PHP布隆过滤器的优缺点及适用场景分析

class BloomFilter
{
    private $bits;   // 位数组
    private $hashNum;   // 哈希函数的个数

    public function __construct($size, $hashNum)
    {
        $this->bits = array_fill(0, $size, 0);
        $this->hashNum = $hashNum;
    }

    public function add($element)
    {
        for ($i = 0; $i < $this->hashNum; $i++) {
            $hash = $this->hash($element, $i);
            $this->bits[$hash] = 1;
        }
    }

    public function contains($element)
    {
        for ($i = 0; $i < $this->hashNum; $i++) {
            $hash = $this->hash($element, $i);
            if ($this->bits[$hash] != 1) {
                return false;
            }
        }
        return true;
    }

    private function hash($element, $seed)
    {
        $element = md5($element);
        $length = strlen($element);
        $hash = 0;

        for ($i = 0; $i < $length; $i++) {
            $hash = $hash * $seed + ord($element[$i]);
        }
        return $hash % count($this->bits);
    }
}

// 使用示例
$bloomFilter = new BloomFilter(1024, 3);
$bloomFilter->add("https://example.com");
$bloomFilter->add("https://example.net");

$contains1 = $bloomFilter->contains("https://example.com");
$contains2 = $bloomFilter->contains("https://example.org");

var_dump($contains1);   // 输出：bool(true)
var_dump($contains2);   // 输出：bool(false)