辅助排序和二次排序案例

1 需求有如下订单数据,现在需要求出每一个订单中最贵的商品。

0000001 Pdt_01 222.8
0000001 Pdt_06 25.8
0000002 Pdt_03 522.8
0000002 Pdt_04 122.4
0000002 Pdt_05 722.4
0000003 Pdt_01 222.8
0000003 Pdt_02 33.8

2 分析
1）利用“订单 id 和成交金额”作为 key，可以将 map 阶段读取到的所有订单数据按
照 id 分区，按照金额排序，发送到 reduce。
2）在 reduce 端利用 groupingcomparator 将订单 id 相同的 kv 聚合成组，然后取第一个即是最大值。

3 代码实现
1） 定义订单信息 OrderBean

package com.da.order;

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

import org.apache.hadoop.io.WritableComparable;

public class OrderBean implements WritableComparable<OrderBean> {
    private int orderId;
    private double price;

    public OrderBean() {
        super();
    }

    public OrderBean(int orderId, double price) {
        super();
        this.orderId = orderId;
        this.price = price;
    }

    public void set(int orderId, double price) {
        this.orderId = orderId;
        this.price = price;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(orderId);
        out.writeDouble(price);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.orderId = in.readInt();
        this.price = in.readDouble();
    }

    @Override
    public String toString() {
        return orderId + "\t" + price;
    }

    public int getOrderId() {
        return orderId;
    }

    public void setOrderId(int orderId) {
        this.orderId = orderId;
    }

    public double getPrice() {
        return price;
    }

    public void setPrice(double price) {
        this.price = price;
    }

    @Override
    public int compareTo(OrderBean o) {
        int result;
        if (this.orderId > o.getOrderId()) {
            result = 1;
        } else if (this.orderId < o.getOrderId()) {
            result = -1;
        } else {
            result = this.price > o.getPrice() ? -1 : 1;
        }
        return result;
    }

}

2） 编写 OrderMapper

package com.da.order;

import java.io.IOException;

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

public class OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {
    private OrderBean k = new OrderBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1 获取一行
        String line = value.toString();
        // 2 截取
        String[] files = line.split(" ");
        // 3 封装对象
        int id = Integer.parseInt(files[0]);
        double price = Double.parseDouble(files[2]);
        k.set(id, price);
        // 4 写出
        context.write(k, NullWritable.get());
    }
}

3） 编写 OrderPartitioner

package com.da.order;

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

public class OrderPartitioner extends Partitioner<OrderBean, NullWritable> {

    @Override
    public int getPartition(OrderBean key, NullWritable value, int numPartitions) {
        return (key.getOrderId() & Integer.MAX_VALUE) % numPartitions;
    }

}

4）编写 OrderGroupingComparator

package com.da.order;

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

public class OrderGroupingComparator extends WritableComparator {
    protected OrderGroupingComparator() {
        super(OrderBean.class, true);
    }

    @SuppressWarnings("rawtypes")
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        OrderBean aBean = (OrderBean) a;
        OrderBean bBean = (OrderBean) b;

        int result;
        if (aBean.getOrderId() > bBean.getOrderId()) {
            result = 1;
        } else if (aBean.getOrderId() < bBean.getOrderId()) {
            result = -1;
        } else {
            result = 0;
        }
        return result;
    }
}

5） 编写 OrderReducer

package com.da.order;

import java.io.IOException;

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

public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {
    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context)
            throws IOException, InterruptedException {
        context.write(key, NullWritable.get());
    }
}

6） 编写 OrderDriver

package com.da.order;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class OrderDriver {
    public static void main(String[] args) throws Exception {
        // 1 获取配置信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2 设置 jar 包加载路径
        job.setJarByClass(OrderDriver.class);
        // 3 加载 map/reduce 类
        job.setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);
        // 4 设置 map 输出数据 key 和 value 类型
        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);
        // 5 设置最终输出数据的 key 和 value 类型
        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);
        // 6 设置输入数据和输出数据路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 10 设置 reduce 端的分组
        job.setGroupingComparatorClass(OrderGroupingComparator.class);
        // 7 设置分区
        job.setPartitionerClass(OrderPartitioner.class);
        // 8 设置 reduce 个数
        job.setNumReduceTasks(3);
        // 9 提交
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);

    }
}