按照订单将商品分组，并按照价格倒序排列，在reduce端压缩输出

需求：将下面数据，按照定单号分组，并按照价格倒序排列

订单号        商品       价格

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

......

1：创建OrderBean类

package GroupingComparator;

import lombok.AllArgsConstructor;
import lombok.NoArgsConstructor;
import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

@AllArgsConstructor
@NoArgsConstructor
public class OrderBean implements WritableComparable<OrderBean> {
    //订单id号
    private int order_id;
    //价格
    private double price;

    public int getOrder_id() {
        return order_id;
    }
    public void setOrder_id(int order_id) {
        this.order_id = order_id;
    }
    public double getPrice() {
        return price;
    }
    public void setPrice(double price) {
        this.price = price;
    }
    @Override
    public String toString() {
        return order_id + "\t" + price;
    }
    //序列化
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(order_id);
        out.writeDouble(price);
    }
    //反序列化
    @Override
    public void readFields(DataInput in) throws IOException {
        this.order_id = in.readInt();
        this.price = in.readDouble();
    }
    //二次排序
    @Override
    public int compareTo(OrderBean o) {
        int result;
        if(this.order_id > o.getOrder_id()) {
            return 1;
        }else if (this.order_id < o.getOrder_id()){
            return -1;
        }else {
            //id正序，price倒序
            result = this.price > o.getPrice() ? -1 : 1;
        }
        return result;
    }
}

2：创建OrderMap类

package GroupingComparator;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;

//<id & price>
public class OrderMap extends Mapper<LongWritable, Text,OrderBean, NullWritable> {
    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:截取数据
        String[] fields = line.split("\t");
        //3:封装数据
        k.setOrder_id(Integer.parseInt(fields[0]));
        k.setPrice(Double.parseDouble(fields[2]));
        //4:输出
        context.write(k, NullWritable.get());
    }
}

3：创建OrderReducer类

package GroupingComparator;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;

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());
    }
}

4：创建OrderGroupingComparator类

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

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

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

        int result;
        if(aBean.getOrder_id() > bBean.getOrder_id()){
            return 1;
        }else  if(aBean.getOrder_id() < bBean.getOrder_id()){
            return -1;
        }else {
            result = aBean.getPrice()>bBean.getPrice()? -1:1;
        }
        return result;
    }
}

5：创建OrderPartition类

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


public class OrderPartition extends Partitioner<OrderBean, NullWritable> {
    @Override
    public int getPartition(OrderBean key, NullWritable value, int i) {
        return (key.getOrder_id() & Integer.MAX_VALUE) % i;
    }
}

6：创建OrderDriver类，这里同时写了Map和Reduce的压缩，在实际中可以分别选择使用，也可同时使用

package GroupingComparator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.CompressionCodec;
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 OrderDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"E:\\bigdata_code\\GroupingComparator.txt", "E:\\bigdata_code\\out"};

        //1.获取配置信息,创建job任务
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //开启Map端的输出压缩,设置压缩方式
        conf.setBoolean("mapreduce.map.output.compress",true);
        conf.setClass("mapreduce.map.output.compress.codec", BZip2Codec.class, CompressionCodec.class);

        //2.设置jar包加载路径
        job.setJarByClass(OrderDriver.class);

        //3.加载Map类，设置输入输出数据类
        job.setMapperClass(OrderMap.class);
        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);


        //4.设置Reduce类，设置输入输出数据类
        job.setReducerClass(OrderReducer.class);
        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);

        //5设置reduce端的分组
        job.setGroupingComparatorClass(OrderGroupingComparator.class);

        //定义分区和设置分区数
        job.setPartitionerClass(OrderPartition.class);
        job.setNumReduceTasks(3);

        //指定数据输入的路径和输出路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //设置reduce压缩，压缩格式
        FileOutputFormat.setCompressOutput(job,true);
        FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);

        //提交任务
        job.waitForCompletion(true);
    }
}