MapReduce利用分区，排序，分组规则

数据：

order001,u001,小米6,1999.9,2
order001,u001,雀巢咖啡,99.0,2
order001,u001,安慕希,250.0,2
order001,u001,经典红双喜,200.0,4
order001,u001,防水电脑包,400.0,2
order002,u002,小米手环,199.0,3
order002,u002,榴莲,15.0,10
order002,u002,苹果,4.5,20
order002,u002,肥皂,10.0,40

订单实体类：控制比较

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

import org.apache.hadoop.io.WritableComparable;
//重写排序必须同时实现序列化接口
public class OrderBean implements WritableComparable<OrderBean>{

	private String orderId;
	private String userId;
	private String pdtName;
	private float price;
	private int number;
	private float amountFee;
        /** getter，setter方法略  */

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeUTF(this.orderId);
		out.writeUTF(this.userId);
		out.writeUTF(this.pdtName);
		out.writeFloat(this.price);
		out.writeInt(this.number);

	}

	@Override
	public void readFields(DataInput in) throws IOException {
		this.orderId = in.readUTF();
		this.userId = in.readUTF();
		this.pdtName = in.readUTF();
		this.price = in.readFloat();
		this.number = in.readInt();
		this.amountFee = this.price * this.number;
	}

	// 排序规则：先比总金额，如果相同，再比商品名称
	@Override
	public int compareTo(OrderBean o) {
		return this.orderId.compareTo(o.getOrderId())==0?Float.compare(o.getAmountFee(), this.getAmountFee()):this.orderId.compareTo(o.getOrderId());
	}

}

控制分区：OrderIdPartitioner
 

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

public class OrderIdPartitioner extends Partitioner<OrderBean, NullWritable>{

    @Override
    public int getPartition(OrderBean key, NullWritable value, int numPartitions) {
        // 按照订单中的orderid来分发数据
        return (key.getOrderId().hashCode() & Integer.MAX_VALUE) % numPartitions;
    }

}

控制分组：OrderIdGroupingComparator

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

public class OrderIdGroupingComparator extends WritableComparator{
	//调用父类的构造方法，父类通过反射创建对象实例
	public OrderIdGroupingComparator() {
		super(OrderBean.class,true);
	}
	
	@Override
	public int compare(WritableComparable a, WritableComparable b) {
		
		OrderBean o1 = (OrderBean) a;
		OrderBean o2 = (OrderBean) b;
		
		return o1.getOrderId().compareTo(o2.getOrderId());
	}
	
}

测试：

import java.io.IOException;

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

public class OrderTopn {

	public static class OrderTopnMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable>{
		OrderBean orderBean = new OrderBean();
		NullWritable v = NullWritable.get();
		@Override
		protected void map(LongWritable key, Text value,
				Mapper<LongWritable, Text, OrderBean, NullWritable>.Context context)
				throws IOException, InterruptedException {
			
			String[] fields = value.toString().split(",");
			
			orderBean.set(fields[0], fields[1], fields[2], Float.parseFloat(fields[3]), Integer.parseInt(fields[4]));
			
			context.write(orderBean,v);
		}
		
		
	}
	
	
	public static class OrderTopnReducer extends Reducer< OrderBean, NullWritable,  OrderBean, NullWritable>{
		
		/**
		 * 虽然reduce方法中的参数key只有一个，但是只要迭代器迭代一次，key中的值就会变
		 */
		@Override
		protected void reduce(OrderBean key, Iterable<NullWritable> values,
				Reducer<OrderBean, NullWritable, OrderBean, NullWritable>.Context context)
				throws IOException, InterruptedException {
			int i=0;
			for (NullWritable v : values) {
				context.write(key, v);
				if(++i==3) return;
			}
			
		}
		
		
	}
	
	public static void main(String[] args) throws Exception {

		
		Configuration conf = new Configuration(); // 默认只加载core-default.xml core-site.xml
		conf.setInt("order.top.n", 2);
		
		Job job = Job.getInstance(conf);

		job.setJarByClass(OrderTopn.class);

		job.setMapperClass(OrderTopnMapper.class);
		job.setReducerClass(OrderTopnReducer.class);
		
                //设置排序，分区，分组规则
		job.setPartitionerClass(OrderIdPartitioner.class);
		job.setGroupingComparatorClass(OrderIdGroupingComparator.class);
		
		job.setNumReduceTasks(2);

		job.setMapOutputKeyClass(OrderBean.class);
		job.setMapOutputValueClass(NullWritable.class);
		
		job.setOutputKeyClass(OrderBean.class);
		job.setOutputValueClass(NullWritable.class);

		FileInputFormat.setInputPaths(job, new Path("F:\\mrdata\\order\\input"));
		FileOutputFormat.setOutputPath(job, new Path("F:\\mrdata\\order\\out-3"));

		job.waitForCompletion(true);
	}
	
}