-
-
-
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;
-
-
-
-
-
-
-
-
-
-
}
-
return hash;
-
}
-
-
-
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;
-
-
}
-
return hash;
-
}
-
-
-
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;
-
}
-
-
-
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;
-
}
-
-
-
template<class T>
-
size_t JSHash(const T *str)
-
{
-
if(!*str)
-
return 0;
-
register size_t hash = 1315423911;
-
while (size_t ch = (size_t)*str++)
-
{
-
hash ^= ((hash << 5) + ch + (hash >> 2));
-
}
-
return hash;
-
}
-
-
-
template<class T>
-
size_t DEKHash(const T* str)
-
{
-
if(!*str)
-
return 0;
-
register size_t hash = 1315423911;
-
while (size_t ch = (size_t)*str++)
-
{
-
hash = ((hash << 5) ^ (hash >> 27)) ^ ch;
-
}
-
return hash;
-
}
-
-
-
template<class T>
-
size_t FNVHash(const T* str)
-
{
-
if(!*str)
-
return 0;
-
register size_t hash = 2166136261;
-
while (size_t ch = (size_t)*str++)
-
{
-
hash *= 16777619;
-
hash ^= ch;
-
}
-
return hash;
-
}
-
-
-
template<class T>
-
size_t DJBHash(const T *str)
-
{
-
if(!*str)
-
return 0;
-
register size_t hash = 5381;
-
while (size_t ch = (size_t)*str++)
-
{
-
hash += (hash << 5) + ch;
-
}
-
return hash;
-
}
-
-
-
template<class T>
-
size_t DJB2Hash(const T *str)
-
{
-
if(!*str)
-
return 0;
-
register size_t hash = 5381;
-
while (size_t ch = (size_t)*str++)
-
{
-
hash = hash * 33 ^ ch;
-
}
-
return hash;
-
}
-
-
-
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;
-
}
-
-
-
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;
-
}
这些hash的散列质量及效率作了一个简单测试,测试结果如下:
测试1:对100000个由大小写字母与数字随机的ANSI字符串(无重复,每个字符串最大长度不超过64字符)进行散列:
字符串函数
|
冲突数
|
除1000003取余后的冲突数
|
BKDRHash
|
0
|
4826
|
SDBMHash
|
2
|
4814
|
RSHash
|
2
|
4886
|
APHash
|
0
|
4846
|
ELFHash
|
1515
|
6120
|
JSHash
|
779
|
5587
|
DEKHash
|
863
|
5643
|
FNVHash
|
2
|
4872
|
DJBHash
|
832
|
5645
|
DJB2Hash
|
695
|
5309
|
PJWHash
|
1515
|
6120
|
测试2:对100000个由任意UNICODE组成随机字符串(无重复,每个字符串最大长度不超过64字符)进行散列:
字符串函数
|
冲突数
|
除1000003取余后的冲突数
|
BKDRHash
|
3
|
4710
|
SDBMHash
|
3
|
4904
|
RSHash
|
3
|
4822
|
APHash
|
2
|
4891
|
ELFHash
|
16
|
4869
|
JSHash
|
3
|
4812
|
DEKHash
|
1
|
4755
|
FNVHash
|
1
|
4803
|
DJBHash
|
1
|
4749
|
DJB2Hash
|
2
|
4817
|
PJWHash
|
16
|
4869
|
测试3:对1000000个随机ANSI字符串(无重复,每个字符串最大长度不超过64字符)进行散列:
字符串函数
|
耗时(毫秒)
|
BKDRHash
|
109
|
SDBMHash
|
109
|
RSHash
|
124
|
APHash
|
187
|
ELFHash
|
249
|
JSHash
|
172
|
DEKHash
|
140
|
FNVHash
|
125
|
DJBHash
|
125
|
DJB2Hash
|
125
|
PJWHash
|
234
|
结论:也许是我的样本存在一些特殊性,在对ASCII码字符串进行散列时,PJW与ELF Hash(它们其实是同一种算法)无论是质量还是效率,都相当糟糕;例如:"b5"与“aE",这两个字符串按照PJW散列出来的hash值就是一样的。 另外,其它几种依靠异或来散列的哈希函数,如:JS/DEK/DJB Hash,在对字母与数字组成的字符串的散列效果也不怎么好。相对而言,还是BKDR与SDBM这类简单的Hash效率与效果更好。
其他:
作者:icefireelf
出处:http://blog.csdn.net/icefireelf/article/details/5796529
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。对于以上几种哈 希函数,我对其进行了一个小小的评测。
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。
/* 一些Hash算法的转换:将乘除算法转为加减移位*/
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);
}
阅读(2835) | 评论(0) | 转发(0) |