U+2024 Sentence_Terminal (#806)

* U+2024 Sentence_Terminal * also Term * add invariant
unicode-org · May 5, 2024 · a5c5716 · a5c5716
1 parent 064c55c
commit a5c5716
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt
@@ -1,5 +1,5 @@
 # PropList-16.0.0.txt
-# Date: 2024-04-30, 21:48:28 GMT
+# Date: 2024-05-05, 01:21:00 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
@@ -156,6 +156,7 @@ FF63          ; Quotation_Mark # Pe       HALFWIDTH RIGHT CORNER BRACKET
 1B7D..1B7E    ; Terminal_Punctuation # Po   [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG
 1C3B..1C3F    ; Terminal_Punctuation # Po   [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK
 1C7E..1C7F    ; Terminal_Punctuation # Po   [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
+2024          ; Terminal_Punctuation # Po       ONE DOT LEADER
 203C..203D    ; Terminal_Punctuation # Po   [2] DOUBLE EXCLAMATION MARK..INTERROBANG
 2047..2049    ; Terminal_Punctuation # Po   [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
 2E2E          ; Terminal_Punctuation # Po       REVERSED QUESTION MARK
@@ -227,7 +228,7 @@ FF64          ; Terminal_Punctuation # Po       HALFWIDTH IDEOGRAPHIC COMMA
 1BC9F         ; Terminal_Punctuation # Po       DUPLOYAN PUNCTUATION CHINOOK FULL STOP
 1DA87..1DA8A  ; Terminal_Punctuation # Po   [4] SIGNWRITING COMMA..SIGNWRITING COLON
 
-# Total code points: 277
+# Total code points: 278
 
 # ================================================
 
@@ -1535,6 +1536,7 @@ FF65          ; Other_ID_Continue # Po       HALFWIDTH KATAKANA MIDDLE DOT
 1B7D..1B7E    ; Sentence_Terminal # Po   [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG
 1C3B..1C3C    ; Sentence_Terminal # Po   [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL
 1C7E..1C7F    ; Sentence_Terminal # Po   [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD
+2024          ; Sentence_Terminal # Po       ONE DOT LEADER
 203C..203D    ; Sentence_Terminal # Po   [2] DOUBLE EXCLAMATION MARK..INTERROBANG
 2047..2049    ; Sentence_Terminal # Po   [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK
 2E2E          ; Sentence_Terminal # Po       REVERSED QUESTION MARK
@@ -1590,7 +1592,7 @@ FF61          ; Sentence_Terminal # Po       HALFWIDTH IDEOGRAPHIC FULL STOP
 1BC9F         ; Sentence_Terminal # Po       DUPLOYAN PUNCTUATION CHINOOK FULL STOP
 1DA88         ; Sentence_Terminal # Po       SIGNWRITING FULL STOP
 
-# Total code points: 156
+# Total code points: 157
 
 # ================================================
 

diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt
@@ -507,6 +507,10 @@ $combiningExclusions ⊇ [$firstNonStarter & \p{dt=canonical}]
 
 \p{Terminal_Punctuation} ⊃ \p{STerm}
 
+# Sentence terminal punctuation is exactly
+# ambiguous sentence terminal punctuation and unambiguous sentence terminal punctuation.
+\p{Sentence_Terminal} = [\p{sb=ATerm}\p{sb=STerm}]
+
 # 132-M3 if a character has a general category of "Number", it must have a numeric type that is not equal to "none".
 
 [\p{General_Category=Decimal_Number}\p{General_Category=Letter_Number}\p{General_Category=Other_Number}] ∥ \p{Numeric_Type=None}