几种字符串哈希HASH算法的性能比较..docx

几种字符串哈希HASH算法的性能比较 2011年01月26日 星期三 19:40这不就是要找hash table的hash function吗？??1 概述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，本文尝试分析一些经典软件中使用到的字符串 Hash函数在执行效率、离散性、空间利用率等方面的性能问题。2 经典字符串Hash函数介绍作者阅读过大量经典软件原代码，下面分别介绍几个经典软件中出现的字符串Hash函数。2.1 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;}2.2 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;if (str == NULL) return(0);l=(strlen(str)+1)/2;s=(unsigned short *)str;for (i=0; iret^=(s[i](i0x0f));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)((v2)^v)0x0f;ret=(ret(32-r));ret=0xFFFFFFFFL;ret^=v*v;c++;}return((ret16)^ret);}在下面的测量过程中我们分别将上面的两个函数标记为OpenSSL_Hash1和OpenSSL_Hash2，至于上面的实现中使用MD5算法的实现函数我们不作测试。2.3 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;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 e