zoukankan      html  css  js  c++  java
  • bmh算法

    #include <string.h>
    #include <limits.h>
     
    /* Returns a pointer to the first occurrence of "needle"
     * within "haystack", or NULL if not found. Works like
     * memmem().
     */
     
    /* Note: In this example needle is a C string. The ending
     * 0x00 will be cut off, so you could call this example with
     * boyermoore_horspool_memmem(haystack, hlen, "abc", sizeof("abc"))
     */
    const unsigned char *
    boyermoore_horspool_memmem(const unsigned char* haystack, size_t hlen,
                               const unsigned char* needle,   size_t nlen)
    {
        size_t scan = 0;
        size_t bad_char_skip[UCHAR_MAX + 1]; /* Officially called:
                                              * bad character shift */
     
        /* Sanity checks on the parameters */
        if (nlen <= 0 || !haystack || !needle)
            return NULL;
     
        /* ---- Preprocess ---- */
        /* Initialize the table to default value */
        /* When a character is encountered that does not occur
         * in the needle, we can safely skip ahead for the whole
         * length of the needle.
         */
        for (scan = 0; scan <= UCHAR_MAX; scan = scan + 1)
            bad_char_skip[scan] = nlen;
     
        /* C arrays have the first byte at [0], therefore:
         * [nlen - 1] is the last byte of the array. */
        size_t last = nlen - 1;
     
        /* Then populate it with the analysis of the needle */
        for (scan = 0; scan < last; scan = scan + 1)
            bad_char_skip[needle[scan]] = last - scan;
     
        /* ---- Do the matching ---- */
     
        /* Search the haystack, while the needle can still be within it. */
        while (hlen >= nlen)
        {
            /* scan from the end of the needle */
            for (scan = last; haystack[scan] == needle[scan]; scan = scan - 1)
                if (scan == 0) /* If the first byte matches, we've found it. */
                    return haystack;
     
            /* otherwise, we need to skip some bytes and start again.
               Note that here we are getting the skip value based on the last byte
               of needle, no matter where we didn't match. So if needle is: "abcd"
               then we are skipping based on 'd' and that value will be 4, and
               for "abcdd" we again skip on 'd' but the value will be only 1.
               The alternative of pretending that the mismatched character was
               the last character is slower in the normal case (E.g. finding
               "abcd" in "...azcd..." gives 4 by using 'd' but only
               4-2==2 using 'z'. */
            hlen     -= bad_char_skip[haystack[last]];
            haystack += bad_char_skip[haystack[last]];
        }
     
        return NULL;
    }
  • 相关阅读:
    网络数据处理缓冲区和缓冲池实现
    主机入侵防御系统(HIPS)分析
    Windows的进程间通信
    Windows的进程间通信
    通过HookNtCreateSection 动态监控驱动sys、动态链接库dll、可执行文件exe加载
    通过HookNtCreateSection 动态监控驱动sys、动态链接库dll、可执行文件exe加载
    HOOK NtCreateSection
    HOOK NtCreateSection
    CreateProcess函数详解及示例
    CreateProcess函数详解及示例
  • 原文地址:https://www.cnblogs.com/maifengqiang/p/3108219.html
Copyright © 2011-2022 走看看