Java 布隆算法结构
public class BloomFilterDemo {
private Listseeds = Arrays.asList(10,20,30,40,50,60,70,80);
private ListsimpleHashes =new ArrayList<>();
private static final int MAXIMUM_CAPACITY =1 <<30;
private BitSetbitSet =new BitSet(MAXIMUM_CAPACITY);//32亿大的布隆结构
public static void main(String[] args) {
String s ="www.baidus";
BloomFilterDemo bd =new BloomFilterDemo();
//bd.addValue(s);
System.out.println(bd.getValue(s));
}
public BloomFilterDemo() {
seeds.stream().forEach(seed ->{
simpleHashes.add(new SimpleHash(MAXIMUM_CAPACITY,seed));
});
}
boolean isTrue = Boolean.TRUE;
/**
* 获取布隆值是否存在
* @param value
* @return
*/
public boolean getValue(Object value) {
simpleHashes.stream().forEach(sh ->{
isTrue =isTrue &&bitSet.get(sh.key(value));//是true为true 遇到false 全是false
});
return isTrue;
}
/**
* 放入过滤值到布隆结构中
* @param value
*/
public void addValue(Object value) {
simpleHashes.stream().forEach(simpleHash -> {
System.out.println(simpleHash.key(value));
bitSet.set(simpleHash.key(value),true);
});
}
/**
* 8个Hash因子解决来减少Hash碰撞
*/
public static class SimpleHash {
private int capacity;
private int seed;
public SimpleHash(int capacity,int seed) {
this.capacity = capacity;
this.seed = seed;
}
final int hash(Object key) {
int h;
return (key ==null) ?0 : (h = key.hashCode()) ^ (h >>>seed);//HashMap原理 解决hash碰撞 不懂 可以去理解HashMap 源码
}
final int key(Object key) {
return hash(key) & (capacity-1);
}
}
}