大数据hadoop3.1.3——Hadoop序列化以及案例操作

1、序列化概述

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。

  @Override
  public int compareTo(FlowBean o)
  {
     //倒序排列，从大到小
     return this.sumFlow > o.getSumFlow() ? -1 : 1;
  }    

3 序列化案例实操

2．需求分析

3．编写MapReduce程序

（1）编写流量统计的Bean对象

package com.caron.mr.writable;

import org.apache.hadoop.io.Writable;

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

/**
 * @author Caron
 * @create 2020-04-16-20:11
 * @Description
 * @Version
 */
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 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;
    }
    /**
     * 重写toString方法
     * @return
     */
    @Override
    public String toString() {
        return this.upFlow + "/t" + this.downFlow + "/t" + this.sumFlow;
    }
    /**
     * 提供无参构造器，反序列化会反射调用
     */
    public FlowBean() { }
    /**
     *  序列化方法
     * @param dataOutput
     * @throws IOException
     */
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }
    /**
     *  反序列化方法
     * @param dataInput
     * @throws IOException
     */
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();
    }
}

（2）编写Mapper类

package com.caron.mr.writable;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
 * @author Caron
 * @create 2020-04-16-20:11
 * @Description
 * @Version
 */
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 {
        //处理一行数据
        String line = value.toString();
        //切割数据
        String[] splits = line.split("\t");
        //封装key
        outK.set(splits[1]);
        //封装value
        outV.setUpFlow(Long.parseLong(splits[splits.length-3]));
        outV.setDownFlow(Long.parseLong(splits[splits.length-2]));
        outV.getSumFlow();
        //写出
        context.write(outK,outV);
    }
}

（3）编写Reducer类

package com.caron.mr.writable;

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

import java.io.IOException;

/**
 * @author Caron
 * @create 2020-04-16-20:11
 * @Description
 * @Version
 */
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 {
        //总上行
        long totalUpFlow = 0;
        //总下行
        long totalDownFlow = 0;
        //总流量
        long totalSumFlow = 0;
        //处理一个手机号的
        for (FlowBean flowBean :
                values) {
            totalUpFlow += flowBean.getUpFlow();
            totalDownFlow += flowBean.getDownFlow();
            totalSumFlow += flowBean.getSumFlow();
        }
        //封装
        outV.setUpFlow(totalUpFlow);
        outV.setDownFlow(totalDownFlow);
        outV.setSumFlow(totalSumFlow);
        //写出
        context.write(key,outV);
    }
}

（4）编写Driver驱动类

package com.caron.mr.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 Caron
 * @create 2020-04-16-20:11
 * @Description
 * @Version
 */
public class FlowDrriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        job.setJarByClass(FlowDrriver.class);
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        FileInputFormat.setInputPaths(job,new Path("F:/input/in.txt"));
        FileOutputFormat.setOutputPath(job,new Path("F:/output"));
        job.waitForCompletion(true);
    }
}