diff options
Diffstat (limited to 'util/unicode/data/SentenceBreakProperty.txt')
| -rw-r--r-- | util/unicode/data/SentenceBreakProperty.txt | 24 |
1 files changed, 15 insertions, 9 deletions
diff --git a/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt index f29dc4e199..d714d59d3a 100644 --- a/util/unicode/data/SentenceBreakProperty.txt +++ b/util/unicode/data/SentenceBreakProperty.txt @@ -1,8 +1,8 @@ -# SentenceBreakProperty-6.2.0.txt -# Date: 2012-05-23, 20:35:14 GMT [MD] +# SentenceBreakProperty-6.3.0.txt +# Date: 2013-09-25, 18:59:01 GMT [MD] # # Unicode Character Database -# Copyright (c) 1991-2012 Unicode, Inc. +# Copyright (c) 1991-2013 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see http://www.unicode.org/reports/tr44/ @@ -217,7 +217,8 @@ 19B0..19C0 ; Extend # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY 19C8..19C9 ; Extend # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2 1A17..1A18 ; Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; Extend # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; Extend # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; Extend # Mn BUGINESE VOWEL SIGN AE 1A55 ; Extend # Mc TAI THAM CONSONANT SIGN MEDIAL RA 1A56 ; Extend # Mn TAI THAM CONSONANT SIGN MEDIAL LA 1A57 ; Extend # Mc TAI THAM CONSONANT SIGN LA TANG LAI @@ -396,13 +397,15 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 00AD ; Format # Cf SOFT HYPHEN 0600..0604 ; Format # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT +061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK +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 202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Format # Cf [5] WORD JOINER..INVISIBLE PLUS -206A..206F ; Format # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +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 @@ -410,7 +413,7 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN E0001 ; Format # Cf LANGUAGE TAG E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 137 +# Total code points: 143 # ================================================ @@ -419,13 +422,12 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG 0020 ; Sp # Zs SPACE 00A0 ; Sp # Zs NO-BREAK SPACE 1680 ; Sp # Zs OGHAM SPACE MARK -180E ; Sp # Zs MONGOLIAN VOWEL SEPARATOR 2000..200A ; Sp # Zs [11] EN QUAD..HAIR SPACE 202F ; Sp # Zs NARROW NO-BREAK SPACE 205F ; Sp # Zs MEDIUM MATHEMATICAL SPACE 3000 ; Sp # Zs IDEOGRAPHIC SPACE -# Total code points: 21 +# Total code points: 20 # ================================================ @@ -2246,6 +2248,10 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 207E ; Close # Pe SUPERSCRIPT RIGHT PARENTHESIS 208D ; Close # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Close # Pe SUBSCRIPT RIGHT PARENTHESIS +2308 ; Close # Ps LEFT CEILING +2309 ; Close # Pe RIGHT CEILING +230A ; Close # Ps LEFT FLOOR +230B ; Close # Pe RIGHT FLOOR 2329 ; Close # Ps LEFT-POINTING ANGLE BRACKET 232A ; Close # Pe RIGHT-POINTING ANGLE BRACKET 275B..275E ; Close # So [4] HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT @@ -2385,7 +2391,7 @@ FF60 ; Close # Pe FULLWIDTH RIGHT WHITE PARENTHESIS FF62 ; Close # Ps HALFWIDTH LEFT CORNER BRACKET FF63 ; Close # Pe HALFWIDTH RIGHT CORNER BRACKET -# Total code points: 177 +# Total code points: 181 # ================================================ |