[ Web Proxy ]
URL:
Viewing: https://raw.githubusercontent.com/python-emscripten/cpython/master/Objects/stringlib/fastsearch.h [Back]  [Original]

/* stringlib: fastsearch implementation */

#define STRINGLIB_FASTSEARCH_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 using
   Python's ordinary string types, but may cause problems if you're
   using this code in other contexts.  also, the count mode returns -1
   if there cannot possible be a match in the target string, and 0 if
   it has actually checked for matches, but didn't find any.  callers
   beware! */

#define FAST_COUNT 0
#define FAST_SEARCH 1
#define FAST_RSEARCH 2

#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  MEMCHR_CUT_OFF) {
#if STRINGLIB_SIZEOF_CHAR == 1
        p = memrchr(s, ch, n);
        if (p != NULL)
            return (p - s);
        return -1;
#else
        /* use memrchr if we can choose a needle without too many likely
           false positives */
        const STRINGLIB_CHAR *s1;
        Py_ssize_t n1;
        unsigned char needle = ch & 0xff;
        /* If looking for a multiple of 256, we'd have too
           many false positives looking for the '\0' byte in UCS2
           and UCS4 representations. */
        if (needle != 0) {
            do {
                void *candidate = memrchr(s, needle,
                                          n * sizeof(STRINGLIB_CHAR));
                if (candidate == NULL)
                    return -1;
                n1 = n;
                p = (const STRINGLIB_CHAR *)
                        _Py_ALIGN_DOWN(candidate, sizeof(STRINGLIB_CHAR));
                n = p - s;
                if (*p == ch)
                    return n;
                /* False positive */
                if (n1 - n > MEMCHR_CUT_OFF)
                    continue;
                if (n  s1) {
                    p--;
                    if (*p == ch)
                        return (p - s);
                }
                n = p - s;
            }
            while (n > MEMCHR_CUT_OFF);
        }
#endif
    }
#endif  /* HAVE_MEMRCHR */
    p = s + n;
    while (p > s) {
        p--;
        if (*p == ch)
            return (p - s);
    }
    return -1;
}

#undef MEMCHR_CUT_OFF

Py_LOCAL_INLINE(Py_ssize_t)
FASTSEARCH(const STRINGLIB_CHAR* s, Py_ssize_t n,
           const STRINGLIB_CHAR* p, Py_ssize_t m,
           Py_ssize_t maxcount, int mode)
{
    unsigned long mask;
    Py_ssize_t skip, count = 0;
    Py_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  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 (i > 0 && !STRINGLIB_BLOOM(mask, s[i-1]))
                    i = i - m;
                else
                    i = i - skip;
            } else {
                /* skip: check if previous character is part of pattern */
                if (i > 0 && !STRINGLIB_BLOOM(mask, s[i-1]))
                    i = i - m;
            }
        }
    }

    if (mode != FAST_COUNT)
        return -1;
    return count;
}


Web Proxy Viewer  |  New URL  |  Original Page