Remove or correct non-NFD confusables

See unicode-org/properties#486

Author: roozbehp

unicodetools/data/security/dev/confusables.txt

@@ -1,5 +1,5 @@
 # confusablesSummaryIdentifier.txt
-# Date: 2025-10-25, 07:52:31 GMT
+# Date: 2025-11-13, 04:42:22 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
@@ -164,11 +164,10 @@
 	(‎ J ‎)	004A	 LATIN CAPITAL LETTER J
 ←	(‎ Ј ‎)	0408	 CYRILLIC CAPITAL LETTER JE
 
-#	K	Κ	К	K
+#	K	Κ	К
 	(‎ K ‎)	004B	 LATIN CAPITAL LETTER K
 ←	(‎ Κ ‎)	039A	 GREEK CAPITAL LETTER KAPPA
 ←	(‎ К ‎)	041A	 CYRILLIC CAPITAL LETTER KA
-←	(‎ K ‎)	212A	 KELVIN SIGN
 
 #	M	Μ	М
 	(‎ M ‎)	004D	 LATIN CAPITAL LETTER M
@@ -1012,10 +1011,6 @@
 ←	(‎ ஜ ‎)	0B9C	 TAMIL LETTER JA
 ←	(‎ ജ ‎)	0D1C	 MALAYALAM LETTER JA	# →ஜ→
 
-#	ஒள	ஔ
-	(‎ ஒள ‎)	0B92 0BB3	 TAMIL LETTER O, TAMIL LETTER LLA
-←	(‎ ஔ ‎)	0B94	 TAMIL LETTER AU
-
 #	ண	ണ
 	(‎ ண ‎)	0BA3	 TAMIL LETTER NNA
 ←	(‎ ണ ‎)	0D23	 MALAYALAM LETTER NNA
@@ -1461,5 +1456,5 @@
 	(‎ へ ‎)	3078	 HIRAGANA LETTER HE
 ←	(‎ ヘ ‎)	30D8	 KATAKANA LETTER HE
 
-# total : 524
+# total : 522
 

unicodetools/data/security/dev/confusablesSummary.txt

@@ -3967,8 +3967,6 @@ FFE8 ;  |    # ( ￨ → │) HALFWIDTH FORMS LIGHT VERTICAL →  pipe
 ‰ ;  ⁰/₀₀ 
 ‱ ;  ⁰/₀₀₀ 
 þ ;  ƿ 
-Å ;  Ȧ 
-å ;  ȧ 
 
 0629 ; 006F 0308 # Teh marbuta
 06C3 ; 0629 # ...goal
@@ -4595,7 +4593,7 @@ A793 ; 0454 # ( ꞓ ) LATIN SMALL LETTER C WITH BAR =>U+0454 ( є ) CYRILLIC SMA
 ∔	;	+̇
 ∸	;	−̇
 ≐	;	 =̇
-≑	;	≐̣
+2251	;	003D 0323 0307
 ≗	;	 =̊
 ≙	;	 =̂
 ≚	;	 =̌
@@ -5534,22 +5532,24 @@ A7F1 ; 02E2  # ( ꟱ → ˢ ) MODIFIER LETTER CAPITAL S → MODIFIER LETTER SMAL
 # Unicode 17.0 (post-UTC #183)
 20C1 ; FDFC  # ( ⃁ → ﷼ ) SAUDI RIYAL SIGN → RIAL SIGN
 2B73F ; 6138  # ( 愸 → 𫜿 ) CJK UNIFIED IDEOGRAPH 2B73F → CJK UNIFIED IDEOGRAPH 6138
-2F81D ; 20674  # ( 𠙴 → 凵 ) CJK UNIFIED IDEOGRAPH 2F81D → CJK UNIFIED IDEOGRAPH 20674
-2F82D ; 2D161  # ( 𭅡 → 卑 ) CJK UNIFIED IDEOGRAPH 2F82D → CJK UNIFIED IDEOGRAPH 2D161
-2F85B ; 21533  # ( 𡔳 → 壷 ) CJK UNIFIED IDEOGRAPH 2F85B → CJK UNIFIED IDEOGRAPH 21533
-2F85D ; 21587  # ( 𡖇 → 多 ) CJK UNIFIED IDEOGRAPH 2F85D → CJK UNIFIED IDEOGRAPH 21587
-2F860 ; 216A7  # ( 𡚧 → 𡚨 ) CJK UNIFIED IDEOGRAPH 2F860 → CJK UNIFIED IDEOGRAPH 216A7
-2F89C ; 22505  # ( 𢔅 → 徚 ) CJK UNIFIED IDEOGRAPH 2F89C → CJK UNIFIED IDEOGRAPH 22505
-2F905 ; 23D40  # ( 𣵀 → 涅 ) CJK UNIFIED IDEOGRAPH 2F905 → CJK UNIFIED IDEOGRAPH 23D40
-2F927 ; 2AEC5  # ( 𪻅 → 𤠔 ) CJK UNIFIED IDEOGRAPH 2F927 → CJK UNIFIED IDEOGRAPH 2AEC5
-2F92B ; 248FD  # ( 𤣽 → 玥 ) CJK UNIFIED IDEOGRAPH 2F92B → CJK UNIFIED IDEOGRAPH 248FD
-2F935 ; 24C36  # ( 𤰶 → 𤰶 ) CJK UNIFIED IDEOGRAPH 2F935 → CJK UNIFIED IDEOGRAPH 24C36
-2F943 ; 2511A  # ( 𥄚 → 𥄙 ) CJK UNIFIED IDEOGRAPH 2F943 → CJK UNIFIED IDEOGRAPH 2511A
-2F96E ; 31E7C  # ( 𱹼 → 緇 ) CJK UNIFIED IDEOGRAPH 2F96E → CJK UNIFIED IDEOGRAPH 31E7C
-2F97E ; 2659D  # ( 𦖝 → 𦖨 ) CJK UNIFIED IDEOGRAPH 2F97E → CJK UNIFIED IDEOGRAPH 2659D
-2F9A4 ; 26D06  # ( 𦴆 → 𦰶 ) CJK UNIFIED IDEOGRAPH 2F9A4 → CJK UNIFIED IDEOGRAPH 26D06
-2F9CB ; 4695  # ( 䚕 → 𧢮 ) CJK UNIFIED IDEOGRAPH 2F9CB → CJK UNIFIED IDEOGRAPH 4695
-2F9D6 ; 25AD4  # ( 𥫔 → 贛 ) CJK UNIFIED IDEOGRAPH 2F9D6 → CJK UNIFIED IDEOGRAPH 25AD4
+# Following lines originally refereed to CJK compatibility characters,
+# which were not OK in confusables (PAG ref #486). The codepoints have been
+# replaced with the unified ideograph they decompose to.
+51F5 ; 20674
+5351 ; 2D161
+58F7 ; 21533
+591A ; 21587
+216A8 ; 216A7
+5F9A ; 22505
+6D85 ; 23D40
+24814 ; 2AEC5
+73A5 ; 248FD
+25119 ; 2511A
+7DC7 ; 31E7C
+265A8 ; 2659D
+26C36 ; 26D06
+278AE ; 4695
+8D1B ; 25AD4
 
 # High priority confusables for Tibetan (PAG ref #402)
 0F7B ; 0F7A 0F7A  # (  ཻ → ེེ ) TIBETAN VOWEL SIGN EE → TIBETAN VOWEL SIGN E, TIBETAN VOWEL SIGN E
@@ -5617,7 +5617,6 @@ A7F1 ; 02E2  # ( ꟱ → ˢ ) MODIFIER LETTER CAPITAL S → MODIFIER LETTER SMAL
 0A47 ; 0947
 09F0 ; 09B0
 1031 ; 0B47
-0B94 ; 0B92 0BB3
 0D25 ; 0BAE
 0D16 ; 0BB5
 0D46 ; 0BC6
@@ -5818,3 +5817,10 @@ A8CF ; 007C 007C # SAURASHTRA DOUBLE DANDA
 514C ; 5151
 980B ; 2EA07
 2EDB5 ; 32A8F
+
+# Pairs add to compensate for removal of non-NFD characters and sequences.
+# These were previously confusable due to transitivity, but now need to be
+# listed explicitly.
+2EBF ; 2EBE
+2EC0 ; 2EBE
+9FC3 ; 4039