logo头像

博学广问,自律静思

[转载]各种字符串Hash函数

常用的字符串Hash函数还有ELFHash,APHash等等,都是十分简单有效的方法。这些函数使用位运算使得每一个字符都对最后的函数值产生影响。另外还有以MD5和SHA1为代表的杂凑函数,这些函数几乎不可能找到碰撞。

常用字符串哈希函数有BKDRHash,APHash,DJBHash,JSHash,RSHash,SDBMHash,PJWHash,ELFHash等等。

具体的代码分享

//SDBMHash
unsigned int SDBMHash(char *str)
{
unsigned int hash = 0;

while (*str)
{
    // equivalent to: hash = 65599\*hash + (\*str++);
    hash = (*str++) + (hash << 6) + (hash << 16) - hash;
}

return (hash & 0x7FFFFFFF);

}

// RS Hash Function
unsigned int RSHash(char *str)
{
unsigned int b = 378551;
unsigned int a = 63689;
unsigned int hash = 0;

while (*str)
{
    hash = hash * a + (*str++);
    a *= b;
}

return (hash & 0x7FFFFFFF);

}

// JS Hash Function
unsigned int JSHash(char *str)
{
unsigned int hash = 1315423911;

while (*str)
{
    hash ^= ((hash << 5) + (*str++) + (hash >> 2));
}

return (hash & 0x7FFFFFFF);

}

// P. J. Weinberger Hash Function
unsigned int PJWHash(char *str)
{
unsigned int BitsInUnignedInt = (unsigned int)(sizeof(unsigned int) * 8);
unsigned int ThreeQuarters = (unsigned int)((BitsInUnignedInt * 3) / 4);
unsigned int OneEighth = (unsigned int)(BitsInUnignedInt / 8);
unsigned int HighBits = (unsigned int)(0xFFFFFFFF) << (BitsInUnignedInt - OneEighth);
unsigned int hash = 0;
unsigned int test = 0;

while (*str)
{
    hash = (hash << OneEighth) + (*str++);
    if ((test = hash & HighBits) != 0)
    {
        hash = ((hash ^ (test >> ThreeQuarters)) & (~HighBits));
    }
}

return (hash & 0x7FFFFFFF);

}

// ELF Hash Function
unsigned int ELFHash(char *str)
{
unsigned int hash = 0;
unsigned int x = 0;

while (*str)
{
    hash = (hash << 4) + (*str++);
    if ((x = hash & 0xF0000000L) != 0)
    {
        hash ^= (x >> 24);
        hash &= ~x;
    }
}

return (hash & 0x7FFFFFFF);

}

// BKDR Hash Function
unsigned int BKDRHash(char *str)
{
unsigned int seed = 131; // 31 131 1313 13131 131313 etc..
unsigned int hash = 0;

while (*str)
{
    hash = hash * seed + (*str++);
}

return (hash & 0x7FFFFFFF);

}

// DJB Hash Function
unsigned int DJBHash(char *str)
{
unsigned int hash = 5381;

while (*str)
{
    hash += (hash << 5) + (*str++);
}

return (hash & 0x7FFFFFFF);

}

// AP Hash Function
unsigned int APHash(char *str)
{
unsigned int hash = 0;
int i;

for (i=0; *str; i++)
{
    if ((i & 1) == 0)
    {
        hash ^= ((hash << 7) ^ (*str++) ^ (hash >> 3));
    }
    else
    {
        hash ^= (~((hash << 11) ^ (*str++) ^ (hash >> 5)));
    }
}

return (hash & 0x7FFFFFFF);

}