hadoop复合键排序使用方法

标签：style   io   ar   使用   java   sp   on   ad   ef   

在hadoop中处理复杂业务时，需要用到复合键，复合不同于单纯的继承Writable接口，而是继承了WritableComparable<T>接口，而实际上，WritableComparable<T>接口继承了Writable和Comparable<T>接口，如果只需要使用某一个类作为传值对象而不是作为key，继承Writable接口即可。

上源码：

public interface WritableComparable<T> extends Writable, Comparable<T> {
}

public interface Writable {

  void write(DataOutput out) throws IOException;

  void readFields(DataInput in) throws IOException;
}

public interface Comparable<T> {
    
    public int compareTo(T o);
}

public class SortKey implements WritableComparable<SortKey>{
	
	private Text name;
	private IntWritable right;
	

	public SortKey() {
		set(new Text(), new IntWritable());
	}
	
	
	public SortKey(Text name, IntWritable right) {
		set(name, right);
	}


	private void set(Text name,IntWritable right){
		this.name = name;
		this.right = right;
	}
	
	

	/**
	 * @return the name
	 */
	public Text getName() {
		return name;
	}


	/**
	 * @param name the name to set
	 */
	public void setName(Text name) {
		this.name = name;
	}


	/**
	 * @return the right
	 */
	public IntWritable getRight() {
		return right;
	}


	/**
	 * @param right the right to set
	 */
	public void setRight(IntWritable right) {
		this.right = right;
	}


	@Override
	public void write(DataOutput out) throws IOException {
		name.write(out);
		right.write(out);
	}

	@Override
	public void readFields(DataInput in) throws IOException {
		name.readFields(in);
		right.readFields(in);
	}

	@Override
	public int compareTo(SortKey o) {
		int cmp = name.compareTo(o.name);
		if(cmp != 0){
			return cmp;
		}else{
			return right.compareTo(o.right);
		}
	}

<span style="white-space:pre">	</span>//到目前为止，你只能将其作为key来使用，但是如果你需要按照key的某一个值来排序，以下是重点

	
	static{
		WritableComparator.define(SortKey.class, new Comparator());
	}
	
	public static class Comparator extends WritableComparator{
		
	    private static final Text.Comparator TEXT_COMPARATOR = new Text.Comparator();
		
		protected Comparator() {
			super(SortKey.class);
		}

		/* (non-Javadoc)
		 * @see org.apache.hadoop.io.WritableComparator#compare(byte[], int, int, byte[], int, int)
		 */
		@Override
		public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {
			try{
				int firstL1 = WritableUtils.decodeVIntSize(b1[s1]) + readVInt(b1, s1);
				int firstL2 = WritableUtils.decodeVIntSize(b2[s2]) + readVInt(b2, s2);
	            return TEXT_COMPARATOR.compare(b1, s1, firstL1, b2, s2, firstL2);
			}catch(Exception e){
				throw new IllegalArgumentException(e);
			}
		}	
	}

}

hadoop复合键排序使用方法

标签：style   io   ar   使用   java   sp   on   ad   ef   

原文地址：http://blog.csdn.net/qingmu0803/article/details/40590637