Boyer Moore 算法实现？

Question

C 中是否有 Boyer-Moore 字符串搜索算法的工作示例？ 我看过一些网站，但它们看起来很糟糕，包括维基百科。

谢谢。

Answer 1

子字符串搜索算法的最佳站点：

http://igm.univ-mlv.fr/~lecroq/string/

Answer 2

在 Bob Stout 的Snippets 网站上有几个 Boyer-Moore-Horspool 的实现（包括周日的变体）。据我所知，Ray Gardner 在BMHSRCH.C 中的实现没有错误¹，而且绝对是我见过或听说过的最快的。然而，这并不是最容易理解的——他使用了一些相当棘手的代码来使内部循环尽可能简单。我可能有偏见，但我认为我在PBMSRCH.C 中的版本² 更容易理解（虽然肯定会慢一些）。

¹ 在其限制范围内 - 它最初是为 MS-DOS 编写的，并且可以为提供更多内存的环境使用重写。
² 这不知何故被贴上“Pratt-Boyer-Moore”的标签，但实际上是周日的 Boyer-Moore-Horspool 的变体（虽然我当时不知道也没有发表，但我相信我实际上发明了大约一年周日之前）。

Answer 3

这是我用很多奇怪的测试用例强调的 C90 实现：

#ifndef MAX
#define MAX(a,b)  ((a > b) ? (a) : (b))
#endif

void  fillBadCharIndexTable (
    /*----------------------------------------------------------------
    function:
       the table fits for 8 bit character only (including utf-8)
    parameters: */
    size_t  aBadCharIndexTable [],
    char const *  const pPattern,
    size_t  const patternLength)
    /*----------------------------------------------------------------*/
{
    size_t  i;
    size_t  remainingPatternLength = patternLength - 1;

    for (i = 0;  i < 256; ++i) {
        aBadCharIndexTable [i] = patternLength;
    }
    for (i = 0;  i < patternLength;  ++i) {
        aBadCharIndexTable [pPattern [i]] = remainingPatternLength--;
    }
}

void  fillGoodSuffixRuleTable (
    /*----------------------------------------------------------------
    function:
       the table fits for patterns of length < 256; for longer patterns ... (1 of)
       - increase the static size
       - use variable length arrays and >= C99 compilers
       - allocate (and finally release) heap according to demand
    parameters: */
    size_t  aGoodSuffixIndexTable [],
    char const *  const pPattern,
    size_t  const patternLength)
    /*----------------------------------------------------------------*/
{
    size_t  const highestPatternIndex = patternLength - 1;
    size_t  prefixLength = 1;

    /* complementary prefix length, i.e. difference from highest possible pattern index and prefix length */
    size_t  cplPrefixLength = highestPatternIndex;

    /* complementary length of recently inspected pattern substring which is simultaneously pattern prefix and suffix */
    size_t  cplPrefixSuffixLength = patternLength;

    /* too hard to explain in a C source ;-) */
    size_t  iRepeatedSuffixMax;

    aGoodSuffixIndexTable [cplPrefixLength] = patternLength;

    while (cplPrefixLength > 0) {
        if (!strncmp (pPattern,  pPattern + cplPrefixLength,  prefixLength)) {
            cplPrefixSuffixLength = cplPrefixLength;
        }

        aGoodSuffixIndexTable [--cplPrefixLength] = cplPrefixSuffixLength + prefixLength++;
    }

    if (pPattern [0] != pPattern [highestPatternIndex]) {
        aGoodSuffixIndexTable [highestPatternIndex] = highestPatternIndex;
    }

    for (iRepeatedSuffixMax = 1;  iRepeatedSuffixMax < highestPatternIndex;  ++iRepeatedSuffixMax) {
        size_t  iSuffix = highestPatternIndex;
        size_t  iRepeatedSuffix = iRepeatedSuffixMax;

        do {
            if (pPattern [iRepeatedSuffix] != pPattern [iSuffix]) {
                aGoodSuffixIndexTable [iSuffix] = highestPatternIndex - iRepeatedSuffix;
                break;
            }

            --iSuffix;
        } while (--iRepeatedSuffix > 0);
    }
}

char const *  boyerMoore (
    /*----------------------------------------------------------------
    function:
       find a pattern (needle) inside a text (haystack)
    parameters: */
    char const *  const pHaystack,
    size_t  const haystackLength,
    char const *  const pPattern)
    /*----------------------------------------------------------------*/
{
    size_t  const patternLength = strlen (pPattern);
    size_t  const highestPatternIndex = patternLength - 1;
    size_t  aBadCharIndexTable [256];
    size_t  aGoodSuffixIndexTable [256];

    if (*pPattern == '\0') {
        return pHaystack;
    }

    if (patternLength <= 1) {
        return strchr (pHaystack,  *pPattern);
    }

    if (patternLength >= sizeof aGoodSuffixIndexTable) {
        /* exit for too long patterns */
        return 0;
    }

    {
        char const *  pInHaystack = pHaystack + highestPatternIndex;

        /* search preparation */
        fillBadCharIndexTable (
            aBadCharIndexTable,
            pPattern,
            patternLength);
        fillGoodSuffixRuleTable (
            aGoodSuffixIndexTable,
            pPattern,
            patternLength);

        /* search execution */
        while (pInHaystack++ < pHaystack + haystackLength) {
            int  iPattern = (int) highestPatternIndex;

            while (*--pInHaystack == pPattern [iPattern]) {
                if (--iPattern < 0) {
                    return pInHaystack;
                }
            }

            pInHaystack += MAX (aBadCharIndexTable [*pInHaystack],  aGoodSuffixIndexTable [iPattern]);
        }
    }

    return 0;
}