IDEA手写自定义bean对象实现序列化接口Writable

评论

需求：统计每一个手机号耗费的总上行流量、下行流量、总流量

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
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

输入数据格式：
1
2
7 	13560436666	120.196.100.99		1116		 954			200
id	手机号码		网络ip			上行流量  下行流量     网络状态码

期望输出数据格式：
1
2
13560436666 		1116		      954 			2070
手机号码		    上行流量        下行流量		总流量

自定义流量统计Bean对象：FlowBean

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
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() {//反射需要提供无参构造方法
    }

    @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;
    }

    /**
     * 序列化方法
     * @param dataOutput：框架提供的数据出口
     * @throws IOException
     */
    public void write(DataOutput dataOutput) throws IOException {
        //顺序和反序列化的顺序要一模一样
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    /**
     * 反序列化方法
     * @param dataInput：框架提供的数据来源
     * @throws IOException
     */
    public void readFields(DataInput dataInput) throws IOException {
        //顺序和序列化的顺序要一模一样
        upFlow = dataInput.readLong();
        downFlow = dataInput.readLong();
        sumFlow = dataInput.readLong();
    }
}

FlowDriver:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
package com.atguigu.flow;

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, 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:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
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> {
    /**
     * LongWritable:框架输入类型的Key，这行在行首在文件中的偏移量
     * Text:框架输入类型的Value，这行的内容
     * Text:Mapper的输入类型Key
     * FlowBean:Mapper的输入类型Value
     */
    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");
        phone.set(fields[1]);
        long upFlow = Long.parseLong(fields[fields.length - 3]);
        long downFlow = Long.parseLong(fields[fields.length - 2]);
        flow.set(upFlow,downFlow);
        context.write(phone,flow);
    }
}

FlowReducer:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
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);
    }
}

InstantCWeedStudent

个人简介。