Hadoop 自定义序列化MapReduce实战

Posted 2021-09-06 阳光大男孩!

前言

我笑了，跑个mapReduce，执行了三十秒

自定义序列化

这次实现手机号上行下行流量的求和，模拟使用MapReduce实现

Bean

import org.apache.hadoop.io.Writable;

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

//1 继承 Writable 接口
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

    //2 提供无参构造
    public FlowBean() {
    }

    //3 提供三个参数的 getter 和 setter 方法
    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;
    }

    //4 实现序列化和反序列化方法,注意顺序一定要保持一致
    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

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

    //5 重写 ToString
    @Override
    public String toString() {
        return upFlow + "\\t" + downFlow + "\\t" + sumFlow;
    }
}

Mapper——处理的是每行数据

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

import java.io.IOException;

public class FlowMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
    // 输入的value
    private Text outK = new Text();
    // 输出的value
    private FlowBean outV = new FlowBean();

    @Override
    protected void map(LongWritable key, Text value, Mapper.Context context)
            throws IOException, InterruptedException {
        //1 获取一行数据,转成字符串
        // 18833025128 100 200
        String line = value.toString();
        //2 切割数据
        String[] split = line.split(" ");
        //3 抓取我们需要的数据:手机号,上行流量,下行流量
        String phone = split[0];
        String up = split[1];
        String down = split[2];
        //4 封装 outK outV
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow(Long.parseLong(up)+Long.parseLong(down));
        System.out.println("mapper.................结束");
        System.out.println(outV);
        //5 写出 outK outV
        context.write(outK, outV);
    }
}

Reducer——对Mapper的将结果进行整合

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


public class FlowReducer extends Reducer<Text,FlowBean, Text,FlowBean> {
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
       // 给定的是key以及集合的累加
        FlowBean flowBean = new FlowBean();
        long upFlow = 0;
        long downFlow = 0;
        long sumFlow = 0;
        for (FlowBean f:values){
            upFlow +=f.getUpFlow();
            downFlow +=f.getDownFlow();
            sumFlow +=f.getSumFlow();
        }
        flowBean.setUpFlow(upFlow);
        flowBean.setDownFlow(downFlow);
        flowBean.setSumFlow(sumFlow);

        System.out.println("reducer................结束");
        System.out.println(flowBean);
        context.write(key,flowBean);
    }
}

Driver——任务驱动类，用于执行任务

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.FileOutputStream;
import java.io.IOException;


public class FlowDriver {
    // 这里为了直观显示参数 使用了硬编码的形式，实际开发中可以通过外部传参
    private static final String HDFS_URL = "hdfs://192.168.56.80:9000";
    private static final String HADOOP_USER_NAME = "root";

    // 需要打包并在服务器上执行  hadoop jar hadoop-word-count-1.0.jar  com.heibaiying.flow.FlowDriver
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 获取job
        Configuration configuration = new Configuration();
        System.setProperty("HADOOP_USER_NAME", HADOOP_USER_NAME);
        // 指明HDFS的地址
        configuration.set("fs.defaultFS", HDFS_URL);
        Job job = Job.getInstance(configuration);
        // 设置jar
        job.setJarByClass(FlowDriver.class);
        // 关键mapper、reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
        // 设置mapper输出的key和value
        job.setMapOutputKeyClass(Text.class);

        job.setOutputValueClass(FlowBean.class);
        // 设置最终输出的key、value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        FileInputFormat.setInputPaths(job,new Path("/test/text.txt"));
        FileOutputFormat.setOutputPath(job,new Path("/test/text1.txt"));
        boolean b = job.waitForCompletion(true);
        System.out.println(b);
    }
}

测试

准备文件text.txt，内容为18888888 100 200
需要打包到hadoop集群上，执行

hadoop jar hadoop-word-count-1.0.jar  com.heibaiying.flow.FlowDriver

输出为自定义bean