【转】ChainMapper 实例理解二
package com.oncedq.code; import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.text.SimpleDateFormat; import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.jobcontrol.Job;
import org.apache.hadoop.mapred.jobcontrol.JobControl;
import org.apache.hadoop.mapred.lib.ChainMapper; import com.oncedq.code.util.DateUtil; public class ProcessSample {
public static class ExtractMappper extends MapReduceBase implements
Mapper<LongWritable, Text, LongWritable, Conn1> { @Override
public void map(LongWritable arg0, Text arg1,
OutputCollector<LongWritable, Conn1> arg2, Reporter arg3)
throws IOException {
String line = arg1.toString();
String[] strs = line.split(";");
Conn1 conn1 = new Conn1();
conn1.orderKey = Long.parseLong(strs[0]);
conn1.customer = Long.parseLong(strs[1]);
conn1.state = strs[2];
conn1.price = Double.parseDouble(strs[3]);
conn1.orderDate = DateUtil.getDateFromString(strs[4], "yyyy-MM-dd");
LongWritable lw = new LongWritable(conn1.orderKey);
arg2.collect(lw, conn1);
} } private static class Conn1 implements WritableComparable<Conn1> {
public long orderKey;
public long customer;
public String state;
public double price;
public java.util.Date orderDate; @Override
public void readFields(DataInput in) throws IOException {
orderKey = in.readLong();
customer = in.readLong();
state = Text.readString(in);
price = in.readDouble();
orderDate = DateUtil.getDateFromString(Text.readString(in),
"yyyy-MM-dd");
} @Override
public void write(DataOutput out) throws IOException {
out.writeLong(orderKey);
out.writeLong(customer);
Text.writeString(out, state);
out.writeDouble(price);
Text.writeString(out, DateUtil.getDateStr(orderDate, "yyyy-MM-dd"));
} @Override
public int compareTo(Conn1 arg0) {
// TODO Auto-generated method stub
return 0;
} } public static class Filter1Mapper extends MapReduceBase implements
Mapper<LongWritable, Conn1, LongWritable, Conn2> { @Override
public void map(LongWritable inKey, Conn1 c2,
OutputCollector<LongWritable, Conn2> collector, Reporter report)
throws IOException {
if (c2.state.equals("F")) {
Conn2 inValue = new Conn2();
inValue.customer = c2.customer;
inValue.orderDate = c2.orderDate;
inValue.orderKey = c2.orderKey;
inValue.price = c2.price;
inValue.state = c2.state;
collector.collect(inKey, inValue);
}
} } private static class Conn2 implements WritableComparable<Conn1> {
public long orderKey;
public long customer;
public String state;
public double price;
public java.util.Date orderDate; @Override
public void readFields(DataInput in) throws IOException {
orderKey = in.readLong();
customer = in.readLong();
state = Text.readString(in);
price = in.readDouble();
orderDate = DateUtil.getDateFromString(Text.readString(in),
"yyyy-MM-dd");
} @Override
public void write(DataOutput out) throws IOException {
out.writeLong(orderKey);
out.writeLong(customer);
Text.writeString(out, state);
out.writeDouble(price);
Text.writeString(out, DateUtil.getDateStr(orderDate, "yyyy-MM-dd"));
} @Override
public int compareTo(Conn1 arg0) {
// TODO Auto-generated method stub
return 0;
} } public static class RegexMapper extends MapReduceBase implements
Mapper<LongWritable, Conn2, LongWritable, Conn3> { @Override
public void map(LongWritable inKey, Conn2 c3,
OutputCollector<LongWritable, Conn3> collector, Reporter report)
throws IOException {
c3.state = c3.state.replaceAll("F", "Find");
Conn3 c2 = new Conn3();
c2.customer = c3.customer;
c2.orderDate = c3.orderDate;
c2.orderKey = c3.orderKey;
c2.price = c3.price;
c2.state = c3.state;
collector.collect(inKey, c2);
}
} private static class Conn3 implements WritableComparable<Conn1> {
public long orderKey;
public long customer;
public String state;
public double price;
public java.util.Date orderDate; @Override
public void readFields(DataInput in) throws IOException {
orderKey = in.readLong();
customer = in.readLong();
state = Text.readString(in);
price = in.readDouble();
orderDate = DateUtil.getDateFromString(Text.readString(in),
"yyyy-MM-dd");
} @Override
public void write(DataOutput out) throws IOException {
out.writeLong(orderKey);
out.writeLong(customer);
Text.writeString(out, state);
out.writeDouble(price);
Text.writeString(out, DateUtil.getDateStr(orderDate, "yyyy-MM-dd"));
} @Override
public int compareTo(Conn1 arg0) {
// TODO Auto-generated method stub
return 0;
} } public static class LoadMapper extends MapReduceBase implements
Mapper<LongWritable, Conn3, LongWritable, Conn3> { @Override
public void map(LongWritable arg0, Conn3 arg1,
OutputCollector<LongWritable, Conn3> arg2, Reporter arg3)
throws IOException {
arg2.collect(arg0, arg1);
} } public static void main(String[] args) {
JobConf job = new JobConf(ProcessSample.class);
job.setJobName("ProcessSample");
job.setNumReduceTasks(0);
job.setInputFormat(TextInputFormat.class);
job.setOutputFormat(TextOutputFormat.class);
JobConf mapper1 = new JobConf();
JobConf mapper2 = new JobConf();
JobConf mapper3 = new JobConf();
JobConf mapper4 = new JobConf();
ChainMapper cm = new ChainMapper();
cm.addMapper(job, ExtractMappper.class, LongWritable.class, Text.class,
LongWritable.class, Conn1.class, true, mapper1);
cm.addMapper(job, Filter1Mapper.class, LongWritable.class, Conn1.class,
LongWritable.class, Conn2.class, true, mapper2);
cm.addMapper(job, RegexMapper.class, LongWritable.class, Conn2.class,
LongWritable.class, Conn3.class, true, mapper3);
cm.addMapper(job, LoadMapper.class, LongWritable.class, Conn3.class,
LongWritable.class, Conn3.class, true, mapper4);
FileInputFormat.setInputPaths(job, new Path("orderData"));
FileOutputFormat.setOutputPath(job, new Path("orderDataOutput"));
Job job1;
try {
job1 = new Job(job);
JobControl jc = new JobControl("test");
jc.addJob(job1);
jc.run();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} }
}
【转】ChainMapper 实例理解二的更多相关文章
- 【转】ChainMapper 实例理解一
通过ChainMapper可以将多个map类合并成一个map任务. 下面个这个例子没什么实际意思,但是很好的演示了ChainMapper的作用. 源文件100 tom 90101 mary 85102 ...
- [学习笔记]一个实例理解Lingo的灵敏性分析
一个实例理解Lingo的灵敏性分析 线性规划问题的三个重要概念: 最优解就是反应取得最优值的决策变量所对应的向量. 最优基就是最优单纯形表的基本变量所对应的系数矩阵如果其行列式是非 ...
- SQL Server 2008 数据库镜像部署实例之二 配置镜像,实施手动故障转移
SQL Server 2008 数据库镜像部署实例之二 配置镜像,实施手动故障转移 上一篇文章已经为配置镜像数据库做好了准备,接下来就要进入真正的配置阶段 一.在镜像数据库服务器上设置安全性并启动数据 ...
- Selenium2学习-022-WebUI自动化实战实例-020-JavaScript 在 Selenium 自动化中的应用实例之二(获取浏览器显示区域大小)
前几篇文章中简略概述了,如何获取.设置浏览器窗口大小,那么我们该如何获取浏览器显示区域的大小呢?此文讲对此进行简略概述,敬请各位小主参阅.若有不足之处,敬请各位大神指正,不胜感激! 获取浏览器显示区域 ...
- python学习_数据处理编程实例(二)
在上一节python学习_数据处理编程实例(二)的基础上数据发生了变化,文件中除了学生的成绩外,新增了学生姓名和出生年月的信息,因此将要成变成:分别根据姓名输出每个学生的无重复的前三个最好成绩和出生年 ...
- SonarQube4.4+Jenkins进行代码检查实例之二
SonarQube4.4+Jenkins进行代码检查实例之二 SonarQube4.4+Jenkins进行代码检查实例之二
- 一些有用的javascript实例分析(二)
原文:一些有用的javascript实例分析(二) 5 求出数组中所有数字的和 window.onload = function () { var oBtn = document.getElement ...
- C语言库函数大全及应用实例十二
原文:C语言库函数大全及应用实例十二 [编程资料]C语言库函数大全及应用实例十二 函数名: setrgbpalette ...
- 通过实例理解 RabbitMQ 的基本概念
先说下自己开发的实例. 最近在使用 Spring Cloud Config 做分布式配置中心(基于 SVN/Git),当所有服务启动后,SVN/Git 中的配置文件更改后,客户端服务读取的还是旧的配置 ...
随机推荐
- linux系统字符集
Linux中中文乱码问题通常是由于字符集与windows不兼容所引起,windows的中文字符集是双字节的GBK编码linux采用的是3字节的utf-8编码,所以在windows下用工具连接linux ...
- mark 一下
Android资源管理框架(Asset Manager)简要介绍和学习计划 http://www.cnblogs.com/hjtdlx/p/4332060.html
- CentOS linux 下eclipse+cdt编译报undefined reffrece to *
- POJ 2771 二分图(最大独立集)
Guardian of Decency Time Limit: 3000MS Memory Limit: 65536K Total Submissions: 5244 Accepted: 21 ...
- EasyMock的原理及使用方法
就不费劲转过来了https://www.ibm.com/developerworks/cn/opensource/os-cn-easymock/这上面介绍的比较全.
- hadoop源码阅读
1.Hadoop的包的功能分析 2.由于Hadoop的MapReduce和HDFS都有通信的需求,需要对通信的对象进行序列化.Hadoop并没有采用java的序列化,而是引入它自己的系统.org.ap ...
- vs 折叠跟展开所有方法。
Ctrl + M + O: 折叠所有方法 Ctrl + M + M: 折叠或者展开当前方法 Ctrl + M + L: 展开所有方法
- 由于lightdm.conf 错误无法进入ubuntu 的办法
由于自己向默认登录GNOME桌面,所以修改了lightdm,由于参数错误,结果无法启动桌面? 这是需要进入shell界面: 1.选择cancel ,如果虚拟机下无法点击cancel按钮,可以使用快捷键 ...
- javascript面向对象知识点
首先,声明何为对象:对象是键值对的集合 其次,声明:变量就是键值对 再次,声明:函数也是变量 1. JavaScript包含:ECMAScript(核心).DOM(文档对象模型)和BOM(浏览器对象模 ...
- char 数组和 int 之间转化
上周工作结束,来到斯凯网络也将近半个月来. 没有新人的感念,最多的是将自己当作一个战士. 废话不多说,直接入正题,在没有仔细考虑问题之前我们总会 觉得:这尼玛的有毛线难度啊,不就是一个 int 转为c ...