summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/WordBreakProperty.txt
diff options
context:
space:
mode:
Diffstat (limited to 'util/unicode/data/WordBreakProperty.txt')
-rw-r--r--util/unicode/data/WordBreakProperty.txt61
1 files changed, 41 insertions, 20 deletions
diff --git a/util/unicode/data/WordBreakProperty.txt b/util/unicode/data/WordBreakProperty.txt
index 2caa16b46b..ad2b10992c 100644
--- a/util/unicode/data/WordBreakProperty.txt
+++ b/util/unicode/data/WordBreakProperty.txt
@@ -1,8 +1,8 @@
-# WordBreakProperty-6.2.0.txt
-# Date: 2012-08-13, 19:12:09 GMT [MD]
+# WordBreakProperty-6.3.0.txt
+# Date: 2013-07-05, 14:09:03 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/
@@ -17,6 +17,33 @@
# ================================================
+0022 ; Double_Quote # Po QUOTATION MARK
+
+# Total code points: 1
+
+# ================================================
+
+0027 ; Single_Quote # Po APOSTROPHE
+
+# Total code points: 1
+
+# ================================================
+
+05D0..05EA ; Hebrew_Letter # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
+05F0..05F2 ; Hebrew_Letter # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
+FB1D ; Hebrew_Letter # Lo HEBREW LETTER YOD WITH HIRIQ
+FB1F..FB28 ; Hebrew_Letter # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV
+FB2A..FB36 ; Hebrew_Letter # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH
+FB38..FB3C ; Hebrew_Letter # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH
+FB3E ; Hebrew_Letter # Lo HEBREW LETTER MEM WITH DAGESH
+FB40..FB41 ; Hebrew_Letter # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH
+FB43..FB44 ; Hebrew_Letter # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
+FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED
+
+# Total code points: 74
+
+# ================================================
+
000D ; CR # Cc <control-000D>
# Total code points: 1
@@ -226,7 +253,8 @@
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
@@ -403,12 +431,14 @@ 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
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
@@ -416,7 +446,7 @@ 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: 136
+# Total code points: 142
# ================================================
@@ -472,8 +502,6 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
0531..0556 ; ALetter # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
0559 ; ALetter # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING
0561..0587 ; ALetter # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
-05D0..05EA ; ALetter # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
-05F0..05F2 ; ALetter # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD
05F3 ; ALetter # Po HEBREW PUNCTUATION GERESH
0620..063F ; ALetter # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
0640 ; ALetter # Lm ARABIC TATWEEL
@@ -774,14 +802,7 @@ D7B0..D7C6 ; ALetter # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAE
D7CB..D7FB ; ALetter # Lo [49] HANGUL JONGSEONG NIEUN-RIEUL..HANGUL JONGSEONG PHIEUPH-THIEUTH
FB00..FB06 ; ALetter # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FB13..FB17 ; ALetter # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
-FB1D ; ALetter # Lo HEBREW LETTER YOD WITH HIRIQ
-FB1F..FB28 ; ALetter # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV
-FB2A..FB36 ; ALetter # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH
-FB38..FB3C ; ALetter # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH
-FB3E ; ALetter # Lo HEBREW LETTER MEM WITH DAGESH
-FB40..FB41 ; ALetter # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH
-FB43..FB44 ; ALetter # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
-FB46..FBB1 ; ALetter # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
+FB50..FBB1 ; ALetter # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBD3..FD3D ; ALetter # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
FD50..FD8F ; ALetter # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
FD92..FDC7 ; ALetter # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
@@ -913,12 +934,13 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1EEA5..1EEA9 ; ALetter # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
1EEAB..1EEBB ; ALetter # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
-# Total code points: 24941
+# Total code points: 24867
# ================================================
003A ; MidLetter # Po COLON
00B7 ; MidLetter # Po MIDDLE DOT
+02D7 ; MidLetter # Sk MODIFIER LETTER MINUS SIGN
0387 ; MidLetter # Po GREEK ANO TELEIA
05F4 ; MidLetter # Po HEBREW PUNCTUATION GERSHAYIM
2027 ; MidLetter # Po HYPHENATION POINT
@@ -926,7 +948,7 @@ FE13 ; MidLetter # Po PRESENTATION FORM FOR VERTICAL COLON
FE55 ; MidLetter # Po SMALL COLON
FF1A ; MidLetter # Po FULLWIDTH COLON
-# Total code points: 8
+# Total code points: 9
# ================================================
@@ -949,7 +971,6 @@ FF1B ; MidNum # Po FULLWIDTH SEMICOLON
# ================================================
-0027 ; MidNumLet # Po APOSTROPHE
002E ; MidNumLet # Po FULL STOP
2018 ; MidNumLet # Pi LEFT SINGLE QUOTATION MARK
2019 ; MidNumLet # Pf RIGHT SINGLE QUOTATION MARK
@@ -958,7 +979,7 @@ FE52 ; MidNumLet # Po SMALL FULL STOP
FF07 ; MidNumLet # Po FULLWIDTH APOSTROPHE
FF0E ; MidNumLet # Po FULLWIDTH FULL STOP
-# Total code points: 8
+# Total code points: 7
# ================================================