WritableComparable区内排序

目录

需求：

原始数据：

实现代码：

结果：

---

需求：

原始数据：

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

实现代码：

package com.isea.sort;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class FlowBean implements WritableComparable<FlowBean> {
    private Long upFlow;
    private Long downFlow;
    private Long sumFlow;

    public FlowBean() {
    }

    public FlowBean(Long upFlow, Long downFlow) {
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.sumFlow = upFlow + 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 {
        upFlow = in.readLong();
        downFlow = in.readLong();
        sumFlow = in.readLong();
    }

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

    @Override
    public int compareTo(FlowBean o) {
        if (sumFlow > o.getSumFlow()){
            return -1;
        }else if (sumFlow < o.getSumFlow()){
            return  1;
        }else {
            return 0;
        }
    }

    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;
    }
}

package com.isea.sort;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class FlowCountMapper extends Mapper<LongWritable, Text, FlowBean, Text> {

    FlowBean k = new FlowBean();
    Text v = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

//        获取一行
        String line = value.toString();

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

//        封装对象
        v.set(splits[0]);

        k.setUpFlow(Long.valueOf(splits[1]));
        k.setDownFlow(Long.valueOf(splits[2]));
        k.setSumFlow(Long.valueOf(splits[3]));

//        写出
        context.write(k, v);
    }
}

package com.isea.sort;

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

import java.io.IOException;

public class FlowCountSortReducer extends Reducer<FlowBean, Text,Text,FlowBean> {
    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
//        循环写入
        for (Text value : values) {
            context.write(value,key);
        }
    }
}

package com.isea.sort;

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

        args = new String[]{"g:/input1/phone_sort_src.txt","g:/output3"};

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        job.setJarByClass(FlowCountSortDriver.class);

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

        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountSortReducer.class);

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

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

        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

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

package com.isea.sort;

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

public class ProvincePartitioner extends Partitioner<FlowBean, Text> {
    @Override
    public int getPartition(FlowBean flowBean, Text text, int numPartitions) {
        int partition = 4;

//        获取手机号的前三位
        String prePhoneNum = text.toString().substring(0,3);
        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 = 3;
        }
        return partition;
    }
}

结果：