Changes to Line_Break assignments from UTC-180 (#893)

* UTC-180-A54 Change the Line_Break assignment of U+19DA NEW TAI LUE THAM DIGIT ONE from Line_Break=Complex Context to Line_Break=Numeric in LineBreak.txt. For Unicode 16.0. See L2/24-162 item 5.4. * UTC-180-A55 change the Line_Break property of U+2150..U+2153, U+2156..U+215A, and U+215C..U+215D (VULGAR FRACTION ONE SEVENTH, ONE NINTH, ONE TENTH, ONE THIRD, TWO FIFTHS, THREE FIFTHS, FOUR FIFTHS, ONE SIXTH, FIVE SIXTHS, THREE EIGHTHS, and FIVE EIGHTHS) to lb=AI. For Unicode 16.0. See L2/24-162 item 5.5. * Regenerate UCD * Appease invariants
unicode-org · Jul 29, 2024 · bd37dbc · bd37dbc
1 parent c41ca11
commit bd37dbc
Show file tree

Hide file tree

Showing 5 changed files with 20 additions and 27 deletions.
diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt
@@ -1,5 +1,5 @@
 # LineBreak-16.0.0.txt
-# Date: 2024-05-11, 16:57:19 GMT
+# Date: 2024-07-29, 16:26:55 GMT
 # © 2024 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
@@ -748,7 +748,7 @@
 1980..19AB     ; SA # Lo    [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
 19B0..19C9     ; SA # Lo    [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
 19D0..19D9     ; NU # Nd    [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
-19DA           ; SA # No         NEW TAI LUE THAM DIGIT ONE
+19DA           ; NU # No         NEW TAI LUE THAM DIGIT ONE
 19DE..19DF     ; SA # So     [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV
 19E0..19FF     ; AL # So    [32] KHMER SYMBOL PATHAMASAT..KHMER SYMBOL DAP-PRAM ROC
 1A00..1A16     ; AL # Lo    [23] BUGINESE LETTER KA..BUGINESE LETTER HA
@@ -1018,12 +1018,7 @@
 214C..214D     ; AL # So     [2] PER SIGN..AKTIESELSKAB
 214E           ; AL # Ll         TURNED SMALL F
 214F           ; AL # So         SYMBOL FOR SAMARITAN SOURCE
-2150..2153     ; AL # No     [4] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION ONE THIRD
-2154..2155     ; AI # No     [2] VULGAR FRACTION TWO THIRDS..VULGAR FRACTION ONE FIFTH
-2156..215A     ; AL # No     [5] VULGAR FRACTION TWO FIFTHS..VULGAR FRACTION FIVE SIXTHS
-215B           ; AI # No         VULGAR FRACTION ONE EIGHTH
-215C..215D     ; AL # No     [2] VULGAR FRACTION THREE EIGHTHS..VULGAR FRACTION FIVE EIGHTHS
-215E           ; AI # No         VULGAR FRACTION SEVEN EIGHTHS
+2150..215E     ; AI # No    [15] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION SEVEN EIGHTHS
 215F           ; AL # No         FRACTION NUMERATOR ONE
 2160..216B     ; AI # Nl    [12] ROMAN NUMERAL ONE..ROMAN NUMERAL TWELVE
 216C..216F     ; AL # Nl     [4] ROMAN NUMERAL FIFTY..ROMAN NUMERAL ONE THOUSAND

diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt
@@ -1,5 +1,5 @@
 # SentenceBreakProperty-16.0.0.txt
-# Date: 2024-05-13, 20:53:44 GMT
+# Date: 2024-07-29, 16:27:32 GMT
 # © 2024 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
@@ -2617,6 +2617,7 @@ FFDA..FFDC    ; OLetter # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 1810..1819    ; Numeric # Nd  [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
 1946..194F    ; Numeric # Nd  [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE
 19D0..19D9    ; Numeric # Nd  [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
+19DA          ; Numeric # No       NEW TAI LUE THAM DIGIT ONE
 1A80..1A89    ; Numeric # Nd  [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE
 1A90..1A99    ; Numeric # Nd  [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE
 1B50..1B59    ; Numeric # Nd  [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE
@@ -2668,7 +2669,7 @@ FF10..FF19    ; Numeric # Nd  [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
 1E950..1E959  ; Numeric # Nd  [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
 1FBF0..1FBF9  ; Numeric # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 
-# Total code points: 774
+# Total code points: 775
 
 # ================================================
 

diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt
@@ -1,5 +1,5 @@
 # WordBreakProperty-16.0.0.txt
-# Date: 2024-04-30, 21:48:43 GMT
+# Date: 2024-07-29, 16:27:36 GMT
 # © 2024 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
@@ -1430,6 +1430,7 @@ FF0E          ; MidNumLet # Po       FULLWIDTH FULL STOP
 1810..1819    ; Numeric # Nd  [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
 1946..194F    ; Numeric # Nd  [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE
 19D0..19D9    ; Numeric # Nd  [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
+19DA          ; Numeric # No       NEW TAI LUE THAM DIGIT ONE
 1A80..1A89    ; Numeric # Nd  [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE
 1A90..1A99    ; Numeric # Nd  [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE
 1B50..1B59    ; Numeric # Nd  [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE
@@ -1481,7 +1482,7 @@ FF10..FF19    ; Numeric # Nd  [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
 1E950..1E959  ; Numeric # Nd  [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
 1FBF0..1FBF9  ; Numeric # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 
-# Total code points: 773
+# Total code points: 774
 
 # ================================================
 

diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt
@@ -1,5 +1,5 @@
 # DerivedLineBreak-16.0.0.txt
-# Date: 2024-05-11, 16:57:14 GMT
+# Date: 2024-07-29, 16:26:50 GMT
 # © 2024 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
@@ -512,6 +512,7 @@ FFE0          ; PO # Sc       FULLWIDTH CENT SIGN
 1810..1819    ; NU # Nd  [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
 1946..194F    ; NU # Nd  [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE
 19D0..19D9    ; NU # Nd  [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
+19DA          ; NU # No       NEW TAI LUE THAM DIGIT ONE
 1A80..1A89    ; NU # Nd  [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE
 1A90..1A99    ; NU # Nd  [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE
 1BB0..1BB9    ; NU # Nd  [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE
@@ -555,7 +556,7 @@ ABF0..ABF9    ; NU # Nd  [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE
 1E950..1E959  ; NU # Nd  [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
 1FBF0..1FBF9  ; NU # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 
-# Total code points: 694
+# Total code points: 695
 
 # ================================================
 
@@ -956,9 +957,6 @@ ABF0..ABF9    ; NU # Nd  [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE
 214C..214D    ; AL # So   [2] PER SIGN..AKTIESELSKAB
 214E          ; AL # L&       TURNED SMALL F
 214F          ; AL # So       SYMBOL FOR SAMARITAN SOURCE
-2150..2153    ; AL # No   [4] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION ONE THIRD
-2156..215A    ; AL # No   [5] VULGAR FRACTION TWO FIFTHS..VULGAR FRACTION FIVE SIXTHS
-215C..215D    ; AL # No   [2] VULGAR FRACTION THREE EIGHTHS..VULGAR FRACTION FIVE EIGHTHS
 215F          ; AL # No       FRACTION NUMERATOR ONE
 216C..216F    ; AL # Nl   [4] ROMAN NUMERAL FIFTY..ROMAN NUMERAL ONE THOUSAND
 217A..2182    ; AL # Nl   [9] SMALL ROMAN NUMERAL ELEVEN..ROMAN NUMERAL TEN THOUSAND
@@ -1615,7 +1613,7 @@ FFED..FFEE    ; AL # So   [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
 1FB00..1FB92  ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
 1FB94..1FBEF  ; AL # So  [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE
 
-# Total code points: 26690
+# Total code points: 26679
 
 # ================================================
 
@@ -2658,7 +2656,6 @@ FFFC          ; CB # So       OBJECT REPLACEMENT CHARACTER
 1970..1974    ; SA # Lo   [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
 1980..19AB    ; SA # Lo  [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
 19B0..19C9    ; SA # Lo  [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
-19DA          ; SA # No       NEW TAI LUE THAM DIGIT ONE
 19DE..19DF    ; SA # So   [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV
 1A20..1A54    ; SA # Lo  [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA
 1A55          ; SA # Mc       TAI THAM CONSONANT SIGN MEDIAL RA
@@ -2714,7 +2711,7 @@ AADE..AADF    ; SA # Po   [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI
 1173F         ; SA # So       AHOM SYMBOL VI
 11740..11746  ; SA # Lo   [7] AHOM LETTER CA..AHOM LETTER LLA
 
-# Total code points: 758
+# Total code points: 757
 
 # ================================================
 
@@ -2748,9 +2745,7 @@ AADE..AADF    ; SA # Po   [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI
 2113          ; AI # L&       SCRIPT SMALL L
 2121..2122    ; AI # So   [2] TELEPHONE SIGN..TRADE MARK SIGN
 212B          ; AI # L&       ANGSTROM SIGN
-2154..2155    ; AI # No   [2] VULGAR FRACTION TWO THIRDS..VULGAR FRACTION ONE FIFTH
-215B          ; AI # No       VULGAR FRACTION ONE EIGHTH
-215E          ; AI # No       VULGAR FRACTION SEVEN EIGHTHS
+2150..215E    ; AI # No  [15] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION SEVEN EIGHTHS
 2160..216B    ; AI # Nl  [12] ROMAN NUMERAL ONE..ROMAN NUMERAL TWELVE
 2170..2179    ; AI # Nl  [10] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL TEN
 2189          ; AI # No       VULGAR FRACTION ZERO THIRDS
@@ -2840,7 +2835,7 @@ FFFD          ; AI # So       REPLACEMENT CHARACTER
 1F130..1F169  ; AI # So  [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
 1F170..1F1AC  ; AI # So  [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
 
-# Total code points: 707
+# Total code points: 718
 
 # ================================================
 

diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt
@@ -818,7 +818,8 @@ Let $OPInclusions := [\u00A1\u00BF\u2E18\U00013258-\U0001325A\U00013286\U0001328
 # 15.1.0: and those from scripts that use the Brahmic style of context analysis,
 #  4.0.1: plus these characters: 066B ARABIC DECIMAL SEPARATOR, 066C ARABIC THOUSANDS SEPARATOR.
 # 15.1.0: Action item UTC-176-A81: change [[:PCM:]-\u070F] lb=AL->NU
-Let $NUInclusions := [\u066B\u066C]
+# 16.0.0: UTC-180-A54: U+19DA from lb=SA to lb=NU.
+Let $NUInclusions := [\u066B\u066C\u19DA]
 Let $NUFormats := [[:PCM:]-[\u070F]]
 \p{LB=NU} = [\p{GC=Nd} $NUInclusions $NUFormats - \p{EA=F} - $BrahmicLineBreaking]
 
@@ -889,8 +890,8 @@ Let $SAScripts := [
 ]
 $SAScripts ⊇ \p{LineBreak=SA}
 
-# And in $SA scripts, they are all the alphabetic spacing characters, plus some odd Cf & Mn, plus the NEW TAI LUE THAM DIGIT ONE
-Let $SAScriptExceptions := [\x{1173A}\x{1173B}\x{1173F} \u19DA\u109E\u109F\u19DE\u19DF\u1AA0-\u1AA6\u1AA8-\u1AAD\uAA77-\uAA79\uAADE-\uAADF]
+# And in $SA scripts, they are all the alphabetic spacing characters, plus some odd Cf & Mn
+Let $SAScriptExceptions := [\x{1173A}\x{1173B}\x{1173F} \u109E\u109F\u19DE\u19DF\u1AA0-\u1AA6\u1AA8-\u1AAD\uAA77-\uAA79\uAADE-\uAADF]
 # 7.0 Added AA7D
 # 12.0 Removed Myanmar spacing marks which were assigned Other_Alphabetic: 1063..1064, 1069..106D, 1087..108C, 108F, 109A..109B, AA7B, AA7D