Hadoop序列化

Hadoop序列化

概述

1. 序列化

   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

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。

4. Hadoop序列化特点

   • 紧凑：高效实用存储空间
   • 快速：读写数据的额外开销小
   • 可扩展：可随着通讯协议的升级而升级
   • 互操作：支持多语言交互

实现

自定义bean对象实现序列化接口（Writable）

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();
   }
   

   注：重写的序列化方法和反序列化方法顺序完全一致：因为服务器交互的通道类似于队列模式，因此需要有相同顺序

5. 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

6. 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;
   }
   

案例代码

序列化Bean对象

package com.mr.flowcount;

import org.apache.hadoop.io.Writable;

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

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

    public FlowBean() {
    }

    public FlowBean(long upFlow, long downFlow) {
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        sumFlow = upFlow + downFlow;
    }

    //序列化方法
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    //反序列化方法
    @Override
    public void readFields(DataInput in) throws IOException {
        //必须要求和序列化方法顺序一致
        long upFlow = in.readLong();
        long downFlow = in.readLong();
        long sumFlow = in.readLong();
    }

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

    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;
    }
}

Mapper

package com.mr.flowcount;

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

import java.io.IOException;

public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        Text k = new Text();
        FlowBean v = new FlowBean();

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

        //用\t切割
        String[] fields = line.split("\t");

        //封装对象
        k.set(fields[1]);//封装手机号

        long upFlow = Long.parseLong(fields[fields.length - 3]);
        long downFlow = Long.parseLong(fields[fields.length - 2]);

        v.setUpFlow(upFlow);
        v.setDownFlow(downFlow);

        //写出
        context.write(k,v);
    }
}

Reducer

package com.mr.flowcount;

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

import java.io.IOException;

public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean> {

    FlowBean v = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        
        long sum_upFlow = 0;
        long sum_downFlow = 0;

        //累加求和
        for (FlowBean flowBean : values) {
            sum_upFlow += flowBean.getUpFlow();
            sum_downFlow += flowBean.getDownFlow();
        }

        v.setSumFlow(sum_upFlow + sum_downFlow);

        //写出
        context.write(key, v);
    }
}

Driver

package com.mr.flowcount;
import java.io.IOException;
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;

public class FlowCountDriver {

	public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
		
		// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
		args = new String[] { "D:/MyFile/Document/learning/Hadoop/codetest/input2", 			"D:/MyFile/Document/learning/Hadoop/codetest/output2" };

		// 1 获取配置信息，或者job对象实例
		Configuration configuration = new Configuration();
		Job job = Job.getInstance(configuration);

		// 6 指定本程序的jar包所在的本地路径
		job.setJarByClass(FlowCountDriver.class);

		// 2 指定本业务job要使用的mapper/Reducer业务类
		job.setMapperClass(FlowCountMapper.class);
		job.setReducerClass(FlowCountReducer.class);

		// 3 指定mapper输出数据的kv类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(FlowBean.class);

		// 4 指定最终输出的数据的kv类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowBean.class);
		
		// 5 指定job的输入原始文件所在目录
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		// 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
		boolean result = job.waitForCompletion(true);
		System.exit(result ? 0 : 1);
	}
}