bloom filter + murmurhash

最新推荐文章于 2024-08-05 16:15:09 发布

转载最新推荐文章于 2024-08-05 16:15:09 发布 · 126 阅读

本文深入探讨了一种哈希方法的核心思想及其应用，特别介绍了MurmurHash2算法的实现原理与特性，包括如何通过计算多个普通哈希函数映射到哈希表，并通过公式计算采取多少个普通哈希函数和多大映射空间使正确率变得最低。同时，文章详细解析了MurmurHash2算法的两个版本：针对64位平台的MurmurHash64A和针对32位平台的MurmurHash64B。

是一种hash方法，其实核心思想就是，将一个字符串通过多个普通hash函数映射到hash表上，然后再进行检索的时候同样计算hash函数，如果全都都hash表上出现过，那么说明有极大的可能出现过，如果没有出现那么一定没有出现过。

可以通过公式计算采取多少个普通hash函数和多大映射空间使正确率变得最低。

有一个称为万能hash函数的，看了下简介看起来很屌，所以纪录下来。

//-----------------------------------------------------------------------------
// MurmurHash2, 64-bit versions, by Austin Appleby

// The same caveats as 32-bit MurmurHash2 apply here - beware of alignment 
// and endian-ness issues if used across multiple platforms.

typedef unsigned long int uint64_t;

// 64-bit hash for 64-bit platforms
uint64_t MurmurHash64A ( const void * key, int len, unsigned int seed )
{
        const uint64_t m = 0xc6a4a7935bd1e995;
        const int r = 47;

        uint64_t h = seed ^ (len * m);

        const uint64_t * data = (const uint64_t *)key;
        const uint64_t * end = data + (len/8);

        while(data != end)
        {
                uint64_t k = *data++;

                k *= m; 
                k ^= k >> r; 
                k *= m; 

                h ^= k;
                h *= m; 
        }

        const unsigned char * data2 = (const unsigned char*)data;

        switch(len & 7)
        {
        case 7: h ^= uint64_t(data2[6]) << 48;
        case 6: h ^= uint64_t(data2[5]) << 40;
        case 5: h ^= uint64_t(data2[4]) << 32;
        case 4: h ^= uint64_t(data2[3]) << 24;
        case 3: h ^= uint64_t(data2[2]) << 16;
        case 2: h ^= uint64_t(data2[1]) << 8;
        case 1: h ^= uint64_t(data2[0]);
                h *= m;
        };
 
        h ^= h >> r;
        h *= m;
        h ^= h >> r;

        return h;
} 


// 64-bit hash for 32-bit platforms
uint64_t MurmurHash64B ( const void * key, int len, unsigned int seed )
{
        const unsigned int m = 0x5bd1e995;
        const int r = 24;

        unsigned int h1 = seed ^ len;
        unsigned int h2 = 0;

        const unsigned int * data = (const unsigned int *)key;

        while(len >= 8)
        {
                unsigned int k1 = *data++;
                k1 *= m; k1 ^= k1 >> r; k1 *= m;
                h1 *= m; h1 ^= k1;
                len -= 4;

                unsigned int k2 = *data++;
                k2 *= m; k2 ^= k2 >> r; k2 *= m;
                h2 *= m; h2 ^= k2;
                len -= 4;
        }

        if(len >= 4)
        {
                unsigned int k1 = *data++;
                k1 *= m; k1 ^= k1 >> r; k1 *= m;
                h1 *= m; h1 ^= k1;
                len -= 4;
        }

        switch(len)
        {
        case 3: h2 ^= ((unsigned char*)data)[2] << 16;
        case 2: h2 ^= ((unsigned char*)data)[1] << 8;
        case 1: h2 ^= ((unsigned char*)data)[0];
                        h2 *= m;
        };

        h1 ^= h2 >> 18; h1 *= m;
        h2 ^= h1 >> 22; h2 *= m;
        h1 ^= h2 >> 17; h1 *= m;
        h2 ^= h1 >> 19; h2 *= m;

        uint64_t h = h1;

        h = (h << 32) | h2;

        return h;
}