526互联

hadoop2.7. 序列化对象

发布时间 2023-07-09 19:36:32作者: 何雪原

1.在hadoop中必须序列化对象后，才能进行网络传输,不使用java序列化的原因是：java序列化对象会添加很多信息，造成对象的字节数变大，hadoop序列化为一种高效的序列化

如果在实际生产中，BooleanWrite、IntWrite，Text，FloatWrite等数据类型无法满足要求，就需要对对象进行序列化，

package com.hxy.mr.xuliehua;

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;
    private Long downFlow;
    private Long sumFlow;

    public FlowBean() {
    }

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

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

    }

    @Override
    public void readFields(DataInput in) throws IOException {
        //反序列化方法 必须与序列化写入顺序是一致的，因为序列化后的数据传输是以管道队列的方式传输的，先进先出；
        upFlow = in.readLong();
        downFlow =in.readLong();
        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;
    }
}