Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
f1553b9
UnicodeData.txt lines from L2/24-277
eggrobin Feb 11, 2025
98755ef
Typos in the UnicodeData.txt lines
eggrobin Feb 11, 2025
4a8cd3f
Another typo
eggrobin Feb 11, 2025
2d4a7be
lb assignments according to the proposal, note lb=CL rather than lb=C…
eggrobin Feb 11, 2025
a9986cc
Latin letters, Common punctuation
eggrobin Feb 11, 2025
de5edbc
Regenerate UCD
eggrobin Feb 11, 2025
d06adf7
Failing test for the case pairs
eggrobin Feb 11, 2025
27ff4e1
Another typo in the UnicodeData lines
eggrobin Feb 11, 2025
0ea309e
up to block
eggrobin Feb 11, 2025
253fdb7
Regenerate UCD
eggrobin Feb 11, 2025
32b0a68
Test the unpaired lowercase letters
eggrobin Feb 11, 2025
0ed1ae8
Test ɷ
eggrobin Feb 11, 2025
3df69cd
failing test for the parentheses
eggrobin Feb 11, 2025
0d55f00
bpb bmg
eggrobin Feb 11, 2025
f42e1f3
Failing test for the exclamation marks
eggrobin Feb 11, 2025
8c7b347
Terminal wigglies
eggrobin Feb 11, 2025
c9eac30
Regenerate UCD
eggrobin Feb 11, 2025
7e468f3
Test passes
eggrobin Feb 11, 2025
a921007
Merge remote-tracking branch 'la-vache/main' into EPA
eggrobin Feb 11, 2025
ab6cdab
Lo and compare them to ꟻ
eggrobin Feb 14, 2025
b923d3d
Regenerate UCD
eggrobin Feb 14, 2025
bf767ac
Ignore Block
eggrobin Feb 14, 2025
35792be
Merge remote-tracking branch 'la-vache/main' into EPA
eggrobin Nov 11, 2025
ad196d1
More apt (and failing) comparison for the i-like letters
eggrobin Nov 11, 2025
c4f12f4
Soften the dots
eggrobin Nov 11, 2025
0409fb9
Regenerate UCD
eggrobin Nov 11, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions unicodetools/data/ucd/dev/BidiBrackets.txt
Original file line number Diff line number Diff line change
Expand Up @@ -155,6 +155,8 @@
2E5A; 2E59; c # TOP HALF RIGHT PARENTHESIS
2E5B; 2E5C; o # BOTTOM HALF LEFT PARENTHESIS
2E5C; 2E5B; c # BOTTOM HALF RIGHT PARENTHESIS
2E62; 2E63; o # LEFT PARENTHESIS WITH MIDDLE RING
2E63; 2E62; c # RIGHT PARENTHESIS WITH MIDDLE RING
3008; 3009; o # LEFT ANGLE BRACKET
3009; 3008; c # RIGHT ANGLE BRACKET
300A; 300B; o # LEFT DOUBLE ANGLE BRACKET
Expand Down
2 changes: 2 additions & 0 deletions unicodetools/data/ucd/dev/BidiMirroring.txt
Original file line number Diff line number Diff line change
Expand Up @@ -463,6 +463,8 @@
2E5A; 2E59 # TOP HALF RIGHT PARENTHESIS
2E5B; 2E5C # BOTTOM HALF LEFT PARENTHESIS
2E5C; 2E5B # BOTTOM HALF RIGHT PARENTHESIS
2E62; 2E63 # LEFT PARENTHESIS WITH MIDDLE RING
2E63; 2E62 # RIGHT PARENTHESIS WITH MIDDLE RING
3008; 3009 # LEFT ANGLE BRACKET
3009; 3008 # RIGHT ANGLE BRACKET
300A; 300B # LEFT DOUBLE ANGLE BRACKET
Expand Down
16 changes: 14 additions & 2 deletions unicodetools/data/ucd/dev/CaseFolding.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# CaseFolding-17.0.0.txt
# Date: 2025-07-30, 23:54:36 GMT
# CaseFolding-18.0.0.txt
# Date: 2025-11-11, 13:01:31 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
Expand Down Expand Up @@ -1251,6 +1251,7 @@ A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S
A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S
A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA
A7DC; C; 019B; # LATIN CAPITAL LETTER LAMBDA WITH STROKE
A7DD; C; 0277; # LATIN CAPITAL LETTER CLOSED OMEGA
A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H
AB70; C; 13A0; # CHEROKEE SMALL LETTER A
AB71; C; 13A1; # CHEROKEE SMALL LETTER E
Expand Down Expand Up @@ -1644,6 +1645,17 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
16EB6; C; 16ED1; # BERIA ERFE CAPITAL LETTER UI
16EB7; C; 16ED2; # BERIA ERFE CAPITAL LETTER WASSE
16EB8; C; 16ED3; # BERIA ERFE CAPITAL LETTER AY
1DF68; C; 1DF69; # LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH
1DF6A; C; 1DF6B; # LATIN CAPITAL LETTER PHONOTYPIC ROUNDTOP A
1DF6C; C; 1DF6D; # LATIN CAPITAL LETTER REVERSED SCRUPLE
1DF6E; C; 1DF6F; # LATIN CAPITAL LETTER PHONOTYPIC DIPHTHONG AI
1DF72; C; 1DF73; # LATIN CAPITAL LETTER O WITH CURL
1DF74; C; 1DF75; # LATIN CAPITAL LETTER CLOSED OMEGA WITH LONG STEM
1DF76; C; 1DF77; # LATIN CAPITAL LETTER TURNED CLOSED OMEGA
1DF78; C; 1DF79; # LATIN CAPITAL LETTER PHONOTYPIC TH
1DF7A; C; 1DF7B; # LATIN CAPITAL LETTER U WITH HOOK TAIL
1DF7C; C; 1DF7D; # LATIN CAPITAL LETTER U WITH NOTCH AT BOTTOM
1DF7E; C; 1DF7F; # LATIN CAPITAL LETTER REVERSED ENLARGED SMALL U
1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF
1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI
1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM
Expand Down
7 changes: 5 additions & 2 deletions unicodetools/data/ucd/dev/DerivedAge.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# DerivedAge-18.0.0.txt
# Date: 2025-11-10, 23:51:13 GMT
# Date: 2025-11-11, 13:01:32 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
Expand Down Expand Up @@ -2123,10 +2123,13 @@
# Newly assigned in Unicode 18.0.0 (September, 2025)

20C3 ; 18.0 # UAE DIRHAM SIGN
2E60..2E63 ; 18.0 # [4] WIGGLY EXCLAMATION MARK..RIGHT PARENTHESIS WITH MIDDLE RING
A7DD ; 18.0 # LATIN CAPITAL LETTER CLOSED OMEGA
18D1F..18D20 ; 18.0 # [2] TANGUT IDEOGRAPH-18D1F..TANGUT IDEOGRAPH-18D20
1DF68..1DF81 ; 18.0 # [26] LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH..LATIN CAPITAL LETTER E WITH BENT TOPBAR
1F7DB ; 18.0 # BULLET IN DOUBLE CIRCLE
1F7F1..1F7FF ; 18.0 # [15] CIRCLE WITH DOUBLE VERTICAL AND HORIZONTAL LINE..RHOMBUS

# Total code points: 19
# Total code points: 50

# EOF
139 changes: 113 additions & 26 deletions unicodetools/data/ucd/dev/DerivedCoreProperties.txt

Large diffs are not rendered by default.

47 changes: 41 additions & 6 deletions unicodetools/data/ucd/dev/DerivedNormalizationProps.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# DerivedNormalizationProps-17.0.0.txt
# Date: 2025-01-27, 18:09:14 GMT
# DerivedNormalizationProps-18.0.0.txt
# Date: 2025-11-11, 13:02:00 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
Expand Down Expand Up @@ -5457,6 +5457,7 @@ A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE S
A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S
A7DA ; NFKC_CF; A7DB # L& LATIN CAPITAL LETTER LAMBDA
A7DC ; NFKC_CF; 019B # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
A7DD ; NFKC_CF; 0277 # L& LATIN CAPITAL LETTER CLOSED OMEGA
A7F1 ; NFKC_CF; 0073 # Lm MODIFIER LETTER CAPITAL S
A7F2 ; NFKC_CF; 0063 # Lm MODIFIER LETTER CAPITAL C
A7F3 ; NFKC_CF; 0066 # Lm MODIFIER LETTER CAPITAL F
Expand Down Expand Up @@ -8255,6 +8256,17 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF
1D7FD ; NFKC_CF; 0037 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN
1D7FE ; NFKC_CF; 0038 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT
1D7FF ; NFKC_CF; 0039 # Nd MATHEMATICAL MONOSPACE DIGIT NINE
1DF68 ; NFKC_CF; 1DF69 # L& LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH
1DF6A ; NFKC_CF; 1DF6B # L& LATIN CAPITAL LETTER PHONOTYPIC ROUNDTOP A
1DF6C ; NFKC_CF; 1DF6D # L& LATIN CAPITAL LETTER REVERSED SCRUPLE
1DF6E ; NFKC_CF; 1DF6F # L& LATIN CAPITAL LETTER PHONOTYPIC DIPHTHONG AI
1DF72 ; NFKC_CF; 1DF73 # L& LATIN CAPITAL LETTER O WITH CURL
1DF74 ; NFKC_CF; 1DF75 # L& LATIN CAPITAL LETTER CLOSED OMEGA WITH LONG STEM
1DF76 ; NFKC_CF; 1DF77 # L& LATIN CAPITAL LETTER TURNED CLOSED OMEGA
1DF78 ; NFKC_CF; 1DF79 # L& LATIN CAPITAL LETTER PHONOTYPIC TH
1DF7A ; NFKC_CF; 1DF7B # L& LATIN CAPITAL LETTER U WITH HOOK TAIL
1DF7C ; NFKC_CF; 1DF7D # L& LATIN CAPITAL LETTER U WITH NOTCH AT BOTTOM
1DF7E ; NFKC_CF; 1DF7F # L& LATIN CAPITAL LETTER REVERSED ENLARGED SMALL U
1E030 ; NFKC_CF; 0430 # Lm MODIFIER LETTER CYRILLIC SMALL A
1E031 ; NFKC_CF; 0431 # Lm MODIFIER LETTER CYRILLIC SMALL BE
1E032 ; NFKC_CF; 0432 # Lm MODIFIER LETTER CYRILLIC SMALL VE
Expand Down Expand Up @@ -9178,7 +9190,7 @@ 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: 10583
# Total code points: 10595

# ================================================

Expand Down Expand Up @@ -11620,6 +11632,7 @@ A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE
A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S
A7DA ; NFKC_SCF; A7DB # L& LATIN CAPITAL LETTER LAMBDA
A7DC ; NFKC_SCF; 019B # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
A7DD ; NFKC_SCF; 0277 # L& LATIN CAPITAL LETTER CLOSED OMEGA
A7F1 ; NFKC_SCF; 0073 # Lm MODIFIER LETTER CAPITAL S
A7F2 ; NFKC_SCF; 0063 # Lm MODIFIER LETTER CAPITAL C
A7F3 ; NFKC_SCF; 0066 # Lm MODIFIER LETTER CAPITAL F
Expand Down Expand Up @@ -14418,6 +14431,17 @@ FFF0..FFF8 ; NFKC_SCF; # Cn [9] <reserved-FFF0>..<reserved-F
1D7FD ; NFKC_SCF; 0037 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN
1D7FE ; NFKC_SCF; 0038 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT
1D7FF ; NFKC_SCF; 0039 # Nd MATHEMATICAL MONOSPACE DIGIT NINE
1DF68 ; NFKC_SCF; 1DF69 # L& LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH
1DF6A ; NFKC_SCF; 1DF6B # L& LATIN CAPITAL LETTER PHONOTYPIC ROUNDTOP A
1DF6C ; NFKC_SCF; 1DF6D # L& LATIN CAPITAL LETTER REVERSED SCRUPLE
1DF6E ; NFKC_SCF; 1DF6F # L& LATIN CAPITAL LETTER PHONOTYPIC DIPHTHONG AI
1DF72 ; NFKC_SCF; 1DF73 # L& LATIN CAPITAL LETTER O WITH CURL
1DF74 ; NFKC_SCF; 1DF75 # L& LATIN CAPITAL LETTER CLOSED OMEGA WITH LONG STEM
1DF76 ; NFKC_SCF; 1DF77 # L& LATIN CAPITAL LETTER TURNED CLOSED OMEGA
1DF78 ; NFKC_SCF; 1DF79 # L& LATIN CAPITAL LETTER PHONOTYPIC TH
1DF7A ; NFKC_SCF; 1DF7B # L& LATIN CAPITAL LETTER U WITH HOOK TAIL
1DF7C ; NFKC_SCF; 1DF7D # L& LATIN CAPITAL LETTER U WITH NOTCH AT BOTTOM
1DF7E ; NFKC_SCF; 1DF7F # L& LATIN CAPITAL LETTER REVERSED ENLARGED SMALL U
1E030 ; NFKC_SCF; 0430 # Lm MODIFIER LETTER CYRILLIC SMALL A
1E031 ; NFKC_SCF; 0431 # Lm MODIFIER LETTER CYRILLIC SMALL BE
1E032 ; NFKC_SCF; 0432 # Lm MODIFIER LETTER CYRILLIC SMALL VE
Expand Down Expand Up @@ -15341,7 +15365,7 @@ 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: 10545
# Total code points: 10557

# ================================================

Expand Down Expand Up @@ -16118,7 +16142,7 @@ A7D4 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER DOU
A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S
A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S
A7DA ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA
A7DC ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE
A7DC..A7DD ; Changes_When_NFKC_Casefolded # L& [2] LATIN CAPITAL LETTER LAMBDA WITH STROKE..LATIN CAPITAL LETTER CLOSED OMEGA
A7F1..A7F4 ; Changes_When_NFKC_Casefolded # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
A7F5 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H
A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
Expand Down Expand Up @@ -16309,6 +16333,17 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserv
1D7C3 ; Changes_When_NFKC_Casefolded # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; Changes_When_NFKC_Casefolded # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Changes_When_NFKC_Casefolded # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1DF68 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH
1DF6A ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER PHONOTYPIC ROUNDTOP A
1DF6C ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER REVERSED SCRUPLE
1DF6E ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER PHONOTYPIC DIPHTHONG AI
1DF72 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER O WITH CURL
1DF74 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER CLOSED OMEGA WITH LONG STEM
1DF76 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER TURNED CLOSED OMEGA
1DF78 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER PHONOTYPIC TH
1DF7A ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER U WITH HOOK TAIL
1DF7C ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER U WITH NOTCH AT BOTTOM
1DF7E ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER REVERSED ENLARGED SMALL U
1E030..1E06D ; Changes_When_NFKC_Casefolded # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
1E900..1E921 ; Changes_When_NFKC_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA
1EE00..1EE03 ; Changes_When_NFKC_Casefolded # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
Expand Down Expand Up @@ -16363,6 +16398,6 @@ 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: 10583
# Total code points: 10595

# EOF
9 changes: 7 additions & 2 deletions unicodetools/data/ucd/dev/EastAsianWidth.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# EastAsianWidth-18.0.0.txt
# Date: 2025-11-10, 23:51:44 GMT
# Date: 2025-11-11, 13:02:02 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
Expand Down Expand Up @@ -1432,6 +1432,9 @@
2E5B ; N # Ps BOTTOM HALF LEFT PARENTHESIS
2E5C ; N # Pe BOTTOM HALF RIGHT PARENTHESIS
2E5D ; N # Pd OBLIQUE HYPHEN
2E60..2E61 ; N # Po [2] WIGGLY EXCLAMATION MARK..INVERTED WIGGLY EXCLAMATION MARK
2E62 ; N # Ps LEFT PARENTHESIS WITH MIDDLE RING
2E63 ; N # Pe RIGHT PARENTHESIS WITH MIDDLE RING
2E80..2E99 ; W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5 ; W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
Expand Down Expand Up @@ -1549,7 +1552,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT
A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE
A790..A7DD ; N # L& [78] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER CLOSED OMEGA
A7F1..A7F4 ; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
Expand Down Expand Up @@ -2493,6 +2496,8 @@ FFFD ; A # So REPLACEMENT CHARACTER
1DF0A ; N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
1DF0B..1DF1E ; N # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A ; N # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1DF68..1DF7F ; N # L& [24] LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH..LATIN SMALL LETTER REVERSED U
1DF80..1DF81 ; N # Lo [2] LATIN CAPITAL LETTER A WITH TOPBAR..LATIN CAPITAL LETTER E WITH BENT TOPBAR
1E000..1E006 ; N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E008..1E018 ; N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E01B..1E021 ; N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
Expand Down
9 changes: 7 additions & 2 deletions unicodetools/data/ucd/dev/LineBreak.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# LineBreak-18.0.0.txt
# Date: 2025-11-10, 23:51:46 GMT
# Date: 2025-11-11, 13:02:05 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
Expand Down Expand Up @@ -1414,6 +1414,9 @@
2E5B ; OP # Ps BOTTOM HALF LEFT PARENTHESIS
2E5C ; CP # Pe BOTTOM HALF RIGHT PARENTHESIS
2E5D ; HH # Pd OBLIQUE HYPHEN
2E60..2E61 ; EX # Po [2] WIGGLY EXCLAMATION MARK..INVERTED WIGGLY EXCLAMATION MARK
2E62 ; OP # Ps LEFT PARENTHESIS WITH MIDDLE RING
2E63 ; CL # Pe RIGHT PARENTHESIS WITH MIDDLE RING
2E80..2E99 ; ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5 ; ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
Expand Down Expand Up @@ -1577,7 +1580,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT
A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN
A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT
A790..A7DC ; AL # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE
A790..A7DD ; AL # L& [78] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER CLOSED OMEGA
A7F1..A7F4 ; AL # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q
A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
Expand Down Expand Up @@ -3405,6 +3408,8 @@ FFFD ; AI # So REPLACEMENT CHARACTER
1DF0A ; AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
1DF0B..1DF1E ; AL # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
1DF25..1DF2A ; AL # Ll [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
1DF68..1DF7F ; AL # L& [24] LATIN CAPITAL LETTER PHONOTYPIC A WITH SWASH..LATIN SMALL LETTER REVERSED U
1DF80..1DF81 ; AL # Lo [2] LATIN CAPITAL LETTER A WITH TOPBAR..LATIN CAPITAL LETTER E WITH BENT TOPBAR
1E000..1E006 ; CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E008..1E018 ; CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E01B..1E021 ; CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
Expand Down
Loading
Loading