Hadoop序列化案例

Hadoop序列化案例

统计每一个手机号耗费的总上行流量、总下行流量、总流量

数据：

1	13736230513	192.196.100.1	www.baidu.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.ali.com	1527	2106	200
6 	84188413	192.168.100.3	www.465456.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.kgc.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

Bean对象：

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

/*
1.定义类实现writable接口
2.重写序列化与反序列化方法
3.空参构造
4.重写toString（）；
 */
public class FlowBean implements Writable {
    private long upFlow;
    private long downFlow;
    private long sumFlow;

    @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();
    }

    //重写sumFlow的set方法
    public void setSumFlow() {
        this.sumFlow = this.upFlow + this.downFlow;
    }
}

Mapper:

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 {
        //获取一行
        String line = value.toString();
        //切割
        String[] split = line.split("\t");
        //提前想要的数据，手机号，流量,由于文档中有数据是空，不能使用数值下标的方式提取数据
        //使用split.length-x的方法提取，x具体情况具体分析
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];
        //封装
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();
        //写出
        context.write(outK,outV);
    }
}

Reducer:

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 {
        //遍历集合累加
        long totalUp = 0;
        long totalDown = 0;
        for (FlowBean value : values) {
            totalUp += value.getUpFlow();
            totalDown += value.getDownFlow();
        }
        //封装
        outV.setUpFlow(totalUp);
        outV.setDownFlow(totalDown);
        outV.setSumFlow();
        ///写出
        context.write(key, outV);
    }
}

JobDriver:

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 {
        //获取Job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //设置jar包路径
        job.setJarByClass(FlowDriver.class);
        //关联mapper
        job.setMapperClass(FlowMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        //关联reducer
        job.setReducerClass(FlowReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path("file:///e:/temp1/read2"));
        Path path = new Path("file:///e:/temp1/output");
        if (path.getFileSystem(conf).exists(path)){
            path.getFileSystem(conf).delete(path,true);
        }
        FileOutputFormat.setOutputPath(job,path);
        job.waitForCompletion(true);
    }
}

输出结果：

13470253144	180	180	360
13509468723	7335	110349	117684
13560439638	918	4938	5856
13568436656	3597	25635	29232
13590439668	1116	954	2070
13630577991	6960	690	7650
13682846555	1938	2910	4848
13729199489	240	0	240
13736230513	2481	24681	27162
13768778790	120	120	240
13846544121	264	0	264
13956435636	132	1512	1644
13966251146	240	0	240
13975057813	11058	48243	59301
13992314666	3008	3720	6728
15043685818	3659	3538	7197
15910133277	3156	2936	6092
15959002129	1938	180	2118
18271575951	1527	2106	3633
18390173782	9531	2412	11943
84188413	4116	1432	5548