summaryrefslogtreecommitdiffstats
path: root/util/unicode/data/LineBreak.txt
diff options
context:
space:
mode:
Diffstat (limited to 'util/unicode/data/LineBreak.txt')
-rw-r--r--util/unicode/data/LineBreak.txt30
1 files changed, 20 insertions, 10 deletions
diff --git a/util/unicode/data/LineBreak.txt b/util/unicode/data/LineBreak.txt
index e309836b0e..8a72cabf78 100644
--- a/util/unicode/data/LineBreak.txt
+++ b/util/unicode/data/LineBreak.txt
@@ -1,5 +1,5 @@
-# LineBreak-6.2.0.txt
-# Date: 2012-08-08, 19:26:00 GMT [KW]
+# LineBreak-6.3.0.txt
+# Date: 2013-02-06, 19:45:00 GMT [KW, LI]
#
# Line Break Properties
#
@@ -7,12 +7,12 @@
# Unicode Character Database.
# It contains both normative and informative data.
#
-# 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
#
# The format is two fields separated by a semicolon.
# Field 0: Unicode value
-# Field 1: LineBreak property, consisting of one of the following values:
+# Field 1: Line_Break property, consisting of one of the following values:
# Normative:
# "BK", "CR", "LF", "CM", "SG", "GL", "CB", "SP", "ZW",
# "NL", "WJ", "JL", "JV", "JT", "H2", "H3"
@@ -20,27 +20,31 @@
# "XX", "OP", "CL", "CP", "QU", "NS", "EX", "SY",
# "IS", "PR", "PO", "NU", "AL", "ID", "IN", "HY",
# "BB", "BA", "SA", "AI", "B2", "HL", "CJ", "RI"
-# - All code points, assigned and unassigned, that are not listed
+# - All code points, assigned and unassigned, that are not listed
# explicitly are given the value "XX".
# The unassigned code points that default to "ID" include ranges in the
# following blocks:
# CJK Unified Ideographs Extension A: U+3400..U+4DBF
# CJK Unified Ideographs: U+4E00..U+9FFF
# CJK Compatibility Ideographs: U+F900..U+FAFF
-# CJK Unified Ideographs Extension B: U+20000..U+2A6DF
+# CJK Unified Ideographs Extension B: U+20000..U+2A6DF
# CJK Unified Ideographs Extension C: U+2A700..U+2B73F
# CJK Unified Ideographs Extension D: U+2B740..U+2B81F
# CJK Compatibility Ideographs Supplement: U+2F800..U+2FA1F
# and any other reserved code points on
# Planes 2 and 3: U+20000..U+2FFFD
# U+30000..U+3FFFD
-# - Characters ranges are specified as for other property files in
+# The unassigned code points that default to "PR" comprise a range in the
+# following block:
+# Currency Symbols: U+20A0..U+20CF
+# - Character ranges are specified as for other property files in
# the Unicode Character Database.
#
# The Unicode name of each character is provided in a comment for help
# in identifying the characters.
#
-# See UAX #14: Unicode Line Breaking Algorithm, for more information
+# For more information, see UAX #14: Unicode Line Breaking Algorithm,
+# at http://www.unicode.org/reports/tr14/
#
# @missing: 0000..10FFFF; XX
0000;CM # <control>
@@ -1554,6 +1558,7 @@
0619;CM # ARABIC SMALL DAMMA
061A;CM # ARABIC SMALL KASRA
061B;EX # ARABIC SEMICOLON
+061C;CM # ARABIC LETTER MARK
061E;EX # ARABIC TRIPLE DOT PUNCTUATION MARK
061F;EX # ARABIC QUESTION MARK
0620;AL # ARABIC LETTER KASHMIRI YEH
@@ -7161,6 +7166,10 @@
2062;AL # INVISIBLE TIMES
2063;AL # INVISIBLE SEPARATOR
2064;AL # INVISIBLE PLUS
+2066;CM # LEFT-TO-RIGHT ISOLATE
+2067;CM # RIGHT-TO-LEFT ISOLATE
+2068;CM # FIRST STRONG ISOLATE
+2069;CM # POP DIRECTIONAL ISOLATE
206A;CM # INHIBIT SYMMETRIC SWAPPING
206B;CM # ACTIVATE SYMMETRIC SWAPPING
206C;CM # INHIBIT ARABIC FORM SHAPING
@@ -7236,6 +7245,7 @@
20B8;PR # TENGE SIGN
20B9;PR # INDIAN RUPEE SIGN
20BA;PR # TURKISH LIRA SIGN
+20BB..20CF;PR # <reserved-20BB>..<reserved-20CF>
20D0;CM # COMBINING LEFT HARPOON ABOVE
20D1;CM # COMBINING RIGHT HARPOON ABOVE
20D2;CM # COMBINING LONG VERTICAL LINE OVERLAY
@@ -10711,7 +10721,7 @@
2FF9;ID # IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER RIGHT
2FFA;ID # IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT
2FFB;ID # IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
-3000;ID # IDEOGRAPHIC SPACE
+3000;BA # IDEOGRAPHIC SPACE
3001;CL # IDEOGRAPHIC COMMA
3002;CL # IDEOGRAPHIC FULL STOP
3003;ID # DITTO MARK
@@ -10764,7 +10774,7 @@
3032;ID # VERTICAL KANA REPEAT WITH VOICED SOUND MARK
3033;ID # VERTICAL KANA REPEAT MARK UPPER HALF
3034;ID # VERTICAL KANA REPEAT WITH VOICED SOUND MARK UPPER HALF
-3035;ID # VERTICAL KANA REPEAT MARK LOWER HALF
+3035;CM # VERTICAL KANA REPEAT MARK LOWER HALF
3036;ID # CIRCLED POSTAL MARK
3037;ID # IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL
3038;ID # HANGZHOU NUMERAL TEN