[MapReduce编程案例1-订单分组topn]

1.数据

要求：对每个orderid列出成交额最大的前n条记录。 

2.思路

map任务：将每一行都映射为<orderid,orderBean>,orderid相同的为同一组，orderBean为对数据的封装类

reduce任务：对同一组的数据进行处理，即按成交额从大到小排序，输出前n条即可

1.orderBean类需要实现序列化接口Writable,重写readFields方法(反序列化)和write方法(序列化）

public class OrderBean implements Writable{
	
	private String uid;
	private String oid;
	private String item;
	private int num;
	private float price;
	
	public OrderBean() {
	}
	
	public OrderBean(String uid, String oid, String item, int num, float price) {
		this.uid = uid;
		this.oid = oid;
		this.item = item;
		this.num = num;
		this.price = price;
	}

	public String getUid() {
		return uid;
	}
	public void setUid(String uid) {
		this.uid = uid;
	}
	public String getOid() {
		return oid;
	}
	public void setOid(String oid) {
		this.oid = oid;
	}
	public String getItem() {
		return item;
	}
	public void setItem(String item) {
		this.item = item;
	}
	public int getNum() {
		return num;
	}
	public void setNum(int num) {
		this.num = num;
	}
	public float getPrice() {
		return price;
	}
	public void setPrice(float price) {
		this.price = price;
	}

	@Override
	public String toString() {
		return "OrderBean [uid=" + uid + ", oid=" + oid + ", item=" + item + ", num=" + num + ", price=" + price + "]";
	}
	//mr框架在将二进制数据反序列化成本类的对象时要调用的方法
	//反序列化流程：先从本类反射出一个没有数据的对象，然后从二进制数据中反序列化出各个数据，然后set到这个反射出来的对象
	public void readFields(DataInput in) throws IOException {
		this.uid = in.readUTF();
		this.oid = in.readUTF();
		this.item = in.readUTF();
		this.num = in.readInt();
		this.price = in.readFloat();
	}
	//mr框架在将本类的对象进行序列化操作时要调用的方法
	public void write(DataOutput out) throws IOException {
		out.writeUTF(this.uid);
		out.writeUTF(this.oid);
		out.writeUTF(this.item);
		out.writeInt(this.num);
		out.writeFloat(this.price);
	}
}

2.OrderTopnMapper类继承Mapper<LongWritable, Text, Text, OrderBean>

public class OrderTopnMapper extends Mapper<LongWritable, Text, Text, OrderBean>{
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, OrderBean>.Context context)
			throws IOException, InterruptedException {
		// u01,order001,apple,5,8.5
		String[] split = value.toString().split(",");
		OrderBean orderBean = new OrderBean(split[0], split[1], split[2], Integer.parseInt(split[3]), Float.parseFloat(split[4]));
		context.write(new Text(orderBean.getOid()), orderBean);
		
	}
}

3.OrderTopnReducer类继承Reducer<Text, OrderBean, OrderBean, NullWritable>

public class OrderTopnReducer extends Reducer<Text, OrderBean, OrderBean, NullWritable>{

	@Override
	protected void reduce(Text key, Iterable<OrderBean> values,
			Reducer<Text, OrderBean, OrderBean, NullWritable>.Context context) throws IOException, InterruptedException {
		ArrayList<OrderBean> beans = new ArrayList();
		//每次迭代创建新对象
		for (OrderBean orderBean : values) {
			OrderBean beanNew = new OrderBean();
			try {
				BeanUtils.copyProperties(beanNew, orderBean);
			} catch (Exception e) {
				e.printStackTrace();
			}
			beans.add(beanNew);
		}
		//设置一个比较器，重写compare方法
		Collections.sort(beans, new Comparator<OrderBean>() {
			//返回-1:o1排在o2前面;返回1:o1排在o2后面;
			public int compare(OrderBean o1, OrderBean o2) {
				return o1.getNum()*o1.getPrice()-o2.getNum()*o2.getPrice()>0?1:-1;
			}
		});
		for(int i=0;i<2;i++){
			context.write(beans.get(i), NullWritable.get());
		}
	}
}

4.结果