// 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 ) << (BitsInU
nignedInt - 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 );
}
// SDBM Hash Function
unsigned int SDBMHash( char * str)
{
unsigned int hash = 0 ;
while ( * str)
{
hash = ( * str ++ ) + (hash << 6 ) + (hash << 16 ) - hash;
}
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 );
}
比較經典的字符串hash就這些了吧,"ELF Hash Function" <-這個比較常用.
設 計高效算法往往需要使用Hash鏈表,常數級的查找速度是任何別的算法無法比擬的,Hash鏈表的構造和衝突的不同實現方法對效率當然有一定的影響,然 而Hash函數是Hash鏈表最核心的部分,本文嘗試分析一些經典軟件中使用到的字符串Hash函數在執行效率、離散性、空間利用率等方面的性能問題。
從上表可以看出,這些經典軟件雖然構造字符串Hash函數的方法不同,但是它們的效率都是不錯的,相互之間差距很小,讀者可以參考實際情況從其中借鑑使用。
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 ) << (BitsInU
nignedInt - 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 );
}
// SDBM Hash Function
unsigned int SDBMHash( char * str)
{
unsigned int hash = 0 ;
while ( * str)
{
hash = ( * str ++ ) + (hash << 6 ) + (hash << 16 ) - hash;
}
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 );
}
比較經典的字符串hash就這些了吧,"ELF Hash Function" <-這個比較常用.
字符串hash算法比較
1 概述鏈表查找的時間效率爲O(N),二分法爲log2N,B+ Tree爲log2N,但Hash鏈表查找的時間效率爲O(1)。 |
2 經典字符串Hash函數介紹 |
作者閱讀過大量經典軟件原代碼,下面分別介紹幾個經典軟件中出現的字符串Hash函數。 |
2.1 PHP中出現的字符串Hash函數 |
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; |
} |
2.2 OpenSSL中出現的字符串Hash函數 |
unsigned long lh_strhash(char *str) |
{ |
int i,l; |
unsigned long ret=0; |
unsigned short *s; |
if (str == NULL) return(0); |
l=(strlen(str)+1)/2; |
s=(unsigned short *)str; |
for (i=0; 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 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(32-r)); |
ret&=0xFFFFFFFFL; |
ret^=v*v; |
c++; |
} |
return((ret>>16)^ret); |
} |
在下面的測量過程中我們分別將上面的兩個函數標記爲OpenSSL_Hash1和OpenSSL_Hash2,至於上面的實現中使用MD5算法的實現函數我們不作測試。 |
2.3 MySql中出現的字符串Hash函數 |
#ifndef NEW_HASH_FUNCTION |
/* Calc hashvalue for a key */ |
static uint calc_hashnr(const byte *key,uint length) |
{ |
register uint nr=1, nr2=4; |
while (length--) |
{ |
nr^= (((nr & 63)+nr2)*((uint) (uchar) *key++))+ (nr << 8); |
nr2+=3; |
} |
return((uint) nr); |
} |
/* Calc hashvalue for a key, case indepenently */ |
static uint calc_hashnr_caseup(const byte *key,uint length) |
{ |
register uint nr=1, nr2=4; |
while (length--) |
{ |
nr^= (((nr & 63)+nr2)*((uint) (uchar) toupper(*key++)))+ (nr << 8); |
nr2+=3; |
} |
return((uint) nr); |
} |
#else |
/* |
* Fowler/Noll/Vo hash |
* |
* The basis of the hash algorithm was taken from an idea sent by email to the |
* IEEE Posix P1003.2 mailing list from Phong Vo ([email protected]) and |
* Glenn Fowler ([email protected]). Landon Curt Noll ([email protected]) |
* later improved on their algorithm. |
* |
* The magic is in the interesting relationship between the special prime |
* 16777619 (2^24 + 403) and 2^32 and 2^8. |
* |
* This hash produces the fewest collisions of any function that we've seen so |
* far, and works well on both numbers and strings. |
*/ |
uint calc_hashnr(const byte *key, uint len) |
{ |
const byte *end=key+len; |
uint hash; |
for (hash = 0; key < end; key++) |
{ |
hash *= 16777619; |
hash ^= (uint) *(uchar*) key; |
} |
return (hash); |
} |
uint calc_hashnr_caseup(const byte *key, uint len) |
{ |
const byte *end=key+len; |
uint hash; |
for (hash = 0; key < end; key++) |
{ |
hash *= 16777619; |
hash ^= (uint) (uchar) toupper(*key); |
} |
return (hash); |
} |
#endif |
Mysql中對字符串Hash函數還區分了大小寫,我們的測試中使用不區分大小寫的字符串Hash函數,另外我們將上面的兩個函數分別記爲MYSQL_Hash1和MYSQL_Hash2。 |
2.4 另一個經驗字符串Hash函數 |
unsigned int hash(char *str) |
{ |
register unsigned int h; |
register unsigned char *p; |
for(h=0, p = (unsigned char *)str; *p ; p++) |
h = 31 * h + *p; |
return h; |
} |
3 測試及結果 |
3.1 測試說明 |
從上面給出的經典字符串Hash函數中可以看出,有的涉及到字符串大小敏感問題,我們的測試中只考慮字符串大小寫敏感的函數,另外在上面的函數中有的函數 需要長度參數,有的不需要長度參數,這對函數本身的效率有一定的影響,我們的測試中將對函數稍微作一點修改,全部使用長度參數,並將函數內部出現的計算長 度代碼刪除。 |
我們用來作測試用的Hash鏈表採用經典的拉鍊法解決衝突,另外我們採用靜態分配桶(Hash鏈表長度)的方法來構造Hash鏈表,這主要是爲了簡化我們的實現,並不影響我們的測試結果。 |
測試文本採用單詞表,測試過程中從一個輸入文件中讀取全部不重複單詞構造一個Hash表,測試內容分別是函數總調用次數、函數總調用時間、最大拉鍊長度、 平均拉鍊長度、桶利用率(使用過的桶所佔的比率),其中函數總調用次數是指Hash函數被調用的總次數,爲了測試出函數執行時間,該值在測試過程中作了一 定的放大,函數總調用時間是指Hash函數總的執行時間,最大拉鍊長度是指使用拉鍊法構造鏈表過程中出現的最大拉鍊長度,平均拉鍊長度指拉鍊的平均長度。 |
測試過程中使用的機器配置如下: |
PIII600筆記本,128M內存,windows 2000 server操作系統。 |
3.2 測試結果 |
以下分別是對兩個不同文本文件中的全部不重複單詞構造Hash鏈表的測試結果,測試結果中函數調用次數放大了100倍,相應的函數調用時間也放大了100倍。 |