More Unicode 17.0 Confusables (#1168)

* Arabic confusables for Hindko
* New confusables data based on L2/22-108
* Confusable sequences proposed in L2/22-107
* New confusable data based on L2/22-114
* Confusable sequences mentioned in L2/22-081
* Missing Coptic confusables
* Confusable Katakana-Han pair
* Uncomment commented additions and fix their issues

---------

Co-authored-by: Roozbeh Pournader <[email protected]>

Author: josh-hadley

unicodetools/data/security/dev/confusables.txt

@@ -39,7 +39,6 @@
 0259 ; 04D9 #  schwa ; schwa
 0068 ; 04BB #  h ; shha
 0069 ; 0456 #  i ; i
-026A ; 04CF #  smallcap i ; small palochka (arguable)
 03B9 ; 0269 # iota ; iota 
 03F3 ; 006A ; 0458 # yot ; j ; je
 0138 ; 043A #  kra ; ka

unicodetools/data/security/dev/confusablesSummary.txt

@@ -336,7 +336,6 @@
 
 0131 ;	026A	# ( ı ~ ɪ ) LATIN SMALL LETTER DOTLESS I ~ LATIN LETTER SMALL CAPITAL I
 0131 ;	03B9	# ( ı ~ ι ) LATIN SMALL LETTER DOTLESS I ~ GREEK SMALL LETTER IOTA
-0131 ;	04CF	# ( ı ~ ӏ ) LATIN SMALL LETTER DOTLESS I ~ CYRILLIC SMALL LETTER PALOCHKA
 
 0138 ;	1D0B	# ( ĸ ~ ᴋ ) LATIN SMALL LETTER KRA ~ LATIN LETTER SMALL CAPITAL K
 0138 ;	03BA	# ( ĸ ~ κ ) LATIN SMALL LETTER KRA ~ GREEK SMALL LETTER KAPPA

unicodetools/data/security/dev/data/confusablesSummaryIdentifier.txt

@@ -72,7 +72,6 @@
 018A ;  02BD 0044   # ( Ɗ → ʽD) LATIN CAPITAL LETTER D WITH HOOK → MODIFIER LETTER REVERSED COMMA, LATIN CAPITAL LETTER D
 018C ;  0064 0304   # ( ƌ → d̄) LATIN SMALL LETTER D WITH TOPBAR → LATIN SMALL LETTER D, COMBINING MACRON
 0191 ;  0046 0321   # ( Ƒ → F̡) LATIN CAPITAL LETTER F WITH HOOK → LATIN CAPITAL LETTER F, COMBINING PALATALIZED HOOK BELOW
-0192 ;  0066 0321   # ( ƒ → f̡) LATIN SMALL LETTER F WITH HOOK → LATIN SMALL LETTER F, COMBINING PALATALIZED HOOK BELOW
 0193 ;  0047 02BD   # ( Ɠ → Gʽ) LATIN CAPITAL LETTER G WITH HOOK → LATIN CAPITAL LETTER G, MODIFIER LETTER REVERSED COMMA
 0196 ;  006C    # ( Ɩ → l) LATIN CAPITAL LETTER IOTA → LATIN SMALL LETTER L
 0197 ;  0049 0335   # ( Ɨ → I̵) LATIN CAPITAL LETTER I WITH STROKE → LATIN CAPITAL LETTER I, COMBINING SHORT STROKE OVERLAY
@@ -431,7 +430,6 @@
 09BC ;  093C    # ( ় → ़) BENGALI SIGN NUKTA → DEVANAGARI SIGN NUKTA
 09E0 ;  098B 09C3   # ( ৠ → ঋৃ) BENGALI LETTER VOCALIC RR → BENGALI LETTER VOCALIC R, BENGALI VOWEL SIGN VOCALIC R
 09E1 ;  098C 09E2   # ( ৡ → ঌৢ) BENGALI LETTER VOCALIC LL → BENGALI LETTER VOCALIC L, BENGALI VOWEL SIGN VOCALIC L
-09E6 ;  0030    # ( ০ → 0) BENGALI DIGIT ZERO → DIGIT ZERO
 09EA ;  0038    # ( ৪ → 8) BENGALI DIGIT FOUR → DIGIT EIGHT
 09ED ;  0039    # ( ৭ → 9) BENGALI DIGIT SEVEN → DIGIT NINE
 0A02 ;  0307    # ( ਂ → ̇) GURMUKHI SIGN BINDI → COMBINING DOT ABOVE
@@ -478,7 +476,6 @@
 0B3C ;  0323    # ( ଼ → ̣) ORIYA SIGN NUKTA → COMBINING DOT BELOW
 0B3C ;  0A3C    # ( ଼ → ਼) ORIYA SIGN NUKTA → GURMUKHI SIGN NUKTA
 0B3C ;  0ABC    # ( ଼ → ઼) ORIYA SIGN NUKTA → GUJARATI SIGN NUKTA
-0B66 ;  0030    # ( ୦ → 0) ORIYA DIGIT ZERO → DIGIT ZERO
 0B68 ;  0039    # ( ୨ → 9) ORIYA DIGIT TWO → DIGIT NINE
 0B82 ;  030A    # ( ஂ → ̊) TAMIL SIGN ANUSVARA → COMBINING RING ABOVE
 0B8A ;  0B89 0BB3   # ( ஊ → உள) TAMIL LETTER UU → TAMIL LETTER U, TAMIL LETTER LLA
@@ -539,7 +536,6 @@
 0CB1 ;  0C31    # ( ಱ → ఱ) KANNADA LETTER RRA → TELUGU LETTER RRA
 0CB2 ;  0C32    # ( ಲ → ల) KANNADA LETTER LA → TELUGU LETTER LA
 0CE1 ;  0C8C 0CBE   # ( ೡ → ಌಾ) KANNADA LETTER VOCALIC LL → KANNADA LETTER VOCALIC L, KANNADA VOWEL SIGN AA
-0CE6 ;  0C66    # ( ೦ → ౦) KANNADA DIGIT ZERO → TELUGU DIGIT ZERO
 0CE7 ;  0C67    # ( ೧ → ౧) KANNADA DIGIT ONE → TELUGU DIGIT ONE
 0CE8 ;  0C68    # ( ೨ → ౨) KANNADA DIGIT TWO → TELUGU DIGIT TWO
 0CEF ;  0C6F    # ( ೯ → ౯) KANNADA DIGIT NINE → TELUGU DIGIT NINE
@@ -5574,3 +5570,157 @@ A7F1 ; 02E2  # ( ꟱ → ˢ ) MODIFIER LETTER CAPITAL S → MODIFIER LETTER SMAL
 # High priority confusables for Tibetan (PAG ref #402)
 0F7B ; 0F7A 0F7A  # (  ཻ → ེེ ) TIBETAN VOWEL SIGN EE → TIBETAN VOWEL SIGN E, TIBETAN VOWEL SIGN E
 0F7D ; 0F7C 0F7C  # (  ཽ → ོོ ) TIBETAN VOWEL SIGN OO → TIBETAN VOWEL SIGN O, TIBETAN VOWEL SIGN O
+
+# Arabic confusables for Hindko (PAG ref #412)
+08BE ; 067E 065A
+08BF ; 062A 065A
+08C0 ; 0679 065A
+08C1 ; 0686 065A
+08C2 ; 06A9 065A
+
+# New confusables data based on L2/22-108 (PAG ref #415)
+0945 ; 0306
+0949 ; 093E 0945
+0972 ; 0905 0945
+0BB6 ; 0BB8
+105A ; 1004
+178F ; 178A
+
+# An analysis of confusable sequences proposed in L2/22-107 (PAG ref #416)
+0974 ; 0905 093B
+093B ; 093E 093A
+0D7A ; 0D23 0D4D
+0D7D ; 0D32 0D4D
+0D7E ; 0D33 0D4D
+
+# New confusable data based on L2/22-114 (PAG ref #417)
+09E6 ; 006F
+0B20 ; 004F
+0B66 ; 006F
+0CE6 ; 004F
+17E0 ; 006F
+0AE9 ; 0033
+1004 ; 0063
+0192 ; 0066
+0572 ; 03B7
+01BF ; 0070
+0D1F ; 0073
+014B ; 03B7
+0448 ; 0077
+045F ; 0075 0329
+067A ; 062A
+0752 ; 067E
+068F ; 068E
+0973 ; 0905 093A
+0AB0 ; 0AE8
+0A24 ; 0909
+0975 ; 0905 094F
+0A1F ; 091F
+0A20 ; 0920
+0A2B ; 0922
+0A1C ; 0924 094D 0924
+0A27 ; 092A
+0A72 ; 092A 094D 091F
+0A2E ; 092D
+0A38 ; 092E
+0A15 ; 0935
+0A35 ; 0939
+0A3F ; 093F
+0A48 ; 0948
+0A41 ; 0956
+0A42 ; 0957
+09BF ; 093F
+0A47 ; 0947
+09F0 ; 09B0
+1031 ; 0B47
+0B94 ; 0B92 0BB3
+0D25 ; 0BAE
+0D16 ; 0BB5
+0D46 ; 0BC6
+0D47 ; 0BC7
+0C90 ; 0C10
+0C16 ; 0C96 0323
+0C97 ; 0C17
+0C9D ; 0C1D
+0C9F ; 0C1F
+0CA6 ; 0C26
+0CA8 ; 0C28
+0CB0 ; 0C30
+0CB3 ; 0C33
+0CBF ; 0C3F
+0CC1 ; 0C41
+0CC3 ; 0C43
+1002 ; 0D31
+10D8 ; 0D31
+0D8D ; 0DC3 0DD8
+0DB5 ; 0D91
+0D92 ; 0D91 0DCA
+0D93 ; 0D91 0DD9
+0DB9 ; 0D94
+0DB6 ; 0D9B
+0DC0 ; 0DA0
+0DC4 ; 0DB7
+0AEB ; 0AAA
+0AEB ; 0447
+1023 ; 1000 1039 1000
+1061 ; 101B 103E
+10D7 ; 1010
+723F ; 1102 1171
+535F ; 1106 1161
+4ECA ; 1109 1173 11A8
+5408 ; 1109 1173 11B7
+4E1B ; 110A 1173
+4E15 ; 110C 1169
+9577 ; 1110 1173 11AC
+
+# An analysis of confusable sequences mentioned in L2/22-081 (PAG ref #418)
+256A ; 01C2
+0582 ; 0131
+04CF ; 0049
+
+# Missing Coptic confusables (PAG ref #419)
+03E4 ; 0427
+03E5 ; 0447
+03EC ; 0036
+03ED ; 03C3
+2C82 ; 0042
+2C83 ; 0432
+2C8B ; 03C2
+2C8C ; 2C6B
+2C8D ; 2C6C
+2C8F ; 043D
+2C90 ; 03F4
+2C91 ; 0275
+2C93 ; 0131
+2C97 ; 028C
+2C99 ; 1D0D
+2C9B ; 0274
+2C9C ; 01B7
+2C9D ; 0293
+2CA1 ; 043F
+2CA7 ; 0442
+2CA9 ; 03B3
+2CAF ; 03C8
+2CB0 ; A64C
+2CB2 ; FB29
+2CB3 ; FB29
+2CB5 ; 22D6
+2CB6 ; 039E
+2CB7 ; 2261
+2CBB ; 2212
+2CC0 ; 20BD
+2CC1 ; 03FC
+2CC4 ; 01B7
+2CC5 ; 0292
+2CC7 ; 002F
+2CCB ; 0039
+2CCE ; 0050
+2CCF ; 0070
+2CD3 ; 0036
+2CDD ; 03B4
+2CE0 ; 03C6
+2CE1 ; 03C6
+2CE8 ; 20BD
+
+# Confusable Katakana-Han pair (PAG ref #442)
+1B122 ; 4E8E

unicodetools/data/security/dev/data/source/confusables-intentional.txt

@@ -1037,8 +1037,6 @@
 
 07F5 ;	2018	# ( ‎ߵ‎ ~ ‘ ) NKO LOW TONE APOSTROPHE ~ LEFT SINGLE QUOTATION MARK
 
-0B20 ;	0B66	# ( ଠ ~ ୦ ) ORIYA LETTER TTHA ~ ORIYA DIGIT ZERO
-
 0B85 ;	0BEE	# ( அ ~ ௮ ) TAMIL LETTER A ~ TAMIL DIGIT EIGHT
 
 0B95 ;	0BE7	# ( க ~ ௧ ) TAMIL LETTER KA ~ TAMIL DIGIT ONE

unicodetools/data/security/dev/data/source/confusables-macFonts.txt

@@ -1,5 +1,5 @@
 # formatted-macFonts.txt
-# Date: 2025-05-02, 14:36:22 GMT
+# Date: 2025-07-22, 05:49:36 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
@@ -283,7 +283,6 @@
 
 0131 ;	026A	# ( ı ~ ɪ ) LATIN SMALL LETTER DOTLESS I ~ LATIN LETTER SMALL CAPITAL I
 0131 ;	03B9	# ( ı ~ ι ) LATIN SMALL LETTER DOTLESS I ~ GREEK SMALL LETTER IOTA
-0131 ;	04CF	# ( ı ~ ӏ ) LATIN SMALL LETTER DOTLESS I ~ CYRILLIC SMALL LETTER PALOCHKA
 
 0138 ;	1D0B	# ( ĸ ~ ᴋ ) LATIN SMALL LETTER KRA ~ LATIN LETTER SMALL CAPITAL K
 0138 ;	03BA	# ( ĸ ~ κ ) LATIN SMALL LETTER KRA ~ GREEK SMALL LETTER KAPPA