Hadoop_MapReduc Writable案例

项目的其他文件已在WordCount案例中完成了

只需完成FlowBean类型文件和对其中的Mapper,Reducer,Driver文件进行修改即可

FlowBean.java

package org.cheetah.mapreduce.writable;

import org.apache.hadoop.io.Writable;

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

/**
 * 1、定一个类实现writable接口
 * 2、重写序列化和反序列化接口
 * 3、重写空参构造
 * 4、toString方法
 */
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

    public FlowBean() {
    }

    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 void write(DataOutput out) throws IOException {

        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);

    }

    @Override
    public void readFields(DataInput in) throws IOException {

        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

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

FlowMapper.java

package org.cheetah.mapreduce.writable;

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> {

    private Text outK = new Text();
    private FlowBean outV = new FlowBean();

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, FlowBean>.Context context) throws IOException, InterruptedException {

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

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

        //3、抓取想要的数据
        String phone = split[1];
        String up = split[split.length - 2];
        String down = split[split.length - 1];

        //4、封装
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();//在bean中自动相加了

        //5、写出
        context.write(outK,outV);
    }
}

FlowReducer

package org.cheetah.mapreduce.writable;

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

        //1 便利集合累加值
        long totalUp=0;
        long totalDown=0;
        for (FlowBean value : values) {
            totalUp+=value.getUpFlow();
            totalDown+=value.getDownFlow();
        }

        //2 封装outK，outV
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();

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

FlowDriver

package org.cheetah.mapreduce.writable;

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

        //1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2 获取jar包
        job.setJarByClass(FlowDriver.class);

        //3 关联mapper 和 reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4 设置mapper 输出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 数值数据的输入路径和输出路径
        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);
    }
}

 

之后打包，扔到服务器上，测试即可