MapReduce 的序列化介绍_mapreduce的序列化-优快云博客

本文链接：https://blog.youkuaiyun.com/weixin_44480009/article/details/138369564

一、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。

二、与 Java 序列化比较

Java 序列化是一个重量级序列化框架（Serializable），通过实现 Serializable 接口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），所以不便于在网络中高效传输。
Hadoop序列化（Writable）特点：
- 紧凑：高效使用存储空间。
- 快速：读写数据的额外开销小。
- 互操作：支持多语言的交互

三、Hadoop 序列化的实现步骤

定义一个 bean 类并实现 Writable 接口
重写序列化方法 write()
重写反序列化方法 readFields()
定义一个空参构造方法，反序列化时需要反射调用
重写 toString 方法
若该 bean 需要作为 MapReduce 的 key 使用，则需要实现 Comparable 接口并重写 compareTo 方法
注意：序列化方法和反序列化方法的写读顺序必须完全一致

四、入门案例

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

id   手机号        网络IP           域名         上行流量  下行流量  网络状态码   
1	13736230513	192.196.100.1	www.apple.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.apple.com	1527	2106	200
6 	84188413	192.168.100.3	www.apple.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.apple.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. 定义 Bean 类

实现 Hadoop 序列化接口 Writable

import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

//1 实现 Writable 接口
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

    //2 提供无参构造
    public FlowBean() {}

    //3 提供三个属性的getter和setter方法
    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;
    }

    //4 实现序列化和反序列化方法，注意属性的写读顺序一定要保持一致
    @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();
    }

    //5 重写 toString 方法
    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

3. 定义 Mapper 类

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

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,转成字符串
        String line = value.toString();

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

        //3 抓取需要的数据:手机号,上行流量,下行流量
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];

        //4 封装 outK 和 outV
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();

        //5 写出 outK 和 outV
		context.write(outK, outV);
    }
}

4. 定义 Reducer 类

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

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 totalUp = 0;
        long totalDown = 0;

        //1 遍历values,将其中的上行流量,下行流量分别累加
        for (FlowBean flowBean : values) {
            totalUp += flowBean.getUpFlow();
            totalDown += flowBean.getDownFlow();
        }

        //2 封装outV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();

        //3 写出outK 和 outV
		context.write(key,outV);
    }
}

5. 定义 Driver 类

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;

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

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

        //2 关联Driver类
		job.setJarByClass(FlowDriver.class);

        //3 关联Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4 设置Map端输出KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //5 设置程序最终输出的KV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //6 设置程序的输入输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\inputflow"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\flowoutput"));

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