mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 00:48:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #15379: Fix passing of non-BMP characters as integers for the charmap decoder (already working as unicode strings).

Browse source 
Patch by Serhiy Storchaka.
This commit is contained in:
Antoine Pitrou 2012-09-23 19:55:21 +02:00
parent 20b8d992b0
commit 6f80f5d444
4 changed files with 135 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

28
Objects/unicodeobject.c
View file

@ -5250,12 +5250,36 @@ PyObject *PyUnicode_DecodeCharmap(const char *s,
/* Apply mapping */
if (PyLong_Check(x)) {
long value = PyLong_AS_LONG(x);
if (value < 0 || value > 65535) {
if (value < 0 || value > 0x10FFFF) {
PyErr_SetString(PyExc_TypeError,
"character mapping must be in range(65536)");
"character mapping must be in range(0x110000)");
Py_DECREF(x);
goto onError;
}
#ifndef Py_UNICODE_WIDE
if (value > 0xFFFF) {
/* see the code for 1-n mapping below */
if (extrachars < 2) {
/* resize first */
Py_ssize_t oldpos = p - PyUnicode_AS_UNICODE(v);
Py_ssize_t needed = 10 - extrachars;
extrachars += needed;
/* XXX overflow detection missing */
if (_PyUnicode_Resize(&v,
PyUnicode_GET_SIZE(v) + needed) < 0) {
Py_DECREF(x);
goto onError;
}
p = PyUnicode_AS_UNICODE(v) + oldpos;
}
value -= 0x10000;
*p++ = 0xD800 | (value >> 10);
*p++ = 0xDC00 | (value & 0x3FF);
extrachars -= 2;
}
else
#endif
*p++ = (Py_UNICODE)value;
}
else if (x == Py_None) {