Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2026-04-23 12:21:01 +00:00
Code Issues Projects Releases Packages Wiki Activity

bpo-29456: Fix bugs in unicodedata.normalize: u1176, u11a7 and u11c3 (GH-1958)

Browse source 
Hangul composition check boundaries are wrong for the second character
([0x1161, 0x1176) instead of [0x1161, 0x1176]) and third character ((0x11A7, 0x11C3)
instead of [0x11A7, 0x11C3]).
(cherry picked from commit d134809cd3)

Co-authored-by: Wonsup Yoon <pusnow@me.com>
This commit is contained in:
Miss Islington (bot) 2018-06-15 05:21:55 -07:00 • committed by GitHub
parent a50b825c18
commit 0e2b76ea4e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 22 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

13
Lib/test/test_unicodedata.py
View file

@ -208,6 +208,19 @@ def test_issue10254(self):
b = 'C\u0338' * 20 + '\xC7'
self.assertEqual(self.db.normalize('NFC', a), b)
def test_issue29456(self):
# Fix #29456
u1176_str_a = '\u1100\u1176\u11a8'
u1176_str_b = '\u1100\u1176\u11a8'
u11a7_str_a = '\u1100\u1175\u11a7'
u11a7_str_b = '\uae30\u11a7'
u11c3_str_a = '\u1100\u1175\u11c3'
u11c3_str_b = '\uae30\u11c3'
self.assertEqual(self.db.normalize('NFC', u1176_str_a), u1176_str_b)
self.assertEqual(self.db.normalize('NFC', u11a7_str_a), u11a7_str_b)
self.assertEqual(self.db.normalize('NFC', u11c3_str_a), u11c3_str_b)
def test_east_asian_width(self):
eaw = self.db.east_asian_width
self.assertRaises(TypeError, eaw, b'a')