Hiragana and katakana digraphs (#885)

* UnicodeData.txt lines from L2/24-150 with code points from L2/24-165 §15.

* lb=ID like ゟ and ヿ

* Scripts according to the names

* Regenerate UCD

* Failing test, this will get tricky

* time to mess with the invariants language

* Allow strings in Propertywise tests

* spots

* stringAt

* A test that fails reasonably

* ea=W

* Regenerate UCD

* Regenerate UCD

* Ignore IDNA2008_Category

Author: eggrobin

unicodetools/data/ucd/dev/DerivedAge.txt

@@ -1,5 +1,5 @@
 # DerivedAge-18.0.0.txt
-# Date: 2025-11-28, 13:23:52 GMT
+# Date: 2025-11-28, 15:46:32 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
@@ -2144,6 +2144,7 @@ FDC8..FDCE    ; 17.0 #   [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
 18D1F..18D20  ; 18.0 #   [2] TANGUT IDEOGRAPH-18D1F..TANGUT IDEOGRAPH-18D20
 18E00..19191  ; 18.0 # [914] JURCHEN CHARACTER-18E00..JURCHEN CHARACTER-19191
 191A0..191D2  ; 18.0 #  [51] JURCHEN RADICAL-01..JURCHEN RADICAL-51
+1B123..1B125  ; 18.0 #   [3] HIRAGANA DIGRAPH KOTO..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; 18.0 #   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B168         ; 18.0 #       KATAKANA LETTER SMALL ARCHAIC YE
 1DF1F..1DF24  ; 18.0 #   [6] LATIN SMALL LETTER D-ETH DIGRAPH..LATIN SMALL LETTER T-THETA DIGRAPH
@@ -2154,6 +2155,6 @@ FDC8..FDCE    ; 17.0 #   [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIG
 2B81E         ; 18.0 #       CJK UNIFIED IDEOGRAPH-2B81E
 3D000..3FC3F  ; 18.0 # [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 
-# Total code points: 12828
+# Total code points: 12831
 
 # EOF

unicodetools/data/ucd/dev/DerivedCoreProperties.txt

@@ -1,5 +1,5 @@
 # DerivedCoreProperties-18.0.0.txt
-# Date: 2025-11-28, 13:24:15 GMT
+# Date: 2025-11-28, 15:46:55 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
@@ -1352,7 +1352,7 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 1AFF0..1AFF3  ; Alphabetic # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; Alphabetic # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; Alphabetic # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
-1B000..1B122  ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B000..1B125  ; Alphabetic # Lo [294] KATAKANA LETTER ARCHAIC E..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; Alphabetic # Lo   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132         ; Alphabetic # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; Alphabetic # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -1479,7 +1479,7 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 31350..33479  ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 3D000..3FC3F  ; Alphabetic # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 
-# Total code points: 160212
+# Total code points: 160215
 
 # ================================================
 
@@ -6992,7 +6992,7 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 1AFF0..1AFF3  ; ID_Start # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; ID_Start # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; ID_Start # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
-1B000..1B122  ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B000..1B125  ; ID_Start # Lo [294] KATAKANA LETTER ARCHAIC E..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; ID_Start # Lo   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132         ; ID_Start # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; ID_Start # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -7104,7 +7104,7 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 31350..33479  ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 3D000..3FC3F  ; ID_Start # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 
-# Total code points: 158704
+# Total code points: 158707
 
 # ================================================
 
@@ -8397,7 +8397,7 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 1AFF0..1AFF3  ; ID_Continue # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; ID_Continue # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; ID_Continue # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
-1B000..1B122  ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B000..1B125  ; ID_Continue # Lo [294] KATAKANA LETTER ARCHAIC E..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; ID_Continue # Lo   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132         ; ID_Continue # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; ID_Continue # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -8551,7 +8551,7 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 3D000..3FC3F  ; ID_Continue # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 E0100..E01EF  ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 162050
+# Total code points: 162053
 
 # ================================================
 
@@ -9241,7 +9241,7 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 1AFF0..1AFF3  ; XID_Start # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; XID_Start # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; XID_Start # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
-1B000..1B122  ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B000..1B125  ; XID_Start # Lo [294] KATAKANA LETTER ARCHAIC E..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; XID_Start # Lo   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132         ; XID_Start # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; XID_Start # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -9353,7 +9353,7 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 31350..33479  ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 3D000..3FC3F  ; XID_Start # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 
-# Total code points: 158681
+# Total code points: 158684
 
 # ================================================
 
@@ -10647,7 +10647,7 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 1AFF0..1AFF3  ; XID_Continue # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; XID_Continue # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; XID_Continue # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
-1B000..1B122  ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B000..1B125  ; XID_Continue # Lo [294] KATAKANA LETTER ARCHAIC E..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; XID_Continue # Lo   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132         ; XID_Continue # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; XID_Continue # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -10801,7 +10801,7 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 3D000..3FC3F  ; XID_Continue # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 E0100..E01EF  ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 162031
+# Total code points: 162034
 
 # ================================================
 
@@ -12891,7 +12891,7 @@ FFFC..FFFD    ; Grapheme_Base # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
 1AFF0..1AFF3  ; Grapheme_Base # Lm   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; Grapheme_Base # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; Grapheme_Base # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
-1B000..1B122  ; Grapheme_Base # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B000..1B125  ; Grapheme_Base # Lo [294] KATAKANA LETTER ARCHAIC E..KATAKANA DIGRAPH TOTE
 1B127..1B128  ; Grapheme_Base # Lo   [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132         ; Grapheme_Base # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; Grapheme_Base # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
@@ -13104,7 +13104,7 @@ FFFC..FFFD    ; Grapheme_Base # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
 31350..33479  ; Grapheme_Base # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479
 3D000..3FC3F  ; Grapheme_Base # Lo [11328] SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 
-# Total code points: 170310
+# Total code points: 170313
 
 # ================================================
 

unicodetools/data/ucd/dev/DerivedNormalizationProps.txt

@@ -1,5 +1,5 @@
 # DerivedNormalizationProps-18.0.0.txt
-# Date: 2025-11-27, 17:33:31 GMT
+# Date: 2025-11-28, 15:46:59 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
@@ -1665,6 +1665,7 @@ FFED..FFEE    ; NFKD_QC; N # So   [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
 11938         ; NFKD_QC; N # Mc       DIVES AKURU VOWEL SIGN O
 16121..16128  ; NFKD_QC; N # Mn   [8] GURUNG KHEMA VOWEL SIGN U..GURUNG KHEMA VOWEL SIGN AU
 16D68..16D6A  ; NFKD_QC; N # Lo   [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU
+1B123..1B125  ; NFKD_QC; N # Lo   [3] HIRAGANA DIGRAPH KOTO..KATAKANA DIGRAPH TOTE
 1CCD6..1CCEF  ; NFKD_QC; N # So  [26] OUTLINED LATIN CAPITAL LETTER A..OUTLINED LATIN CAPITAL LETTER Z
 1CCF0..1CCF9  ; NFKD_QC; N # Nd  [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE
 1D15E..1D164  ; NFKD_QC; N # So   [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
@@ -1757,7 +1758,7 @@ FFED..FFEE    ; NFKD_QC; N # So   [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
 1FBF0..1FBF9  ; NFKD_QC; N # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 2F800..2FA1D  ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 
-# Total code points: 17145
+# Total code points: 17148
 
 # ================================================
 
@@ -2079,6 +2080,7 @@ FFED..FFEE    ; NFKC_QC; N # So   [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
 10781..10785  ; NFKC_QC; N # Lm   [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK
 10787..107B0  ; NFKC_QC; N # Lm  [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK
 107B2..107BF  ; NFKC_QC; N # Lm  [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR
+1B123..1B125  ; NFKC_QC; N # Lo   [3] HIRAGANA DIGRAPH KOTO..KATAKANA DIGRAPH TOTE
 1CCD6..1CCEF  ; NFKC_QC; N # So  [26] OUTLINED LATIN CAPITAL LETTER A..OUTLINED LATIN CAPITAL LETTER Z
 1CCF0..1CCF9  ; NFKC_QC; N # Nd  [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE
 1D15E..1D164  ; NFKC_QC; N # So   [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
@@ -2171,7 +2173,7 @@ FFED..FFEE    ; NFKC_QC; N # So   [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
 1FBF0..1FBF9  ; NFKC_QC; N # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 2F800..2FA1D  ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 
-# Total code points: 5024
+# Total code points: 5027
 
 # ================================================
 
@@ -2833,6 +2835,7 @@ FFE3          ; Expands_On_NFKD # Sk       FULLWIDTH MACRON
 11938         ; Expands_On_NFKD # Mc       DIVES AKURU VOWEL SIGN O
 16121..16128  ; Expands_On_NFKD # Mn   [8] GURUNG KHEMA VOWEL SIGN U..GURUNG KHEMA VOWEL SIGN AU
 16D68..16D6A  ; Expands_On_NFKD # Lo   [3] KIRAT RAI VOWEL SIGN AI..KIRAT RAI VOWEL SIGN AU
+1B123..1B125  ; Expands_On_NFKD # Lo   [3] HIRAGANA DIGRAPH KOTO..KATAKANA DIGRAPH TOTE
 1D15E..1D164  ; Expands_On_NFKD # So   [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
 1D1BB..1D1C0  ; Expands_On_NFKD # So   [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK
 1F100..1F10A  ; Expands_On_NFKD # No  [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA
@@ -2845,7 +2848,7 @@ FFE3          ; Expands_On_NFKD # Sk       FULLWIDTH MACRON
 1F213         ; Expands_On_NFKD # So       SQUARED KATAKANA DE
 1F240..1F248  ; Expands_On_NFKD # So   [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
 
-# Total code points: 13410
+# Total code points: 13413
 
 # ================================================
 
@@ -2972,6 +2975,7 @@ FE74          ; Expands_On_NFKC # Lo       ARABIC KASRATAN ISOLATED FORM
 FE76..FE7F    ; Expands_On_NFKC # Lo  [10] ARABIC FATHA ISOLATED FORM..ARABIC SUKUN MEDIAL FORM
 FEF5..FEFC    ; Expands_On_NFKC # Lo   [8] ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
 FFE3          ; Expands_On_NFKC # Sk       FULLWIDTH MACRON
+1B123..1B125  ; Expands_On_NFKC # Lo   [3] HIRAGANA DIGRAPH KOTO..KATAKANA DIGRAPH TOTE
 1D15E..1D164  ; Expands_On_NFKC # So   [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
 1D1BB..1D1C0  ; Expands_On_NFKC # So   [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK
 1F100..1F10A  ; Expands_On_NFKC # No  [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA
@@ -2983,7 +2987,7 @@ FFE3          ; Expands_On_NFKC # Sk       FULLWIDTH MACRON
 1F200..1F201  ; Expands_On_NFKC # So   [2] SQUARE HIRAGANA HOKA..SQUARED KATAKANA KOKO
 1F240..1F248  ; Expands_On_NFKC # So   [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
 
-# Total code points: 1237
+# Total code points: 1240
 
 # ================================================
 
@@ -7231,6 +7235,9 @@ FFF0..FFF8    ; NFKC_CF;                # Cn   [9] <reserved-FFF0>..<reserved-FF
 16EB6         ; NFKC_CF; 16ED1          # L&       BERIA ERFE CAPITAL LETTER UI
 16EB7         ; NFKC_CF; 16ED2          # L&       BERIA ERFE CAPITAL LETTER WASSE
 16EB8         ; NFKC_CF; 16ED3          # L&       BERIA ERFE CAPITAL LETTER AY
+1B123         ; NFKC_CF; 3053 3068      # Lo       HIRAGANA DIGRAPH KOTO
+1B124         ; NFKC_CF; 30C8 30AD      # Lo       KATAKANA DIGRAPH TOKI
+1B125         ; NFKC_CF; 30C8 30C6      # Lo       KATAKANA DIGRAPH TOTE
 1BCA0..1BCA3  ; NFKC_CF;                # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
 1CCD6         ; NFKC_CF; 0061           # So       OUTLINED LATIN CAPITAL LETTER A
 1CCD7         ; NFKC_CF; 0062           # So       OUTLINED LATIN CAPITAL LETTER B
@@ -9248,7 +9255,7 @@ E0080..E00FF  ; NFKC_CF;                # Cn [128] <reserved-E0080>..<reserved-E
 E0100..E01EF  ; NFKC_CF;                # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 E01F0..E0FFF  ; NFKC_CF;                # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 10647
+# Total code points: 10650
 
 # ================================================
 
@@ -13458,6 +13465,9 @@ FFF0..FFF8    ; NFKC_SCF;                # Cn   [9] <reserved-FFF0>..<reserved-F
 16EB6         ; NFKC_SCF; 16ED1          # L&       BERIA ERFE CAPITAL LETTER UI
 16EB7         ; NFKC_SCF; 16ED2          # L&       BERIA ERFE CAPITAL LETTER WASSE
 16EB8         ; NFKC_SCF; 16ED3          # L&       BERIA ERFE CAPITAL LETTER AY
+1B123         ; NFKC_SCF; 3053 3068      # Lo       HIRAGANA DIGRAPH KOTO
+1B124         ; NFKC_SCF; 30C8 30AD      # Lo       KATAKANA DIGRAPH TOKI
+1B125         ; NFKC_SCF; 30C8 30C6      # Lo       KATAKANA DIGRAPH TOTE
 1BCA0..1BCA3  ; NFKC_SCF;                # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
 1CCD6         ; NFKC_SCF; 0061           # So       OUTLINED LATIN CAPITAL LETTER A
 1CCD7         ; NFKC_SCF; 0062           # So       OUTLINED LATIN CAPITAL LETTER B
@@ -15475,7 +15485,7 @@ E0080..E00FF  ; NFKC_SCF;                # Cn [128] <reserved-E0080>..<reserved-
 E0100..E01EF  ; NFKC_SCF;                # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 E01F0..E0FFF  ; NFKC_SCF;                # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 10609
+# Total code points: 10612
 
 # ================================================
 
@@ -16398,6 +16408,7 @@ FFF0..FFF8    ; Changes_When_NFKC_Casefolded # Cn   [9] <reserved-FFF0>..<reserv
 118A0..118BF  ; Changes_When_NFKC_Casefolded # L&  [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
 16E40..16E5F  ; Changes_When_NFKC_Casefolded # L&  [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y
 16EA0..16EB8  ; Changes_When_NFKC_Casefolded # L&  [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY
+1B123..1B125  ; Changes_When_NFKC_Casefolded # Lo   [3] HIRAGANA DIGRAPH KOTO..KATAKANA DIGRAPH TOTE
 1BCA0..1BCA3  ; Changes_When_NFKC_Casefolded # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
 1CCD6..1CCEF  ; Changes_When_NFKC_Casefolded # So  [26] OUTLINED LATIN CAPITAL LETTER A..OUTLINED LATIN CAPITAL LETTER Z
 1CCF0..1CCF9  ; Changes_When_NFKC_Casefolded # Nd  [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE
@@ -16505,6 +16516,6 @@ E0080..E00FF  ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser
 E0100..E01EF  ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 E01F0..E0FFF  ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 10647
+# Total code points: 10650
 
 # EOF

unicodetools/data/ucd/dev/EastAsianWidth.txt

@@ -1,5 +1,5 @@
 # EastAsianWidth-18.0.0.txt
-# Date: 2025-11-28, 13:24:22 GMT
+# Date: 2025-11-28, 15:47:02 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
@@ -2400,7 +2400,7 @@ FFFD           ; A  # So         REPLACEMENT CHARACTER
 1AFF5..1AFFB   ; W  # Lm     [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE   ; W  # Lm     [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B0FF   ; W  # Lo   [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
-1B100..1B122   ; W  # Lo    [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU
+1B100..1B125   ; W  # Lo    [38] HENTAIGANA LETTER RE-3..KATAKANA DIGRAPH TOTE
 1B127..1B128   ; W  # Lo     [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132          ; W  # Lo         HIRAGANA LETTER SMALL KO
 1B150..1B152   ; W  # Lo     [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO

unicodetools/data/ucd/dev/LineBreak.txt

@@ -1,5 +1,5 @@
 # LineBreak-18.0.0.txt
-# Date: 2025-11-28, 13:24:23 GMT
+# Date: 2025-11-28, 15:47:03 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
@@ -3313,7 +3313,7 @@ FFFD           ; AI # So         REPLACEMENT CHARACTER
 1AFF5..1AFFB   ; AL # Lm     [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE   ; AL # Lm     [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B0FF   ; ID # Lo   [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
-1B100..1B122   ; ID # Lo    [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU
+1B100..1B125   ; ID # Lo    [38] HENTAIGANA LETTER RE-3..KATAKANA DIGRAPH TOTE
 1B127..1B128   ; ID # Lo     [2] KATAKANA LETTER ALTERNATE NE..KATAKANA LETTER ALTERNATE WI
 1B132          ; CJ # Lo         HIRAGANA LETTER SMALL KO
 1B150..1B152   ; CJ # Lo     [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO