mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-02 16:13:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

* Beef-up testing of str.__contains__() and str.find().

Browse source 
* Speed-up "x in y" where x has more than one character.

The existing code made excessive calls to the expensive memcmp() function.
The new code uses memchr() to rapidly find a start point for memcmp().
In addition to knowing that the first character is a match, the new code
also checks that the last character is a match.  This significantly reduces
the incidence of false starts (saving memcmp() calls and making quadratic
behavior less likely).

Improves the timings on:
    python -m timeit -r7 -s"x='a'*1000" "'ab' in x"
    python -m timeit -r7 -s"x='a'*1000" "'bc' in x"

Once this code has proven itself, then string_find_internal() should refer
to it rather than running its own version.  Also, something similar may
apply to unicode objects.
This commit is contained in:
Raymond Hettinger 2005-02-20 04:07:08 +00:00
parent 54c273c703
commit 7cbf1bcb3e
2 changed files with 50 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

39
Objects/stringobject.c
View file

@ -1002,8 +1002,12 @@ string_slice(register PyStringObject *a, register int i, register int j)
static int
string_contains(PyObject *a, PyObject *el)
{
const char *lhs, *rhs, *end;
int size;
char *s = PyString_AS_STRING(a);
const char *sub = PyString_AS_STRING(el);
char *last;
int len_sub = PyString_GET_SIZE(el);
int shortsub;
char firstchar, lastchar;
if (!PyString_CheckExact(el)) {
#ifdef Py_USING_UNICODE
@ -1016,20 +1020,29 @@ string_contains(PyObject *a, PyObject *el)
return -1;
}
}
size = PyString_GET_SIZE(el);
rhs = PyString_AS_STRING(el);
lhs = PyString_AS_STRING(a);
/* optimize for a single character */
if (size == 1)
return memchr(lhs, *rhs, PyString_GET_SIZE(a)) != NULL;
end = lhs + (PyString_GET_SIZE(a) - size);
while (lhs <= end) {
if (memcmp(lhs++, rhs, size) == 0)
if (len_sub == 0)
return 1;
/* last points to one char beyond the start of the rightmost
substring. When s<last, there is still room for a possible match
and s[0] through s[len_sub-1] will be in bounds.
shortsub is len_sub minus the last character which is checked
separately just before the memcmp(). That check helps prevent
false starts and saves the setup time for memcmp().
*/
firstchar = sub[0];
shortsub = len_sub - 1;
lastchar = sub[shortsub];
last = s + PyString_GET_SIZE(a) - len_sub + 1;
while (s < last) {
s = memchr(s, firstchar, last-s);
if (s == NULL)
return 0;
assert(s < last);
if (s[shortsub] == lastchar && memcmp(s, sub, shortsub) == 0)
return 1;
s++;
}
return 0;
}