常用hash算法及评测[转]
RS hash 算法
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 */
JS hash 算法
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 */
PJW hash 算法
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 */
ELF hash 算法
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 */
BKDR hash 算法
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 */
SDBM hash 算法
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 */
DJB hash 算法
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 */
DEK hash 算法
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 */
BP hash 算法
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 */
FNV hash 算法
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 */
AP hash 算法
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 */
各种算法评测
| Hash函数 | 数据1 | 数据2 | 数据3 | 数据4 | 数据1得分 | 数据2得分 | 数据3得分 | 数据4得分 | 平均分 |
| BKDRHash | 2 | 0 | 4774 | 481 | 96.55 | 100 | 90.95 | 82.05 | 92.64 |
| APHash | 2 | 3 | 4754 | 493 | 96.55 | 88.46 | 100 | 51.28 | 86.28 |
| DJBHash | 2 | 2 | 4975 | 474 | 96.55 | 92.31 | 0 | 100 | 83.43 |
| JSHash | 1 | 4 | 4761 | 506 | 100 | 84.62 | 96.83 | 17.95 | 81.94 |
| RSHash | 1 | 0 | 4861 | 505 | 100 | 100 | 51.58 | 20.51 | 75.96 |
| SDBMHash | 3 | 2 | 4849 | 504 | 93.1 | 92.31 | 57.01 | 23.08 | 72.41 |
| PJWHash | 30 | 26 | 4878 | 513 | 0 | 0 | 43.89 | 0 | 21.95 |
| ELFHash | 30 | 26 | 4878 | 513 | 0 | 0 | 43.89 | 0 | 21.95 |
其中
数据1为100000个字母和数字组成的随机串哈希冲突个数。
数据2为100000个有意义的英文句子哈希冲突个数。
数据3为数据1的哈希值与1000003(大素数)求模后存储到线性表中冲突的个数。
数据4为数据1的哈希值与10000019(更大素数)求模后存储到线性表中冲突的个数。
经过比较，得出以上平均得分。平均数为平方平均数。
可以发现，
BKDRHash无论是在实际效果还是编码实现中，效果都是最突出的。
APHash也是较为优秀的算法。DJBHash,JSHash,RSHash与SDBMHash各有千秋。
PJWHash与ELFHash效果最差，但得分相似，其算法本质是相似的。
