[转载]最近涉及字符串列表存储，为加快检索速度，搜集了一些哈希函数，C语言的代码保存见内

static unsigned long _crc32_table[256] = {
    0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988, 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 
    0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de, 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, 0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5, 
    0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172, 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59, 
    0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924, 0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 
    0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433, 0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01, 
    0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, 0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65, 
    0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0, 0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 
    0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f, 0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 
    0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a, 0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8, 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, 
    0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc, 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 
    0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b, 0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79, 
    0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236, 0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d, 
    0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713, 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, 0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 
    0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777, 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 
    0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2, 0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9, 
    0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94, 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d
};

unsigned long crc32(unsigned long crc, unsigned char* input, int len)
{
    int i;
    unsigned char index;
    unsigned char* pch;
    pch = input;
    for( i = 0 ; i < len; i++)
    {
        index = (unsigned char)(crc^*pch);
        crc = (crc>>8)^_crc32_table[index];
        pch++;
    }
    return crc;
}

// ELF Hash Function
unsigned int ELF_Hash(unsigned char* input, int len)
{
    unsigned int hash = 0;
    unsigned int x = 0;

    unsigned char* pch;
    pch = (unsigned char*)input;
    for(unsigned int i = 0 ; i < len; i++)
    {
        hash = (hash << 4) + (*pch); //hash左移4位，把当前字符ASCII存入hash低四位。
        pch ++;
        if ((x = hash & 0xF0000000L) != 0)
        {
            //如果最高的四位不为0，则说明字符多余7个，现在正在存第7个字符，如果不处理，再加下一个字符时，第一个字符会被移出，因此要有如下处理。
            //该处理，如果最高位为0，就会仅仅影响5-8位，否则会影响5-31位，因为C语言使用的算数移位
            //因为1-4位刚刚存储了新加入到字符，所以不能>>28
            hash ^= (x >> 24);
            //上面这行代码并不会对X有影响，本身X和hash的高4位相同，下面这行代码&~即对28-31(高4位)位清零。
            hash &= ~x;
        }
    }
    //返回一个符号位为0的数，即丢弃最高位，以免函数外产生影响。(我们可以考虑，如果只有字符，符号位不可能为负)
    return (hash & 0x7FFFFFFF);
}

/// @brief BKDR Hash Function
/// @detail 本算法由于在Brian Kernighan与Dennis Ritchie的《The C Programming Language》一书被展示而得名，是一种简单快捷的hash算法，也是Java目前采用的字符串的Hash算法（累乘因子为31）。
template<class T>
size_t BKDRHash(const T *str)
{
    register size_t hash = 0;
    while (size_t ch = (size_t)*str++)
    {        
        hash = hash * 131 + ch;   // 也可以乘以31、131、1313、13131、131313..
        // 有人说将乘法分解为位运算及加减法可以提高效率，如将上式表达为：hash = hash << 7 + hash << 1 + hash + ch;
        // 但其实在Intel平台上，CPU内部对二者的处理效率都是差不多的，
        // 我分别进行了100亿次的上述两种运算，发现二者时间差距基本为0（如果是Debug版，分解成位运算后的耗时还要高1/3）；
        // 在ARM这类RISC系统上没有测试过，由于ARM内部使用Booth's Algorithm来模拟32位整数乘法运算，它的效率与乘数有关：
        // 当乘数8-31位都为1或0时，需要1个时钟周期
        // 当乘数16-31位都为1或0时，需要2个时钟周期
        // 当乘数24-31位都为1或0时，需要3个时钟周期
        // 否则，需要4个时钟周期
        // 因此，虽然我没有实际测试，但是我依然认为二者效率上差别不大        
    }
    return hash;
}
/// @brief SDBM Hash Function
/// @detail 本算法是由于在开源项目SDBM（一种简单的数据库引擎）中被应用而得名，它与BKDRHash思想一致，只是种子不同而已。
template<class T>
size_t SDBMHash(const T *str)
{
    register size_t hash = 0;
    while (size_t ch = (size_t)*str++)
    {
        hash = 65599 * hash + ch;        
        //hash = (size_t)ch + (hash << 6) + (hash << 16) - hash;
    }
    return hash;
}

/// @brief RS Hash Function
/// @detail 因Robert Sedgwicks在其《Algorithms in C》一书中展示而得名。
template<class T>
size_t RSHash(const T *str)
{
    register size_t hash = 0;
    size_t magic = 63689;    
    while (size_t ch = (size_t)*str++)
    {
        hash = hash * magic + ch;
        magic *= 378551;
    }
    return hash;
}
/// @brief AP Hash Function
/// @detail 由Arash Partow发明的一种hash算法。
template<class T>
size_t APHash(const T *str)
{
    register size_t hash = 0;
    size_t ch;
    for (long i = 0; ch = (size_t)*str++; i++)
    {
        if ((i & 1) == 0)
        {
            hash ^= ((hash << 7) ^ ch ^ (hash >> 3));
        }
        else
        {
            hash ^= (~((hash << 11) ^ ch ^ (hash >> 5)));
        }
    }
    return hash;
}
/// @brief JS Hash Function
/// 由Justin Sobel发明的一种hash算法。
template<class T>
size_t JSHash(const T *str)
{
    if(!*str)         // 这是由本人添加，以保证空字符串返回哈希值0
        return 0;
    register size_t hash = 1315423911;
    while (size_t ch = (size_t)*str++)
    {
        hash ^= ((hash << 5) + ch + (hash >> 2));
    }
    return hash;
}
/// @brief DEK Function
/// @detail 本算法是由于Donald E. Knuth在《Art Of Computer Programming Volume 3》中展示而得名。
template<class T>
size_t DEKHash(const T* str)
{
    if(!*str)         // 这是由本人添加，以保证空字符串返回哈希值0
        return 0;
    register size_t hash = 1315423911;
    while (size_t ch = (size_t)*str++)
    {
        hash = ((hash << 5) ^ (hash >> 27)) ^ ch;
    }
    return hash;
}
/// @brief FNV Hash Function
/// @detail Unix system系统中使用的一种著名hash算法，后来微软也在其hash_map中实现。
template<class T>
size_t FNVHash(const T* str)
{
    if(!*str)    // 这是由本人添加，以保证空字符串返回哈希值0
        return 0;
    register size_t hash = 2166136261;
    while (size_t ch = (size_t)*str++)
    {
        hash *= 16777619;
        hash ^= ch;
    }
    return hash;
}
/// @brief DJB Hash Function
/// @detail 由Daniel J. Bernstein教授发明的一种hash算法。
template<class T>
size_t DJBHash(const T *str)
{
    if(!*str)    // 这是由本人添加，以保证空字符串返回哈希值0
        return 0;
    register size_t hash = 5381;
    while (size_t ch = (size_t)*str++)
    {
        hash += (hash << 5) + ch;
    }
    return hash;
}
/// @brief DJB Hash Function 2
/// @detail 由Daniel J. Bernstein 发明的另一种hash算法。
template<class T>
size_t DJB2Hash(const T *str)
{
    if(!*str)    // 这是由本人添加，以保证空字符串返回哈希值0
        return 0;
    register size_t hash = 5381;
    while (size_t ch = (size_t)*str++)
    {
        hash = hash * 33 ^ ch;
    }
    return hash;
}
/// @brief PJW Hash Function
/// @detail 本算法是基于AT&T贝尔实验室的Peter J. Weinberger的论文而发明的一种hash算法。
template<class T>
size_t PJWHash(const T *str)
{
    static const size_t TotalBits        = sizeof(size_t) * 8;
    static const size_t ThreeQuarters    = (TotalBits  * 3) / 4;
    static const size_t OneEighth        = TotalBits / 8;
    static const size_t HighBits        = ((size_t)-1) << (TotalBits - OneEighth);    

    register size_t hash = 0;
    size_t magic = 0;    
    while (size_t ch = (size_t)*str++)
    {
        hash = (hash << OneEighth) + ch;
        if ((magic = hash & HighBits) != 0)
        {
            hash = ((hash ^ (magic >> ThreeQuarters)) & (~HighBits));
        }
    }
    return hash;
}
/// @brief ELF Hash Function
/// @detail 由于在Unix的Extended Library Function被附带而得名的一种hash算法，它其实就是PJW Hash的变形。
template<class T>
size_t ELFHash(const T *str)
{
    static const size_t TotalBits        = sizeof(size_t) * 8;
    static const size_t ThreeQuarters    = (TotalBits  * 3) / 4;
    static const size_t OneEighth        = TotalBits / 8;
    static const size_t HighBits        = ((size_t)-1) << (TotalBits - OneEighth);    
    register size_t hash = 0;
    size_t magic = 0;
    while (size_t ch = (size_t)*str++)
    {
        hash = (hash << OneEighth) + ch;
        if ((magic = hash & HighBits) != 0)
        {
            hash ^= (magic >> ThreeQuarters);
            hash &= ~magic;
        }        
    }
    return hash;
}

unsigned int RSHash(char* str, unsigned int len)  
{  
    unsigned int b    = 378551;  
    unsigned int a    = 63689;  
    unsigned int hash = 0;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = hash * a + (*str);  
        a    = a * b;  
    }  
    return hash;  
}  
/* End Of RS Hash Function */  

unsigned int JSHash(char* str, unsigned int len)  
{  
    unsigned int hash = 1315423911;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash ^= ((hash << 5) + (*str) + (hash >> 2));  
    }  
    return hash;  
}  
/* End Of JS Hash Function */  

unsigned int PJWHash(char* str, unsigned int len)  
{  
    const unsigned int BitsInUnsignedInt = (unsigned int)(sizeof(unsigned int) * 8);  
    const unsigned int ThreeQuarters     = (unsigned int)((BitsInUnsignedInt  * 3) / 4);  
    const unsigned int OneEighth         = (unsigned int)(BitsInUnsignedInt / 8);  
    const unsigned int HighBits          = (unsigned int)(0xFFFFFFFF) << (BitsInUnsignedInt - OneEighth);  
    unsigned int hash              = 0;  
    unsigned int test              = 0;  
    unsigned int i                 = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = (hash << OneEighth) + (*str);  
        if((test = hash & HighBits)  != 0)  
        {  
            hash = (( hash ^ (test >> ThreeQuarters)) & (~HighBits));  
        }  
    }  
    return hash;  
}  
/* End Of  P. J. Weinberger Hash Function */  

unsigned int ELFHash(char* str, unsigned int len)  
{  
    unsigned int hash = 0;  
    unsigned int x    = 0;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = (hash << 4) + (*str);  
        if((x = hash & 0xF0000000L) != 0)  
        {  
            hash ^= (x >> 24);  
        }  
        hash &= ~x;  
    }  
    return hash;  
}  
/* End Of ELF Hash Function */  

unsigned int BKDRHash(char* str, unsigned int len)  
{  
    unsigned int seed = 131; /* 31 131 1313 13131 131313 etc.. */  
    unsigned int hash = 0;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = (hash * seed) + (*str);  
    }  
    return hash;  
}  
/* End Of BKDR Hash Function */  

unsigned int SDBMHash(char* str, unsigned int len)  
{  
    unsigned int hash = 0;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = (*str) + (hash << 6) + (hash << 16) - hash;  
    }  
    return hash;  
}  
/* End Of SDBM Hash Function */  

unsigned int DJBHash(char* str, unsigned int len)  
{  
    unsigned int hash = 5381;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = ((hash << 5) + hash) + (*str);  
    }  
    return hash;  
}  
/* End Of DJB Hash Function */  

unsigned int DEKHash(char* str, unsigned int len)  
{  
    unsigned int hash = len;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = ((hash << 5) ^ (hash >> 27)) ^ (*str);  
    }  
    return hash;  
}  
/* End Of DEK Hash Function */  

unsigned int BPHash(char* str, unsigned int len)  
{  
    unsigned int hash = 0;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash = hash << 7 ^ (*str);  
    }  
    return hash;  
}  

/* End Of BP Hash Function */  
unsigned int FNVHash(char* str, unsigned int len)  
{  
    const unsigned int fnv_prime = 0x811C9DC5;  
    unsigned int hash      = 0;  
    unsigned int i         = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash *= fnv_prime;  
        hash ^= (*str);  
    }  
    return hash;  
}  
/* End Of FNV Hash Function */  
unsigned int APHash(char* str, unsigned int len)  
{  
    unsigned int hash = 0xAAAAAAAA;  
    unsigned int i    = 0;  
    for(i = 0; i < len; str++, i++)  
    {  
        hash ^= ((i & 1) == 0) ? (  (hash <<  7) ^ (*str) * (hash >> 3)) :  
            (~((hash << 11) + (*str) ^ (hash >> 5)));  
    }  
    return hash;  
}  
/* End Of AP Hash Function */  

//PHP中出现的字符串Hash函数
static unsigned long hashpjw(char *arKey, unsigned int nKeyLength)
{
    unsigned long h = 0, g;
    char *arEnd=arKey+nKeyLength;

    while (arKey < arEnd) {
        h = (h << 4) + *arKey++;
        if ((g = (h & 0xF0000000))) {
            h = h ^ (g >> 24);
            h = h ^ g;
        }
    }
    return h;
}

// OpenSSL中出现的字符串Hash函数 
unsigned int lh_strhash(void *src)
{
    int i, l;
    unsigned long ret = 0;
    unsigned short *s;
    char *str = (char *)src;
    if (str == NULL)
        return(0);
    l = (strlen(str) + 1) / 2;
    s = (unsigned short *)str;

    for (i = 0; i < l; i++) 
        ret ^= s[i]<<(i&0x0f);

    return(ret);
}

/*
 * The following hash seems to work very well on normal text strings no
 * collisions on /usr/dict/words and it distributes on %2^n quite well, not
 * as good as MD5, but still good.
 */
unsigned long OPENSSL_LH_strhash(const char *c)
{
    unsigned long ret = 0;
    long n;
    unsigned long v;
    int r;

    if ((c == NULL) || (*c == '\0'))
        return (ret);
/*-
    unsigned char b[16];
    MD5(c,strlen(c),b);
    return(b[0]|(b[1]<<8)|(b[2]<<16)|(b[3]<<24));
*/

    n = 0x100;
    while (*c) {
        v = n | (*c);
        n += 0x100;
        r = (int)((v >> 2) ^ v) & 0x0f;
        ret = (ret << r) | (ret >> (32 - r));
        ret &= 0xFFFFFFFFL;
        ret ^= v * v;
        c++;
    }
    return ((ret >> 16) ^ ret);
}