Thanks to visit codestin.com
Credit goes to github.com

Skip to content

gh-80667: Fix Tangut ideographs names in unicodedata #144789

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
serhiy-storchaka merged 11 commits into from
Feb 16, 2026
Merged

gh-80667: Fix Tangut ideographs names in unicodedata #144789

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
0609eb2
unicodedata: Fix Tangut Ideograph names
wismill Jul 26, 2023
3821e1b
News entry
wismill Jul 26, 2023
b2c4e92
Add test
wismill Jul 26, 2023
2e1560c
Merge branch 'main' into wip/tangut-ideographs
serhiy-storchaka Feb 13, 2026
2ae016c
Fix code and tests.
serhiy-storchaka Feb 13, 2026
b69fdfc
Add lookup tests and fix case-insensitivity for Tangut ideographs.
serhiy-storchaka Feb 13, 2026
accd150
Add tests that work without network and with UCD 3.2.0.
serhiy-storchaka Feb 13, 2026
c09400c
Share some common code.
serhiy-storchaka Feb 13, 2026
629531f
Generalize code for Hangul syllables and CJK and Tangut ideographs.
serhiy-storchaka Feb 14, 2026
a270a29
Update the NEWS file.
serhiy-storchaka Feb 14, 2026
163e6c9
Add tests for invalid names.
serhiy-storchaka Feb 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Add lookup tests and fix case-insensitivity for Tangut ideographs.
  • Loading branch information
@serhiy-storchaka
serhiy-storchaka committed Feb 13, 2026
commit b69fdfc483e45cf8b72804547a939a5f57a43e8d
24 changes: 24 additions & 0 deletions Lib/test/test_ucn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,30 @@ def test_cjk_unified_ideographs(self):
self.checkletter("cjK UniFIeD idEogRAph-2aBcD", "\U0002abcd")
self.checkletter("CJk uNIfiEd IDeOGraPH-2AbCd", "\U0002abcd")

def test_tangut_ideographs(self):
self.checkletter("TANGUT IDEOGRAPH-17000", "\U00017000")
self.checkletter("TANGUT IDEOGRAPH-187FF", "\U000187ff")
self.checkletter("TANGUT IDEOGRAPH-18D00", "\U00018D00")
self.checkletter("TANGUT IDEOGRAPH-18D1E", "\U00018d1e")
self.checkletter("tangut ideograph-18d1e", "\U00018d1e")

def test_egyptian_hieroglyphs(self):
self.checkletter("EGYPTIAN HIEROGLYPH-13460", "\U00013460")
self.checkletter("EGYPTIAN HIEROGLYPH-143FA", "\U000143fa")
self.checkletter("egyptian hieroglyph-143fa", "\U000143fa")

def test_khitan_small_script_characters(self):
self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18B00", "\U00018b00")
self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18CD5", "\U00018cd5")
self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18CFF", "\U00018cff")
self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18CFF", "\U00018cff")
self.checkletter("khitan small script character-18cff", "\U00018cff")

def test_nushu_characters(self):
self.checkletter("NUSHU CHARACTER-1B170", "\U0001b170")
self.checkletter("NUSHU CHARACTER-1B2FB", "\U0001b2fb")
self.checkletter("nushu character-1b2fb", "\U0001b2fb")

def test_bmp_characters(self):
for code in range(0x10000):
char = chr(code)
Expand Down
11 changes: 6 additions & 5 deletions Modules/unicodedata.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1498,7 +1498,7 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
}

/* Check for Tangut ideographs. */
if (strncmp(name, "TANGUT IDEOGRAPH-", 17) == 0) {
if (PyOS_strnicmp(name, "TANGUT IDEOGRAPH-", 17) == 0) {
/* Five hexdigits must follow. */
unsigned int v = 0;
name += 17;
Expand All @@ -1507,10 +1507,11 @@ _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++;
Expand Down