Skip to content

Commit 3643357

Browse files
committed
Confusables data for Devanagari UE and UUE - generated data
1 parent 069bed4 commit 3643357

File tree

4 files changed

+40
-37
lines changed

4 files changed

+40
-37
lines changed

unicodetools/data/security/dev/confusables.txt

Lines changed: 11 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusables.txt
2-
# Date: 2025-07-22, 05:49:37 GMT
2+
# Date: 2025-08-11, 18:24:57 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
@@ -180,6 +180,13 @@ A6F1 ; 0304 ; MA # ( ꛱ → ̄ ) BAMUM COMBINING MARK TUKWENTIS → COMBINING M
180180
1CD9 ; 032D ; MA # ( ᳙ → ̭ ) VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER → COMBINING CIRCUMFLEX ACCENT BELOW #
181181

182182
1CD8 ; 032E ; MA # ( ᳘ → ̮ ) VEDIC TONE CANDRA BELOW → COMBINING BREVE BELOW #
183+
0956 ; 032E ; MA # ( ॖ → ̮ ) DEVANAGARI VOWEL SIGN UE → COMBINING BREVE BELOW #
184+
0A41 ; 032E ; MA # ( ੁ → ̮ ) GURMUKHI VOWEL SIGN U → COMBINING BREVE BELOW # →ॖ→
185+
11B62 ; 032E ; MA # ( 𑭢 → ̮ ) SHARADA VOWEL SIGN UE → COMBINING BREVE BELOW # →ॖ→
186+
187+
0957 ; 032E 032E ; MA # ( ॗ → ̮̮ ) DEVANAGARI VOWEL SIGN UUE → COMBINING BREVE BELOW, COMBINING BREVE BELOW #
188+
0A42 ; 032E 032E ; MA # ( ੂ → ̮̮ ) GURMUKHI VOWEL SIGN UU → COMBINING BREVE BELOW, COMBINING BREVE BELOW # →ॗ→
189+
11B63 ; 032E 032E ; MA # ( 𑭣 → ̮̮ ) SHARADA VOWEL SIGN UUE → COMBINING BREVE BELOW, COMBINING BREVE BELOW # →ॗ→
183190

184191
0952 ; 0331 ; MA # ( ॒ → ̱ ) DEVANAGARI STRESS SIGN ANUDATTA → COMBINING MACRON BELOW #
185192
0320 ; 0331 ; MA # ( ̠ → ̱ ) COMBINING MINUS SIGN BELOW → COMBINING MACRON BELOW #
@@ -5869,9 +5876,9 @@ FE19 ; 2D57 ; MA #* ( ︙ → ⵗ ) PRESENTATION FORM FOR VERTICAL HORIZONTAL EL
58695876

58705877
114BD ; 09D7 ; MA # ( 𑒽 → ৗ ) TIRHUTA VOWEL SIGN SHORT O → BENGALI AU LENGTH MARK #
58715878

5872-
0A09 ; 0A73 11B62 ; MA # ( ਉ → ੳ𑭢 ) GURMUKHI LETTER U → GURMUKHI URA, SHARADA VOWEL SIGN UE # →ੳੁ→
5879+
0A09 ; 0A73 032E ; MA # ( ਉ → ੳ̮ ) GURMUKHI LETTER U → GURMUKHI URA, COMBINING BREVE BELOW # →ੳੁ→
58735880

5874-
0A0A ; 0A73 11B63 ; MA # ( ਊ → ੳ𑭣 ) GURMUKHI LETTER UU → GURMUKHI URA, SHARADA VOWEL SIGN UUE # →ੳੂ→
5881+
0A0A ; 0A73 032E 032E ; MA # ( ਊ → ੳ̮̮ ) GURMUKHI LETTER UU → GURMUKHI URA, COMBINING BREVE BELOW, COMBINING BREVE BELOW # →ੳੂ→
58755882

58765883
0A10 ; 0A05 0948 ; MA # ( ਐ → ਅै ) GURMUKHI LETTER AI → GURMUKHI LETTER A, DEVANAGARI VOWEL SIGN AI # →ਅੈ→
58775884

@@ -9946,12 +9953,6 @@ A7CF ; A7CE ; MA # ( ꟏ → ꟎ ) LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIV
99469953

99479954
0348 ; 10EFA ; MA # ( ͈ → 𐻺 ) COMBINING DOUBLE VERTICAL LINE BELOW → ARABIC DOUBLE VERTICAL BAR BELOW #
99489955

9949-
0956 ; 11B62 ; MA # ( ॖ → 𑭢 ) DEVANAGARI VOWEL SIGN UE → SHARADA VOWEL SIGN UE #
9950-
0A41 ; 11B62 ; MA # ( ੁ → 𑭢 ) GURMUKHI VOWEL SIGN U → SHARADA VOWEL SIGN UE # →ॖ→
9951-
9952-
0957 ; 11B63 ; MA # ( ॗ → 𑭣 ) DEVANAGARI VOWEL SIGN UUE → SHARADA VOWEL SIGN UUE #
9953-
0A42 ; 11B63 ; MA # ( ੂ → 𑭣 ) GURMUKHI VOWEL SIGN UU → SHARADA VOWEL SIGN UUE # →ॗ→
9954-
99559956
0947 ; 11B64 ; MA # ( े → 𑭤 ) DEVANAGARI VOWEL SIGN E → SHARADA VOWEL SIGN SHORT E #
99569957
0A47 ; 11B64 ; MA # ( ੇ → 𑭤 ) GURMUKHI VOWEL SIGN EE → SHARADA VOWEL SIGN SHORT E # →े→
99579958

@@ -9990,5 +9991,5 @@ A7CF ; A7CE ; MA # ( ꟏ → ꟎ ) LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIV
99909991

99919992
6138 ; 2B73F ; MA # ( 愸 → 𫜿 ) CJK UNIFIED IDEOGRAPH-6138 → CJK UNIFIED IDEOGRAPH-2B73F #
99929993

9993-
# total: 6565
9994+
# total: 6567
99949995

unicodetools/data/security/dev/confusablesSummary.txt

Lines changed: 16 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# confusablesSummary.txt
2-
# Date: 2025-07-22, 05:49:37 GMT
2+
# Date: 2025-08-11, 18:24:57 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
@@ -5754,10 +5754,19 @@
57545754
(‎ ̭ ‎) 032D COMBINING CIRCUMFLEX ACCENT BELOW
57555755
← (‎ ᳙ ‎) 1CD9 VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER
57565756

5757-
# ̮ ᳘
5757+
# ̮ 𑭢 ॖ ੁ
57585758
(‎ ̮ ‎) 032E COMBINING BREVE BELOW
5759+
← (‎ 𑭢 ‎) 11B62 SHARADA VOWEL SIGN UE # →ॖ→
5760+
← (‎ ॖ ‎) 0956 DEVANAGARI VOWEL SIGN UE
5761+
← (‎ ੁ ‎) 0A41 GURMUKHI VOWEL SIGN U # →ॖ→
57595762
← (‎ ᳘ ‎) 1CD8 VEDIC TONE CANDRA BELOW
57605763

5764+
# ̮̮ 𑭣 ॗ ੂ
5765+
(‎ ̮̮ ‎) 032E 032E COMBINING BREVE BELOW, COMBINING BREVE BELOW
5766+
← (‎ 𑭣 ‎) 11B63 SHARADA VOWEL SIGN UUE # →ॗ→
5767+
← (‎ ॗ ‎) 0957 DEVANAGARI VOWEL SIGN UUE
5768+
← (‎ ੂ ‎) 0A42 GURMUKHI VOWEL SIGN UU # →ॗ→
5769+
57615770
# ̳ ͇
57625771
(‎ ̳ ‎) 0333 COMBINING DOUBLE LOW LINE
57635772
← (‎ ͇ ‎) 0347 COMBINING EQUALS SIGN BELOW
@@ -8690,16 +8699,6 @@
86908699
← (‎ ੍ ‎) 0A4D GURMUKHI SIGN VIRAMA
86918700
← (‎ ્ ‎) 0ACD GUJARATI SIGN VIRAMA
86928701

8693-
# 𑭢 ॖ ੁ
8694-
(‎ ॖ ‎) 0956 DEVANAGARI VOWEL SIGN UE
8695-
← (‎ 𑭢 ‎) 11B62 SHARADA VOWEL SIGN UE
8696-
← (‎ ੁ ‎) 0A41 GURMUKHI VOWEL SIGN U
8697-
8698-
# 𑭣 ॗ ੂ
8699-
(‎ ॗ ‎) 0957 DEVANAGARI VOWEL SIGN UUE
8700-
← (‎ 𑭣 ‎) 11B63 SHARADA VOWEL SIGN UUE
8701-
← (‎ ੂ ‎) 0A42 GURMUKHI VOWEL SIGN UU
8702-
87038702
# । ꠰
87048703
(‎ । ‎) 0964 DEVANAGARI DANDA
87058704
← (‎ ꠰ ‎) A830 NORTH INDIC FRACTION ONE QUARTER
@@ -8882,15 +8881,15 @@
88828881
(‎ ਅੌ ‎) 0A05 0A4C GURMUKHI LETTER A, GURMUKHI VOWEL SIGN AU
88838882
← (‎ ਔ ‎) 0A14 GURMUKHI LETTER AU
88848883

8885-
# ੳੁ ੳ𑭢
8884+
# ੳੁ ੳ̮
88868885
(‎ ਉ ‎) 0A09 GURMUKHI LETTER U
88878886
← (‎ ੳੁ ‎) 0A73 0A41 GURMUKHI URA, GURMUKHI VOWEL SIGN U
8888-
← (‎ ੳ𑭢 ‎) 0A73 11B62 GURMUKHI URA, SHARADA VOWEL SIGN UE # →ੳੁ→
8887+
← (‎ ੳ̮ ‎) 0A73 032E GURMUKHI URA, COMBINING BREVE BELOW # →ੳੁ→
88898888

8890-
# ੳੂ ੳ𑭣
8889+
# ੳ̮̮ ੳੂ
88918890
(‎ ਊ ‎) 0A0A GURMUKHI LETTER UU
8891+
← (‎ ੳ̮̮ ‎) 0A73 032E 032E GURMUKHI URA, COMBINING BREVE BELOW, COMBINING BREVE BELOW # →ੳੂ→
88928892
← (‎ ੳੂ ‎) 0A73 0A42 GURMUKHI URA, GURMUKHI VOWEL SIGN UU
8893-
← (‎ ੳ𑭣 ‎) 0A73 11B63 GURMUKHI URA, SHARADA VOWEL SIGN UUE # →ੳੂ→
88948893

88958894
# અા આ
88968895
(‎ અા ‎) 0A85 0ABE GUJARATI LETTER A, GUJARATI VOWEL SIGN AA
@@ -17836,5 +17835,5 @@
1783617835
(‎ 𪘀 ‎) 2A600 CJK UNIFIED IDEOGRAPH-2A600
1783717836
← (‎ 𪘀 ‎) 2FA1D CJK COMPATIBILITY IDEOGRAPH-2FA1D
1783817837

17839-
# total : 7575
17838+
# total : 7577
1784017839

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: 2025-07-22, 05:49:37 GMT
2+
# Date: 2025-08-11, 18:24:57 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
@@ -546,6 +546,14 @@
546546
← (‎ ઼ ‎) 0ABC GUJARATI SIGN NUKTA
547547
← (‎ ଼ ‎) 0B3C ORIYA SIGN NUKTA
548548

549+
# ॖ ੁ
550+
(‎ ॖ ‎) 0956 DEVANAGARI VOWEL SIGN UE
551+
← (‎ ੁ ‎) 0A41 GURMUKHI VOWEL SIGN U
552+
553+
# ॗ ੂ
554+
(‎ ॗ ‎) 0957 DEVANAGARI VOWEL SIGN UUE
555+
← (‎ ੂ ‎) 0A42 GURMUKHI VOWEL SIGN UU
556+
549557
# Γ Г
550558
(‎ Γ ‎) 0393 GREEK CAPITAL LETTER GAMMA
551559
← (‎ Г ‎) 0413 CYRILLIC CAPITAL LETTER GHE
@@ -919,14 +927,6 @@
919927
← (‎ ੍ ‎) 0A4D GURMUKHI SIGN VIRAMA
920928
← (‎ ્ ‎) 0ACD GUJARATI SIGN VIRAMA
921929

922-
# ॖ ੁ
923-
(‎ ॖ ‎) 0956 DEVANAGARI VOWEL SIGN UE
924-
← (‎ ੁ ‎) 0A41 GURMUKHI VOWEL SIGN U
925-
926-
# ॗ ੂ
927-
(‎ ॗ ‎) 0957 DEVANAGARI VOWEL SIGN UUE
928-
← (‎ ੂ ‎) 0A42 GURMUKHI VOWEL SIGN UU
929-
930930
# २ ર ૨
931931
(‎ २ ‎) 0968 DEVANAGARI DIGIT TWO
932932
← (‎ ર ‎) 0AB0 GUJARATI LETTER RA # →૨→

unicodetools/data/security/dev/data/source/formatted-source.txt

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# formatted-source.txt
2-
# Date: 2025-07-22, 05:49:36 GMT
2+
# Date: 2025-08-11, 18:24:56 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
@@ -1265,8 +1265,11 @@
12651265

12661266
032D ; 1CD9 # ( ̭ ~ ᳙ ) COMBINING CIRCUMFLEX ACCENT BELOW ~ VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER
12671267

1268+
032E ; 0956 # ( ̮ ~ ॖ ) COMBINING BREVE BELOW ~ DEVANAGARI VOWEL SIGN UE
12681269
032E ; 1CD8 # ( ̮ ~ ᳘ ) COMBINING BREVE BELOW ~ VEDIC TONE CANDRA BELOW
12691270

1271+
032E 032E ; 0957 # ( ̮̮ ~ ॗ ) COMBINING BREVE BELOW, COMBINING BREVE BELOW ~ DEVANAGARI VOWEL SIGN UUE
1272+
12701273
0331 ; 0320 # ( ̱ ~ ̠ ) COMBINING MACRON BELOW ~ COMBINING MINUS SIGN BELOW
12711274
0331 ; 0952 # ( ̱ ~ ॒ ) COMBINING MACRON BELOW ~ DEVANAGARI STRESS SIGN ANUDATTA
12721275

0 commit comments

Comments
 (0)