Update UCD source files up to Unicode 6.3.0

Change-Id: I9ab58a659af1e758b172a24aa95bce1fea89c33d
Reviewed-by: Lars Knoll <lars.knoll@digia.com>

tests/auto/corelib/tools/qchar/data/NormalizationTest.txt

@@ -1,8 +1,8 @@
-# NormalizationTest-6.2.0.txt
+# NormalizationTest-6.3.0.txt
-# Date: 2012-08-14, 17:54:58 GMT [MD]
+# Date: 2012-12-20, 22:18:30 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/
 #

tests/auto/corelib/tools/qtextboundaryfinder/data/GraphemeBreakTest.txt

@@ -1,8 +1,8 @@
-# GraphemeBreakTest-6.2.0.txt
+# GraphemeBreakTest-6.3.0.txt
-# Date: 2012-08-22, 12:41:15 GMT [MD]
+# Date: 2012-12-20, 22:18:29 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/
 #

tests/auto/corelib/tools/qtextboundaryfinder/data/LineBreakTest.txt

@@ -1,8 +1,8 @@
-# LineBreakTest-6.2.0.txt
+# LineBreakTest-6.3.0.txt
-# Date: 2012-08-22, 12:41:17 GMT [MD]
+# Date: 2012-12-20, 22:18:30 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/
 #
@@ -6214,7 +6214,7 @@
 × 3067 ÷ 4F7F ÷	#  × [0.3] HIRAGANA LETTER DE (ID) ÷ [999.0] CJK UNIFIED IDEOGRAPH-4F7F (ID) ÷ [0.3]
 × 3059 ÷ 308B ÷	#  × [0.3] HIRAGANA LETTER SU (ID) ÷ [999.0] HIRAGANA LETTER RU (ID) ÷ [0.3]
 × 306E ÷ 30D1 ÷ 30F3 ÷	#  × [0.3] HIRAGANA LETTER NO (ID) ÷ [999.0] KATAKANA LETTER PA (ID) ÷ [999.0] KATAKANA LETTER N (ID) ÷ [0.3]
-× 3046 ÷ 3000 ÷ 3048 ÷ 3000 ÷ 304A × 300D ÷	#  × [0.3] HIRAGANA LETTER U (ID) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] HIRAGANA LETTER E (ID) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] HIRAGANA LETTER O (ID) × [13.02] RIGHT CORNER BRACKET (CL) ÷ [0.3]
+× 3046 × 3000 ÷ 3048 × 3000 ÷ 304A × 300D ÷	#  × [0.3] HIRAGANA LETTER U (ID) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] HIRAGANA LETTER E (ID) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] HIRAGANA LETTER O (ID) × [13.02] RIGHT CORNER BRACKET (CL) ÷ [0.3]
 × 308B × 0020 ÷ C740 ÷ C601 × 0020 ÷ 306B ÷	#  × [0.3] HIRAGANA LETTER RU (ID) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE EUN (H3) ÷ [999.0] HANGUL SYLLABLE YEONG (H3) × [7.01] SPACE (SP) ÷ [18.0] HIRAGANA LETTER NI (ID) ÷ [0.3]
 × 3057 × 3087 ÷ 3046 × 3002 ÷	#  × [0.3] HIRAGANA LETTER SI (ID) × [21.03] HIRAGANA LETTER SMALL YO (CJ_NS) ÷ [999.0] HIRAGANA LETTER U (ID) × [13.02] IDEOGRAPHIC FULL STOP (CL) ÷ [0.3]
 × 30E0 ÷ 306E ÷ 4E00 ÷	#  × [0.3] KATAKANA LETTER MU (ID) ÷ [999.0] HIRAGANA LETTER NO (ID) ÷ [999.0] CJK UNIFIED IDEOGRAPH-4E00 (ID) ÷ [0.3]
@@ -6226,15 +6226,15 @@
 × 0061 × 002E ÷ 0032 × 0020 ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [7.01] SPACE (SP) ÷ [0.3]
 × 0061 × 002E ÷ 0032 × 0020 ÷ 0915 ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [7.01] SPACE (SP) ÷ [18.0] DEVANAGARI LETTER KA (AL) ÷ [0.3]
 × 0061 × 002E ÷ 0032 × 0020 ÷ 672C ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [7.01] SPACE (SP) ÷ [18.0] CJK UNIFIED IDEOGRAPH-672C (ID) ÷ [0.3]
-× 0061 × 002E ÷ 0032 ÷ 3000 ÷ 672C ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] CJK UNIFIED IDEOGRAPH-672C (ID) ÷ [0.3]
+× 0061 × 002E ÷ 0032 × 3000 ÷ 672C ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] CJK UNIFIED IDEOGRAPH-672C (ID) ÷ [0.3]
-× 0061 × 002E ÷ 0032 ÷ 3000 ÷ 307E ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] HIRAGANA LETTER MA (ID) ÷ [0.3]
+× 0061 × 002E ÷ 0032 × 3000 ÷ 307E ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] HIRAGANA LETTER MA (ID) ÷ [0.3]
-× 0061 × 002E ÷ 0032 ÷ 3000 ÷ 0033 ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] DIGIT THREE (NU) ÷ [0.3]
+× 0061 × 002E ÷ 0032 × 3000 ÷ 0033 ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] DIGIT THREE (NU) ÷ [0.3]
 × 0061 × 0062 × 002E × 0020 ÷ 0032 ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER B (AL) × [13.02] FULL STOP (IS) × [7.01] SPACE (SP) ÷ [18.0] DIGIT TWO (NU) ÷ [0.3]
 × 0041 × 002E ÷ 0031 × 0020 ÷ BABB ÷	#  × [0.3] LATIN CAPITAL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT ONE (NU) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE MOS (H3) ÷ [0.3]
 × BD24 ÷ C5B4 × 002E × 0020 ÷ 0041 × 002E ÷ 0032 × 0020 ÷ BCFC ÷	#  × [0.3] HANGUL SYLLABLE BWASS (H3) ÷ [999.0] HANGUL SYLLABLE EO (H2) × [13.02] FULL STOP (IS) × [7.01] SPACE (SP) ÷ [18.0] LATIN CAPITAL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE BOL (H3) ÷ [0.3]
 × BD10 ÷ C694 × 002E × 0020 ÷ 0041 × 002E ÷ 0033 × 0020 ÷ BABB ÷	#  × [0.3] HANGUL SYLLABLE BWA (H2) ÷ [999.0] HANGUL SYLLABLE YO (H2) × [13.02] FULL STOP (IS) × [7.01] SPACE (SP) ÷ [18.0] LATIN CAPITAL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT THREE (NU) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE MOS (H3) ÷ [0.3]
 × C694 × 002E × 0020 ÷ 0041 × 002E ÷ 0034 × 0020 ÷ BABB ÷	#  × [0.3] HANGUL SYLLABLE YO (H2) × [13.02] FULL STOP (IS) × [7.01] SPACE (SP) ÷ [18.0] LATIN CAPITAL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT FOUR (NU) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE MOS (H3) ÷ [0.3]
-× 0061 × 002E ÷ 0032 ÷ 3000 ÷ 300C ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) ÷ [0.3]
+× 0061 × 002E ÷ 0032 × 3000 ÷ 300C ÷	#  × [0.3] LATIN SMALL LETTER A (AL) × [13.02] FULL STOP (IS) ÷ [999.0] DIGIT TWO (NU) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] LEFT CORNER BRACKET (OP) ÷ [0.3]
 × 306B ÷ 300C × 30D0 ÷ 0028 × 0062 × 0061 × 0029 × 300D ÷ 3084 ÷ 300C × 30B9 ÷	#  × [0.3] HIRAGANA LETTER NI (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] KATAKANA LETTER BA (ID) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] LATIN SMALL LETTER B (AL) × [28.0] LATIN SMALL LETTER A (AL) × [13.02] RIGHT PARENTHESIS (CP) × [13.02] RIGHT CORNER BRACKET (CL) ÷ [999.0] HIRAGANA LETTER YA (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] KATAKANA LETTER SU (ID) ÷ [0.3]
 × 308B ÷ 300C × 0055 × 004B ÷ 30DD ÷ 30F3 ÷ 30C9 × 300D × FF09 × 3001 ÷ 30A8 ÷	#  × [0.3] HIRAGANA LETTER RU (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] LATIN CAPITAL LETTER U (AL) × [28.0] LATIN CAPITAL LETTER K (AL) ÷ [999.0] KATAKANA LETTER PO (ID) ÷ [999.0] KATAKANA LETTER N (ID) ÷ [999.0] KATAKANA LETTER DO (ID) × [13.02] RIGHT CORNER BRACKET (CL) × [13.02] FULLWIDTH RIGHT PARENTHESIS (CL) × [13.02] IDEOGRAPHIC COMMA (CL) ÷ [999.0] KATAKANA LETTER E (ID) ÷ [0.3]
 × 306F × 3001 ÷ 300C × 003D × 0072 × 0061 × 006E × 0064 × 0028 × 0029 × 300D ÷ 3068 ÷	#  × [0.3] HIRAGANA LETTER HA (ID) × [13.02] IDEOGRAPHIC COMMA (CL) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] EQUALS SIGN (AL) × [28.0] LATIN SMALL LETTER R (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER N (AL) × [28.0] LATIN SMALL LETTER D (AL) × [30.01] LEFT PARENTHESIS (OP) × [13.02] RIGHT PARENTHESIS (CP) × [13.02] RIGHT CORNER BRACKET (CL) ÷ [999.0] HIRAGANA LETTER TO (ID) ÷ [0.3]
@@ -6243,7 +6243,7 @@
 × 3066 ÷ 300C × BD24 ÷ C5B4 × 003F × 300D ÷ 3068 ÷	#  × [0.3] HIRAGANA LETTER TE (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] HANGUL SYLLABLE BWASS (H3) ÷ [999.0] HANGUL SYLLABLE EO (H2) × [13.01] QUESTION MARK (EX) × [13.02] RIGHT CORNER BRACKET (CL) ÷ [999.0] HIRAGANA LETTER TO (ID) ÷ [0.3]
 × 306E ÷ 300C × 305D ÷	#  × [0.3] HIRAGANA LETTER NO (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] HIRAGANA LETTER SO (ID) ÷ [0.3]
 × 306F ÷ 300C × 30A8 ÷	#  × [0.3] HIRAGANA LETTER HA (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] KATAKANA LETTER E (ID) ÷ [0.3]
-× 4F8B × FF1A ÷ 300C × 3042 ÷ 3000 ÷ 3044 ÷	#  × [0.3] CJK UNIFIED IDEOGRAPH-4F8B (ID) × [21.03] FULLWIDTH COLON (NS) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] HIRAGANA LETTER A (ID) ÷ [999.0] IDEOGRAPHIC SPACE (ID) ÷ [999.0] HIRAGANA LETTER I (ID) ÷ [0.3]
+× 4F8B × FF1A ÷ 300C × 3042 × 3000 ÷ 3044 ÷	#  × [0.3] CJK UNIFIED IDEOGRAPH-4F8B (ID) × [21.03] FULLWIDTH COLON (NS) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] HIRAGANA LETTER A (ID) × [21.01] IDEOGRAPHIC SPACE (BA) ÷ [999.0] HIRAGANA LETTER I (ID) ÷ [0.3]
 × 304F × 3001 ÷ 300C × D3C9 ÷ C591 ÷ C740 ÷	#  × [0.3] HIRAGANA LETTER KU (ID) × [13.02] IDEOGRAPHIC COMMA (CL) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] HANGUL SYLLABLE PYEONG (H3) ÷ [999.0] HANGUL SYLLABLE YANG (H3) ÷ [999.0] HANGUL SYLLABLE EUN (H3) ÷ [0.3]
 × 306B ÷ 300C × C81C ÷ BAA9 ÷ 0028 × 984C ÷ 540D × 0029 ÷ C740 ÷	#  × [0.3] HIRAGANA LETTER NI (ID) ÷ [999.0] LEFT CORNER BRACKET (OP) × [14.0] HANGUL SYLLABLE JE (H2) ÷ [999.0] HANGUL SYLLABLE MOG (H3) ÷ [999.0] LEFT PARENTHESIS (OP) × [14.0] CJK UNIFIED IDEOGRAPH-984C (ID) ÷ [999.0] CJK UNIFIED IDEOGRAPH-540D (ID) × [13.02] RIGHT PARENTHESIS (CP) ÷ [999.0] HANGUL SYLLABLE EUN (H3) ÷ [0.3]
 × 5178 ÷ 300E × 30A6 × 30A3 ÷ 30AD ÷	#  × [0.3] CJK UNIFIED IDEOGRAPH-5178 (ID) ÷ [999.0] LEFT WHITE CORNER BRACKET (OP) × [14.0] KATAKANA LETTER U (ID) × [21.03] KATAKANA LETTER SMALL I (CJ_NS) ÷ [999.0] KATAKANA LETTER KI (ID) ÷ [0.3]

tests/auto/corelib/tools/qtextboundaryfinder/data/SentenceBreakTest.txt

@@ -1,8 +1,8 @@
-# SentenceBreakTest-6.2.0.txt
+# SentenceBreakTest-6.3.0.txt
-# Date: 2012-08-22, 12:41:18 GMT [MD]
+# Date: 2012-12-20, 22:18:42 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/
 #

util/unicode/data/ArabicShaping.txt

@@ -1,5 +1,5 @@
-# ArabicShaping-6.2.0.txt
+# ArabicShaping-6.3.0.txt
-# Date: 2012-05-15, 21:05:00 GMT [KW]
+# Date: 2012-11-14, 21:48:00 GMT [KW]
 #
 # This file is a normative contributory data file in the
 # Unicode Character Database.
@@ -11,15 +11,19 @@
 # property values for Arabic, Syriac, N'Ko, and Mandaic
 # positional shaping, repeating in machine readable form the
 # information exemplified in Tables 8-3, 8-8, 8-9, 8-10, 8-13, 8-14,
-# 8-15, 13-5, 14-5, and 14-6 of The Unicode Standard, Version 6.2.
+# 8-15, 13-5, 14-5, and 14-6 of The Unicode Standard, Version 6.3.
+# This file also defines Joining_Type values for Mongolian and
+# Phags-pa positional shaping, which is not listed in tables in
+# the standard. 
 #
-# See sections 8.2, 8.3, 13.5, and 14.12 of The Unicode Standard, 
+# See sections 8.2, 8.3, 10.4, 13.2, 13.5, and 14.12 of The Unicode Standard, 
-# Version 6.2 for more information.
+# Version 6.3 for more information.
 #
 # Each line contains four fields, separated by a semicolon.
 #
 # Field 0: the code point, in 4-digit hexadecimal
-#   form, of an Arabic, Syriac, N'Ko, or Mandaic character.
+#   form, of an Arabic, Syriac, N'Ko, Mandaic, Mongolian,
+#   Phags-pa, or other character.
 #
 # Field 1: gives a short schematic name for that character.
 #   The schematic name is descriptive of the shape, based as
@@ -35,7 +39,13 @@
 #   C Join_Causing
 #   U Non_Joining
 #   T Transparent
-#     See Section 8.2, Arabic for more information on these types.
+#
+# See Section 8.2, Arabic for more information on these joining types.
+# Note that for cursive joining scripts which are typically rendered
+# top-to-bottom, rather than right-to-left, Joining_Type=L conventionally
+# refers to bottom joining, and Joining_Type=R conventionally refers
+# to top joining. See Section 10.4 Phags-pa for more information on the
+# interpretation of joining types in vertical layout.
 #
 # Field 3: defines the joining group (property name: Joining_Group)
 #
@@ -68,8 +78,9 @@
 # to jg=No_Joining_Group in this data file. Other, more specific
 # joining group values will be defined only if an explicit proposal
 # to define those values exactly has been approved by the UTC. This
-# is the convention exemplified by the N'Ko and Mandaic scripts. Only the Arabic
+# is the convention exemplified by the N'Ko, Mandaic, Mongolian,
-# and Syriac scripts currently have explicit joining group values defined.
+# and Phags-pa scripts. Only the Arabic and Syriac scripts
+# currently have explicit joining group values defined.
 #
 # Note: Code points that are not explicitly listed in this file are
 # either of joining type T or U:
@@ -81,8 +92,6 @@
 # For an explicit listing of characters of joining type T, see
 # the derived property file DerivedJoiningType.txt.
 #
-# There are currently no characters of joining type L defined in Unicode.
-#
 # #############################################################
  
 # Unicode; Schematic Name; Joining Type; Joining Group
@@ -417,9 +426,205 @@
 08AB; WAW WITH DOT WITHIN; R; WAW
 08AC; ROHINGYA YEH; R; ROHINGYA YEH
 
+# Mongolian Characters
+
+1806; MONGOLIAN TODO SOFT HYPHEN; U; No_Joining_Group
+1807; MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER; D; No_Joining_Group
+180A; MONGOLIAN NIRUGU; C; No_Joining_Group
+180E; MONGOLIAN VOWEL SEPARATOR; U; No_Joining_Group
+1820; MONGOLIAN A; D; No_Joining_Group
+1821; MONGOLIAN E; D; No_Joining_Group
+1822; MONGOLIAN I; D; No_Joining_Group
+1823; MONGOLIAN O; D; No_Joining_Group
+1824; MONGOLIAN U; D; No_Joining_Group
+1825; MONGOLIAN OE; D; No_Joining_Group
+1826; MONGOLIAN UE; D; No_Joining_Group
+1827; MONGOLIAN EE; D; No_Joining_Group
+1828; MONGOLIAN NA; D; No_Joining_Group
+1829; MONGOLIAN ANG; D; No_Joining_Group
+182A; MONGOLIAN BA; D; No_Joining_Group
+182B; MONGOLIAN PA; D; No_Joining_Group
+182C; MONGOLIAN QA; D; No_Joining_Group
+182D; MONGOLIAN GA; D; No_Joining_Group
+182E; MONGOLIAN MA; D; No_Joining_Group
+182F; MONGOLIAN LA; D; No_Joining_Group
+1830; MONGOLIAN SA; D; No_Joining_Group
+1831; MONGOLIAN SHA; D; No_Joining_Group
+1832; MONGOLIAN TA; D; No_Joining_Group
+1833; MONGOLIAN DA; D; No_Joining_Group
+1834; MONGOLIAN CHA; D; No_Joining_Group
+1835; MONGOLIAN JA; D; No_Joining_Group
+1836; MONGOLIAN YA; D; No_Joining_Group
+1837; MONGOLIAN RA; D; No_Joining_Group
+1838; MONGOLIAN WA; D; No_Joining_Group
+1839; MONGOLIAN FA; D; No_Joining_Group
+183A; MONGOLIAN KA; D; No_Joining_Group
+183B; MONGOLIAN KHA; D; No_Joining_Group
+183C; MONGOLIAN TSA; D; No_Joining_Group
+183D; MONGOLIAN ZA; D; No_Joining_Group
+183E; MONGOLIAN HAA; D; No_Joining_Group
+183F; MONGOLIAN ZRA; D; No_Joining_Group
+1840; MONGOLIAN LHA; D; No_Joining_Group
+1841; MONGOLIAN ZHI; D; No_Joining_Group
+1842; MONGOLIAN CHI; D; No_Joining_Group
+1843; MONGOLIAN TODO LONG VOWEL SIGN; D; No_Joining_Group
+1844; MONGOLIAN TODO E; D; No_Joining_Group
+1845; MONGOLIAN TODO I; D; No_Joining_Group
+1846; MONGOLIAN TODO O; D; No_Joining_Group
+1847; MONGOLIAN TODO U; D; No_Joining_Group
+1848; MONGOLIAN TODO OE; D; No_Joining_Group
+1849; MONGOLIAN TODO UE; D; No_Joining_Group
+184A; MONGOLIAN TODO ANG; D; No_Joining_Group
+184B; MONGOLIAN TODO BA; D; No_Joining_Group
+184C; MONGOLIAN TODO PA; D; No_Joining_Group
+184D; MONGOLIAN TODO QA; D; No_Joining_Group
+184E; MONGOLIAN TODO GA; D; No_Joining_Group
+184F; MONGOLIAN TODO MA; D; No_Joining_Group
+1850; MONGOLIAN TODO TA; D; No_Joining_Group
+1851; MONGOLIAN TODO DA; D; No_Joining_Group
+1852; MONGOLIAN TODO CHA; D; No_Joining_Group
+1853; MONGOLIAN TODO JA; D; No_Joining_Group
+1854; MONGOLIAN TODO TSA; D; No_Joining_Group
+1855; MONGOLIAN TODO YA; D; No_Joining_Group
+1856; MONGOLIAN TODO WA; D; No_Joining_Group
+1857; MONGOLIAN TODO KA; D; No_Joining_Group
+1858; MONGOLIAN TODO GAA; D; No_Joining_Group
+1859; MONGOLIAN TODO HAA; D; No_Joining_Group
+185A; MONGOLIAN TODO JIA; D; No_Joining_Group
+185B; MONGOLIAN TODO NIA; D; No_Joining_Group
+185C; MONGOLIAN TODO DZA; D; No_Joining_Group
+185D; MONGOLIAN SIBE E; D; No_Joining_Group
+185E; MONGOLIAN SIBE I; D; No_Joining_Group
+185F; MONGOLIAN SIBE IY; D; No_Joining_Group
+1860; MONGOLIAN SIBE UE; D; No_Joining_Group
+1861; MONGOLIAN SIBE U; D; No_Joining_Group
+1862; MONGOLIAN SIBE ANG; D; No_Joining_Group
+1863; MONGOLIAN SIBE KA; D; No_Joining_Group
+1864; MONGOLIAN SIBE GA; D; No_Joining_Group
+1865; MONGOLIAN SIBE HA; D; No_Joining_Group
+1866; MONGOLIAN SIBE PA; D; No_Joining_Group
+1867; MONGOLIAN SIBE SHA; D; No_Joining_Group
+1868; MONGOLIAN SIBE TA; D; No_Joining_Group
+1869; MONGOLIAN SIBE DA; D; No_Joining_Group
+186A; MONGOLIAN SIBE JA; D; No_Joining_Group
+186B; MONGOLIAN SIBE FA; D; No_Joining_Group
+186C; MONGOLIAN SIBE GAA; D; No_Joining_Group
+186D; MONGOLIAN SIBE HAA; D; No_Joining_Group
+186E; MONGOLIAN SIBE TSA; D; No_Joining_Group
+186F; MONGOLIAN SIBE ZA; D; No_Joining_Group
+1870; MONGOLIAN SIBE RAA; D; No_Joining_Group
+1871; MONGOLIAN SIBE CHA; D; No_Joining_Group
+1872; MONGOLIAN SIBE ZHA; D; No_Joining_Group
+1873; MONGOLIAN MANCHU I; D; No_Joining_Group
+1874; MONGOLIAN MANCHU KA; D; No_Joining_Group
+1875; MONGOLIAN MANCHU RA; D; No_Joining_Group
+1876; MONGOLIAN MANCHU FA; D; No_Joining_Group
+1877; MONGOLIAN MANCHU ZHA; D; No_Joining_Group
+1880; MONGOLIAN ALI GALI ANUSVARA ONE; U; No_Joining_Group
+1881; MONGOLIAN ALI GALI VISARGA ONE; U; No_Joining_Group
+1882; MONGOLIAN ALI GALI DAMARU; U; No_Joining_Group
+1883; MONGOLIAN ALI GALI UBADAMA; U; No_Joining_Group
+1884; MONGOLIAN ALI GALI INVERTED UBADAMA; U; No_Joining_Group
+1885; MONGOLIAN ALI GALI BALUDA; U; No_Joining_Group
+1886; MONGOLIAN ALI GALI THREE BALUDA; U; No_Joining_Group
+1887; MONGOLIAN ALI GALI A; D; No_Joining_Group
+1888; MONGOLIAN ALI GALI I; D; No_Joining_Group
+1889; MONGOLIAN ALI GALI KA; D; No_Joining_Group
+188A; MONGOLIAN ALI GALI NGA; D; No_Joining_Group
+188B; MONGOLIAN ALI GALI CA; D; No_Joining_Group
+188C; MONGOLIAN ALI GALI TTA; D; No_Joining_Group
+188D; MONGOLIAN ALI GALI TTHA; D; No_Joining_Group
+188E; MONGOLIAN ALI GALI DDA; D; No_Joining_Group
+188F; MONGOLIAN ALI GALI NNA; D; No_Joining_Group
+1890; MONGOLIAN ALI GALI TA; D; No_Joining_Group
+1891; MONGOLIAN ALI GALI DA; D; No_Joining_Group
+1892; MONGOLIAN ALI GALI PA; D; No_Joining_Group
+1893; MONGOLIAN ALI GALI PHA; D; No_Joining_Group
+1894; MONGOLIAN ALI GALI SSA; D; No_Joining_Group
+1895; MONGOLIAN ALI GALI ZHA; D; No_Joining_Group
+1896; MONGOLIAN ALI GALI ZA; D; No_Joining_Group
+1897; MONGOLIAN ALI GALI AH; D; No_Joining_Group
+1898; MONGOLIAN TODO ALI GALI TA; D; No_Joining_Group
+1899; MONGOLIAN TODO ALI GALI ZHA; D; No_Joining_Group
+189A; MONGOLIAN MANCHU ALI GALI GHA; D; No_Joining_Group
+189B; MONGOLIAN MANCHU ALI GALI NGA; D; No_Joining_Group
+189C; MONGOLIAN MANCHU ALI GALI CA; D; No_Joining_Group
+189D; MONGOLIAN MANCHU ALI GALI JHA; D; No_Joining_Group
+189E; MONGOLIAN MANCHU ALI GALI TTA; D; No_Joining_Group
+189F; MONGOLIAN MANCHU ALI GALI DDHA; D; No_Joining_Group
+18A0; MONGOLIAN MANCHU ALI GALI TA; D; No_Joining_Group
+18A1; MONGOLIAN MANCHU ALI GALI DHA; D; No_Joining_Group
+18A2; MONGOLIAN MANCHU ALI GALI SSA; D; No_Joining_Group
+18A3; MONGOLIAN MANCHU ALI GALI CYA; D; No_Joining_Group
+18A4; MONGOLIAN MANCHU ALI GALI ZHA; D; No_Joining_Group
+18A5; MONGOLIAN MANCHU ALI GALI ZA; D; No_Joining_Group
+18A6; MONGOLIAN ALI GALI HALF U; D; No_Joining_Group
+18A7; MONGOLIAN ALI GALI HALF YA; D; No_Joining_Group
+18A8; MONGOLIAN MANCHU ALI GALI BHA; D; No_Joining_Group
+18AA; MONGOLIAN MANCHU ALI GALI LHA; D; No_Joining_Group
+
 # Other
 
 200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
 200D; ZERO WIDTH JOINER; C; No_Joining_Group
+2066; LEFT-TO-RIGHT ISOLATE; U; No_Joining_Group
+2067; RIGHT-TO-LEFT ISOLATE; U; No_Joining_Group
+2068; FIRST STRONG ISOLATE; U; No_Joining_Group
+2069; POP DIRECTIONAL ISOLATE; U; No_Joining_Group
+
+# Phags-Pa Characters
+
+A840; PHAGS-PA KA; D; No_Joining_Group
+A841; PHAGS-PA KHA; D; No_Joining_Group
+A842; PHAGS-PA GA; D; No_Joining_Group
+A843; PHAGS-PA NGA; D; No_Joining_Group
+A844; PHAGS-PA CA; D; No_Joining_Group
+A845; PHAGS-PA CHA; D; No_Joining_Group
+A846; PHAGS-PA JA; D; No_Joining_Group
+A847; PHAGS-PA NYA; D; No_Joining_Group
+A848; PHAGS-PA TA; D; No_Joining_Group
+A849; PHAGS-PA THA; D; No_Joining_Group
+A84A; PHAGS-PA DA; D; No_Joining_Group
+A84B; PHAGS-PA NA; D; No_Joining_Group
+A84C; PHAGS-PA PA; D; No_Joining_Group
+A84D; PHAGS-PA PHA; D; No_Joining_Group
+A84E; PHAGS-PA BA; D; No_Joining_Group
+A84F; PHAGS-PA MA; D; No_Joining_Group
+A850; PHAGS-PA TSA; D; No_Joining_Group
+A851; PHAGS-PA TSHA; D; No_Joining_Group
+A852; PHAGS-PA DZA; D; No_Joining_Group
+A853; PHAGS-PA WA; D; No_Joining_Group
+A854; PHAGS-PA ZHA; D; No_Joining_Group
+A855; PHAGS-PA ZA; D; No_Joining_Group
+A856; PHAGS-PA SMALL A; D; No_Joining_Group
+A857; PHAGS-PA YA; D; No_Joining_Group
+A858; PHAGS-PA RA; D; No_Joining_Group
+A859; PHAGS-PA LA; D; No_Joining_Group
+A85A; PHAGS-PA SHA; D; No_Joining_Group
+A85B; PHAGS-PA SA; D; No_Joining_Group
+A85C; PHAGS-PA HA; D; No_Joining_Group
+A85D; PHAGS-PA A; D; No_Joining_Group
+A85E; PHAGS-PA I; D; No_Joining_Group
+A85F; PHAGS-PA U; D; No_Joining_Group
+A860; PHAGS-PA E; D; No_Joining_Group
+A861; PHAGS-PA O; D; No_Joining_Group
+A862; PHAGS-PA QA; D; No_Joining_Group
+A863; PHAGS-PA XA; D; No_Joining_Group
+A864; PHAGS-PA FA; D; No_Joining_Group
+A865; PHAGS-PA GGA; D; No_Joining_Group
+A866; PHAGS-PA EE; D; No_Joining_Group
+A867; PHAGS-PA SUBJOINED WA; D; No_Joining_Group
+A868; PHAGS-PA SUBJOINED YA; D; No_Joining_Group
+A869; PHAGS-PA TTA; D; No_Joining_Group
+A86A; PHAGS-PA TTHA; D; No_Joining_Group
+A86B; PHAGS-PA DDA; D; No_Joining_Group
+A86C; PHAGS-PA NNA; D; No_Joining_Group
+A86D; PHAGS-PA ALTERNATE YA; D; No_Joining_Group
+A86E; PHAGS-PA VOICELESS SHA; D; No_Joining_Group
+A86F; PHAGS-PA VOICED HA; D; No_Joining_Group
+A870; PHAGS-PA ASPIRATED FA; D; No_Joining_Group
+A871; PHAGS-PA SUBJOINED RA; D; No_Joining_Group
+A872; PHAGS-PA SUPERFIXED RA; L; No_Joining_Group
+A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group
 
 # EOF

util/unicode/data/BidiMirroring.txt

@@ -1,19 +1,19 @@
-# BidiMirroring-6.2.0.txt
+# BidiMirroring-6.3.0.txt
-# Date: 2012-05-15, 24:19:00 GMT [KW, LI]
+# Date: 2013-02-12, 08:20:00 GMT [KW, LI]
 #
 # Bidi_Mirroring_Glyph Property
 # 
 # This file is an informative contributory data file in the
 # 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
 #
 # This data file lists characters that have the Bidi_Mirrored=Yes property
 # value, for which there is another Unicode character that typically has a glyph
 # that is the mirror image of the original character's glyph.
 #
-# The repertoire covered by the file is Unicode 6.2.0.
+# The repertoire covered by the file is Unicode 6.3.0.
 # 
 # The file contains a list of lines with mappings from one code point
 # to another one for character-based mirroring.
@@ -42,7 +42,7 @@
 # 
 # This file was originally created by Markus Scherer.
 # Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler,
-# and for Unicode 6.1 and 6.2 by Ken Whistler and Laurentiu Iancu.
+# and for Unicode 6.1, 6.2, and 6.3 by Ken Whistler and Laurentiu Iancu.
 # 
 # ############################################################
 #
@@ -204,8 +204,8 @@
 276F; 276E # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
 2770; 2771 # HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT
 2771; 2770 # HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
-2772; 2773 # LIGHT LEFT TORTOISE SHELL BRACKET
+2772; 2773 # LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT
-2773; 2772 # LIGHT RIGHT TORTOISE SHELL BRACKET
+2773; 2772 # LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT
 2774; 2775 # MEDIUM LEFT CURLY BRACKET ORNAMENT
 2775; 2774 # MEDIUM RIGHT CURLY BRACKET ORNAMENT
 27C3; 27C4 # OPEN SUBSET

util/unicode/data/Blocks.txt

@@ -1,5 +1,5 @@
-# Blocks-6.2.0.txt
+# Blocks-6.3.0.txt
-# Date: 2012-05-14, 22:42:00 GMT [KW, LI]
+# Date: 2012-12-02, 09:45:00 GMT [KW, LI]
 #
 # Unicode Character Database
 # Copyright (c) 1991-2012 Unicode, Inc.

util/unicode/data/CaseFolding.txt

@@ -1,8 +1,8 @@
-# CaseFolding-6.2.0.txt
+# CaseFolding-6.3.0.txt
-# Date: 2012-08-14, 17:54:49 GMT [MD]
+# Date: 2012-12-20, 22:14:35 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/
 #

util/unicode/data/DerivedAge.txt

@@ -1,8 +1,8 @@
-# DerivedAge-6.2.0.txt
+# DerivedAge-6.3.0.txt
-# Date: 2012-09-20, 21:30:39 GMT [MD]
+# Date: 2013-08-27, 18:11:46 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/
 #
@@ -503,7 +503,8 @@ FFFC          ; 2.1 #       OBJECT REPLACEMENT CHARACTER
 16A0..16F0    ; 3.0 #  [81] RUNIC LETTER FEHU FEOH FE F..RUNIC BELGTHOR SYMBOL
 1780..17DC    ; 3.0 #  [93] KHMER LETTER KA..KHMER SIGN AVAKRAHASANYA
 17E0..17E9    ; 3.0 #  [10] KHMER DIGIT ZERO..KHMER DIGIT NINE
-1800..180E    ; 3.0 #  [15] MONGOLIAN BIRGA..MONGOLIAN VOWEL SEPARATOR
+1800..180D    ; 3.0 #  [14] MONGOLIAN BIRGA..MONGOLIAN FREE VARIATION SELECTOR THREE
+180E          ; 3.0 #       MONGOLIAN VOWEL SEPARATOR
 1810..1819    ; 3.0 #  [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
 1820..1877    ; 3.0 #  [88] MONGOLIAN LETTER A..MONGOLIAN LETTER MANCHU ZHA
 1880..18A9    ; 3.0 #  [42] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI DAGALGA
@@ -1304,4 +1305,15 @@ FA2E..FA2F    ; 6.1 #   [2] CJK COMPATIBILITY IDEOGRAPH-FA2E..CJK COMPATIBILITY
 
 # Total code points: 1
 
+# ================================================
+
+# Age=V6_3
+
+# Newly assigned in Unicode 6.3.0 (September, 2013)
+
+061C          ; 6.3 #       ARABIC LETTER MARK
+2066..2069    ; 6.3 #   [4] LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE
+
+# Total code points: 5
+
 # EOF

util/unicode/data/DerivedNormalizationProps.txt

@@ -1,8 +1,8 @@
-# DerivedNormalizationProps-6.2.0.txt
+# DerivedNormalizationProps-6.3.0.txt
-# Date: 2012-05-23, 20:34:48 GMT [MD]
+# Date: 2013-03-02, 16:07:38 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/
 
@@ -3377,6 +3377,7 @@ FFE3          ; Expands_On_NFKC # Sk       FULLWIDTH MACRON
 0555          ; NFKC_CF; 0585           # L&       ARMENIAN CAPITAL LETTER OH
 0556          ; NFKC_CF; 0586           # L&       ARMENIAN CAPITAL LETTER FEH
 0587          ; NFKC_CF; 0565 0582      # L&       ARMENIAN SMALL LIGATURE ECH YIWN
+061C          ; NFKC_CF;                # Cf       ARABIC LETTER MARK
 0675          ; NFKC_CF; 0627 0674      # Lo       ARABIC LETTER HIGH HAMZA ALEF
 0676          ; NFKC_CF; 0648 0674      # Lo       ARABIC LETTER HIGH HAMZA WAW
 0677          ; NFKC_CF; 06C7 0674      # Lo       ARABIC LETTER U WITH HAMZA ABOVE
@@ -3468,6 +3469,7 @@ FFE3          ; Expands_On_NFKC # Sk       FULLWIDTH MACRON
 115F..1160    ; NFKC_CF;                # Lo   [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
 17B4..17B5    ; NFKC_CF;                # Mn   [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
 180B..180D    ; NFKC_CF;                # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+180E          ; NFKC_CF;                # Cf       MONGOLIAN VOWEL SEPARATOR
 1D2C          ; NFKC_CF; 0061           # Lm       MODIFIER LETTER CAPITAL A
 1D2D          ; NFKC_CF; 00E6           # Lm       MODIFIER LETTER CAPITAL AE
 1D2E          ; NFKC_CF; 0062           # Lm       MODIFIER LETTER CAPITAL B
@@ -3870,8 +3872,8 @@ FFE3          ; Expands_On_NFKC # Sk       FULLWIDTH MACRON
 2057          ; NFKC_CF; 2032 2032 2032 2032 #Po   QUADRUPLE PRIME
 205F          ; NFKC_CF; 0020           # Zs       MEDIUM MATHEMATICAL SPACE
 2060..2064    ; NFKC_CF;                # Cf   [5] WORD JOINER..INVISIBLE PLUS
-2065..2069    ; NFKC_CF;                # Cn   [5] <reserved-2065>..<reserved-2069>
+2065          ; NFKC_CF;                # Cn       <reserved-2065>
-206A..206F    ; NFKC_CF;                # Cf   [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+2066..206F    ; NFKC_CF;                # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
 2070          ; NFKC_CF; 0030           # No       SUPERSCRIPT ZERO
 2071          ; NFKC_CF; 0069           # Lm       SUPERSCRIPT LATIN SMALL LETTER I
 2074          ; NFKC_CF; 0034           # No       SUPERSCRIPT FOUR
@@ -8403,7 +8405,7 @@ E0080..E00FF  ; NFKC_CF;                # Cn [128] <reserved-E0080>..<reserved-E
 E0100..E01EF  ; NFKC_CF;                # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 E01F0..E0FFF  ; NFKC_CF;                # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 9944
+# Total code points: 9946
 
 # ================================================
 
@@ -8698,6 +8700,7 @@ E01F0..E0FFF  ; NFKC_CF;                # Cn [3600] <reserved-E01F0>..<reserved-
 0526          ; Changes_When_NFKC_Casefolded # L&       CYRILLIC CAPITAL LETTER SHHA WITH DESCENDER
 0531..0556    ; Changes_When_NFKC_Casefolded # L&  [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH
 0587          ; Changes_When_NFKC_Casefolded # L&       ARMENIAN SMALL LIGATURE ECH YIWN
+061C          ; Changes_When_NFKC_Casefolded # Cf       ARABIC LETTER MARK
 0675..0678    ; Changes_When_NFKC_Casefolded # Lo   [4] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER HIGH HAMZA YEH
 0958..095F    ; Changes_When_NFKC_Casefolded # Lo   [8] DEVANAGARI LETTER QA..DEVANAGARI LETTER YYA
 09DC..09DD    ; Changes_When_NFKC_Casefolded # Lo   [2] BENGALI LETTER RRA..BENGALI LETTER RHA
@@ -8733,6 +8736,7 @@ E01F0..E0FFF  ; NFKC_CF;                # Cn [3600] <reserved-E01F0>..<reserved-
 115F..1160    ; Changes_When_NFKC_Casefolded # Lo   [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
 17B4..17B5    ; Changes_When_NFKC_Casefolded # Mn   [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
 180B..180D    ; Changes_When_NFKC_Casefolded # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+180E          ; Changes_When_NFKC_Casefolded # Cf       MONGOLIAN VOWEL SEPARATOR
 1D2C..1D2E    ; Changes_When_NFKC_Casefolded # Lm   [3] MODIFIER LETTER CAPITAL A..MODIFIER LETTER CAPITAL B
 1D30..1D3A    ; Changes_When_NFKC_Casefolded # Lm  [11] MODIFIER LETTER CAPITAL D..MODIFIER LETTER CAPITAL N
 1D3C..1D4D    ; Changes_When_NFKC_Casefolded # Lm  [18] MODIFIER LETTER CAPITAL O..MODIFIER LETTER SMALL G
@@ -8914,8 +8918,8 @@ E01F0..E0FFF  ; NFKC_CF;                # Cn [3600] <reserved-E01F0>..<reserved-
 2057          ; Changes_When_NFKC_Casefolded # Po       QUADRUPLE PRIME
 205F          ; Changes_When_NFKC_Casefolded # Zs       MEDIUM MATHEMATICAL SPACE
 2060..2064    ; Changes_When_NFKC_Casefolded # Cf   [5] WORD JOINER..INVISIBLE PLUS
-2065..2069    ; Changes_When_NFKC_Casefolded # Cn   [5] <reserved-2065>..<reserved-2069>
+2065          ; Changes_When_NFKC_Casefolded # Cn       <reserved-2065>
-206A..206F    ; Changes_When_NFKC_Casefolded # Cf   [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+2066..206F    ; Changes_When_NFKC_Casefolded # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
 2070          ; Changes_When_NFKC_Casefolded # No       SUPERSCRIPT ZERO
 2071          ; Changes_When_NFKC_Casefolded # Lm       SUPERSCRIPT LATIN SMALL LETTER I
 2074..2079    ; Changes_When_NFKC_Casefolded # No   [6] SUPERSCRIPT FOUR..SUPERSCRIPT NINE
@@ -9363,6 +9367,6 @@ E0080..E00FF  ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser
 E0100..E01EF  ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 E01F0..E0FFF  ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 9944
+# Total code points: 9946
 
 # EOF

util/unicode/data/GraphemeBreakProperty.txt

@@ -1,8 +1,8 @@
-# GraphemeBreakProperty-6.2.0.txt
+# GraphemeBreakProperty-6.3.0.txt
-# Date: 2012-08-13, 19:12:02 GMT [MD]
+# Date: 2013-03-02, 16:07:40 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/
 
@@ -35,16 +35,18 @@
 007F..009F    ; Control # Cc  [33] <control-007F>..<control-009F>
 00AD          ; Control # Cf       SOFT HYPHEN
 0600..0604    ; Control # Cf   [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT
+061C          ; Control # Cf       ARABIC LETTER MARK
 06DD          ; Control # Cf       ARABIC END OF AYAH
 070F          ; Control # Cf       SYRIAC ABBREVIATION MARK
+180E          ; Control # Cf       MONGOLIAN VOWEL SEPARATOR
 200B          ; Control # Cf       ZERO WIDTH SPACE
 200E..200F    ; Control # Cf   [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
 2028          ; Control # Zl       LINE SEPARATOR
 2029          ; Control # Zp       PARAGRAPH SEPARATOR
 202A..202E    ; Control # Cf   [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
 2060..2064    ; Control # Cf   [5] WORD JOINER..INVISIBLE PLUS
-2065..2069    ; Control # Cn   [5] <reserved-2065>..<reserved-2069>
+2065          ; Control # Cn       <reserved-2065>
-206A..206F    ; Control # Cf   [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+2066..206F    ; Control # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
 D800..DFFF    ; Control # Cs [2048] <surrogate-D800>..<surrogate-DFFF>
 FEFF          ; Control # Cf       ZERO WIDTH NO-BREAK SPACE
 FFF0..FFF8    ; Control # Cn   [9] <reserved-FFF0>..<reserved-FFF8>
@@ -58,7 +60,7 @@ E0020..E007F  ; Control # Cf  [96] TAG SPACE..CANCEL TAG
 E0080..E00FF  ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF>
 E01F0..E0FFF  ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 
-# Total code points: 6023
+# Total code points: 6025
 
 # ================================================
 
@@ -196,6 +198,7 @@ E01F0..E0FFF  ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
 1932          ; Extend # Mn       LIMBU SMALL LETTER ANUSVARA
 1939..193B    ; Extend # Mn   [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
 1A17..1A18    ; Extend # Mn   [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
+1A1B          ; Extend # Mn       BUGINESE VOWEL SIGN AE
 1A56          ; Extend # Mn       TAI THAM CONSONANT SIGN MEDIAL LA
 1A58..1A5E    ; Extend # Mn   [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA
 1A60          ; Extend # Mn       TAI THAM SIGN SAKOT
@@ -304,7 +307,7 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 1D242..1D244  ; Extend # Mn   [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
 E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 1317
+# Total code points: 1318
 
 # ================================================
 
@@ -370,7 +373,7 @@ E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 1933..1938    ; SpacingMark # Mc   [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA
 19B5..19B7    ; SpacingMark # Mc   [3] NEW TAI LUE VOWEL SIGN E..NEW TAI LUE VOWEL SIGN O
 19BA          ; SpacingMark # Mc       NEW TAI LUE VOWEL SIGN AY
-1A19..1A1B    ; SpacingMark # Mc   [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
+1A19..1A1A    ; SpacingMark # Mc   [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
 1A55          ; SpacingMark # Mc       TAI THAM CONSONANT SIGN MEDIAL RA
 1A57          ; SpacingMark # Mc       TAI THAM CONSONANT SIGN LA TANG LAI
 1A6D..1A72    ; SpacingMark # Mc   [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI
@@ -427,7 +430,7 @@ ABEC          ; SpacingMark # Mc       MEETEI MAYEK LUM IYEK
 1D166         ; SpacingMark # Mc       MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
 1D16D         ; SpacingMark # Mc       MUSICAL SYMBOL COMBINING AUGMENTATION DOT
 
-# Total code points: 291
+# Total code points: 290
 
 # ================================================
 

util/unicode/data/LineBreak.txt

@@ -1,5 +1,5 @@
-# LineBreak-6.2.0.txt
+# LineBreak-6.3.0.txt
-# Date: 2012-08-08, 19:26:00 GMT [KW]
+# 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

util/unicode/data/NormalizationCorrections.txt

@@ -1,10 +1,10 @@
-# NormalizationCorrections-6.2.0.txt
+# NormalizationCorrections-6.3.0.txt
-# Date: 2012-05-15, 22:25:00 GMT [KW, LI]
+# Date: 2013-01-02, 08:39:00 GMT [KW, LI]
 #
 # This file is a normative contributory data file in the
 # 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
 #
 # The normalization stability policy of the Unicode Consortium

util/unicode/data/Scripts.txt

@@ -1,8 +1,8 @@
-# Scripts-6.2.0.txt
+# Scripts-6.3.0.txt
-# Date: 2012-06-04, 17:21:29 GMT [MD]
+# Date: 2013-07-05, 14:09:02 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/
 
@@ -136,7 +136,7 @@
 2055..205E    ; Common # Po  [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS
 205F          ; Common # Zs       MEDIUM MATHEMATICAL SPACE
 2060..2064    ; Common # Cf   [5] WORD JOINER..INVISIBLE PLUS
-206A..206F    ; Common # Cf   [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+2066..206F    ; Common # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
 2070          ; Common # No       SUPERSCRIPT ZERO
 2074..2079    ; Common # No   [6] SUPERSCRIPT FOUR..SUPERSCRIPT NINE
 207A..207C    ; Common # Sm   [3] SUPERSCRIPT PLUS SIGN..SUPERSCRIPT EQUALS SIGN
@@ -200,7 +200,10 @@
 21D5..21F3    ; Common # So  [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW
 21F4..22FF    ; Common # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP
 2300..2307    ; Common # So   [8] DIAMETER SIGN..WAVY LINE
-2308..230B    ; Common # Sm   [4] LEFT CEILING..RIGHT FLOOR
+2308          ; Common # Ps       LEFT CEILING
+2309          ; Common # Pe       RIGHT CEILING
+230A          ; Common # Ps       LEFT FLOOR
+230B          ; Common # Pe       RIGHT FLOOR
 230C..231F    ; Common # So  [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER
 2320..2321    ; Common # Sm   [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL
 2322..2328    ; Common # So   [7] FROWN..KEYBOARD
@@ -392,6 +395,7 @@ A830..A835    ; Common # No   [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC
 A836..A837    ; Common # So   [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK
 A838          ; Common # Sc       NORTH INDIC RUPEE MARK
 A839          ; Common # So       NORTH INDIC QUANTITY MARK
+A9CF          ; Common # Lm       JAVANESE PANGRANGKEP
 FD3E          ; Common # Ps       ORNATE LEFT PARENTHESIS
 FD3F          ; Common # Pe       ORNATE RIGHT PARENTHESIS
 FDFD          ; Common # So       ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
@@ -576,7 +580,7 @@ FFFC..FFFD    ; Common # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
 E0001         ; Common # Cf       LANGUAGE TAG
 E0020..E007F  ; Common # Cf  [96] TAG SPACE..CANCEL TAG
 
-# Total code points: 6413
+# Total code points: 6418
 
 # ================================================
 
@@ -757,6 +761,7 @@ FB46..FB4F    ; Hebrew # Lo  [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
 060D          ; Arabic # Po       ARABIC DATE SEPARATOR
 060E..060F    ; Arabic # So   [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA
 0610..061A    ; Arabic # Mn  [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
+061C          ; Arabic # Cf       ARABIC LETTER MARK
 061E          ; Arabic # Po       ARABIC TRIPLE DOT PUNCTUATION MARK
 0620..063F    ; Arabic # Lo  [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
 0641..064A    ; Arabic # Lo  [10] ARABIC LETTER FEH..ARABIC LETTER YEH
@@ -827,7 +832,7 @@ FE76..FEFC    ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
 1EEAB..1EEBB  ; Arabic # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 1EEF0..1EEF1  ; Arabic # Sm   [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
 
-# Total code points: 1235
+# Total code points: 1236
 
 # ================================================
 
@@ -1377,7 +1382,7 @@ AB28..AB2E    ; Ethiopic # Lo   [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
 1806          ; Mongolian # Pd       MONGOLIAN TODO SOFT HYPHEN
 1807..180A    ; Mongolian # Po   [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU
 180B..180D    ; Mongolian # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
-180E          ; Mongolian # Zs       MONGOLIAN VOWEL SEPARATOR
+180E          ; Mongolian # Cf       MONGOLIAN VOWEL SEPARATOR
 1810..1819    ; Mongolian # Nd  [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
 1820..1842    ; Mongolian # Lo  [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
 1843          ; Mongolian # Lm       MONGOLIAN LETTER TODO LONG VOWEL SIGN
@@ -1612,7 +1617,8 @@ E0100..E01EF  ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
 
 1A00..1A16    ; Buginese # Lo  [23] BUGINESE LETTER KA..BUGINESE LETTER HA
 1A17..1A18    ; Buginese # Mn   [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
-1A19..1A1B    ; Buginese # Mc   [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE
+1A19..1A1A    ; Buginese # Mc   [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O
+1A1B          ; Buginese # Mn       BUGINESE VOWEL SIGN AE
 1A1E..1A1F    ; Buginese # Po   [2] BUGINESE PALLAWA..BUGINESE END OF SECTION
 
 # Total code points: 30
@@ -1974,11 +1980,10 @@ A9BA..A9BB    ; Javanese # Mc   [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL S
 A9BC          ; Javanese # Mn       JAVANESE VOWEL SIGN PEPET
 A9BD..A9C0    ; Javanese # Mc   [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON
 A9C1..A9CD    ; Javanese # Po  [13] JAVANESE LEFT RERENGGAN..JAVANESE TURNED PADA PISELEH
-A9CF          ; Javanese # Lm       JAVANESE PANGRANGKEP
 A9D0..A9D9    ; Javanese # Nd  [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE
 A9DE..A9DF    ; Javanese # Po   [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN
 
-# Total code points: 91
+# Total code points: 90
 
 # ================================================
 

util/unicode/data/SentenceBreakProperty.txt

@@ -1,8 +1,8 @@
-# SentenceBreakProperty-6.2.0.txt
+# SentenceBreakProperty-6.3.0.txt
-# Date: 2012-05-23, 20:35:14 GMT [MD]
+# 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
 
 # ================================================
 

util/unicode/data/SpecialCasing.txt

@@ -1,8 +1,8 @@
-# SpecialCasing-6.2.0.txt
+# SpecialCasing-6.3.0.txt
-# Date: 2012-05-23, 20:35:15 GMT [MD]
+# Date: 2013-05-08, 13:54:51 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/
 #
@@ -39,7 +39,7 @@
 # A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
 #
 # A context for a character C is defined by Section 3.13 Default Case 
-# Operations, of The Unicode Standard, Version 5.0.
+# Algorithms, of The Unicode Standard, Version 6.3.
 # (This is identical to the context defined by Unicode 4.1.0,
 #  as specified in http://www.unicode.org/versions/Unicode4.1.0/)
 #

util/unicode/data/UnicodeData.txt

@@ -1509,6 +1509,7 @@
 0619;ARABIC SMALL DAMMA;Mn;31;NSM;;;;;N;;;;;
 061A;ARABIC SMALL KASRA;Mn;32;NSM;;;;;N;;;;;
 061B;ARABIC SEMICOLON;Po;0;AL;;;;;N;;;;;
+061C;ARABIC LETTER MARK;Cf;0;AL;;;;;N;;;;;
 061E;ARABIC TRIPLE DOT PUNCTUATION MARK;Po;0;AL;;;;;N;;;;;
 061F;ARABIC QUESTION MARK;Po;0;AL;;;;;N;;;;;
 0620;ARABIC LETTER KASHMIRI YEH;Lo;0;AL;;;;;N;;;;;
@@ -5296,7 +5297,7 @@
 180B;MONGOLIAN FREE VARIATION SELECTOR ONE;Mn;0;NSM;;;;;N;;;;;
 180C;MONGOLIAN FREE VARIATION SELECTOR TWO;Mn;0;NSM;;;;;N;;;;;
 180D;MONGOLIAN FREE VARIATION SELECTOR THREE;Mn;0;NSM;;;;;N;;;;;
-180E;MONGOLIAN VOWEL SEPARATOR;Zs;0;WS;;;;;N;;;;;
+180E;MONGOLIAN VOWEL SEPARATOR;Cf;0;BN;;;;;N;;;;;
 1810;MONGOLIAN DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;;
 1811;MONGOLIAN DIGIT ONE;Nd;0;L;;1;1;1;N;;;;;
 1812;MONGOLIAN DIGIT TWO;Nd;0;L;;2;2;2;N;;;;;
@@ -5751,7 +5752,7 @@
 1A18;BUGINESE VOWEL SIGN U;Mn;220;NSM;;;;;N;;;;;
 1A19;BUGINESE VOWEL SIGN E;Mc;0;L;;;;;N;;;;;
 1A1A;BUGINESE VOWEL SIGN O;Mc;0;L;;;;;N;;;;;
-1A1B;BUGINESE VOWEL SIGN AE;Mc;0;L;;;;;N;;;;;
+1A1B;BUGINESE VOWEL SIGN AE;Mn;0;NSM;;;;;N;;;;;
 1A1E;BUGINESE PALLAWA;Po;0;L;;;;;N;;;;;
 1A1F;BUGINESE END OF SECTION;Po;0;L;;;;;N;;;;;
 1A20;TAI THAM LETTER HIGH KA;Lo;0;L;;;;;N;;;;;
@@ -7116,6 +7117,10 @@
 2062;INVISIBLE TIMES;Cf;0;BN;;;;;N;;;;;
 2063;INVISIBLE SEPARATOR;Cf;0;BN;;;;;N;;;;;
 2064;INVISIBLE PLUS;Cf;0;BN;;;;;N;;;;;
+2066;LEFT-TO-RIGHT ISOLATE;Cf;0;LRI;;;;;N;;;;;
+2067;RIGHT-TO-LEFT ISOLATE;Cf;0;RLI;;;;;N;;;;;
+2068;FIRST STRONG ISOLATE;Cf;0;FSI;;;;;N;;;;;
+2069;POP DIRECTIONAL ISOLATE;Cf;0;PDI;;;;;N;;;;;
 206A;INHIBIT SYMMETRIC SWAPPING;Cf;0;BN;;;;;N;;;;;
 206B;ACTIVATE SYMMETRIC SWAPPING;Cf;0;BN;;;;;N;;;;;
 206C;INHIBIT ARABIC FORM SHAPING;Cf;0;BN;;;;;N;;;;;
@@ -7738,10 +7743,10 @@
 2305;PROJECTIVE;So;0;ON;;;;;N;;;;;
 2306;PERSPECTIVE;So;0;ON;;;;;N;;;;;
 2307;WAVY LINE;So;0;ON;;;;;N;;;;;
-2308;LEFT CEILING;Sm;0;ON;;;;;Y;;;;;
+2308;LEFT CEILING;Ps;0;ON;;;;;Y;;;;;
-2309;RIGHT CEILING;Sm;0;ON;;;;;Y;;;;;
+2309;RIGHT CEILING;Pe;0;ON;;;;;Y;;;;;
-230A;LEFT FLOOR;Sm;0;ON;;;;;Y;;;;;
+230A;LEFT FLOOR;Ps;0;ON;;;;;Y;;;;;
-230B;RIGHT FLOOR;Sm;0;ON;;;;;Y;;;;;
+230B;RIGHT FLOOR;Pe;0;ON;;;;;Y;;;;;
 230C;BOTTOM RIGHT CROP;So;0;ON;;;;;N;;;;;
 230D;BOTTOM LEFT CROP;So;0;ON;;;;;N;;;;;
 230E;TOP RIGHT CROP;So;0;ON;;;;;N;;;;;
@@ -18740,8 +18745,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
 12453;CUNEIFORM NUMERIC SIGN FOUR BAN2 VARIANT FORM;Nl;0;L;;;;4;N;;;;;
 12454;CUNEIFORM NUMERIC SIGN FIVE BAN2;Nl;0;L;;;;5;N;;;;;
 12455;CUNEIFORM NUMERIC SIGN FIVE BAN2 VARIANT FORM;Nl;0;L;;;;5;N;;;;;
-12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;-1;N;;;;;
+12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;2;N;;;;;
-12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;-1;N;;;;;
+12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;3;N;;;;;
 12458;CUNEIFORM NUMERIC SIGN ONE ESHE3;Nl;0;L;;;;1;N;;;;;
 12459;CUNEIFORM NUMERIC SIGN TWO ESHE3;Nl;0;L;;;;2;N;;;;;
 1245A;CUNEIFORM NUMERIC SIGN ONE THIRD DISH;Nl;0;L;;;;1/3;N;;;;;

util/unicode/data/WordBreakProperty.txt

@@ -1,8 +1,8 @@
-# WordBreakProperty-6.2.0.txt
+# WordBreakProperty-6.3.0.txt
-# Date: 2012-08-13, 19:12:09 GMT [MD]
+# 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
+FB50..FBB1    ; ALetter # Lo  [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
-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
 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
 
 # ================================================