hadoop中序自定义bean对象实现序列化接口

需求分析：如下所示，统计每一个手机号耗费的总上行流量、下行流量、总流量。
数据依次为 id 手机号 ip地址 域名 上行流量 下行流量 状态码

预期的输出格式：
13736230513 2481 24681 27162

案例分析：

代码过程：
1.自定义bean对象：

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;

    // 1 实现writable接口
public class FlowBean implements Writable{

    private long upFlow;
    private long downFlow;
    private long sumFlow;

    //2  反序列化时，需要反射调用空参构造函数，所以必须有一个空参的构造器
    public FlowBean() {
        super();
    }

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

    //3  写序列化方法

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

    //4 反序列化方法,注意反序列化方法读顺序必须和写序列化方法的写顺序必须一致

    public void readFields(DataInput in) throws IOException {
        this.upFlow  = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

    // 5 编写toString方法，方便后续打印到文本
    @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 sum_upFlow, long sum_downFlow) {
        upFlow = sum_upFlow;
        downFlow = sum_downFlow;
        sumFlow = sum_upFlow+sum_downFlow;
    }
    
}

2.Mapper阶段

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

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

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

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

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

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

        // 3 封装对象
       k.set(fields[1]); //手机号作为Key
       v.setUpFlow(Long.parseLong(fields[fields.length-3]));   //上行流量
       v.setDownFlow(Long.parseLong(fields[fields.length-2]));   //下行流量

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

3. Reducer阶段

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

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

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

        long sum_upFlow = 0;
        long sum_downFlow = 0;

        // 1 遍历所用bean，将其中的上行流量，下行流量分别累加，因为可能出现同一个手机号
        for (FlowBean flowBean : values) {
            sum_upFlow += flowBean.getUpFlow();
            sum_downFlow += flowBean.getDownFlow();
        }

        // 2 封装对象
        FlowBean bean = new FlowBean(sum_upFlow, sum_downFlow);
        bean.set(sum_upFlow,sum_downFlow);

        // 3 写出
        context.write(key, bean);
    }
}

4. 驱动类

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 FlowsumDriver {

    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[] { "e:/bean/bean.txt", "e:/output1" };

        // 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(FlowsumDriver.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);
    }
}

运行后截图，这里可以看到程序已经按照我们预期的结果输出：