Hadoop序列化（含案例）

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（implements Writable）
（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) {
	return this.sumFlow > o.getSumFlow() ? -1 : 1;
}

3. 序列化案例实操（MapReduce程序）

（1）编写流量统计的Bean对象

package flowsum;

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


    //空参构造，为了后续反射用
    public FlowBean() {
        super();
    }

    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 {
        //必须和序列化一致
       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;
    }

    public void set(long upFlow1, long downFlow1) {
        upFlow = upFlow1;
        downFlow = downFlow1;
        sumFlow = upFlow1 + downFlow1;
    }
}

（2）编写Mapper类

package flowsum;

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> {

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

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

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

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

        //3.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);
//        v.set(upFlow,downFlow);

        //4.写出
        context.write(k,v);

    }
}

（3）编写Reducer类

package flowsum;

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

import java.io.IOException;

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

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

        //1.累加求和
        long sum_upFlow = 0;
        long sum_downFlow = 0;
        for (FlowBean value : values){
            sum_upFlow += value.getUpFlow();
            sum_downFlow += value.getDownFlow();
        }

        v.set(sum_upFlow,sum_downFlow);

        //2.写出
        context.write(key,v);

    }
}

（4）编写Driver驱动类

package flowsum;

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

        args = new String[]{"f:/MR_IO/input","f:/MR_IO/output_Flo"};
        //1.获取Job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2设置jar路径
        job.setJarByClass(FlowCountDriver.class);

        //3.关联Mapper和Reducer
        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountReduce.class);

        //4.设置Mapper输出的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //5.设置最终输出的key和value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //6.设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //7.提交Job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);

    }
}