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

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]).
This commit is contained in:
Wonsup Yoon 2018-06-15 21:03:14 +09:00 committed by Xiang Zhang
parent ceeef10cdb
commit d134809cd3
4 changed files with 22 additions and 3 deletions

View file

@ -208,6 +208,19 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
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')