几种经典的HASH算法的实现(源代码)
合集下载
相关主题
- 1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。
return((ret>>16)^ret); } ●MySql 中出现的字符串 Hash 函数 #ifndef NEW_HASH_FUNCTION
/* Calc hashvalue for a key */ static uint calc_hashnr(const byte *key,uint length) { register uint nr=1, nr2=4;
for(h=0, p = (unsigned char *)str; *p ; p++) h = 31 * h + *p;
return h;
}
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;
for (hash = 0; key < end; key++) { hash *= 16777619; hash ^= (uint) (uchar) toupper(*key); }
return (hash); } #endif
Mysql 中对字符串 Hash 函数还区分了大小写
●另一个经典字符串 Hash 函数 unsigned int hash(char *str) { register unsigned int h; register unsigned char *p;
●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 long lh_strhash(char *str) { int i,l; unsigned long ret=0; unsigned short *s;
链表查找的时间效率为 O(N)，二分法为 log2N，B+ Tree 为 log2N，但 Hash 链表查找的时间效率为 O(1)。 设计高效算法往往需要使用 Hash 链表，常数级的查找速度是任何别的算法无法比拟的，Hash 链表的构造和 冲突的不同实现方法对效率当然有一定的影响，然 而 Hash 函数是 Hash 链表最核心的部分，下面是几款经 典软件中使用到的字符串 Hash 函数实现，通过阅读这些代码，我们可以在 Hash 算法的执行效率、离散性、 空间利用率等方面有比较深刻的了解。 下面分别介绍几个经典软件中出现的字符串 Hash 函数。
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++; }
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)+nr2பைடு நூலகம்*((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 (kpv@research.att.com) and * Glenn Fowler (gsf@research.att.com). Landon Curt Noll (chongo@toad.com) * 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;
/* Calc hashvalue for a key */ static uint calc_hashnr(const byte *key,uint length) { register uint nr=1, nr2=4;
for(h=0, p = (unsigned char *)str; *p ; p++) h = 31 * h + *p;
return h;
}
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;
for (hash = 0; key < end; key++) { hash *= 16777619; hash ^= (uint) (uchar) toupper(*key); }
return (hash); } #endif
Mysql 中对字符串 Hash 函数还区分了大小写
●另一个经典字符串 Hash 函数 unsigned int hash(char *str) { register unsigned int h; register unsigned char *p;
●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 long lh_strhash(char *str) { int i,l; unsigned long ret=0; unsigned short *s;
链表查找的时间效率为 O(N)，二分法为 log2N，B+ Tree 为 log2N，但 Hash 链表查找的时间效率为 O(1)。 设计高效算法往往需要使用 Hash 链表，常数级的查找速度是任何别的算法无法比拟的，Hash 链表的构造和 冲突的不同实现方法对效率当然有一定的影响，然 而 Hash 函数是 Hash 链表最核心的部分，下面是几款经 典软件中使用到的字符串 Hash 函数实现，通过阅读这些代码，我们可以在 Hash 算法的执行效率、离散性、 空间利用率等方面有比较深刻的了解。 下面分别介绍几个经典软件中出现的字符串 Hash 函数。
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++; }
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)+nr2பைடு நூலகம்*((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 (kpv@research.att.com) and * Glenn Fowler (gsf@research.att.com). Landon Curt Noll (chongo@toad.com) * 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;