mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 17:08:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

When decoding UTF-16, don't assume that the buffer is in native endianness

Browse source 
when checking surrogates.
This commit is contained in:
Martin v. Löwis 2001-06-26 22:43:40 +00:00
parent 208efe5640
commit ac93bc2501
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Objects/unicodeobject.c
View file

@ -1065,16 +1065,16 @@ PyObject *PyUnicode_DecodeUTF16(const char *s,
errmsg = "unexpected end of data";
goto utf16Error;
}
if (0xDC00 <= *q && *q <= 0xDFFF) {
if (0xD800 <= ch && ch <= 0xDBFF) {
Py_UCS2 ch2 = *q++;
#ifdef BYTEORDER_IS_LITTLE_ENDIAN
if (bo == 1)
ch = (ch >> 8) | (ch << 8);
ch2 = (ch2 >> 8) | (ch2 << 8);
#else
if (bo == -1)
ch = (ch >> 8) | (ch << 8);
ch2 = (ch2 >> 8) | (ch2 << 8);
#endif
if (0xD800 <= ch && ch <= 0xDBFF) {
if (0xDC00 <= ch2 && ch2 <= 0xDFFF) {
#if Py_UNICODE_SIZE == 2
/* This is valid data (a UTF-16 surrogate pair), but
we are not able to store this information since our