大数据——mapreduce分析数据更改源码之分组机制、分区机制、排序机制（map返回值key为对象）

map返回值对象封装：
排序规则的修改和mapreduceIO封装

public class OrderBean implements WritableComparable<OrderBean>{

	private String orderId;
	private String userId;
	private String pdtName;
	private float price;
	private int number;
	private float amountFee;

	public void set(String orderId, String userId, String pdtName, float price, int number) {
		this.orderId = orderId;
		this.userId = userId;
		this.pdtName = pdtName;
		this.price = price;
		this.number = number;
		this.amountFee = price * number;
	}

	public String getOrderId() {
		return orderId;
	}

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

	public String getUserId() {
		return userId;
	}

	public void setUserId(String userId) {
		this.userId = userId;
	}

	public String getPdtName() {
		return pdtName;
	}

	public void setPdtName(String pdtName) {
		this.pdtName = pdtName;
	}

	public float getPrice() {
		return price;
	}

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

	public int getNumber() {
		return number;
	}

	public void setNumber(int number) {
		this.number = number;
	}

	public float getAmountFee() {
		return amountFee;
	}

	public void setAmountFee(float amountFee) {
		this.amountFee = amountFee;
	}

	@Override
	public String toString() {

		return this.orderId + "," + this.userId + "," + this.pdtName + "," + this.price + "," + this.number + ","
				+ this.amountFee;
	}

	@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;
	}

	// 比较规则：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());
		
	}

}

分区规则修改：

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;
	}

}

分组规则修改：

public class OrderIdGroupingComparator extends WritableComparator{
	
	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());
	}
	
	

}

mapreduce逻辑和输出：

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);
		
		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);
	}
	
}