Hadoop的序列化和反序列化

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。
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。
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）。
4）Hadoop 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

我们以统计手机的流量为例，去写一个例子

1	13736230513	192.196.100.1	www.atguigu.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.atguigu.com	1527	2106	200
6 	84188413	192.168.100.3	www.atguigu.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.atguigu.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

首先创建一个Maven工程

 

设置maven配置

  然后我们添加对应的jar包

<dependencies>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>3.1.3</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.12</version>
        <scope>test</scope>
    </dependency>
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-log4j12</artifactId>
        <version>1.7.30</version>
    </dependency>
</dependencies>

然后创建bean对象

package com.gk.mapreduce;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
 * create with IntelliJ IDEA
 *
 * @Project :hadoop-writable
 * @Package :com.gk.mapreduce
 * @ClassName :
 * @CreateTime :2022/3/919:38
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 **/
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

    // 提供无参构造
    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.upFlow + this.downFlow;
    }

    // 实现序列化和反序列化方法，注意顺序一定要保存一致
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();
    }

    // 重写toString方法
    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

创建Mapper

package com.gk.mapreduce;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * create with IntelliJ IDEA
 *
 * @Project :hadoop-writable
 * @Package :com.gk.mapreduce
 * @ClassName :
 * @CreateTime :2022/3/919:44
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 **/
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, Context context) throws IOException, InterruptedException {

        // 1.获取一行数据
        String line = value.toString();

        // 2.切割数据
        String[] split = line.split("\t");

        // 3.抓取我们需要的数据：手机号，上行流量，下行流量
        String phone = split[1];
        String upFlow = split[split.length - 3];
        String downFlow = split[split.length - 2];
        
        // 4.封装outK，outV
        outK.set(phone);
        outV.setUpFlow(Long.valueOf(upFlow));
        outV.setDownFlow(Long.valueOf(downFlow));
        outV.setSumFlow();
        
        // 5.写出
        context.write(outK,outV);
    }
}

编写Reducer

package com.gk.mapreduce;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * create with IntelliJ IDEA
 *
 * @Project :hadoop-writable
 * @Package :com.gk.mapreduce
 * @ClassName :
 * @CreateTime :2022/3/919:51
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 **/
public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
    private FlowBean outV = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {

        long upFlow = 0;
        long downFlow = 0;

        // 1.遍历获取数据
        for (FlowBean value : values) {
            upFlow += value.getUpFlow();
            downFlow += value.getDownFlow();
        }
        
        // 2.封装outV
        outV.setUpFlow(upFlow);
        outV.setDownFlow(downFlow);
        outV.setSumFlow();
        
        // 3.写出
        context.write(key,outV);
    }
}

编写Driver

package com.gk.mapreduce;

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;

/**
 * create with IntelliJ IDEA
 *
 * @Project :hadoop-writable
 * @Package :com.gk.mapreduce
 * @ClassName :
 * @CreateTime :2022/3/919:56
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 **/
public class FlowDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 1.获取job
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2.读取jar包
        job.setJarByClass(FlowDriver.class);

        // 3.连接mapper和reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        // 4.mapper的输出格式
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        // 5.最终结果的输出格式
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        // 6.输入文件和输出文件路径
        FileInputFormat.setInputPaths(job, new Path("E:\\SGG-Hadoop\\wcInput"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\SGG-Hadoop\\wcOutput"));

        // 7.提交job
        boolean flag = job.waitForCompletion(true);
        System.exit(flag ? 0 : 1);

    }
}

现在让我们去执行以下main方法

 

 

 

 大家可以去对比一下数据，已经将对应号码的流量进行相加减