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

Merge 150c685373 into 61dd9fdad7

Browse source
This commit is contained in:
James 2025-07-10 06:54:57 +03:00 • committed by GitHub
commit 7fcc364645
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 15 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Lib/test/test_ucn.py
View file

@ -240,6 +240,11 @@ class UnicodeNamesTest(unittest.TestCase):
x.decode, 'unicode-escape'
)
def test_issue80667(self):
self.assertEqual(str(b'\\N{cjK UniFIeD idEogRAph-732B}', "unicode-escape"), '猫')
self.assertEqual(str(b'\\N{cjK UniFIeD idEogRAph-732b}', "unicode-escape"), '猫')
self.assertEqual(str(b'\\N{haNGul SYllABle WAe}', "unicode-escape"), '왜')
if __name__ == "__main__":
unittest.main()

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++;