Escrita a mano MapReduce tipo de WritableComparable sea TopN (Java)

prefacio

Tren escribió antes de ordenar su conjunto, utilizando RawComparator para lograr! Esto se consigue utilizando WritableComparable!

Fuentes de datos

     tel    up	down total
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
13560439639	918	4938	5856
13560439631	918	4938	5856
13560439632	918	4938	5856
13560439633	918	4938	5856

Frijol

package com.zhengkw.topn;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.WritableComparable;

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

/**
 * @ClassName:FlowBean
 * @author: zhengkw
 * @description:
 * @date: 20/02/27上午 9:51
 * @version:1.0
 * @since: jdk 1.8
 */
public class FlowBean implements WritableComparable<FlowBean> {

    //上行
    private long upFlow;
    // 下行
    private long downFlow;
    // 总量
    private long totalFlow;

    //序列化
    @Override
    public void write(DataOutput out) throws IOException {

        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(totalFlow);
    }

    //反序列化
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.totalFlow = in.readLong();
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public void setTotalFlow(long totalFlow) {
        this.totalFlow = totalFlow;
    }

    public long getUpFlow() {
        return upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public long getTotalFlow() {
        return totalFlow;
    }

    public FlowBean() {
        super();
    }

    /**
     * @param o 比较器被调用时 keyin作为参数传递
     * @descrption:只比较总流量
     * @return: int
     * @date: 20/02/27 上午 10:01
     * @author: zhengkw
     */
    @Override
    public int compareTo(FlowBean o) {
        return this.totalFlow > o.getTotalFlow() ? -1 : 1;
    }

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

Mapper

package com.zhengkw.topn;

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

import java.io.IOException;

/**
 * @ClassName:TopNMapper
 * @author: zhengkw
 * @description: 按照手机号求和以后总流量倒序排序(mapper截取封装)
 * @date: 20/02/27上午 9:49
 * @version:1.0
 * @since: jdk 1.8
 */
public class TopNMapper extends Mapper<LongWritable, Text, FlowBean, Text> {

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

    //13509468723	117684	110349	228033
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        String line = value.toString();
        String[] val = line.split("\t");
        v.set(val[0]);
        k.setUpFlow(Long.parseLong(val[1]));
        k.setDownFlow(Long.parseLong(val[2]));
        k.setTotalFlow(Long.parseLong(val[3]));

        context.write(k, v);
    }
}

reducir

package com.zhengkw.topn;

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

import java.io.IOException;

/**
 * @ClassName:TopNMapper
 * @author: zhengkw
 * @description: 按照手机号求和以后总流量倒序排序(mapper截取封装)
 * @date: 20/02/27上午 9:49
 * @version:1.0
 * @since: jdk 1.8
 */
public class TopNMapper extends Mapper<LongWritable, Text, FlowBean, Text> {

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

    //13509468723	117684	110349	228033
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        String line = value.toString();
        String[] val = line.split("\t");
        v.set(val[0]);
        k.setUpFlow(Long.parseLong(val[1]));
        k.setDownFlow(Long.parseLong(val[2]));
        k.setTotalFlow(Long.parseLong(val[3]));

        context.write(k, v);
    }
}

conductor

package com.zhengkw.topn;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

/**
 * @ClassName:TopNDriver
 * @author: zhengkw
 * @description: 最后一次手写
 * @date: 20/02/27上午 10:50
 * @version:1.0
 * @since: jdk 1.8
 */
public class TopNDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 输入路径
        Path inputPath = new Path("f:/output1");
        // 输出路径
        Path outputPath = new Path("f:/output2");

        Configuration conf = new Configuration();

        //判断输出路径是否已经存在 存在则删除
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(outputPath)) {
            fs.delete(outputPath, true);
        }
        // 创建job
        Job job = Job.getInstance(conf);
        //设置3个类
        job.setJarByClass(TopNDriver.class);
        job.setMapperClass(TopNMapper.class);
        job.setReducerClass(TopNReducer.class);

        //设置2个阶段的K V类
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);

        //指定最终输出的 KV 类
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);


        //设置输入输出路径
        FileInputFormat.setInputPaths(job, inputPath);
        FileOutputFormat.setOutputPath(job, outputPath);

        //提交job true打印job信息  获取返回值退出程序
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);

    }
}

resumen

/**
 * @param o 比较器被调用时 keyin作为参数传递
 * @descrption:只比较总流量
 * @return: int
 * @date: 20/02/27 上午 10:01
 * @author: zhengkw
 */
@Override
public int compareTo(FlowBean o) {
    return this.totalFlow > o.getTotalFlow() ? -1 : 1;
}

Debido KEYOUT Mapper es un grano de costumbre, por lo que es necesario reescribir COMPARATO () con el fin de permitir que dos objetos para comparar el tamaño!