bpo-29456: Fix bugs in unicodedata.normalize: u1176, u11a7 and u11c3 (GH-1958) (GH-7704)
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 d134809cd3764c6a634eab7bb8995e3e2eff14d5)
Co-authored-by: Wonsup Yoon <pusnow@me.com>
diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py
index c30ecf4..11f2cda 100644
--- a/Lib/test/test_unicodedata.py
+++ b/Lib/test/test_unicodedata.py
@@ -204,6 +204,19 @@
b = u'C\u0338' * 20 + u'\xC7'
self.assertEqual(self.db.normalize('NFC', a), b)
+ def test_issue29456(self):
+ # Fix #29456
+ u1176_str_a = u'\u1100\u1176\u11a8'
+ u1176_str_b = u'\u1100\u1176\u11a8'
+ u11a7_str_a = u'\u1100\u1175\u11a7'
+ u11a7_str_b = u'\uae30\u11a7'
+ u11c3_str_a = u'\u1100\u1175\u11c3'
+ u11c3_str_b = u'\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, 'a')