traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Issue #13621: Optimize str.replace(char1, char2) 

Use findchar() which is more optimized than a dummy loop using
PyUnicode_READ().  PyUnicode_READ() is a complex and slow macro.
This commit is contained in:
Victor Stinner 2011-12-18 02:43:08 +01:00
parent b511aca596
commit f644110816
1 changed files with 21 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
Objects/unicodeobject.c
View File

@ -10285,7 +10285,6 @@ replace(PyObject *self, PyObject *str1,
maxchar = Py_MAX(maxchar, maxchar_str2);
if (len1 == len2) {
Py_ssize_t i;
/* same length */
if (len1 == 0)
goto nothing;
@ -10293,9 +10292,12 @@ replace(PyObject *self, PyObject *str1,
/* replace characters */
Py_UCS4 u1, u2;
int rkind;
Py_ssize_t index, pos;
char *src;
u1 = PyUnicode_READ_CHAR(str1, 0);
if (findchar(sbuf, PyUnicode_KIND(self),
slen, u1, 1) < 0)
pos = findchar(sbuf, PyUnicode_KIND(self), slen, u1, 1);
if (pos < 0)
goto nothing;
u2 = PyUnicode_READ_CHAR(str2, 0);
u = PyUnicode_New(slen, maxchar);
@ -10303,16 +10305,26 @@ replace(PyObject *self, PyObject *str1,
goto error;
copy_characters(u, 0, self, 0, slen);
rkind = PyUnicode_KIND(u);
for (i = 0; i < PyUnicode_GET_LENGTH(u); i++)
if (PyUnicode_READ(rkind, PyUnicode_DATA(u), i) == u1) {
if (--maxcount < 0)
PyUnicode_WRITE(rkind, PyUnicode_DATA(u), pos, u2);
index = 0;
src = sbuf;
while (--maxcount)
{
pos++;
src += pos * PyUnicode_KIND(self);
slen -= pos;
index += pos;
pos = findchar(src, PyUnicode_KIND(self), slen, u1, 1);
if (pos < 0)
break;
PyUnicode_WRITE(rkind, PyUnicode_DATA(u), i, u2);
PyUnicode_WRITE(rkind, PyUnicode_DATA(u), index + pos, u2);
}
}
else {
int rkind = skind;
char *res;
Py_ssize_t i;
if (kind1 < rkind) {
/* widen substring */