@[toc]
12.Hadoop序列化
12.1序列化概述
12.1.1什么是序列化
序列化就是把内存中的对象,转换成字节序列
(或其他数据传输协议)以便于存储到磁盘(持久化)和网络传输。
反序列化就是将收到字节序列(或其他数据传输协议)或者是磁盘的持久化数据,转换成内存中的对象。
12.1.2为什么要序列化
一般来说,“活的”对象只生存在内存里,关机断电就没有了。而且“活的”对象只能由本地的进程使用,不能被发送到网络上的另外一台计算机。 然而序列化可以存储“活的”对象,可以将“活的”对象发送到远程计算机。
12.1.3为什么不用Java的序列化
Java的序列化是一个重量级序列化框架(Serializable)
,一个对象被序列化后,会附带很多额外的信息(各种校验信息,Header,继承体系等),不便于在网络中高效传输。所以,Hadoop自己开发了一套序列化机制(Writable)。
12.1.4Hadoop序列化特点:
(1)紧凑 :高效使用存储空间。
(2)快速:读写数据的额外开销小。
(3)互操作:支持多语言的交互
12.2自定义bean对象实现序列化接口(Writable)
在企业开发中往往常用的基本序列化类型不能满足所有需求,比如在Hadoop框架内部传递一个bean对象,那么该对象就需要实现序列化接口。
具体实现bean对象序列化步骤如下7步。
(1)必须实现Writable接口
(2)反序列化时,需要反射调用空参构造函数,所以必须有空参构造
public FlowBean() {
super();
}
(3)重写序列化方法
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
(4)重写反序列化方法
@Override
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
downFlow = in.readLong();
sumFlow = in.readLong();
}
(5)注意反序列化的顺序和序列化的顺序完全一致
(6)要想把结果显示在文件中,需要重写toString(),可用"\t"分开,方便后续用。
(7)如果需要将自定义的bean放在key中传输,则还需要实现Comparable接口,因为MapReduce框中的Shuffle过程要求对key必须能排序。详见后面排序案例。
@Override
public int compareTo(FlowBean o) {
// 倒序排列,从大到小
return this.sumFlow > o.getSumFlow() ? -1 : 1;
}
12.3序列化案例实操
12.3.1需求
统计每一个手机号耗费的总上行流量、总下行流量、总流量
(1)输入数据
1 13736230513 192.196.100.1 www.baidu.com 2481 24681 200
2 13846544121 192.196.100.2 264 0 200
3 13956435636 192.196.100.3 132 1512 200
4 13966251146 192.168.100.1 240 0 404
5 18271575951 192.168.100.2 www.baidu.com 1527 2106 200
6 84188413 192.168.100.3 www.baidu.com 4116 1432 200
7 13590439668 192.168.100.4 1116 954 200
8 15910133277 192.168.100.5 www.hao123.com 3156 2936 200
9 13729199489 192.168.100.6 240 0 200
10 13630577991 192.168.100.7 www.shouhu.com 6960 690 200
11 15043685818 192.168.100.8 www.baidu.com 3659 3538 200
12 15959002129 192.168.100.9 www.baidu.com 1938 180 500
13 13560439638 192.168.100.10 918 4938 200
14 13470253144 192.168.100.11 180 180 200
15 13682846555 192.168.100.12 www.qq.com 1938 2910 200
16 13992314666 192.168.100.13 www.gaga.com 3008 3720 200
17 13509468723 192.168.100.14 www.qinghua.com 7335 110349 404
18 18390173782 192.168.100.15 www.sogou.com 9531 2412 200
19 13975057813 192.168.100.16 www.baidu.com 11058 48243 200
20 13768778790 192.168.100.17 120 120 200
21 13568436656 192.168.100.18 www.alibaba.com 2481 24681 200
22 13568436656 192.168.100.19 1116 954 200
(2)输入数据格式:
7 13560436666 120.196.100.99 1116 954 200
id 手机号码 网络ip 上行流量 下行流量 网络状态码
(3)期望输出数据格式
13560436666 1116 954 2070
手机号码 上行流量 下行流量 总流量
12.3.2需求分析
12.3.3编写MapReduce程序
穿创建一个包 com.summer.mapreduce.writable,然后创建一个java程序,FlowBean
12.3.3.1编写流量统计的Bean对象
package com.summer.mapreduce.writable;
/**
* @author Redamancy
* @create 2022-08-23 11:26
*/
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
* 1、定义类实现writable接口
* 2、重写序列化和反序列化
* 3、重写空参构造
* 4、toString方法
*/
public class FlowBean implements Writable {
private long upFlow;//上行流量
private long downFlow;//下行流量
private long sumFlow;//总流量
//空参构造
public FlowBean() {
}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getDownFlow() {
return downFlow;
}
public void setDownFlow(long downFlow) {
this.downFlow = downFlow;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
public void setSumFlow() {
this.sumFlow = this.downFlow + this.upFlow;
}
@Override
public void write(DataOutput dataOutput) throws IOException {
dataOutput.writeLong(upFlow);
dataOutput.writeLong(downFlow);
dataOutput.writeLong(sumFlow);
}
@Override
public void readFields(DataInput dataInput) throws IOException {
this.upFlow = dataInput.readLong();
this.downFlow = dataInput.readLong();
this.sumFlow = dataInput.readLong();
}
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
}
12.3.3.2编写Mapper类
创建一个FlowMapper类
package com.summer.mapreduce.writable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* @author Redamancy
* @create 2022-08-23 22:40
*/
public class FlowMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
private Text outK = new Text();
private FlowBean outV = new FlowBean();
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, FlowBean>.Context context) throws IOException, InterruptedException {
//1 获取一行
//1 13736230513 192.196.100.1 www.baidu.com 2481 24681 200
String line = value.toString();
//2 切割
//1,13736230513,192.196.100.1,www.baidu.com,2481,24681,200
//2,13846544121,192.196.100.2,264,0,200
String[] split = line.split("\t");
//3 抓取想要的数据
//因为数据有些有网址,有些没有网址,所有从往后前数是最合适的
//手机号13736230513
//上行流量和下行流量:2481,24681
String phone = split[1];
String up = split[split.length - 3];
String down = split[split.length - 2];
//4 封装
outK.set(phone);
outV.setUpFlow(Long.parseLong(up));
outV.setDownFlow(Long.parseLong(down));
outV.setSumFlow();
//5 写出
context.write(outK, outV);
}
}
12.3.3.3编写Reducer类
创建一个FlowReducer类
package com.summer.mapreduce.writable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* @author Redamancy
* @create 2022-08-23 22:58
*/
public class FlowReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
private FlowBean outV = new FlowBean();
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Reducer<Text, FlowBean, Text, FlowBean>.Context context) throws IOException, InterruptedException {
//1 遍历集合累加值
long totalUp = 0;
long totalDown = 0;
for (FlowBean value : values) {
totalUp += value.getUpFlow();
totalDown += value.getDownFlow();
}
//2 封装outK,outV
outV.setUpFlow(totalUp);
outV.setDownFlow(totalDown);
outV.setSumFlow();
//3 写出
context.write(key,outV);
}
}
12.3.3.4编写Driver驱动类
创建一个FlowDriver类
package com.summer.mapreduce.writable;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
/**
* @author Redamancy
* @create 2022-08-23 23:05
*/
public class FlowDriver {
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
//1 获取job
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 设置jar包路径
job.setJarByClass(FlowDriver.class);
//3 关联mapper和reduccer
job.setMapperClass(FlowMapper.class);
job.setReducerClass(FlowReducer.class);
//4 设置map输出的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
//5 设置最终输出的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
//6 设置输入路径和输出路径
FileInputFormat.setInputPaths(job, new Path("D:\\Acode\\Hadoop\\input\\Flowphonedata"));
//输出的路径为空,要是有该文件,则会报错
FileOutputFormat.setOutputPath(job, new Path("D:\\Acode\\Hadoop\\output\\outputFlowphonedata"));
//7 提交job
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}