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

  1. 【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 ...

  2. [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 ...

  3. 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 ...

  4. 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 ...

  5. 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 ...

  6. 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

  7. 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 ...

  8. 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 ...

  9. 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

  1. php include

    get_include_path  获取当前 include_path 配置选项的值,在当前代码目录未找到include文件时,则到include_path去include. set_include_ ...

  2. Octopus系列之接下来的任务

    更新默认国家[已实现] 更新每页显示条数的后台控制[已实现] 更新国家和区域的Ajax的关联[已实现] 更新详情页面的 属性选择 脚本提示[已实现 可以做到和兰亭一样的效果了] 增加优惠方案的设置和批 ...

  3. Jsp页面中使用fckeditor控件的两种方法 [转]

    fckeditor控件请到官方网站下载http://www.fckeditor.net,本例主要用到FCKeditor_2.6.3.zip.fckeditor-java-demo-2.4.1.zip. ...

  4. redhat enterprixe 5.0 下DHCP服务器rpm安装配置及其测试

    一.了解DHCP DHCP服务提供动态指定IP地址和配置参数的机制.有动态和静态两种方式. 二.rpm安装 因为配过Samba,所以感觉挺简单. 首先找到主程序和几个附属程序的rpm的安装包.应该都是 ...

  5. WordPress的神器

    导读 Markdown 是一种简单的标记语言,旨在帮助你花费更小的代价来格式化纯文本文档.在 WordPress 下你可以使用 HTML 或者可视化编辑器来格式化你的文档,但是使用 markdown ...

  6. 二模 (9)day1

    第一题: 题目大意: 给出一个n位01串,要么不动它,要么把它删掉一个字符,要么插入一个字符(0或1),要么把一个1变成0,.使得有1的位置号的总和是n+1的倍数,或者是0. 解题过程: 1.直接枚举 ...

  7. SWPFILE实现(增加swap空间)

    1.mkdir /var/swap chmod  700  /var/swap(可以不用设置) 2.dd if=/dev/zero of=/var/swap/file bs=1024 count=65 ...

  8. Linux访问Windows磁盘实现共享

    业务需求说明:公司在部署hadoop集群和DB server与SAN存储,公司的想法是前端通过DB Server能够将非结构化的数据能放进SAN存储当中,而hadoop集群也能够访问这个SAN存储.因 ...

  9. ajax 中的一些方法应用

    <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...

  10. Android USB Connections Explained: MTP, PTP, and USB Mass Storage

    Android USB Connections Explained: MTP, PTP, and USB Mass Storage Older Android devices support USB ...