哈希算法將任意長度的二進制值映射爲固定長度的較小二進制值，這個小的二進制值稱爲哈希值。哈希值是一段數據唯一且極其緊湊的數值表示形式。如果散列一段明文而且哪怕只更改該段落的一個字母，隨後的哈希都將產生不同的值。要找到散列爲同一個值的兩個不同的輸入，在計算上是不可能的，所以數據的哈希值可以檢驗數據的完整性。
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)。
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，下面是幾款經典軟件中使用到的字符串Hash函數實現，通過閱讀這些代碼，我們可以在Hash算法的執行效率、離散性、空間利用率等方面有比較深刻的瞭解。
下面分別介紹幾個經典軟件中出現的字符串Hash函數。
●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;
}
●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);
}
●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
●另一個經典字符串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;
}