Hadoop序列化案例实操

目录

1.需求

2.需求分析

3.自定义对象和三个类的程序

（1）编写流量统计的Bean对象

（2）编写Mapper类

（3）编写Reducer类

（4）编写Driver驱动类

3.结果

---

1.需求

统计每一个手机号耗费的总上行流量、总下行流量、总流量

（1）输入数据：txt文件

（2）输入数据格式

（3）期望输出数据格式

2.需求分析

 

 3.自定义对象和三个类的程序

（1）编写流量统计的Bean对象

/**
 * 1、定义类实现writable接口
 * 2、重写序列化和反序列化方法
 * 3、重写空参构造
 * 4、toString方法
 */
public class FlowBean implements Writable {
    private long upFlow;
    private long downFlow;
    private long sumFlow;

    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 {
        //序列化和反序列化顺序一致
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

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

（2）编写Mapper类

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, Context context) throws IOException, InterruptedException {
        //1、获取一行
        //1	13736230513	192.196.100.1	www.atguigu.com	2481	24681	200
        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 - 3];
        String down = split[split.length - 2];

        //4、封装
        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));//String->Long
        outV.setDownFlow(Long.parseLong(down));
        outV.setSumFlow();

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

（3）编写Reducer类

public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {
    private FlowBean outV = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        //1、遍历集合累加值
        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、写出
        context.write(key,outV);
    }
}

（4）编写Driver驱动类

public class FlowDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(FlowDriver.class);

        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

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

        FileInputFormat.setInputPaths(job,new Path("D:\\code\\Hadoop\\input\\inputflow"));
        FileOutputFormat.setOutputPath(job,new Path("D:\\code\\Hadoop\\output4"));

        boolean result = job.waitForCompletion(true);
        System.exit(result? 0:1);
    }

}

3.结果

从输出文件夹中找