Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2026-04-14 07:41:00 +00:00
Code Issues Projects Releases Packages Wiki Activity

[3.14] gh-80667: Fix case-sensitivity of some Unicode literal escapes (GH-107281) (GH-144753)

Browse source 
Lookup for CJK ideograms and Hangul syllables is now case-insensitive,
as is the case for other character names.
(cherry picked from commit e66f4a5a9c)

Co-authored-by: James <snoopjedi@gmail.com>
This commit is contained in:
Miss Islington (bot) 2026-02-12 18:22:05 +01:00 • committed by GitHub
parent 7f5a3acded
commit ac9e9e2c8f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 18 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Lib/test/test_ucn.py
View file

@ -88,6 +88,9 @@ def test_hangul_syllables(self):
self.checkletter("HANGUL SYLLABLE HWEOK", "\ud6f8")
self.checkletter("HANGUL SYLLABLE HIH", "\ud7a3")
self.checkletter("haNGul SYllABle WAe", '\uc65c')
self.checkletter("HAngUL syLLabLE waE", '\uc65c')
self.assertRaises(ValueError, unicodedata.name, "\ud7a4")
def test_cjk_unified_ideographs(self):
@ -103,6 +106,11 @@ def test_cjk_unified_ideographs(self):
self.checkletter("CJK UNIFIED IDEOGRAPH-2B81D", "\U0002B81D")
self.checkletter("CJK UNIFIED IDEOGRAPH-3134A", "\U0003134A")
self.checkletter("cjK UniFIeD idEogRAph-3aBc", "\u3abc")
self.checkletter("CJk uNIfiEd IDeOGraPH-3AbC", "\u3abc")
self.checkletter("cjK UniFIeD idEogRAph-2aBcD", "\U0002abcd")
self.checkletter("CJk uNIfiEd IDeOGraPH-2AbCd", "\U0002abcd")
def test_bmp_characters(self):
for code in range(0x10000):
char = chr(code)

2
Misc/NEWS.d/next/Core_and_Builtins/2023-07-26-00-03-00.gh-issue-80667.N7Dh8B.rst Normal file
View file

@ -0,0 +1,2 @@
Literals using the ``\N{name}`` escape syntax can now construct CJK
ideographs and Hangul syllables using case-insensitive names.

15
Modules/unicodedata.c
View file

@ -1362,7 +1362,7 @@ find_syllable(const char *str, int *len, int *pos, int count, int column)
len1 = Py_SAFE_DOWNCAST(strlen(s), size_t, int);
if (len1 <= *len)
continue;
if (strncmp(str, s, len1) == 0) {
if (PyOS_strnicmp(str, s, len1) == 0) {
*len = len1;
*pos = i;
}
@ -1394,7 +1394,7 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
* PUA */
/* Check for hangul syllables. */
if (strncmp(name, "HANGUL SYLLABLE ", 16) == 0) {
if (PyOS_strnicmp(name, "HANGUL SYLLABLE ", 16) == 0) {
int len, L = -1, V = -1, T = -1;
const char *pos = name + 16;
find_syllable(pos, &len, &L, LCount, 0);
@ -1412,7 +1412,7 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
}
/* Check for unified ideographs. */
if (strncmp(name, "CJK UNIFIED IDEOGRAPH-", 22) == 0) {
if (PyOS_strnicmp(name, "CJK UNIFIED IDEOGRAPH-", 22) == 0) {
/* Four or five hexdigits must follow. */
unsigned int v;
v = 0;
@ -1422,10 +1422,11 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
return 0;
while (namelen--) {
v *= 16;
if (*name >= '0' && *name <= '9')
v += *name - '0';
else if (*name >= 'A' && *name <= 'F')
v += *name - 'A' + 10;
Py_UCS1 c = Py_TOUPPER(*name);
if (c >= '0' && c <= '9')
v += c - '0';
else if (c >= 'A' && c <= 'F')
v += c - 'A' + 10;
else
return 0;
name++;