time Limit: 20 Sec Memory Limit: 128 MBSubmit: 651 Solved: 338 Description 小A有一个1-2^N的排列A[1..2^N], ...
- IIS 7.5 配置伪静态
IIS 7.5 配置伪静态_win服务器_脚本之家 win7下IIS的安装和配置 图文教程详细出处参考:http://www.jb51.net/article/29787.htm http://blo ...
- eclipse - copy类的全名
由于多次操作,感觉eclipse应该提供这个功能,网上搜一下,发现需要安装插件. 下载地址为 http://www.jave.de/eclipse/copyfully/copyfully_1.2.0. ...
- Linux系统文本命令快速登录与退出
Linux是一个多用户的操作系统,用户要使用该系统,首先必须登录系统,使用完系统后,必须退出系统.用户登录系统时,为了使系统能够识别自己,必须输入用户名和密码,经系统验证无误后方能进入系统.在系统安装 ...
- mvc wcf 并发提示,存储Application,验证是否有用户在操作
System.Web.HttpContext httpContext = System.Web.HttpContext.Current; Hashtable departmentSalary = (H ...
- iOS 网络与多线程--7.Performselector消息处理方法
创建一个IOSApp类 IOSApp.h文件 #import <Foundation/Foundation.h> @interface IOSApp : NSObject // 1.添加一 ...