MapReduce2_序列化

MapReduce2_序列化

---

---

1. Hadoop序列化

1.1 和Java序列化比较

Java的序列化框架Serializable序列化一个对象之后会附带很多额外的信息，比如校验信息，Header，继承体系等，不利于在网络中传输。

Hadoop的序列化机制Writable

• 紧凑：省空间
• 快速：额外开销小
• 互操作：多语言交互

1.2 bean对象实现序列化接口

1. 实现Writable接口
2. 创建空参构造
   • 反序列化时，需要反射调用空参构造，所以必须有
3. 重写序列化方法
4. 重写反序列化方法
5. 注意反序列化的顺序和序列化完全一致
6. 要想把结果显示在文件中，需要重写toString，可用\t分开，方便使用
7. 如果需要将自定义的bean放在key中传输，则还需要实现Comparable，因为MapReduce框中的Shuffle过程要求对key必须能排序

2. 上下行流量统计案例

2.1 项目目的

将txt文件数据进行分割，统计每个手机号的上行流量，下行流量，总流量

2.2 思路

将手机号，上行流量，下行流量，总流量四个属性封装成一个FlowBean对象

Map阶段对每行数据进行切分

Reduce阶段对数据进行累加

注意的点：

因为需要Map阶段向Reduce阶段传输，所以需要对FlowBean对象进行序列化

2.3 代码实现

2.3.1 FlowBean

实现hadoop.io.Writable接口

重写write()方法和readFields()方法，注意写和读属性的顺序应一致

留出空参构造器

重写toString方法，方便Map阶段切分

package edu.tyut.mapreduce.writbale;

import org.apache.hadoop.io.Writable;

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

/**
 * @author Ricardo Jia
 * @description
 * @since 2021-08-17
 */
public class FlowBean implements Writable {
    private long upFlow;//上传流量
    private long downFlow;//下载流量
    private long sumFlow;//总流量

    public FlowBean() {
    }

    @Override
    public void write(DataOutput out) throws IOException {
       out.writeLong(upFlow);
       out.writeLong(downFlow);
       out.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        //注意读的顺序和写的顺序保持一致
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

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

2.3.2 FlowMapper

继承hadoop.mapreduce.Mapper类

重写map方法

package edu.tyut.mapreduce.writbale;

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

import java.io.IOException;

/**
 * @author Ricardo Jia
 * @description
 * @since 2021-08-17
 */
public class FlowMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
    private final Text outK = new Text();
    private final FlowBean outV = new FlowBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行数据，转成字符串
        String line = value.toString();
        //切割数据
        String regex = "\t";
        String[] split = line.split(regex);
        //抓取需要的手机号，上行流量，下行流量
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length -2];
        //设置outK，outV值
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();
        //封装outK,outV
        context.write(outK,outV);
    }
}

2.3.3 FlowReducer

继承hadoop.mapreduce.Reducer类

重写reduce方法

package edu.tyut.mapreduce.writbale;

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

import java.io.IOException;

/**
 * @author Ricardo Jia
 * @description
 * @since 2021-08-17
 */
public class FlowReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
    private final FlowBean outV = new FlowBean();
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Reducer<Text, FlowBean, Text, FlowBean>.Context context) throws IOException, InterruptedException {
        long totalUp = 0;
        long totalDown = 0;
        //遍历values，将上行流量和下行流量进行累加
        for (FlowBean value : values) {
            totalUp += value.getUpFlow();
            totalDown += value.getDownFlow();
        }
        //设置outKV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();
        //封装outK和outV
        context.write(key, outV);
    }
}

2.3.4 FlowDriver

1. 获取job对象，设置configuration信息
2. 设置运行的jar包的启动类
3. 关联Mapper和Reducer
4. 设置map的输入和输出类型
5. 关联最终输出的KV类型
6. 设置程序最终输入输出路径
7. 提交job

package edu.tyut.mapreduce.writbale;

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 Ricardo Jia
 * @description
 * @since 2021-08-17
 */
public class FlowDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //获取job对象
        Configuration conf  = new Configuration();
        Job job = Job.getInstance(conf);
        //关联Driver类
        job.setJarByClass(FlowDriver.class);
        //关联Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        //设置Map端输出KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        //设置最终输出的KV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //设置程序最终输入输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\dev\\hadoop\\phone_data.txt"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\dev\\hadoop\\FlowOutput"));
        //提交job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

3. 运行结果