Word_Break=ALetter for ¸ (#1157)

* In UCD file WordBreakProperty.txt, assign Word_Break=ALetter to U+00B8 ¸ CEDILLA.

* Regenerate UCD

* a strange invariant

Author: eggrobin

unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt

@@ -1,5 +1,5 @@
 # WordBreakProperty-17.0.0.txt
-# Date: 2025-04-25, 16:57:39 GMT
+# Date: 2025-05-26, 17:27:16 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
@@ -692,6 +692,7 @@ FF71..FF9D    ; Katakana # Lo  [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
 0061..007A    ; ALetter # L&  [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z
 00AA          ; ALetter # Lo       FEMININE ORDINAL INDICATOR
 00B5          ; ALetter # L&       MICRO SIGN
+00B8          ; ALetter # Sk       CEDILLA
 00BA          ; ALetter # Lo       MASCULINE ORDINAL INDICATOR
 00C0..00D6    ; ALetter # L&  [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS
 00D8..00F6    ; ALetter # L&  [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS
@@ -1383,7 +1384,7 @@ FFDA..FFDC    ; ALetter # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 1F150..1F169  ; ALetter # So  [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
 1F170..1F189  ; ALetter # So  [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
 
-# Total code points: 34001
+# Total code points: 34002
 
 # ================================================
 

unicodetools/src/main/java/org/unicode/text/UCD/ToolUnicodePropertySource.java

@@ -1291,7 +1291,7 @@ public int getMaxWidth(boolean isShort) {
                             .remove(0x200D)
                             .remove(0x200B)
                             .removeAll(tags)
-                            // 174-CXX.
+                            // 175-C24.
                             .removeAll(gcb.getSet("Prepend")),
                     "Format");
             unicodeMap.putAll(
@@ -1324,8 +1324,10 @@ public int getMaxWidth(boolean isShort) {
                             // Armenian punctuation marks that occur within words; see
                             // http://www.unicode.org/L2/L2018/18115.htm#155-C3
                             .addAll(new UnicodeSet("[\\u055B\\u055C\\u055E]"))
-                            // 174-CXX.
-                            .add(0x070F),
+                            // 175-C24.
+                            .add(0x070F)
+                            // https://github.com/unicode-org/properties/issues/400.
+                            .add(0x00B8),
                     "ALetter");
             unicodeMap.putAll(
                     new UnicodeSet("[\\u00B7\\u0387\\u05F4\\u2027\\u003A\\uFE13\\uFE55\\uFF1A]"),

unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt

@@ -926,6 +926,8 @@ Let $uax31table3 := [\u0027\u002D\u002E\u003A\u00B7\u058A\u05F3\u05F4\u0F0B\u200
 
 Let $WBRemovals := [\u0387\u0604\u2018\u2024\u202F\u2E2F\uFE13\uFE52\uFE55\uFF07\uFF0E\uFF1A\u200c\u200d'.\:\u00AD\u00B7\u05F3\u05F4\u0600-\u0603\u06DD\u070F\u17B4\u17B5\u200E\u200F\u2019\u2027\u202A-\u202E\u2060-\u2064\u206A-\u206F\uFEFF\uFFF9-\uFFFB\u02C2-\u02C5\u02D2-\u02D6\u02DE-\u02DF\u02ED\u02EF-\u02FF\uA720-\uA721\uA789-\uA78A\uAB5B\u055B\u055C\u055E\U000110BD\U0001D173-\U0001D17A\U000E0001\U000E0020-\U000E007F\p{gc=Cf}\p{Block=Enclosed Alphanumerics}[\u02D7\u0605\u061C\u180E\u2066-\u2069\U0001BCA0-\U0001BCA3\U0001F130-\U0001F149\U0001F150-\U0001F169\U0001F170-\U0001F189\U0001F3FB-\U0001F3FF]]
 Let $WBRemovals13 := [\u02E5-\u02EB\u055A\u058A\uA708-\uA716\u055F]
+Let $WBRemoval17 := [\u00B8]
+
 # 9.0 corrected \p{gc=Cf} and added 202F
 # 10.0 added 34 characters which were absorbed into WB=LE (see http://www.unicode.org/reports/tr29/tr29-30d2.html#ALetter)
 # 11.0 added 5 skin tone modifiers which were absorbed into WB=Extend
@@ -936,7 +938,7 @@ Let $WBRemovals13 := [\u02E5-\u02EB\u055A\u058A\uA708-\uA716\u055F]
 Let $Uax31Removals := [\-\u058A\u0F0B\u2010\u30A0\u30FB\u2E2F\u17B4-\u17B5]
 # 6.1.0 adjust SAMVAT, KHMER VOWEL INHERENT*
 
-[\p{Alpha}\p{WB=Extend}\p{WB=FO}\p{WB=LE}\p{WB=ML}\p{WB=MB}\p{WB=EX}-$WBRemovals-$WBRemovals13] = [$gcAllLetters $gcAllMarks \p{gc=Nl}\p{gc=Pc}-$Uax31Removals]
+[\p{Alpha}\p{WB=Extend}\p{WB=FO}\p{WB=LE}\p{WB=ML}\p{WB=MB}\p{WB=EX}-$WBRemovals-$WBRemovals13-$WBRemoval17] = [$gcAllLetters $gcAllMarks \p{gc=Nl}\p{gc=Pc}-$Uax31Removals]
 
 # Don’t break words after GCB=Prepend characters (that would be within a
 # grapheme cluster).