Python中的stringlib字符串查找算法是Boyer-Moore, Horspool, Sunday, Bloom Filter几种算法的合成体, 大概的原理如下:

def find(s, p):# find first occurrence of p in sn = len(s)m = len(p)skip = delta1(p)[p[m-1]]i = 0while i <= n-m:if s[i+m-1] == p[m-1]: # (boyer-moore)# potential matchif s[i:i+m-1] == p[:m-1]:return iif s[i+m] not in p:i = i + m + 1 # (sunday)else:i = i + skip # (horspool)else:# skipif s[i+m] not in p:i = i + m + 1 # (sunday)else:i = i + 1return -1 # not found

以下是具体实现:

/* stringlib: fastsearch implementation */#ifndef STRINGLIB_FASTSEARCH_H
#define STRINGLIB_FASTSEARCH_H#include <stdint.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>/* fast search/count implementation, based on a mix between boyer-moore and horspool, with a few more bells and whistles on the top.for some more background, see: http://effbot.org/zone/stringlib.htm *//* note: fastsearch may access s[n], which isn't a problem when usingPython's ordinary string types, but may cause problems if you'reusing this code in other contexts.  also, the count mode returns -1if there cannot possible be a match in the target string, and 0 ifit has actually checked for matches, but didn't find any.  callersbeware! */#define FAST_COUNT 0
#define FAST_SEARCH 1
#define FAST_RSEARCH 2#ifndef LONG_BIT
#define LONG_BIT 32
#endif#if LONG_BIT >= 128
#define STRINGLIB_BLOOM_WIDTH 128
#elif LONG_BIT >= 64
#define STRINGLIB_BLOOM_WIDTH 64
#elif LONG_BIT >= 32
#define STRINGLIB_BLOOM_WIDTH 32
#else
#error "LONG_BIT is smaller than 32"
#endif#define STRINGLIB_BLOOM_ADD(mask, ch) \((mask |= (1UL << ((ch) & (STRINGLIB_BLOOM_WIDTH -1)))))
#define STRINGLIB_BLOOM(mask, ch)     \((mask &  (1UL << ((ch) & (STRINGLIB_BLOOM_WIDTH -1)))))ssize_t fastsearch(const char *s, ssize_t n,const char *p, ssize_t m,ssize_t maxcount, int mode)
{unsigned long mask;ssize_t skip, count = 0;ssize_t i, j, mlast, w;w = n - m;if (w < 0 || (mode == FAST_COUNT && maxcount == 0)) {return -1;}/* look for special cases */if (m <= 1) {if (m <= 0) {return -1;}/* use special case for 1-character strings */if (mode == FAST_COUNT) {for (i = 0; i < n; i++)if (s[i] == p[0]) {count++;if (count == maxcount) {return maxcount;}}return count;}else if (mode == FAST_SEARCH) {for (i = 0; i < n; i++)if (s[i] == p[0]) {return i;}}else {      /* FAST_RSEARCH */for (i = n - 1; i > -1; i--)if (s[i] == p[0]) {return i;}}return -1;}mlast = m - 1;skip = mlast - 1;mask = 0;if (mode != FAST_RSEARCH) {/* create compressed boyer-moore delta 1 table *//* process pattern[:-1] */for (i = 0; i < mlast; i++) {STRINGLIB_BLOOM_ADD(mask, p[i]);if (p[i] == p[mlast]) {skip = mlast - i - 1;}}/* process pattern[-1] outside the loop */STRINGLIB_BLOOM_ADD(mask, p[mlast]);for (i = 0; i <= w; i++) {/* note: using mlast in the skip path slows things down on x86 */if (s[i + m - 1] == p[m - 1]) {/* candidate match */for (j = 0; j < mlast; j++)if (s[i + j] != p[j]) {break;}if (j == mlast) {/* got a match! */if (mode != FAST_COUNT) {return i;}count++;if (count == maxcount) {return maxcount;}i = i + mlast;continue;}/* miss: check if next character is part of pattern */if (!STRINGLIB_BLOOM(mask, s[i + m])) {i = i + m;}else {i = i + skip;}}else {/* skip: check if next character is part of pattern */if (!STRINGLIB_BLOOM(mask, s[i + m])) {i = i + m;}}}}else {      /* FAST_RSEARCH *//* create compressed boyer-moore delta 1 table *//* process pattern[0] outside the loop */STRINGLIB_BLOOM_ADD(mask, p[0]);/* process pattern[:0:-1] */for (i = mlast; i > 0; i--) {STRINGLIB_BLOOM_ADD(mask, p[i]);if (p[i] == p[0]) {skip = i - 1;}}for (i = w; i >= 0; i--) {if (s[i] == p[0]) {/* candidate match */for (j = mlast; j > 0; j--)if (s[i + j] != p[j]) {break;}if (j == 0)/* got a match! */{return i;}/* miss: check if previous character is part of pattern */if (!STRINGLIB_BLOOM(mask, s[i - 1])) {i = i - m;}else {i = i - skip;}}else {/* skip: check if previous character is part of pattern */if (!STRINGLIB_BLOOM(mask, s[i - 1])) {i = i - m;}}}}if (mode != FAST_COUNT) {return -1;}return count;
}#endif

测试代码

#include <arch/cycle.h>int main(int argc, char **argv)
{char *str = "GET / HTTP 1.0\r\nHost: www.xxx.com\r\nCache: \r\nCache:\r\n Length:\r\n";ssize_t rc = 0;uint64_t start, end;start = get_cycle_count();rc = fastsearch(str, strlen(str), "Cache:", 6, 2, FAST_SEARCH);end = get_cycle_count();printf("fastsearch return %u cost %llu \n", rc, end - start);printf("result = %s\n", str + rc);rc = fastsearch(str, strlen(str), "Cache:", 6, -1, FAST_COUNT);printf("result = %u\n", rc);return 0;
}

看stringlib测试数据, 还是蛮可以的.

我在tile平台上测试发现还没有snort中的BMH算法速度快.

不过这个只是单一测试, 没有考虑到cache的情况, 仅供参考.

原文参考:

The stringlib Library 有详细的描叙.

提取Python stringlib中的BMHBNFS字符串查找算法相关推荐

暴力子字符串查找算法
暴力子字符串查找算法的名字虽然很霸气,但是效率不是很高.是一种简单.粗暴的查找方式. 在最坏的情况下,暴力子字符串查找算法在长度为N的文本中查找长度为M的模式需要~NM次字符比较. 核心思想:就是对主 ...
python实现kd树以及最近邻查找算法
python实现kd树以及最近邻查找算法一.kd树简介二.kd树生成 1.确定切分域 2.确定数据域 3.理解递归树 4.python实现递归树代码三.kd树上的最近邻查找算法 1.生成搜索路径 ...
Rabin-Karp 指纹字符串查找算法
Rabin-Karp 指纹字符串查找算法 M.O.Rabin 和 R.A.Karp 发明了一种完全不同的基于散列的字符串查找算法.我们需要计算模式字符串的散列函数,然后用相同的散列函数计算文本中所有可 ...
基于中间代码的优化中，循环的查找算法有哪些？循环优化的方法有哪些？举例说明。
基于中间代码的优化中,循环的查找算法有哪些?循环优化的方法有哪些?举例说明. 基于中间代码的优化中,循环的查找算法有哪些?循环优化的方法有哪些?举例说明. 西北工业大学编译原理课件第八章代码优化.p ...
python 提取文字段落中的日期字符串
需求在日常业务开发中常常会碰到需要从一段文字中提取时间的情况.例如从文字中提取发布时间.创建时间等.针对不同的文字情况.不同的时间格式,这里整理一份关于提取大部分文字段落中日期时间的代码.有需要的直 ...
Python API快餐教程(1) - 字符串查找API
摘要: 字符串查找API 字符串处理相关API 字符串是7种序列类型中的一种. 除了序列的操作函数,比如len()来求字符串长度之外,Python还为字符串提供丰富到可以写个编辑器的API. 查找类A ...
python基础（一）字符串查找
(2)字符串查找 .count() 功能:计算指定的字符在字符串里出现的次数有多少格式:字符串.count(查找字符串[,开始索引[,结束索引]]) 返回值:整数 .find() 功能与index( ...
字符串查找算法BF、KMP详解
字符串查找: BF算法: (朴素查找算法) 当查找不成功时,主串返回刚刚起始字符的下一个,子串返回第一个字符位置时间复杂度:O(n*m) int BF(const char* str, const ...
Rabin-Karp字符串查找算法学习：poj1200
本来准备学习Hash的,结果看PPT讲的第一个算法竟然是跟字符串处理相关的,本来Hash中也有一块专门讲字符串Hash的,就按照<算法导论>中的分类,把这个分到"字符串处理&qu ...
leetcode中关于使用二分查找算法思想deal的题型
学习了二分查找的算法思想之后,再leetcode上写了一道常见的简单面试题,现在用博客记录一下我学习刷题的笔记! leetcode 题号69:Sqrt(x)(经典的面试题) 给你一个非负整数 x ,计 ...

提取Python stringlib中的BMHBNFS字符串查找算法

The stringlib Library 有详细的描叙.

提取Python stringlib中的BMHBNFS字符串查找算法相关推荐

最新文章

热门文章