summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/SentenceBreakProperty.txt
diff options
context:
space:
mode:
Diffstat (limited to 'util/unicode/data/SentenceBreakProperty.txt')
-rw-r--r--util/unicode/data/SentenceBreakProperty.txt28
1 files changed, 15 insertions, 13 deletions
diff --git a/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt
index 66fbf01eda..f848af1d11 100644
--- a/util/unicode/data/SentenceBreakProperty.txt
+++ b/util/unicode/data/SentenceBreakProperty.txt
@@ -1,6 +1,6 @@
-# SentenceBreakProperty-15.0.0.txt
-# Date: 2022-08-05, 22:17:35 GMT
-# © 2022 Unicode®, Inc.
+# SentenceBreakProperty-15.1.0.txt
+# Date: 2023-07-28, 23:34:37 GMT
+# © 2023 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
#
@@ -580,12 +580,8 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# ================================================
00AD ; Format # Cf SOFT HYPHEN
-0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
061C ; Format # Cf ARABIC LETTER MARK
-06DD ; Format # Cf ARABIC END OF AYAH
070F ; Format # Cf SYRIAC ABBREVIATION MARK
-0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
-08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH
180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR
200B ; Format # Cf ZERO WIDTH SPACE
200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@@ -594,14 +590,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE
FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
-110BD ; Format # Cf KAITHI NUMBER SIGN
-110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE
13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
E0001 ; Format # Cf LANGUAGE TAG
-# Total code points: 72
+# Total code points: 60
# ================================================
@@ -2537,19 +2531,24 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
+2EBF0..2EE5D ; OLetter # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D
2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
-# Total code points: 132036
+# Total code points: 132658
# ================================================
0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE
+0600..0605 ; Numeric # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE
0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
066B..066C ; Numeric # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR
+06DD ; Numeric # Cf ARABIC END OF AYAH
06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE
07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE
+0890..0891 ; Numeric # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE
+08E2 ; Numeric # Cf ARABIC DISPUTED END OF AYAH
0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE
09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE
@@ -2586,6 +2585,8 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE
10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE
+110BD ; Numeric # Cf KAITHI NUMBER SIGN
+110CD ; Numeric # Cf KAITHI NUMBER SIGN ABOVE
110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE
11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE
111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
@@ -2611,7 +2612,7 @@ 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: 682
+# Total code points: 694
# ================================================
@@ -2640,6 +2641,7 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP
1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR
166E ; STerm # Po CANADIAN SYLLABICS FULL STOP
1735..1736 ; STerm # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION
+17D4..17D5 ; STerm # Po [2] KHMER SIGN KHAN..KHMER SIGN BARIYOOSAN
1803 ; STerm # Po MONGOLIAN FULL STOP
1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP
1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK
@@ -2702,7 +2704,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP
1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA88 ; STerm # Po SIGNWRITING FULL STOP
-# Total code points: 151
+# Total code points: 153
# ================================================