自定义分区Partitionor

目录

需求：

需求分析：

代码实现：

测试1，

测试2，

测试3，

分区总结：

---

需求：

将统计结果按照手机归属地不同省份输出到不同文件中（分区）

数据源：

1	13736230513	192.196.100.1	www.isea.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.isea.com	1527	2106	200
6 	84188413	192.168.100.3	www.isea.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.isea.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

期望结果： 手机号136、137、138、139开头都分别放到一个独立的4个文件中，其他开头的放到一个文件中。

需求分析：

代码实现：

package com.isea.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(long upFlow, long downFlow) {
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + downFlow;
    }

//   无参构造方法，反序列化时候需要用到
    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 set(Long upFlow,Long downFlow){
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        sumFlow = upFlow + downFlow;
    }

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

//    序列化方法
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

//    反序列化方法
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }
}

package com.isea.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> {
    // 键值对的准备
    private Text phone = new Text();
    private FlowBean flowBean = new FlowBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//        1,获取一行
        String line = value.toString();

//        2，切割数据 "\t"
        String[] field = line.split("\t");

//        3，封装对象
        phone.set(field[1]);

        long upFlow = Long.parseLong(field[field.length - 3]);
        long downFlow = Long.parseLong(field[field.length - 2]);
        flowBean.setUpFlow(upFlow);
        flowBean.setDownFlow(downFlow);

//        4，写给reduce
        context.write(phone,flowBean);
    }
}

package com.isea.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 resultFlowBean = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        long sumUp = 0;
        long sumDown = 0;

//        1，累加求和
        for (FlowBean value : values) {
            sumDown += value.getDownFlow();
            sumUp += value.getUpFlow();
        }
        resultFlowBean.set(sumUp,sumDown);

//        2，输出
        context.write(key,resultFlowBean);
    }
}

package com.isea.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 FlowSumDriver {

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

        args = new String[]{"G:/input1","G:/output3"};
//    1,获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

//    2，设置jar的路径
        job.setJarByClass(FlowSumDriver.class);

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

        job.setPartitionerClass(ProvincePartion.class);
        job.setNumReduceTasks(5);

//    4，设置Mapper输出的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
//    5，设置最终的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

//    6, 设置输入输出的路径
        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);

    }

}

package com.isea.flow;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class ProvincePartion extends Partitioner<Text,FlowBean> {
    @Override
    public int getPartition(Text text, FlowBean flowBean, int numPartitions) {
        String prePhoneNum = text.toString().substring(0,3);
        int partition = 4;
        if ("136".equals(prePhoneNum)){
            partition = 0;
        }else if ("137".equals(prePhoneNum)){
            partition = 1;
        }else if ("138".equals(prePhoneNum)){
            partition = 2;
        }else if ("139".equals(prePhoneNum)){
            partition = 4;
        }
        return partition;
    }
}

结果：

测试1，

 

测试2，

测试3，

分区总结：