mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-03 16:39:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Fix PyUnicode_Substring() for start >= length and start > end

Browse source 
Remove the fast-path for 1-character string: unicode_fromascii() and
_PyUnicode_FromUCS*() now have their own fast-path for 1-character strings.
This commit is contained in:
Victor Stinner 2012-05-03 02:32:34 +02:00
parent b6cd014d75
commit 684d5fd420
1 changed files with 8 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

14
Objects/unicodeobject.c
View file

@ -12067,20 +12067,22 @@ PyUnicode_Substring(PyObject *self, Py_ssize_t start, Py_ssize_t end)
if (PyUnicode_READY(self) == -1) if (PyUnicode_READY(self) == -1)
return NULL; return NULL;
end = Py_MIN(end, PyUnicode_GET_LENGTH(self)); length = PyUnicode_GET_LENGTH(self);
end = Py_MIN(end, length);
if (start == 0 && end == PyUnicode_GET_LENGTH(self)) if (start == 0 && end == length)
return unicode_result_unchanged(self); return unicode_result_unchanged(self);
length = end - start;
if (length == 1)
return unicode_getitem(self, start);
if (start < 0 || end < 0) { if (start < 0 || end < 0) {
PyErr_SetString(PyExc_IndexError, "string index out of range"); PyErr_SetString(PyExc_IndexError, "string index out of range");
return NULL; return NULL;
} }
if (start >= length || end < start) {
assert(end == length);
return PyUnicode_New(0, 0);
}
length = end - start;
if (PyUnicode_IS_ASCII(self)) { if (PyUnicode_IS_ASCII(self)) {
data = PyUnicode_1BYTE_DATA(self); data = PyUnicode_1BYTE_DATA(self);
return unicode_fromascii(data + start, length); return unicode_fromascii(data + start, length);