Add some high-priority confusables

See unicode-org/properties#458

Note that U+031B vs U+02BC and U+0674 vs U+0654 are not added yet.
They seem to need changes to the Java code.

Author: roozbehp

unicodetools/data/security/dev/confusables.txt

@@ -1,5 +1,5 @@
 # confusables.txt
-# Date: 2025-10-17, 00:06:13 GMT
+# Date: 2025-10-25, 07:52:31 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
@@ -35,6 +35,12 @@
 0341 ;	0301 ;	MA	# ( ́ → ́ ) COMBINING ACUTE TONE MARK → COMBINING ACUTE ACCENT	# 
 0954 ;	0301 ;	MA	# ( ॔ → ́ ) DEVANAGARI ACUTE ACCENT → COMBINING ACUTE ACCENT	# 
 064E ;	0301 ;	MA	# ( َ → ́ ) ARABIC FATHA → COMBINING ACUTE ACCENT	# 
+07A6 ;	0301 ;	MA	# ( ަ → ́ ) THAANA ABAFILI → COMBINING ACUTE ACCENT	# 
+
+030B ;	0301 0301 ;	MA	# ( ̋ → ́́ ) COMBINING DOUBLE ACUTE ACCENT → COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT	# 
+064B ;	0301 0301 ;	MA	# ( ً → ́́ ) ARABIC FATHATAN → COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT	# →̋→
+08F0 ;	0301 0301 ;	MA	# ( ࣰ → ́́ ) ARABIC OPEN FATHATAN → COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT	# →ً→→̋→
+07A7 ;	0301 0301 ;	MA	# ( ާ → ́́ ) THAANA AABAAFILI → COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT	# →ަަ→
 
 0340 ;	0300 ;	MA	# ( ̀ → ̀ ) COMBINING GRAVE TONE MARK → COMBINING GRAVE ACCENT	# 
 0953 ;	0300 ;	MA	# ( ॓ → ̀ ) DEVANAGARI GRAVE ACCENT → COMBINING GRAVE ACCENT	# 
@@ -70,6 +76,7 @@ A6F0 ;	0302 ;	MA	# ( ꛰ → ̂ ) BAMUM COMBINING MARK KOQNDON → COMBINING CIR
 309A ;	030A ;	MA	# ( ゚ → ̊ ) COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK → COMBINING RING ABOVE	# 
 0652 ;	030A ;	MA	# ( ْ → ̊ ) ARABIC SUKUN → COMBINING RING ABOVE	# 
 0B82 ;	030A ;	MA	# ( ஂ → ̊ ) TAMIL SIGN ANUSVARA → COMBINING RING ABOVE	# 
+0F7E ;	030A ;	MA	# ( ཾ → ̊ ) TIBETAN SIGN RJES SU NGA RO → COMBINING RING ABOVE	# 
 1036 ;	030A ;	MA	# ( ံ → ̊ ) MYANMAR SIGN ANUSVARA → COMBINING RING ABOVE	# 
 17C6 ;	030A ;	MA	# ( ំ → ̊ ) KHMER SIGN NIKAHIT → COMBINING RING ABOVE	# 
 11300 ;	030A ;	MA	# ( 𑌀 → ̊ ) GRANTHA SIGN COMBINING ANUSVARA ABOVE → COMBINING RING ABOVE	# →ஂ→
@@ -78,13 +85,11 @@ A6F0 ;	0302 ;	MA	# ( ꛰ → ̂ ) BAMUM COMBINING MARK KOQNDON → COMBINING CIR
 302C ;	030A ;	MA	# ( 〬 → ̊ ) IDEOGRAPHIC DEPARTING TONE MARK → COMBINING RING ABOVE	# →゚→
 0366 ;	030A ;	MA	# ( ͦ → ̊ ) COMBINING LATIN SMALL LETTER O → COMBINING RING ABOVE	# 
 2DEA ;	030A ;	MA	# ( ⷪ → ̊ ) COMBINING CYRILLIC LETTER O → COMBINING RING ABOVE	# →ͦ→
+07B0 ;	030A ;	MA	# ( ް → ̊ ) THAANA SUKUN → COMBINING RING ABOVE	# 
 
 08EB ;	0308 ;	MA	# ( ࣫ → ̈ ) ARABIC TONE TWO DOTS ABOVE → COMBINING DIAERESIS	# 
 07F3 ;	0308 ;	MA	# ( ߳ → ̈ ) NKO COMBINING DOUBLE DOT ABOVE → COMBINING DIAERESIS	# 
 
-064B ;	030B ;	MA	# ( ً → ̋ ) ARABIC FATHATAN → COMBINING DOUBLE ACUTE ACCENT	# 
-08F0 ;	030B ;	MA	# ( ࣰ → ̋ ) ARABIC OPEN FATHATAN → COMBINING DOUBLE ACUTE ACCENT	# →ً→
-
 0342 ;	0303 ;	MA	# ( ͂ → ̃ ) COMBINING GREEK PERISPOMENI → COMBINING TILDE	# 
 0653 ;	0303 ;	MA	# ( ٓ → ̃ ) ARABIC MADDAH ABOVE → COMBINING TILDE	# 
 
@@ -126,6 +131,7 @@ A6F1 ;	0304 ;	MA	# ( ꛱ → ̄ ) BAMUM COMBINING MARK TUKWENTIS → COMBINING M
 0357 ;	0350 ;	MA	# ( ͗ → ͐ ) COMBINING RIGHT HALF RING ABOVE → COMBINING RIGHT ARROWHEAD ABOVE	# →ࣿ→→ࣸ→
 08FF ;	0350 ;	MA	# ( ࣿ → ͐ ) ARABIC MARK SIDEWAYS NOON GHUNNA → COMBINING RIGHT ARROWHEAD ABOVE	# →ࣸ→
 08F8 ;	0350 ;	MA	# ( ࣸ → ͐ ) ARABIC RIGHT ARROWHEAD ABOVE → COMBINING RIGHT ARROWHEAD ABOVE	# 
+07AA ;	0350 ;	MA	# ( ު → ͐ ) THAANA UBUFILI → COMBINING RIGHT ARROWHEAD ABOVE	# 
 
 0900 ;	0352 ;	MA	# ( ऀ → ͒ ) DEVANAGARI SIGN INVERTED CANDRABINDU → COMBINING FERMATA	# 
 
@@ -141,6 +147,8 @@ A6F1 ;	0304 ;	MA	# ( ꛱ → ̄ ) BAMUM COMBINING MARK TUKWENTIS → COMBINING M
 
 031A ;	1AE9 ;	MA	# ( ̚ → ᫩ ) COMBINING LEFT ANGLE ABOVE → COMBINING LEFT ANGLE CENTRED ABOVE	# 
 
+07AB ;	0350 0350 ;	MA	# ( ޫ → ͐͐ ) THAANA OOBOOFILI → COMBINING RIGHT ARROWHEAD ABOVE, COMBINING RIGHT ARROWHEAD ABOVE	# →ުު→
+
 1CED ;	0316 ;	MA	# ( ᳭ → ̖ ) VEDIC SIGN TIRYAK → COMBINING GRAVE ACCENT BELOW	# 
 
 1CDC ;	0329 ;	MA	# ( ᳜ → ̩ ) VEDIC TONE KATHAKA ANUDATTA → COMBINING VERTICAL LINE BELOW	# 
@@ -173,6 +181,7 @@ A6F1 ;	0304 ;	MA	# ( ꛱ → ̄ ) BAMUM COMBINING MARK TUKWENTIS → COMBINING M
 111CA ;	0323 ;	MA	# ( 𑇊 → ̣ ) SHARADA SIGN NUKTA → COMBINING DOT BELOW	# →़→
 114C3 ;	0323 ;	MA	# ( 𑓃 → ̣ ) TIRHUTA SIGN NUKTA → COMBINING DOT BELOW	# →়→
 10A3A ;	0323 ;	MA	# ( 𐨺 → ̣ ) KHAROSHTHI SIGN DOT BELOW → COMBINING DOT BELOW	# 
+0E3A ;	0323 ;	MA	# ( ฺ → ̣ ) THAI CHARACTER PHINTHU → COMBINING DOT BELOW	# 
 
 08EE ;	0324 ;	MA	# ( ࣮ → ̤ ) ARABIC TONE TWO DOTS BELOW → COMBINING DIAERESIS BELOW	# 
 1CDE ;	0324 ;	MA	# ( ᳞ → ̤ ) VEDIC TONE TWO DOTS BELOW → COMBINING DIAERESIS BELOW	# 
@@ -209,6 +218,9 @@ FC61 ;	FE78 0651 ;	MA	#* ( ‎ﱡ‎ → ‎ﹸّ‎ ) ARABIC LIGATURE SHADDA WI
 
 061A ;	0650 ;	MA	# ( ؚ → ِ ) ARABIC SMALL KASRA → ARABIC KASRA	# 
 0317 ;	0650 ;	MA	# ( ̗ → ِ ) COMBINING ACUTE ACCENT BELOW → ARABIC KASRA	# 
+07A8 ;	0650 ;	MA	# ( ި → ِ ) THAANA IBIFILI → ARABIC KASRA	# →̗→
+
+07A9 ;	0650 0650 ;	MA	# ( ީ → ِِ ) THAANA EEBEEFILI → ARABIC KASRA, ARABIC KASRA	# →ިި→
 
 FCF4 ;	FE7B 0651 ;	MA	# ( ‎ﳴ‎ → ‎ﹻّ‎ ) ARABIC LIGATURE SHADDA WITH KASRA MEDIAL FORM → ARABIC KASRA MEDIAL FORM, ARABIC SHADDA	# 
 
@@ -230,6 +242,8 @@ FC63 ;	FE7C 0670 ;	MA	#* ( ‎ﱣ‎ → ‎ﹼٰ‎ ) ARABIC LIGATURE SHADDA WI
 0D03 ;	0983 ;	MA	# ( ഃ → ঃ ) MALAYALAM SIGN VISARGA → BENGALI SIGN VISARGA	# →ಃ→→ః→→ਃ→
 0D83 ;	0983 ;	MA	# ( ඃ → ঃ ) SINHALA SIGN VISARGAYA → BENGALI SIGN VISARGA	# →ഃ→→ಃ→→ః→→ਃ→
 1038 ;	0983 ;	MA	# ( း → ঃ ) MYANMAR SIGN VISARGA → BENGALI SIGN VISARGA	# →ඃ→→ഃ→→ಃ→→ః→→ਃ→
+17C7 ;	0983 ;	MA	# ( ះ → ঃ ) KHMER SIGN REAHMUK → BENGALI SIGN VISARGA	# 
+11303 ;	0983 ;	MA	# ( 𑌃 → ঃ ) GRANTHA SIGN VISARGA → BENGALI SIGN VISARGA	# 
 114C1 ;	0983 ;	MA	# ( 𑓁 → ঃ ) TIRHUTA SIGN VISARGA → BENGALI SIGN VISARGA	# 
 
 17CB ;	0E48 ;	MA	# ( ់ → ่ ) KHMER SIGN BANTOC → THAI CHARACTER MAI EK	# 
@@ -2724,8 +2738,8 @@ A4E1 ;	004C ;	MA	# ( ꓡ → L ) LISU LETTER LA → LATIN CAPITAL LETTER L	#
 1041B ;	004C ;	MA	# ( 𐐛 → L ) DESERET CAPITAL LETTER ETH → LATIN CAPITAL LETTER L	# 
 10526 ;	004C ;	MA	# ( 𐔦 → L ) ELBASAN LETTER GHAMMA → LATIN CAPITAL LETTER L	# 
 
-FD3C ;	006C 030B ;	MA	# ( ‎ﴼ‎ → l̋ ) ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM → LATIN SMALL LETTER L, COMBINING DOUBLE ACUTE ACCENT	# →‎اً‎→
-FD3D ;	006C 030B ;	MA	# ( ‎ﴽ‎ → l̋ ) ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM → LATIN SMALL LETTER L, COMBINING DOUBLE ACUTE ACCENT	# →‎اً‎→
+FD3C ;	006C 0301 0301 ;	MA	# ( ‎ﴼ‎ → ĺ́ ) ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM → LATIN SMALL LETTER L, COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT	# →‎اً‎→
+FD3D ;	006C 0301 0301 ;	MA	# ( ‎ﴽ‎ → ĺ́ ) ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM → LATIN SMALL LETTER L, COMBINING ACUTE ACCENT, COMBINING ACUTE ACCENT	# →‎اً‎→
 
 FE82 ;	006C 0303 ;	MA	# ( ‎ﺂ‎ → l̃ ) ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM → LATIN SMALL LETTER L, COMBINING TILDE	# →‎آ‎→
 FE81 ;	006C 0303 ;	MA	# ( ‎ﺁ‎ → l̃ ) ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM → LATIN SMALL LETTER L, COMBINING TILDE	# →‎آ‎→
@@ -5759,6 +5773,12 @@ FC03 ;	0649 0654 0649 ;	MA	# ( ‎ﰃ‎ → ‎ىٔى‎ ) ARABIC LIGATURE YEH
 FC69 ;	0649 0654 0649 ;	MA	# ( ‎ﱩ‎ → ‎ىٔى‎ ) ARABIC LIGATURE YEH WITH HAMZA ABOVE WITH YEH FINAL FORM → ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE, ARABIC LETTER ALEF MAKSURA	# →‎ئي‎→
 FC04 ;	0649 0654 0649 ;	MA	# ( ‎ﰄ‎ → ‎ىٔى‎ ) ARABIC LIGATURE YEH WITH HAMZA ABOVE WITH YEH ISOLATED FORM → ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE, ARABIC LETTER ALEF MAKSURA	# →‎ئي‎→
 
+1DFE ;	07AC ;	MA	# ( ᷾ → ެ ) COMBINING LEFT ARROWHEAD ABOVE → THAANA EBEFILI	# 
+
+07AE ;	07AC 0350 ;	MA	# ( ޮ → ެ͐ ) THAANA OBOFILI → THAANA EBEFILI, COMBINING RIGHT ARROWHEAD ABOVE	# →ެު→
+
+07AD ;	07AC 07AC ;	MA	# ( ޭ → ެެ ) THAANA EYBEYFILI → THAANA EBEFILI, THAANA EBEFILI	# 
+
 102B8 ;	2D40 ;	MA	# ( 𐊸 → ⵀ ) CARIAN LETTER SS → TIFINAGH LETTER YAH	# 
 
 205E ;	2D42 ;	MA	#* ( ⁞ → ⵂ ) VERTICAL FOUR DOTS → TIFINAGH LETTER TUAREG YAH	# 
@@ -6154,6 +6174,10 @@ FE19 ;	2D57 ;	MA	#* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
 
 0D8D ;	0DC3 0DD8 ;	MA	# ( ඍ → සෘ ) SINHALA LETTER IRUYANNA → SINHALA LETTER DANTAJA SAYANNA, SINHALA VOWEL SIGN GAETTA-PILLA	# 
 
+0DF2 ;	0DD8 0DD8 ;	MA	# ( ෲ → ෘෘ ) SINHALA VOWEL SIGN DIGA GAETTA-PILLA → SINHALA VOWEL SIGN GAETTA-PILLA, SINHALA VOWEL SIGN GAETTA-PILLA	# 
+
+0DDB ;	0DD9 0DD9 ;	MA	# ( ෛ → ෙෙ ) SINHALA VOWEL SIGN KOMBU DEKA → SINHALA VOWEL SIGN KOMBUVA, SINHALA VOWEL SIGN KOMBUVA	# 
+
 1CD8 ;	11B62 ;	MA	# ( ᳘ → 𑭢 ) VEDIC TONE CANDRA BELOW → SHARADA VOWEL SIGN UE	# →̮→→ॖ→
 032E ;	11B62 ;	MA	# ( ̮ → 𑭢 ) COMBINING BREVE BELOW → SHARADA VOWEL SIGN UE	# →ॖ→
 0956 ;	11B62 ;	MA	# ( ॖ → 𑭢 ) DEVANAGARI VOWEL SIGN UE → SHARADA VOWEL SIGN UE	# 
@@ -6244,13 +6268,15 @@ FE19 ;	2D57 ;	MA	#* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
 
 0EB3 ;	030A 0EB2 ;	MA	# ( ຳ → ̊າ ) LAO VOWEL SIGN AM → COMBINING RING ABOVE, LAO VOWEL SIGN AA	# →ໍາ→
 
+0EC1 ;	0EC0 0EC0 ;	MA	# ( ແ → ເເ ) LAO VOWEL SIGN EI → LAO VOWEL SIGN E, LAO VOWEL SIGN E	# 
+
 0F02 ;	0F60 0F74 0F82 0F7F ;	MA	#* ( ༂ → འུྂཿ ) TIBETAN MARK GTER YIG MGO -UM RNAM BCAD MA → TIBETAN LETTER -A, TIBETAN VOWEL SIGN U, TIBETAN SIGN NYI ZLA NAA DA, TIBETAN SIGN RNAM BCAD	# 
 
 0F03 ;	0F60 0F74 0F82 0F14 ;	MA	#* ( ༃ → འུྂ༔ ) TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA → TIBETAN LETTER -A, TIBETAN VOWEL SIGN U, TIBETAN SIGN NYI ZLA NAA DA, TIBETAN MARK GTER TSHEG	# 
 
 0F6A ;	0F62 ;	MA	# ( ཪ → ར ) TIBETAN LETTER FIXED-FORM RA → TIBETAN LETTER RA	# 
 
-0F00 ;	0F68 0F7C 0F7E ;	MA	# ( ༀ → ཨོཾ ) TIBETAN SYLLABLE OM → TIBETAN LETTER A, TIBETAN VOWEL SIGN O, TIBETAN SIGN RJES SU NGA RO	# 
+0F00 ;	0F68 0F7C 030A ;	MA	# ( ༀ → ཨོ̊ ) TIBETAN SYLLABLE OM → TIBETAN LETTER A, TIBETAN VOWEL SIGN O, COMBINING RING ABOVE	# →ཨོཾ→
 
 0F77 ;	0FB2 0F71 0F80 ;	MA	# ( ཷ → ྲཱྀ ) TIBETAN VOWEL SIGN VOCALIC RR → TIBETAN SUBJOINED LETTER RA, TIBETAN VOWEL SIGN AA, TIBETAN VOWEL SIGN REVERSED I	# 
 
@@ -6264,6 +6290,8 @@ FE19 ;	2D57 ;	MA	#* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
 
 1734 ;	1715 ;	MA	# ( ᜴ → ᜕ ) HANUNOO SIGN PAMUDPOD → TAGALOG SIGN PAMUDPOD	# 
 
+1022 ;	1075 102C ;	MA	# ( ဢ → ၵာ ) MYANMAR LETTER SHAN A → MYANMAR LETTER SHAN KA, MYANMAR VOWEL SIGN AA	# 
+
 1070 ;	1003 103E ;	MA	# ( ၰ → ဃှ ) MYANMAR LETTER EASTERN PWO KAREN GHWA → MYANMAR LETTER GHA, MYANMAR CONSONANT SIGN MEDIAL HA	# 
 
 1066 ;	1015 103E ;	MA	# ( ၦ → ပှ ) MYANMAR LETTER WESTERN PWO KAREN PWA → MYANMAR LETTER PA, MYANMAR CONSONANT SIGN MEDIAL HA	# 
@@ -6284,8 +6312,16 @@ FE19 ;	2D57 ;	MA	#* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
 
 178F ;	178A ;	MA	# ( ត → ដ ) KHMER LETTER TA → KHMER LETTER DA	# 
 
+17A1 ;	1791 17D2 1794 ;	MA	# ( ឡ → ទ្ប ) KHMER LETTER LA → KHMER LETTER TO, KHMER SIGN COENG, KHMER LETTER BA	# 
+
+17B0 ;	1796 17D2 1792 ;	MA	# ( ឰ → ព្ធ ) KHMER INDEPENDENT VOWEL QAI → KHMER LETTER PO, KHMER SIGN COENG, KHMER LETTER THO	# 
+
 17A3 ;	17A2 ;	MA	# ( ឣ → អ ) KHMER INDEPENDENT VOWEL QAQ → KHMER LETTER QA	# 
 
+17BE ;	17C1 0E35 ;	MA	# ( ើ → េี ) KHMER VOWEL SIGN OE → KHMER VOWEL SIGN E, THAI CHARACTER SARA II	# →េី→
+
+17C4 ;	17C1 17B6 ;	MA	# ( ោ → េា ) KHMER VOWEL SIGN OO → KHMER VOWEL SIGN E, KHMER VOWEL SIGN AA	# 
+
 19D0 ;	199E ;	MA	# ( ᧐ → ᦞ ) NEW TAI LUE DIGIT ZERO → NEW TAI LUE LETTER LOW VA	# 
 
 19D1 ;	19B1 ;	MA	# ( ᧑ → ᦱ ) NEW TAI LUE DIGIT ONE → NEW TAI LUE VOWEL SIGN AA	# 
@@ -9978,5 +10014,5 @@ FACE ;	9F9C ;	MA	# ( 龜 → 龜 ) CJK COMPATIBILITY IDEOGRAPH-FACE → CJK UNIF
 
 2FD5 ;	9FA0 ;	MA	#* ( ⿕ → 龠 ) KANGXI RADICAL FLUTE → CJK UNIFIED IDEOGRAPH-9FA0	# 
 
-# total: 6582
+# total: 6605