二十四、案例：分析日志数据，降序输出TopN

咱们Hadoop篇正文内容就这么多了，接下来的三篇是三个MapReduce的案例，以代码为主，实现过程相对简单。关注专栏《破茧成蝶——大数据篇》查看相关系列的文章~

---

目录

一、需求分析

二、代码实现

---

一、需求分析

现有如下四列的日志数据：

分别代表手机号码、上行流量、下行流量、总流量。现在需要对此数据进行加工，输出流量使用量前5的用户信息。

二、代码实现

2.1 首先定义一个Bean类，值得注意的是这里面有一个compareTo的比较方法，实现降序排序。

package com.xzw.hadoop.mapreduce.topn;

import org.apache.hadoop.io.WritableComparable;

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

/**
 * @author: xzw
 * @create_date: 2020/12/7 10:40
 * @desc:
 * @modifier:
 * @modified_date:
 * @desc:
 */
public class TopNBean implements WritableComparable<TopNBean> {
    private long upFlow;
    private long downFlow;
    private long sumFlow;

    public TopNBean() {
    }

    public TopNBean(long upFlow, long downFlow) {
        super();
        this.upFlow = upFlow;
        this.downFlow = downFlow;
    }

    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;
    }

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

    @Override
    public int compareTo(TopNBean o) {//比较方法，降序排序
        return Long.compare(o.sumFlow, this.sumFlow);
    }

    public void set(long upFlow, long downFlow) {
        this.downFlow = downFlow;
        this.upFlow = upFlow;
        this.sumFlow = downFlow + upFlow;
    }


    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        upFlow = dataInput.readLong();
        downFlow = dataInput.readLong();
        sumFlow = dataInput.readLong();
    }
}

2.2 定义Mapper类

package com.xzw.hadoop.mapreduce.topn;

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

import java.io.IOException;

/**
 * @author: xzw
 * @create_date: 2020/12/7 10:57
 * @desc:
 * @modifier:
 * @modified_date:
 * @desc:
 */
public class TopNMapper extends Mapper<LongWritable, Text, TopNBean, Text> {
    private TopNBean k = new TopNBean();
    private Text v = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");

        v.set(fields[0]);
        k.set(Long.parseLong(fields[1]), Long.parseLong(fields[2]));

        context.write(k, v);
    }
}

2.3 定义让所有数据分到同一组的比较器

package com.xzw.hadoop.mapreduce.topn;

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

/**
 * @author: xzw
 * @create_date: 2020/12/7 11:16
 * @desc: 让所有数据分到同一组的比较器
 * @modifier:
 * @modified_date:
 * @desc:
 */
public class TopNComparator extends WritableComparator {
    protected TopNComparator() {
        super(TopNBean.class, true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        return 0;
    }
}

2.4 定义Reducer类

package com.xzw.hadoop.mapreduce.topn;

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

import java.io.IOException;
import java.util.Iterator;

/**
 * @author: xzw
 * @create_date: 2020/12/7 11:04
 * @desc:
 * @modifier:
 * @modified_date:
 * @desc:
 */
public class TopNReducer extends Reducer<TopNBean, Text, Text, TopNBean> {
    @Override
    protected void reduce(TopNBean key, Iterable<Text> values, Context context) throws IOException,
            InterruptedException {
        Iterator<Text> iterator = values.iterator();
        for (int i = 0; i < 5; i++) {
            if (iterator.hasNext()) {
                context.write(iterator.next(), key);
            }
        }
    }
}

2.5 定义Driver类

package com.xzw.hadoop.mapreduce.topn;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

/**
 * @author: xzw
 * @create_date: 2020/12/7 11:21
 * @desc:
 * @modifier:
 * @modified_date:
 * @desc:
 */
public class TopNDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"e:/input/topn.txt", "e:/output1"};

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

        job.setJarByClass(TopNDriver.class);
        job.setMapperClass(TopNMapper.class);
        job.setReducerClass(TopNReducer.class);

        job.setMapOutputKeyClass(TopNBean.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setGroupingComparatorClass(TopNComparator.class);
        job.setOutputValueClass(TopNBean.class);

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

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

2.6 测试结果