Skip to content

Commit 2aaaac5

Browse files
committed
Uncomment commented additions and fix their issues
1 parent f218e6a commit 2aaaac5

11 files changed

+47
-64
lines changed

unicodetools/data/security/dev/confusables.txt

Lines changed: 8 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusables.txt
2-
# Date: 2025-07-21, 18:09:10 GMT
2+
# Date: 2025-07-22, 05:49:37 GMT
33
# © 2025 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -2222,6 +2222,7 @@ A79D ; 029A ; MA # ( ꞝ → ʚ ) LATIN SMALL LETTER VOLAPUK OE → LATIN SMALL
22222222
1D68F ; 0066 ; MA # ( 𝚏 → f ) MATHEMATICAL MONOSPACE SMALL F → LATIN SMALL LETTER F #
22232223
AB35 ; 0066 ; MA # ( ꬵ → f ) LATIN SMALL LETTER LENIS F → LATIN SMALL LETTER F #
22242224
A799 ; 0066 ; MA # ( ꞙ → f ) LATIN SMALL LETTER F WITH STROKE → LATIN SMALL LETTER F #
2225+
0192 ; 0066 ; MA # ( ƒ → f ) LATIN SMALL LETTER F WITH HOOK → LATIN SMALL LETTER F #
22252226
017F ; 0066 ; MA # ( ſ → f ) LATIN SMALL LETTER LONG S → LATIN SMALL LETTER F #
22262227
1E9D ; 0066 ; MA # ( ẝ → f ) LATIN SMALL LETTER LONG S WITH HIGH STROKE → LATIN SMALL LETTER F #
22272228
0584 ; 0066 ; MA # ( ք → f ) ARMENIAN SMALL LETTER KEH → LATIN SMALL LETTER F #
@@ -2252,8 +2253,6 @@ A4DD ; 0046 ; MA # ( ꓝ → F ) LISU LETTER TSA → LATIN CAPITAL LETTER F #
22522253
102A5 ; 0046 ; MA # ( 𐊥 → F ) CARIAN LETTER R → LATIN CAPITAL LETTER F #
22532254
10525 ; 0046 ; MA # ( 𐔥 → F ) ELBASAN LETTER GHE → LATIN CAPITAL LETTER F #
22542255

2255-
0192 ; 0066 0326 ; MA # ( ƒ → f̦ ) LATIN SMALL LETTER F WITH HOOK → LATIN SMALL LETTER F, COMBINING COMMA BELOW # →f̡→
2256-
22572256
0191 ; 0046 0326 ; MA # ( Ƒ → F̦ ) LATIN CAPITAL LETTER F WITH HOOK → LATIN CAPITAL LETTER F, COMBINING COMMA BELOW # →F̡→
22582257

22592258
1D6E ; 0066 0334 ; MA # ( ᵮ → f̴ ) LATIN SMALL LETTER F WITH MIDDLE TILDE → LATIN SMALL LETTER F, COMBINING TILDE OVERLAY #
@@ -2454,7 +2453,6 @@ FF49 ; 0069 ; MA # ( i → i ) FULLWIDTH LATIN SMALL LETTER I → LATIN SMALL
24542453
2C93 ; 0069 ; MA # ( ⲓ → i ) COPTIC SMALL LETTER IAUDA → LATIN SMALL LETTER I # →ı→
24552454
0456 ; 0069 ; MA # ( і → i ) CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I → LATIN SMALL LETTER I #
24562455
A647 ; 0069 ; MA # ( ꙇ → i ) CYRILLIC SMALL LETTER IOTA → LATIN SMALL LETTER I # →ι→
2457-
04CF ; 0069 ; MA # ( ӏ → i ) CYRILLIC SMALL LETTER PALOCHKA → LATIN SMALL LETTER I # →ı→
24582456
0582 ; 0069 ; MA # ( ւ → i ) ARMENIAN SMALL LETTER YIWN → LATIN SMALL LETTER I # →ı→
24592457
AB75 ; 0069 ; MA # ( ꭵ → i ) CHEROKEE SMALL LETTER V → LATIN SMALL LETTER I #
24602458
13A5 ; 0069 ; MA # ( Ꭵ → i ) CHEROKEE LETTER V → LATIN SMALL LETTER I #
@@ -2647,6 +2645,7 @@ FF4C ; 006C ; MA # ( l → l ) FULLWIDTH LATIN SMALL LETTER L → LATIN SMALL
26472645
1D798 ; 006C ; MA # ( 𝞘 → l ) MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL IOTA → LATIN SMALL LETTER L # →Ι→
26482646
2C92 ; 006C ; MA # ( Ⲓ → l ) COPTIC CAPITAL LETTER IAUDA → LATIN SMALL LETTER L # →Ӏ→
26492647
0406 ; 006C ; MA # ( І → l ) CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I → LATIN SMALL LETTER L #
2648+
04CF ; 006C ; MA # ( ӏ → l ) CYRILLIC SMALL LETTER PALOCHKA → LATIN SMALL LETTER L # →I→
26502649
04C0 ; 006C ; MA # ( Ӏ → l ) CYRILLIC LETTER PALOCHKA → LATIN SMALL LETTER L #
26512650
05D5 ; 006C ; MA # ( ‎ו‎ → l ) HEBREW LETTER VAV → LATIN SMALL LETTER L #
26522651
05DF ; 006C ; MA # ( ‎ן‎ → l ) HEBREW LETTER FINAL NUN → LATIN SMALL LETTER L #
@@ -2959,16 +2958,18 @@ A4E0 ; 004E ; MA # ( ꓠ → N ) LISU LETTER NA → LATIN CAPITAL LETTER N #
29592958
0D02 ; 006F ; MA # ( ം → o ) MALAYALAM SIGN ANUSVARA → LATIN SMALL LETTER O #
29602959
0D82 ; 006F ; MA # ( ං → o ) SINHALA SIGN ANUSVARAYA → LATIN SMALL LETTER O #
29612960
0966 ; 006F ; MA # ( ० → o ) DEVANAGARI DIGIT ZERO → LATIN SMALL LETTER O #
2961+
09E6 ; 006F ; MA # ( ০ → o ) BENGALI DIGIT ZERO → LATIN SMALL LETTER O #
29622962
0A66 ; 006F ; MA # ( ੦ → o ) GURMUKHI DIGIT ZERO → LATIN SMALL LETTER O #
29632963
0AE6 ; 006F ; MA # ( ૦ → o ) GUJARATI DIGIT ZERO → LATIN SMALL LETTER O #
2964+
0B66 ; 006F ; MA # ( ୦ → o ) ORIYA DIGIT ZERO → LATIN SMALL LETTER O #
29642965
0BE6 ; 006F ; MA # ( ௦ → o ) TAMIL DIGIT ZERO → LATIN SMALL LETTER O #
29652966
0C66 ; 006F ; MA # ( ౦ → o ) TELUGU DIGIT ZERO → LATIN SMALL LETTER O #
2966-
0CE6 ; 006F ; MA # ( ೦ → o ) KANNADA DIGIT ZERO → LATIN SMALL LETTER O # →౦→
29672967
0D66 ; 006F ; MA # ( ൦ → o ) MALAYALAM DIGIT ZERO → LATIN SMALL LETTER O #
29682968
0E50 ; 006F ; MA # ( ๐ → o ) THAI DIGIT ZERO → LATIN SMALL LETTER O #
29692969
0ED0 ; 006F ; MA # ( ໐ → o ) LAO DIGIT ZERO → LATIN SMALL LETTER O #
29702970
1040 ; 006F ; MA # ( ၀ → o ) MYANMAR DIGIT ZERO → LATIN SMALL LETTER O #
29712971
17E0 ; 006F ; MA # ( ០ → o ) KHMER DIGIT ZERO → LATIN SMALL LETTER O #
2972+
114D0 ; 006F ; MA # ( 𑓐 → o ) TIRHUTA DIGIT ZERO → LATIN SMALL LETTER O # →০→
29722973
0665 ; 006F ; MA # ( ‎٥‎ → o ) ARABIC-INDIC DIGIT FIVE → LATIN SMALL LETTER O #
29732974
06F5 ; 006F ; MA # ( ۵ → o ) EXTENDED ARABIC-INDIC DIGIT FIVE → LATIN SMALL LETTER O # →‎٥‎→
29742975
FF4F ; 006F ; MA # ( o → o ) FULLWIDTH LATIN SMALL LETTER O → LATIN SMALL LETTER O # →о→
@@ -3034,10 +3035,8 @@ FBA6 ; 006F ; MA # ( ‎ﮦ‎ → o ) ARABIC LETTER HEH GOAL ISOLATED FORM →
30343035

30353036
0030 ; 004F ; MA # ( 0 → O ) DIGIT ZERO → LATIN CAPITAL LETTER O #
30363037
07C0 ; 004F ; MA # ( ‎߀‎ → O ) NKO DIGIT ZERO → LATIN CAPITAL LETTER O # →0→
3037-
09E6 ; 004F ; MA # ( ০ → O ) BENGALI DIGIT ZERO → LATIN CAPITAL LETTER O # →0→
3038-
0B66 ; 004F ; MA # ( ୦ → O ) ORIYA DIGIT ZERO → LATIN CAPITAL LETTER O # →0→
3038+
0CE6 ; 004F ; MA # ( ೦ → O ) KANNADA DIGIT ZERO → LATIN CAPITAL LETTER O #
30393039
3007 ; 004F ; MA # ( 〇 → O ) IDEOGRAPHIC NUMBER ZERO → LATIN CAPITAL LETTER O #
3040-
114D0 ; 004F ; MA # ( 𑓐 → O ) TIRHUTA DIGIT ZERO → LATIN CAPITAL LETTER O # →০→→0→
30413040
118E0 ; 004F ; MA # ( 𑣠 → O ) WARANG CITI DIGIT ZERO → LATIN CAPITAL LETTER O # →0→
30423041
1CCF0 ; 004F ; MA # ( 𜳰 → O ) OUTLINED DIGIT ZERO → LATIN CAPITAL LETTER O # →0→
30433042
1D7CE ; 004F ; MA # ( 𝟎 → O ) MATHEMATICAL BOLD DIGIT ZERO → LATIN CAPITAL LETTER O # →0→
@@ -3072,7 +3071,7 @@ FF2F ; 004F ; MA # ( O → O ) FULLWIDTH LATIN CAPITAL LETTER O → LATIN CAPI
30723071
0555 ; 004F ; MA # ( Օ → O ) ARMENIAN CAPITAL LETTER OH → LATIN CAPITAL LETTER O #
30733072
2D54 ; 004F ; MA # ( ⵔ → O ) TIFINAGH LETTER YAR → LATIN CAPITAL LETTER O #
30743073
12D0 ; 004F ; MA # ( ዐ → O ) ETHIOPIC SYLLABLE PHARYNGEAL A → LATIN CAPITAL LETTER O # →Օ→
3075-
0B20 ; 004F ; MA # ( ଠ → O ) ORIYA LETTER TTHA → LATIN CAPITAL LETTER O # →୦→→0→
3074+
0B20 ; 004F ; MA # ( ଠ → O ) ORIYA LETTER TTHA → LATIN CAPITAL LETTER O #
30763075
104C2 ; 004F ; MA # ( 𐓂 → O ) OSAGE CAPITAL LETTER O → LATIN CAPITAL LETTER O #
30773076
A4F3 ; 004F ; MA # ( ꓳ → O ) LISU LETTER O → LATIN CAPITAL LETTER O #
30783077
118B5 ; 004F ; MA # ( 𑢵 → O ) WARANG CITI CAPITAL LETTER AT → LATIN CAPITAL LETTER O #

unicodetools/data/security/dev/confusablesSummary.txt

Lines changed: 14 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusablesSummary.txt
2-
# Date: 2025-07-21, 18:09:10 GMT
2+
# Date: 2025-07-22, 05:49:37 GMT
33
# © 2025 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -942,27 +942,25 @@
942942
(‎ /̄ ‎) 002F 0304 SOLIDUS, COMBINING MACRON
943943
← (‎ ⧶ ‎) 29F6 SOLIDUS WITH OVERBAR
944944

945-
# O 𑷠 0 ০ ଠ ዐ 〇 Ο О Օ ߀ Ⲟ ⵔ ꓳ 𐊒 𐊫 𐐄 𐔖 𑓐 𑢵 𑣠 𐓂 🯰 𜳰 𜳤 O 𝐎 𝑂 𝑶 𝒪 𝓞 𝔒 𝕆 𝕺 𝖮 𝗢 𝘖 𝙊 𝙾 𝚶 𝛰 𝜪 𝝤 𝞞 𝟎 𝟘 𝟢 𝟬 𝟶
945+
# O 𑷠 0 ଠ ೦ ዐ 〇 Ο О Օ ߀ Ⲟ ⵔ ꓳ 𐊒 𐊫 𐐄 𐔖 𑢵 𑣠 𐓂 🯰 𜳰 𜳤 O 𝐎 𝑂 𝑶 𝒪 𝓞 𝔒 𝕆 𝕺 𝖮 𝗢 𝘖 𝙊 𝙾 𝚶 𝛰 𝜪 𝝤 𝞞 𝟎 𝟘 𝟢 𝟬 𝟶
946946
(‎ 0 ‎) 0030 DIGIT ZERO
947947
← (‎ O ‎) 004F LATIN CAPITAL LETTER O
948948
← (‎ 𑷠 ‎) 11DE0 TOLONG SIKI DIGIT ZERO
949-
← (‎ ‎) 09E6 BENGALI DIGIT ZERO
950-
← (‎ ‎) 0B20 ORIYA LETTER TTHA # →
949+
← (‎ ‎) 0B20 ORIYA LETTER TTHA # →O→
950+
← (‎ ‎) 0CE6 KANNADA DIGIT ZERO # →O
951951
← (‎ ዐ ‎) 12D0 ETHIOPIC SYLLABLE PHARYNGEAL A # →Օ→→О→
952952
← (‎ 〇 ‎) 3007 IDEOGRAPHIC NUMBER ZERO # →O→
953953
← (‎ Ο ‎) 039F GREEK CAPITAL LETTER OMICRON
954954
← (‎ О ‎) 041E CYRILLIC CAPITAL LETTER O
955955
← (‎ Օ ‎) 0555 ARMENIAN CAPITAL LETTER OH # →О→
956956
← (‎ ߀ ‎) 07C0 NKO DIGIT ZERO
957-
← (‎ ୦ ‎) 0B66 ORIYA DIGIT ZERO
958957
← (‎ Ⲟ ‎) 2C9E COPTIC CAPITAL LETTER O # →О→
959958
← (‎ ⵔ ‎) 2D54 TIFINAGH LETTER YAR # →О→
960959
← (‎ ꓳ ‎) A4F3 LISU LETTER O # →O→
961960
← (‎ 𐊒 ‎) 10292 LYCIAN LETTER U # →O→
962961
← (‎ 𐊫 ‎) 102AB CARIAN LETTER O # →O→
963962
← (‎ 𐐄 ‎) 10404 DESERET CAPITAL LETTER LONG O # →O→
964963
← (‎ 𐔖 ‎) 10516 ELBASAN LETTER O # →O→
965-
← (‎ 𑓐 ‎) 114D0 TIRHUTA DIGIT ZERO # →০→
966964
← (‎ 𑢵 ‎) 118B5 WARANG CITI CAPITAL LETTER AT # →O→
967965
← (‎ 𑣠 ‎) 118E0 WARANG CITI DIGIT ZERO
968966
← (‎ 𐓂 ‎) 104C2 OSAGE CAPITAL LETTER O # →O→
@@ -1056,7 +1054,7 @@
10561054
← (‎ 𑷠点 ‎) 11DE0 70B9 TOLONG SIKI DIGIT ZERO, CJK UNIFIED IDEOGRAPH-70B9
10571055
← (‎ ㍘ ‎) 3358 IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR ZERO
10581056

1059-
# l 𑷚 𑷡 𖺪 I 1 | Ɩ ǀ ו ן ا ١ ۱ Ι І Ӏ ߊ ᛁ Ⲓ ⵏ ꓲ 𐊊 𐌉 𖼨 ׀ ∣ 𐌠 𞣇 ⏽ 🯱 𜳱 𜳞 Ⅰ ⅼ I l ℐ ℑ ℓ 𞸀 𞺀 ﺍ ﺎ 𝐈 𝐥 𝐼 𝑙 𝑰 𝒍 𝓁 𝓘 𝓵 𝔩 𝕀 𝕝 𝕴 𝖑 𝖨 𝗅 𝗜 𝗹 𝘐 𝘭 𝙄 𝙡 𝙸 𝚕 𝚰 𝛪 𝜤 𝝞 𝞘 𝟏 𝟙 𝟣 𝟭 𝟷 │
1057+
# l 𑷚 𑷡 𖺪 I 1 | Ɩ ǀ ӏ ו ן ا ١ ۱ Ι І Ӏ ߊ ᛁ Ⲓ ⵏ ꓲ 𐊊 𐌉 𖼨 ׀ ∣ 𐌠 𞣇 ⏽ 🯱 𜳱 𜳞 Ⅰ ⅼ I l ℐ ℑ ℓ 𞸀 𞺀 ﺍ ﺎ 𝐈 𝐥 𝐼 𝑙 𝑰 𝒍 𝓁 𝓘 𝓵 𝔩 𝕀 𝕝 𝕴 𝖑 𝖨 𝗅 𝗜 𝗹 𝘐 𝘭 𝙄 𝙡 𝙸 𝚕 𝚰 𝛪 𝜤 𝝞 𝞘 𝟏 𝟙 𝟣 𝟭 𝟷 │
10601058
(‎ 1 ‎) 0031 DIGIT ONE
10611059
← (‎ l ‎) 006C LATIN SMALL LETTER L
10621060
← (‎ 𑷚 ‎) 11DDA TOLONG SIKI SIGN HECAKA # →|→→l→
@@ -1066,6 +1064,7 @@
10661064
← (‎ | ‎) 007C VERTICAL LINE # →l→
10671065
← (‎ Ɩ ‎) 0196 LATIN CAPITAL LETTER IOTA # →I→
10681066
← (‎ ǀ ‎) 01C0 LATIN LETTER DENTAL CLICK # →I→
1067+
← (‎ ӏ ‎) 04CF CYRILLIC SMALL LETTER PALOCHKA # →I→
10691068
← (‎ ו ‎) 05D5 HEBREW LETTER VAV # →l→
10701069
← (‎ ן ‎) 05DF HEBREW LETTER FINAL NUN # →l→
10711070
← (‎ ا ‎) 0627 ARABIC LETTER ALEF
@@ -3390,8 +3389,9 @@
33903389
← (‎ e̸ ‎) 0065 0338 LATIN SMALL LETTER E, COMBINING LONG SOLIDUS OVERLAY
33913390
← (‎ ɇ ‎) 0247 LATIN SMALL LETTER E WITH STROKE
33923391

3393-
# f ẝ ք ꞙ ꬵ ſ 𝐟 𝑓 𝒇 𝒻 𝓯 𝔣 𝕗 𝖋 𝖿 𝗳 𝘧 𝙛 𝚏
3392+
# f ƒ ẝ ք ꞙ ꬵ ſ 𝐟 𝑓 𝒇 𝒻 𝓯 𝔣 𝕗 𝖋 𝖿 𝗳 𝘧 𝙛 𝚏
33943393
(‎ f ‎) 0066 LATIN SMALL LETTER F
3394+
← (‎ ƒ ‎) 0192 LATIN SMALL LETTER F WITH HOOK
33953395
← (‎ ẝ ‎) 1E9D LATIN SMALL LETTER LONG S WITH HIGH STROKE
33963396
← (‎ ք ‎) 0584 ARMENIAN SMALL LETTER KEH
33973397
← (‎ ꞙ ‎) A799 LATIN SMALL LETTER F WITH STROKE
@@ -3436,11 +3436,6 @@
34363436
← (‎ fŋ ‎) 0066 014B LATIN SMALL LETTER F, LATIN SMALL LETTER ENG
34373437
← (‎ ʩ ‎) 02A9 LATIN SMALL LETTER FENG DIGRAPH # →fŋ→
34383438

3439-
# f̦ f̡ ƒ
3440-
(‎ f̡ ‎) 0066 0321 LATIN SMALL LETTER F, COMBINING PALATALIZED HOOK BELOW
3441-
← (‎ f̦ ‎) 0066 0326 LATIN SMALL LETTER F, COMBINING COMMA BELOW
3442-
← (‎ ƒ ‎) 0192 LATIN SMALL LETTER F WITH HOOK
3443-
34443439
# f̴ ᵮ
34453440
(‎ f̴ ‎) 0066 0334 LATIN SMALL LETTER F, COMBINING TILDE OVERLAY
34463441
← (‎ ᵮ ‎) 1D6E LATIN SMALL LETTER F WITH MIDDLE TILDE
@@ -3507,14 +3502,13 @@
35073502
← (‎ ћ ‎) 045B CYRILLIC SMALL LETTER TSHE # →ħ→
35083503
← (‎ ℏ ‎) 210F PLANCK CONSTANT OVER TWO PI # →ħ→
35093504

3510-
# i ı ɩ ɪ ι і ӏ ւ Ꭵ ⲓ ꙇ ⍳ 𑣃 ꭵ ⅰ i ι ℹ ⅈ 𝐢 𝑖 𝒊 𝒾 𝓲 𝔦 𝕚 𝖎 𝗂 𝗶 𝘪 𝙞 𝚒 𝚤 𝛊 𝜄 𝜾 𝝸 𝞲 ˛ ͺ
3505+
# i ı ɩ ɪ ι і ւ Ꭵ ⲓ ꙇ ⍳ 𑣃 ꭵ ⅰ i ι ℹ ⅈ 𝐢 𝑖 𝒊 𝒾 𝓲 𝔦 𝕚 𝖎 𝗂 𝗶 𝘪 𝙞 𝚒 𝚤 𝛊 𝜄 𝜾 𝝸 𝞲 ˛ ͺ
35113506
(‎ i ‎) 0069 LATIN SMALL LETTER I
35123507
← (‎ ı ‎) 0131 LATIN SMALL LETTER DOTLESS I
35133508
← (‎ ɩ ‎) 0269 LATIN SMALL LETTER IOTA
35143509
← (‎ ɪ ‎) 026A LATIN LETTER SMALL CAPITAL I # →ı→
35153510
← (‎ ι ‎) 03B9 GREEK SMALL LETTER IOTA
35163511
← (‎ і ‎) 0456 CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
3517-
← (‎ ӏ ‎) 04CF CYRILLIC SMALL LETTER PALOCHKA # →ı→
35183512
← (‎ ւ ‎) 0582 ARMENIAN SMALL LETTER YIWN # →ı→
35193513
← (‎ Ꭵ ‎) 13A5 CHEROKEE LETTER V
35203514
← (‎ ⲓ ‎) 2C93 COPTIC SMALL LETTER IAUDA # →ı→
@@ -3739,7 +3733,7 @@
37393733
(‎ n̴ ‎) 006E 0334 LATIN SMALL LETTER N, COMBINING TILDE OVERLAY
37403734
← (‎ ᵰ ‎) 1D70 LATIN SMALL LETTER N WITH MIDDLE TILDE
37413735

3742-
# o ᴏ ᴑ ο σ о օ ס ه ٥ ھ ہ ە ۵ ० ૦ ం ಂ ം ഠ ං ๐ ໐ ဝ ၀ ០ ϭ ੦ ௦ ౦ ൦ ჿ ⲟ 𐐬 ꬽ 𑣈 𑣗 𐓪 o ℴ 𞸤 𞹤 𞺄 ﮦ ﮧ ﮨ ﮩ ﮪ ﮫ ﮬ ﮭ ﻩ ﻪ ﻫ ﻬ 𝐨 𝑜 𝒐 𝓸 𝔬 𝕠 𝖔 𝗈 𝗼 𝘰 𝙤 𝚘 𝛐 𝛔 𝜊 𝜎 𝝄 𝝈 𝝾 𝞂 𝞸 𝞼
3736+
# o ᴏ ᴑ ο σ о օ ס ه ٥ ھ ہ ە ۵ ० ૦ ం ಂ ം ഠ ං ๐ ໐ ဝ ၀ ០ ϭ ੦ ௦ ౦ ൦ ჿ ⲟ 𐐬 ꬽ 𑓐 𑣈 𑣗 𐓪 o ℴ 𞸤 𞹤 𞺄 ﮦ ﮧ ﮨ ﮩ ﮪ ﮫ ﮬ ﮭ ﻩ ﻪ ﻫ ﻬ 𝐨 𝑜 𝒐 𝓸 𝔬 𝕠 𝖔 𝗈 𝗼 𝘰 𝙤 𝚘 𝛐 𝛔 𝜊 𝜎 𝝄 𝝈 𝝾 𝞂 𝞸 𝞼
37433737
(‎ o ‎) 006F LATIN SMALL LETTER O
37443738
← (‎ ᴏ ‎) 1D0F LATIN LETTER SMALL CAPITAL O
37453739
← (‎ ᴑ ‎) 1D11 LATIN SMALL LETTER SIDEWAYS O
@@ -3755,10 +3749,10 @@
37553749
← (‎ ە ‎) 06D5 ARABIC LETTER AE # →‎ه‎→
37563750
← (‎ ۵ ‎) 06F5 EXTENDED ARABIC-INDIC DIGIT FIVE # →‎٥‎→
37573751
← (‎ ० ‎) 0966 DEVANAGARI DIGIT ZERO
3752+
← (‎ ০ ‎) 09E6 BENGALI DIGIT ZERO
37583753
← (‎ ૦ ‎) 0AE6 GUJARATI DIGIT ZERO
37593754
← (‎ ం ‎) 0C02 TELUGU SIGN ANUSVARA
37603755
← (‎ ಂ ‎) 0C82 KANNADA SIGN ANUSVARA
3761-
← (‎ ೦ ‎) 0CE6 KANNADA DIGIT ZERO # →౦→
37623756
← (‎ ം ‎) 0D02 MALAYALAM SIGN ANUSVARA
37633757
← (‎ ഠ ‎) 0D20 MALAYALAM LETTER TTHA
37643758
← (‎ ං ‎) 0D82 SINHALA SIGN ANUSVARAYA
@@ -3769,13 +3763,15 @@
37693763
← (‎ ០ ‎) 17E0 KHMER DIGIT ZERO
37703764
← (‎ ϭ ‎) 03ED COPTIC SMALL LETTER SHIMA # →σ→
37713765
← (‎ ੦ ‎) 0A66 GURMUKHI DIGIT ZERO
3766+
← (‎ ୦ ‎) 0B66 ORIYA DIGIT ZERO
37723767
← (‎ ௦ ‎) 0BE6 TAMIL DIGIT ZERO
37733768
← (‎ ౦ ‎) 0C66 TELUGU DIGIT ZERO
37743769
← (‎ ൦ ‎) 0D66 MALAYALAM DIGIT ZERO
37753770
← (‎ ჿ ‎) 10FF GEORGIAN LETTER LABIAL SIGN
37763771
← (‎ ⲟ ‎) 2C9F COPTIC SMALL LETTER O
37773772
← (‎ 𐐬 ‎) 1042C DESERET SMALL LETTER LONG O
37783773
← (‎ ꬽ ‎) AB3D LATIN SMALL LETTER BLACKLETTER O
3774+
← (‎ 𑓐 ‎) 114D0 TIRHUTA DIGIT ZERO # →০→
37793775
← (‎ 𑣈 ‎) 118C8 WARANG CITI SMALL LETTER E
37803776
← (‎ 𑣗 ‎) 118D7 WARANG CITI SMALL LETTER BU
37813777
← (‎ 𐓪 ‎) 104EA OSAGE SMALL LETTER O
@@ -17840,5 +17836,5 @@
1784017836
(‎ 𪘀 ‎) 2A600 CJK UNIFIED IDEOGRAPH-2A600
1784117837
← (‎ 𪘀 ‎) 2FA1D CJK COMPATIBILITY IDEOGRAPH-2FA1D
1784217838

17843-
# total : 7576
17839+
# total : 7575
1784417840

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

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusablesSummaryIdentifier.txt
2-
# Date: 2025-07-21, 18:09:10 GMT
2+
# Date: 2025-07-22, 05:49:37 GMT
33
# © 2025 Unicode®, Inc.
44
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
55
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -38,11 +38,11 @@
3838
(‎ / ‎) 002F SOLIDUS
3939
← (‎ ノ ‎) 30CE KATAKANA LETTER NO # →⼃→
4040

41-
# O 0 ০ ଠ ዐ 〇 Ο О Օ
41+
# O 0 ଠ ೦ ዐ 〇 Ο О Օ
4242
(‎ 0 ‎) 0030 DIGIT ZERO
4343
← (‎ O ‎) 004F LATIN CAPITAL LETTER O
44-
← (‎ ‎) 09E6 BENGALI DIGIT ZERO
45-
← (‎ ‎) 0B20 ORIYA LETTER TTHA # →
44+
← (‎ ‎) 0B20 ORIYA LETTER TTHA # →O→
45+
← (‎ ‎) 0CE6 KANNADA DIGIT ZERO # →O
4646
← (‎ ዐ ‎) 12D0 ETHIOPIC SYLLABLE PHARYNGEAL A # →Օ→→О→
4747
← (‎ 〇 ‎) 3007 IDEOGRAPHIC NUMBER ZERO # →O→
4848
← (‎ Ο ‎) 039F GREEK CAPITAL LETTER OMICRON
@@ -54,11 +54,12 @@
5454
← (‎ Θ ‎) 0398 GREEK CAPITAL LETTER THETA # →⊖→
5555
← (‎ Ө ‎) 04E8 CYRILLIC CAPITAL LETTER BARRED O # →Ѳ→→Θ→→⊖→
5656

57-
# l I 1 | ו ן ا ١ ۱ Ι І Ӏ
57+
# l I 1 | ӏ ו ן ا ١ ۱ Ι І Ӏ
5858
(‎ 1 ‎) 0031 DIGIT ONE
5959
← (‎ l ‎) 006C LATIN SMALL LETTER L
6060
← (‎ I ‎) 0049 LATIN CAPITAL LETTER I
6161
← (‎ | ‎) 007C VERTICAL LINE # →l→
62+
← (‎ ӏ ‎) 04CF CYRILLIC SMALL LETTER PALOCHKA # →I→
6263
← (‎ ו ‎) 05D5 HEBREW LETTER VAV # →l→
6364
← (‎ ן ‎) 05DF HEBREW LETTER FINAL NUN # →l→
6465
← (‎ ا ‎) 0627 ARABIC LETTER ALEF
@@ -295,12 +296,11 @@
295296
(‎ ħ ‎) 0127 LATIN SMALL LETTER H WITH STROKE
296297
← (‎ ћ ‎) 045B CYRILLIC SMALL LETTER TSHE
297298

298-
# i ı ι і ӏ ւ
299+
# i ı ι і ւ
299300
(‎ i ‎) 0069 LATIN SMALL LETTER I
300301
← (‎ ı ‎) 0131 LATIN SMALL LETTER DOTLESS I
301302
← (‎ ι ‎) 03B9 GREEK SMALL LETTER IOTA
302303
← (‎ і ‎) 0456 CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
303-
← (‎ ӏ ‎) 04CF CYRILLIC SMALL LETTER PALOCHKA # →ı→
304304
← (‎ ւ ‎) 0582 ARMENIAN SMALL LETTER YIWN # →ı→
305305

306306
# j ј
@@ -321,7 +321,7 @@
321321
← (‎ η ‎) 03B7 GREEK SMALL LETTER ETA
322322
← (‎ ղ ‎) 0572 ARMENIAN SMALL LETTER GHAD # →η→
323323

324-
# o ο σ о օ ס ه ٥ ھ ہ ە ۵ ० ૦ ం ಂ ം ഠ ං ๐ ໐ ဝ ၀ ០
324+
# o ο σ о օ ס ه ٥ ھ ہ ە ۵ ० ૦ ం ಂ ം ഠ ං ๐ ໐ ဝ ၀ ០
325325
(‎ o ‎) 006F LATIN SMALL LETTER O
326326
← (‎ ο ‎) 03BF GREEK SMALL LETTER OMICRON
327327
← (‎ σ ‎) 03C3 GREEK SMALL LETTER SIGMA
@@ -335,10 +335,10 @@
335335
← (‎ ە ‎) 06D5 ARABIC LETTER AE # →‎ه‎→
336336
← (‎ ۵ ‎) 06F5 EXTENDED ARABIC-INDIC DIGIT FIVE # →‎٥‎→
337337
← (‎ ० ‎) 0966 DEVANAGARI DIGIT ZERO
338+
← (‎ ০ ‎) 09E6 BENGALI DIGIT ZERO
338339
← (‎ ૦ ‎) 0AE6 GUJARATI DIGIT ZERO
339340
← (‎ ం ‎) 0C02 TELUGU SIGN ANUSVARA
340341
← (‎ ಂ ‎) 0C82 KANNADA SIGN ANUSVARA
341-
← (‎ ೦ ‎) 0CE6 KANNADA DIGIT ZERO # →౦→
342342
← (‎ ം ‎) 0D02 MALAYALAM SIGN ANUSVARA
343343
← (‎ ഠ ‎) 0D20 MALAYALAM LETTER TTHA
344344
← (‎ ං ‎) 0D82 SINHALA SIGN ANUSVARAYA

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

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -39,7 +39,6 @@
3939
0259 ; 04D9 # schwa ; schwa
4040
0068 ; 04BB # h ; shha
4141
0069 ; 0456 # i ; i
42-
026A ; 04CF # smallcap i ; small palochka (arguable)
4342
03B9 ; 0269 # iota ; iota
4443
03F3 ; 006A ; 0458 # yot ; j ; je
4544
0138 ; 043A # kra ; ka

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

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -336,7 +336,6 @@
336336

337337
0131 ; 026A # ( ı ~ ɪ ) LATIN SMALL LETTER DOTLESS I ~ LATIN LETTER SMALL CAPITAL I
338338
0131 ; 03B9 # ( ı ~ ι ) LATIN SMALL LETTER DOTLESS I ~ GREEK SMALL LETTER IOTA
339-
0131 ; 04CF # ( ı ~ ӏ ) LATIN SMALL LETTER DOTLESS I ~ CYRILLIC SMALL LETTER PALOCHKA
340339

341340
0138 ; 1D0B # ( ĸ ~ ᴋ ) LATIN SMALL LETTER KRA ~ LATIN LETTER SMALL CAPITAL K
342341
0138 ; 03BA # ( ĸ ~ κ ) LATIN SMALL LETTER KRA ~ GREEK SMALL LETTER KAPPA

0 commit comments

Comments
 (0)