Hadoop-23、Hadoop序列化

准备处理的txt文档

1	13736230513	192.196.100.1	www.atguigu.com	2481	24681	200
2	13846544121	192.196.100.2			264	0	200
3 	13956435636	192.196.100.3			132	1512	200
4 	13966251146	192.168.100.1			240	0	404
5 	18271575951	192.168.100.2	www.atguigu.com	1527	2106	200
6 	84188413	192.168.100.3	www.atguigu.com	4116	1432	200
7 	13590439668	192.168.100.4			1116	954	200
8 	15910133277	192.168.100.5	www.hao123.com	3156	2936	200
9 	13729199489	192.168.100.6			240	0	200
10 	13630577991	192.168.100.7	www.shouhu.com	6960	690	200
11 	15043685818	192.168.100.8	www.baidu.com	3659	3538	200
12 	15959002129	192.168.100.9	www.atguigu.com	1938	180	500
13 	13560439638	192.168.100.10			918	4938	200
14 	13470253144	192.168.100.11			180	180	200
15 	13682846555	192.168.100.12	www.qq.com	1938	2910	200
16 	13992314666	192.168.100.13	www.gaga.com	3008	3720	200
17 	13509468723	192.168.100.14	www.qinghua.com	7335	110349	404
18 	18390173782	192.168.100.15	www.sogou.com	9531	2412	200
19 	13975057813	192.168.100.16	www.baidu.com	11058	48243	200
20 	13768778790	192.168.100.17			120	120	200
21 	13568436656	192.168.100.18	www.alibaba.com	2481	24681	200
22 	13568436656	192.168.100.19			1116	954	200

建立四个class文件，FlowBean、FlowDriver、FlowMapper、FlowReducer
FlowBean.class

package com.atguigu.flow;

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;
    private long downFlow;
    private long sumFlow;

    public FlowBean() {

    }

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

    public void set(long upFlow, long downFlow){
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }


    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;
    }


    /**
     * 序列方法 Out 框架给我们提供的数据出口
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

    /**
     *
     * @param in 框架提供的数据来源
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }
}

FlowDriver.class

package com.atguigu.flow;

import javafx.scene.text.Text;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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, ClassNotFoundException, InterruptedException {
        //1.获取Job实例
        Job job = Job.getInstance(new Configuration());

        //2. 设置类路径
        job.setJarByClass(FlowDriver.class);

        //3. 设置Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4. 设置输入输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //5. 设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        //6 提交
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0:1);
    }
}

FlowMapper.class

package com.atguigu.flow;


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 phone = new Text();
    private FlowBean flow = new FlowBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");
        //System.out.println(fields);
        phone.set(fields[1]);
        long upFlow = Long.parseLong(fields[fields.length - 3]);
        //System.out.println(upFlow);
        long downFlow = Long.parseLong(fields[fields.length - 2]);
        flow.set(upFlow,downFlow);
        context.write(phone, flow);
    }
}

FlowReducer.class

package com.atguigu.flow;

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 sumFlow = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        long sumUpFlow = 0;
        long sumDownFlow = 0;
        for (FlowBean value : values){
            sumUpFlow += value.getUpFlow();
            sumDownFlow += value.getDownFlow();
        }
        sumFlow.set(sumUpFlow, sumDownFlow);
        context.write(key, sumFlow);
    }
}