Remove and adjust various confusables (#1222)

- Most of these do not appear in NFD form at all, so they were erroneous
- A few others have been adjusted based on public feedback

For details, see unicode-org/properties#457

Author: roozbehp

unicodetools/data/security/dev/confusables.txt

@@ -1,5 +1,5 @@
 # confusablesSummaryIdentifier.txt
-# Date: 2025-10-09, 03:26:38 GMT
+# Date: 2025-10-11, 02:30:37 GMT
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -69,24 +69,17 @@
 ←	(‎ І ‎)	0406	 CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I	# →I→
 ←	(‎ Ӏ ‎)	04C0	 CYRILLIC LETTER PALOCHKA	# →I→
 
-#	lٴ	lٔ	ٴl	1ٔ	1ٴ	أ	اٴ	ٴ1	ٴا	ٲ	أ
+#	lٴ	lٔ	ٴl	1ٔ	1ٴ	أ	اٴ	ٴ1	ٴا	ٲ
 	(‎ 1ٔ ‎)	0031 0654	 DIGIT ONE, ARABIC HAMZA ABOVE
-←	(‎ lٴ ‎)	006C 0674	 LATIN SMALL LETTER L, ARABIC LETTER HIGH HAMZA	# →‎اٴ‎→→‎ٵ‎→→‎ﺃ‎→→‎أ‎→
+←	(‎ lٴ ‎)	006C 0674	 LATIN SMALL LETTER L, ARABIC LETTER HIGH HAMZA	# →‎اٴ‎→→‎ٵ‎→→‎أ‎→
 ←	(‎ lٔ ‎)	006C 0654	 LATIN SMALL LETTER L, ARABIC HAMZA ABOVE	# →‎أ‎→
-←	(‎ ٴl ‎)	0674 006C	 ARABIC LETTER HIGH HAMZA, LATIN SMALL LETTER L	# →‎ٴا‎→→‎ٵ‎→→‎ﺃ‎→→‎أ‎→
-←	(‎ 1ٴ ‎)	0031 0674	 DIGIT ONE, ARABIC LETTER HIGH HAMZA	# →‎اٴ‎→→‎ٵ‎→→‎ﺃ‎→→‎أ‎→
+←	(‎ ٴl ‎)	0674 006C	 ARABIC LETTER HIGH HAMZA, LATIN SMALL LETTER L	# →‎ٴا‎→→‎ٵ‎→→‎أ‎→
+←	(‎ 1ٴ ‎)	0031 0674	 DIGIT ONE, ARABIC LETTER HIGH HAMZA	# →‎اٴ‎→→‎ٵ‎→→‎أ‎→
 ←	(‎ أ ‎)	0627 0654	 ARABIC LETTER ALEF, ARABIC HAMZA ABOVE
-←	(‎ اٴ ‎)	0627 0674	 ARABIC LETTER ALEF, ARABIC LETTER HIGH HAMZA	# →‎ٵ‎→→‎ﺃ‎→→‎أ‎→
-←	(‎ ٴ1 ‎)	0674 0031	 ARABIC LETTER HIGH HAMZA, DIGIT ONE	# →‎ٴا‎→→‎ٵ‎→→‎ﺃ‎→→‎أ‎→
-←	(‎ ٴا ‎)	0674 0627	 ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF	# →‎ٵ‎→→‎ﺃ‎→→‎أ‎→
-←	(‎ ٲ ‎)	0672	 ARABIC LETTER ALEF WITH WAVY HAMZA ABOVE	# →‎أ‎→→‎ٵ‎→→‎ﺃ‎→→‎أ‎→
-←	(‎ أ ‎)	0623	 ARABIC LETTER ALEF WITH HAMZA ABOVE	# →‎ٵ‎→→‎ﺃ‎→→‎أ‎→
-
-#	lٕ	1ٕ	إ	إ
-	(‎ 1ٕ ‎)	0031 0655	 DIGIT ONE, ARABIC HAMZA BELOW
-←	(‎ lٕ ‎)	006C 0655	 LATIN SMALL LETTER L, ARABIC HAMZA BELOW	# →‎اٟ‎→
-←	(‎ إ ‎)	0627 0655	 ARABIC LETTER ALEF, ARABIC HAMZA BELOW	# →lٕ→→‎اٟ‎→
-←	(‎ إ ‎)	0625	 ARABIC LETTER ALEF WITH HAMZA BELOW	# →‎ٳ‎→→‎اٟ‎→
+←	(‎ اٴ ‎)	0627 0674	 ARABIC LETTER ALEF, ARABIC LETTER HIGH HAMZA	# →‎ٵ‎→→‎أ‎→
+←	(‎ ٴ1 ‎)	0674 0031	 ARABIC LETTER HIGH HAMZA, DIGIT ONE	# →‎ٴا‎→→‎ٵ‎→→‎أ‎→
+←	(‎ ٴا ‎)	0674 0627	 ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF	# →‎ٵ‎→→‎أ‎→
+←	(‎ ٲ ‎)	0672	 ARABIC LETTER ALEF WITH WAVY HAMZA ABOVE	# →‎أ‎→
 
 #	3	३	૩	З	Ӡ
 	(‎ 3 ‎)	0033	 DIGIT THREE
@@ -142,11 +135,11 @@
 	(‎ C ‎)	0043	 LATIN CAPITAL LETTER C
 ←	(‎ С ‎)	0421	 CYRILLIC CAPITAL LETTER ES
 
-#	C̦	С̦	Ҫ	Ç
+#	C̦	Ç	С̦	Ҫ
 	(‎ C̦ ‎)	0043 0326	 LATIN CAPITAL LETTER C, COMBINING COMMA BELOW
+←	(‎ Ç ‎)	0043 0327	 LATIN CAPITAL LETTER C, COMBINING CEDILLA	# →Ҫ→→С̡→
 ←	(‎ С̦ ‎)	0421 0326	 CYRILLIC CAPITAL LETTER ES, COMBINING COMMA BELOW	# →С̡→
 ←	(‎ Ҫ ‎)	04AA	 CYRILLIC CAPITAL LETTER ES WITH DESCENDER	# →С̡→
-←	(‎ Ç ‎)	00C7	 LATIN CAPITAL LETTER C WITH CEDILLA	# →Ҫ→→С̡→
 
 #	Ð	Đ
 	(‎ Ð ‎)	00D0	 LATIN CAPITAL LETTER ETH
@@ -186,11 +179,6 @@
 	(‎ N ‎)	004E	 LATIN CAPITAL LETTER N
 ←	(‎ Ν ‎)	039D	 GREEK CAPITAL LETTER NU
 
-#	O'	Oʼ	Ơ
-	(‎ O' ‎)	004F 0027	 LATIN CAPITAL LETTER O, APOSTROPHE
-←	(‎ Oʼ ‎)	004F 02BC	 LATIN CAPITAL LETTER O, MODIFIER LETTER APOSTROPHE
-←	(‎ Ơ ‎)	01A0	 LATIN CAPITAL LETTER O WITH HORN	# →Oʼ→
-
 #	OE	Œ
 	(‎ OE ‎)	004F 0045	 LATIN CAPITAL LETTER O, LATIN CAPITAL LETTER E
 ←	(‎ Œ ‎)	0152	 LATIN CAPITAL LIGATURE OE
@@ -267,11 +255,11 @@
 ←	(‎ င ‎)	1004	 MYANMAR LETTER NGA
 ←	(‎ ၚ ‎)	105A	 MYANMAR LETTER MON NGA	# →င→
 
-#	c̦	с̦	ҫ	ç
+#	c̦	ç	с̦	ҫ
 	(‎ c̦ ‎)	0063 0326	 LATIN SMALL LETTER C, COMBINING COMMA BELOW
+←	(‎ ç ‎)	0063 0327	 LATIN SMALL LETTER C, COMBINING CEDILLA	# →ҫ→→с̡→
 ←	(‎ с̦ ‎)	0441 0326	 CYRILLIC SMALL LETTER ES, COMBINING COMMA BELOW	# →с̡→
 ←	(‎ ҫ ‎)	04AB	 CYRILLIC SMALL LETTER ES WITH DESCENDER	# →с̡→
-←	(‎ ç ‎)	00E7	 LATIN SMALL LETTER C WITH CEDILLA	# →ҫ→→с̡→
 
 #	e	е	ҽ
 	(‎ e ‎)	0065	 LATIN SMALL LETTER E
@@ -352,11 +340,6 @@
 ←	(‎ ၀ ‎)	1040	 MYANMAR DIGIT ZERO
 ←	(‎ ០ ‎)	17E0	 KHMER DIGIT ZERO
 
-#	o'	oʼ	ơ
-	(‎ o' ‎)	006F 0027	 LATIN SMALL LETTER O, APOSTROPHE
-←	(‎ oʼ ‎)	006F 02BC	 LATIN SMALL LETTER O, MODIFIER LETTER APOSTROPHE
-←	(‎ ơ ‎)	01A1	 LATIN SMALL LETTER O WITH HORN	# →oʼ→
-
 #	oe	œ
 	(‎ oe ‎)	006F 0065	 LATIN SMALL LETTER O, LATIN SMALL LETTER E
 ←	(‎ œ ‎)	0153	 LATIN SMALL LIGATURE OE
@@ -365,11 +348,10 @@
 	(‎ ô ‎)	006F 0302	 LATIN SMALL LETTER O, COMBINING CIRCUMFLEX ACCENT
 ←	(‎ ۿ ‎)	06FF	 ARABIC LETTER HEH WITH INVERTED V	# →‎ھٛ‎→
 
-#	oٔ	هٔ	ۀ	ۂ
-	(‎ oٔ ‎)	006F 0654	 LATIN SMALL LETTER O, ARABIC HAMZA ABOVE
-←	(‎ هٔ ‎)	0647 0654	 ARABIC LETTER HEH, ARABIC HAMZA ABOVE	# →‎ۀ‎→
-←	(‎ ۀ ‎)	06D5 0654	 ARABIC LETTER AE, ARABIC HAMZA ABOVE
-←	(‎ ۂ ‎)	06C2	 ARABIC LETTER HEH GOAL WITH HAMZA ABOVE	# →‎ﮤ‎→→‎ۀ‎→
+#	ö	ة	ۃ
+	(‎ ö ‎)	006F 0308	 LATIN SMALL LETTER O, COMBINING DIAERESIS
+←	(‎ ة ‎)	0629	 ARABIC LETTER TEH MARBUTA
+←	(‎ ۃ ‎)	06C3	 ARABIC LETTER TEH MARBUTA GOAL	# →‎ة‎→
 
 #	oာ	ဝာ	တ	თ
 	(‎ oာ ‎)	006F 102C	 LATIN SMALL LETTER O, MYANMAR VOWEL SIGN AA
@@ -433,48 +415,15 @@
 ←	(‎ ・ ‎)	30FB	 KATAKANA MIDDLE DOT	# →•→
 ←	(‎ ‧ ‎)	2027	 HYPHENATION POINT
 
-#	Ö	Ő
-	(‎ Ö ‎)	00D6	 LATIN CAPITAL LETTER O WITH DIAERESIS
-←	(‎ Ő ‎)	0150	 LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
-
 #	ß	ẞ	β
 	(‎ ß ‎)	00DF	 LATIN SMALL LETTER SHARP S
 ←	(‎ ẞ ‎)	1E9E	 LATIN CAPITAL LETTER SHARP S
 ←	(‎ β ‎)	03B2	 GREEK SMALL LETTER BETA
 
-#	ة	ۃ	ö
-	(‎ ö ‎)	00F6	 LATIN SMALL LETTER O WITH DIAERESIS
-←	(‎ ة ‎)	0629	 ARABIC LETTER TEH MARBUTA
-←	(‎ ۃ ‎)	06C3	 ARABIC LETTER TEH MARBUTA GOAL
-
-#	Ă	Ǎ
-	(‎ Ă ‎)	0102	 LATIN CAPITAL LETTER A WITH BREVE
-←	(‎ Ǎ ‎)	01CD	 LATIN CAPITAL LETTER A WITH CARON
-
-#	ă	ǎ
-	(‎ ă ‎)	0103	 LATIN SMALL LETTER A WITH BREVE
-←	(‎ ǎ ‎)	01CE	 LATIN SMALL LETTER A WITH CARON
-
-#	Ğ	Ǧ
-	(‎ Ğ ‎)	011E	 LATIN CAPITAL LETTER G WITH BREVE
-←	(‎ Ǧ ‎)	01E6	 LATIN CAPITAL LETTER G WITH CARON
-
-#	ğ	ǧ
-	(‎ ğ ‎)	011F	 LATIN SMALL LETTER G WITH BREVE
-←	(‎ ǧ ‎)	01E7	 LATIN SMALL LETTER G WITH CARON
-
 #	κ	к
 	(‎ κ ‎)	03BA	 GREEK SMALL LETTER KAPPA
 ←	(‎ к ‎)	043A	 CYRILLIC SMALL LETTER KA
 
-#	Ŭ	Ǔ
-	(‎ Ŭ ‎)	016C	 LATIN CAPITAL LETTER U WITH BREVE
-←	(‎ Ǔ ‎)	01D3	 LATIN CAPITAL LETTER U WITH CARON
-
-#	ŭ	ǔ
-	(‎ ŭ ‎)	016D	 LATIN SMALL LETTER U WITH BREVE
-←	(‎ ǔ ‎)	01D4	 LATIN SMALL LETTER U WITH CARON
-
 #	ьi	ьı	ы
 	(‎ ьi ‎)	044C 0069	 CYRILLIC SMALL LETTER SOFT SIGN, LATIN SMALL LETTER I
 ←	(‎ ьı ‎)	044C 0131	 CYRILLIC SMALL LETTER SOFT SIGN, LATIN SMALL LETTER DOTLESS I
@@ -628,22 +577,6 @@
 	(‎ ձ ‎)	0571	 ARMENIAN SMALL LETTER JA
 ←	(‎ ኔ ‎)	1294	 ETHIOPIC SYLLABLE NEE
 
-#	وٴ	ؤ	ٴو	ؤ
-	(‎ ؤ ‎)	0624	 ARABIC LETTER WAW WITH HAMZA ABOVE
-←	(‎ وٴ ‎)	0648 0674	 ARABIC LETTER WAW, ARABIC LETTER HIGH HAMZA	# →‎ٶ‎→
-←	(‎ ؤ ‎)	0648 0654	 ARABIC LETTER WAW, ARABIC HAMZA ABOVE	# →‎ﺅ‎→→‎ٶ‎→
-←	(‎ ٴو ‎)	0674 0648	 ARABIC LETTER HIGH HAMZA, ARABIC LETTER WAW	# →‎ٶ‎→
-
-#	ىٴ	ىٔ	ئ	يٴ	ٴى	ۓ	ࢨ	ئ
-	(‎ ئ ‎)	0626	 ARABIC LETTER YEH WITH HAMZA ABOVE
-←	(‎ ىٴ ‎)	0649 0674	 ARABIC LETTER ALEF MAKSURA, ARABIC LETTER HIGH HAMZA	# →‎يٴ‎→→‎ٸ‎→
-←	(‎ ىٔ ‎)	0649 0654	 ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE	# →‎ئ‎→→‎ﺉ‎→→‎ٸ‎→
-←	(‎ ئ ‎)	064A 0654	 ARABIC LETTER YEH, ARABIC HAMZA ABOVE	# →‎ﺉ‎→→‎ٸ‎→
-←	(‎ يٴ ‎)	064A 0674	 ARABIC LETTER YEH, ARABIC LETTER HIGH HAMZA	# →‎ٸ‎→
-←	(‎ ٴى ‎)	0674 0649	 ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF MAKSURA	# →‎ٸ‎→
-←	(‎ ۓ ‎)	06D2 0654	 ARABIC LETTER YEH BARREE, ARABIC HAMZA ABOVE	# →‎ىٔ‎→→‎ئ‎→→‎ﺉ‎→→‎ٸ‎→
-←	(‎ ࢨ ‎)	08A8	 ARABIC LETTER YEH WITH TWO DOTS BELOW AND HAMZA ABOVE	# →‎ئ‎→→‎ﺉ‎→→‎ٸ‎→
-
 #	ت	ٺ
 	(‎ ت ‎)	062A	 ARABIC LETTER TEH
 ←	(‎ ٺ ‎)	067A	 ARABIC LETTER TTEHEH
@@ -718,10 +651,10 @@
 
 #	ى	ي	ں	ی	ے	ࢽ
 	(‎ ى ‎)	0649	 ARABIC LETTER ALEF MAKSURA
-←	(‎ ي ‎)	064A	 ARABIC LETTER YEH
+←	(‎ ي ‎)	064A	 ARABIC LETTER YEH	# →‎ی‎→
 ←	(‎ ں ‎)	06BA	 ARABIC LETTER NOON GHUNNA
 ←	(‎ ی ‎)	06CC	 ARABIC LETTER FARSI YEH
-←	(‎ ے ‎)	06D2	 ARABIC LETTER YEH BARREE	# →‎ي‎→
+←	(‎ ے ‎)	06D2	 ARABIC LETTER YEH BARREE	# →‎ی‎→
 ←	(‎ ࢽ ‎)	08BD	 ARABIC LETTER AFRICAN NOON	# →‎ں‎→
 
 #	ى̆	ێ	ݖ
@@ -738,6 +671,15 @@
 	(‎ ٹ ‎)	0679	 ARABIC LETTER TTEH
 ←	(‎ ڻ ‎)	06BB	 ARABIC LETTER RNOON	# →‎ﮢ‎→→‎ﭨ‎→
 
+#	ىٴ	ىٔ	ئ	يٴ	ٴى	ۓ	ࢨ
+	(‎ ىٔ ‎)	0649 0654	 ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE
+←	(‎ ىٴ ‎)	0649 0674	 ARABIC LETTER ALEF MAKSURA, ARABIC LETTER HIGH HAMZA	# →‎يٴ‎→→‎ٸ‎→→‎ئ‎→
+←	(‎ ئ ‎)	064A 0654	 ARABIC LETTER YEH, ARABIC HAMZA ABOVE
+←	(‎ يٴ ‎)	064A 0674	 ARABIC LETTER YEH, ARABIC LETTER HIGH HAMZA	# →‎ٸ‎→→‎ئ‎→
+←	(‎ ٴى ‎)	0674 0649	 ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF MAKSURA	# →‎ٸ‎→→‎ئ‎→
+←	(‎ ۓ ‎)	06D2 0654	 ARABIC LETTER YEH BARREE, ARABIC HAMZA ABOVE
+←	(‎ ࢨ ‎)	08A8	 ARABIC LETTER YEH WITH TWO DOTS BELOW AND HAMZA ABOVE	# →‎ئ‎→
+
 #	پ̆	ࢾ
 	(‎ پ̆ ‎)	067E 0306	 ARABIC LETTER PEH, COMBINING BREVE
 ←	(‎ ࢾ ‎)	08BE	 ARABIC LETTER PEH WITH SMALL V	# →‎پٚ‎→
@@ -1083,15 +1025,6 @@
 	(‎ ெ ‎)	0BC6	 TAMIL VOWEL SIGN E
 ←	(‎ െ ‎)	0D46	 MALAYALAM VOWEL SIGN E
 
-#	ெஈ	ெர	ொ
-	(‎ ெஈ ‎)	0BC6 0B88	 TAMIL VOWEL SIGN E, TAMIL LETTER II
-←	(‎ ெர ‎)	0BC6 0BB0	 TAMIL VOWEL SIGN E, TAMIL LETTER RA
-←	(‎ ொ ‎)	0BCA	 TAMIL VOWEL SIGN O	# →ெர→
-
-#	ெள	ௌ
-	(‎ ெள ‎)	0BC6 0BB3	 TAMIL VOWEL SIGN E, TAMIL LETTER LLA
-←	(‎ ௌ ‎)	0BCC	 TAMIL VOWEL SIGN AU
-
 #	ெெ	െെ	ൈ
 	(‎ ெெ ‎)	0BC6 0BC6	 TAMIL VOWEL SIGN E, TAMIL VOWEL SIGN E
 ←	(‎ െെ ‎)	0D46 0D46	 MALAYALAM VOWEL SIGN E, MALAYALAM VOWEL SIGN E
@@ -1108,11 +1041,6 @@
 	(‎ ே ‎)	0BC7	 TAMIL VOWEL SIGN EE
 ←	(‎ േ ‎)	0D47	 MALAYALAM VOWEL SIGN EE
 
-#	ேஈ	ேர	ோ
-	(‎ ேஈ ‎)	0BC7 0B88	 TAMIL VOWEL SIGN EE, TAMIL LETTER II
-←	(‎ ேர ‎)	0BC7 0BB0	 TAMIL VOWEL SIGN EE, TAMIL LETTER RA
-←	(‎ ோ ‎)	0BCB	 TAMIL VOWEL SIGN OO	# →ேர→
-
 #	అ	ಅ
 	(‎ అ ‎)	0C05	 TELUGU LETTER A
 ←	(‎ ಅ ‎)	0C85	 KANNADA LETTER A
@@ -1470,5 +1398,5 @@
 	(‎ へ ‎)	3078	 HIRAGANA LETTER HE
 ←	(‎ ヘ ‎)	30D8	 KATAKANA LETTER HE
 
-# total : 527
+# total : 500
 

unicodetools/data/security/dev/confusablesSummary.txt

@@ -2,7 +2,7 @@
 13A1	;	0052	#	(Ꭱ → R ) CHEROKEE LETTER E → LATIN CAPITAL LETTER R  
 13A2	;	0054	#	(Ꭲ → T ) CHEROKEE LETTER I → LATIN CAPITAL LETTER T  
 #13A4	;	01A1	#	(Ꭴ → ơ ) CHEROKEE LETTER U → LATIN SMALL LETTER O WITH HORN  
-13A4	;	01A0	#	(Ꭴ → Ƣ ) CHEROKEE LETTER U → LATIN CAPITAL LETTER OI	#	ChAngED to U+01A0 ( Ơ ) LATIN CAPITAL LETTER O WITH HORN
+13A4	;	004F 031B
 13A5	;	0069	#	(Ꭵ → i ) CHEROKEE LETTER V → LATIN SMALL LETTER I    
 13A8	;	0370	#	(Ꭸ → Ͱ ) CHEROKEE LETTER GE → GREEK CAPITAL LETTER HETA  
 #13A8	;	0371	#	(Ꭸ → ͱ ) CHEROKEE LETTER GE → GREEK SMALL LETTER HETA    
@@ -54,9 +54,8 @@
 #13E7	;	004A	#	(Ꮷ → J ) CHEROKEE LETTER TSU → LATIN CAPITAL LETTER J    
 13EB	;	0472	#	(Ꮻ → Ѳ ) CHEROKEE LETTER WI → CYRILLIC CAPITAL LETTER FITA   
 13EE	;	0036	#	(Ꮾ → 6 ) CHEROKEE LETTER WV → DIGIT SIX  
-13EF	;	1FF6	#	(Ꮿ → ῶ ) CHEROKEE LETTER YA → GREEK SMALL LETTER OMEGA WITH PERISPOMENI  
 13F0	;	03B2	#	(Ᏸ → β ) CHEROKEE LETTER YE → GREEK SMALL LETTER BETA    
 13F2	;	0068 0314	#	(Ᏺ → h̔ ) CHEROKEE LETTER YO → LATIN SMALL LETTER H, COMBINING REVERSED COMMA ABOVE  
 13F3	;	0047	#	(Ᏻ → G ) CHEROKEE LETTER YU → LATIN CAPITAL LETTER G 
 13F4	;	0042	#	(Ᏼ → B ) CHEROKEE LETTER YV → LATIN CAPITAL LETTER B 
-# TODO: Add MV and the lowercase characters new in Unicode 8.0
+# TODO: Add MV and the lowercase characters new in Unicode 8.0