diff options
57 files changed, 2189 insertions, 475 deletions
@@ -4345,6 +4345,7 @@ lib/unicore/auxiliary/GCBTest.txt Unicode character database lib/unicore/auxiliary/GraphemeBreakProperty.txt Unicode character database lib/unicore/auxiliary/SentenceBreakProperty.txt Unicode character database lib/unicore/auxiliary/WordBreakProperty.txt Unicode character database +lib/unicore/BidiBrackets.txt Unicode character database lib/unicore/BidiMirroring.txt Unicode character database lib/unicore/Blocks.txt Unicode character database lib/unicore/CaseFolding.txt Unicode character database diff --git a/charclass_invlists.h b/charclass_invlists.h index c2f9f248b1..8cd02bdb1f 100644 --- a/charclass_invlists.h +++ b/charclass_invlists.h @@ -111,7 +111,7 @@ static const UV PerlSpace_invlist[] = { #ifndef PERL_IN_XSUB_RE static const UV XPerlSpace_invlist[] = { - 23, /* Number of elements */ + 21, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -126,8 +126,6 @@ static const UV XPerlSpace_invlist[] = { 161, 5760, 5761, - 6158, - 6159, 8192, 8203, 8232, @@ -253,7 +251,7 @@ static const UV PosixBlank_invlist[] = { #ifndef PERL_IN_XSUB_RE static const UV XPosixBlank_invlist[] = { - 19, /* Number of elements */ + 17, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -266,8 +264,6 @@ static const UV XPosixBlank_invlist[] = { 161, 5760, 5761, - 6158, - 6159, 8192, 8203, 8239, @@ -493,7 +489,7 @@ static const UV PosixSpace_invlist[] = { #ifndef PERL_IN_XSUB_RE static const UV XPosixSpace_invlist[] = { - 23, /* Number of elements */ + 21, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -508,8 +504,6 @@ static const UV XPosixSpace_invlist[] = { 161, 5760, 5761, - 6158, - 6159, 8192, 8203, 8232, diff --git a/dist/Module-CoreList/lib/Module/CoreList.pm b/dist/Module-CoreList/lib/Module/CoreList.pm index 1ec4350d6b..f5e5023805 100644 --- a/dist/Module-CoreList/lib/Module/CoreList.pm +++ b/dist/Module-CoreList/lib/Module/CoreList.pm @@ -9153,6 +9153,7 @@ for my $version (sort { $a <=> $b } keys %delta) { 5.019005 => { delta_from => 5.019004, changed => { + 'Unicode' => '6.3.0', }, removed => { } diff --git a/lib/unicore/ArabicShaping.txt b/lib/unicore/ArabicShaping.txt index fd22f5d6e0..8add8a5a1c 100644 --- a/lib/unicore/ArabicShaping.txt +++ b/lib/unicore/ArabicShaping.txt @@ -1,5 +1,5 @@ -# ArabicShaping-6.2.0.txt -# Date: 2012-05-15, 21:05:00 GMT [KW] +# ArabicShaping-6.3.0.txt +# 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, -# Version 6.2 for more information. +# See sections 8.2, 8.3, 10.4, 13.2, 13.5, and 14.12 of The Unicode Standard, +# 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 -# and Syriac scripts currently have explicit joining group values defined. +# is the convention exemplified by the N'Ko, Mandaic, Mongolian, +# 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 diff --git a/lib/unicore/BidiBrackets.txt b/lib/unicore/BidiBrackets.txt new file mode 100644 index 0000000000..626084e369 --- /dev/null +++ b/lib/unicore/BidiBrackets.txt @@ -0,0 +1,176 @@ +# BidiBrackets-6.3.0.txt +# Date: 2013-08-27, 17:30:00 GMT [AG, LI, KW] +# +# Bidi_Paired_Bracket and Bidi_Paired_Bracket_Type Properties +# +# This file is a normative contributory data file in the Unicode +# Character Database. +# +# Copyright (c) 1991-2013 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Bidi_Paired_Bracket is a normative property of type Miscellaneous, +# which establishes a mapping between characters that are treated as +# bracket pairs by the Unicode Bidirectional Algorithm. +# +# Bidi_Paired_Bracket_Type is a normative property of type Enumeration, +# which classifies characters into opening and closing paired brackets +# for the purposes of the Unicode Bidirectional Algorithm. +# +# This file lists the set of code points with Bidi_Paired_Bracket_Type +# property values Open and Close. The set is derived from the character +# properties General_Category (gc), Bidi_Class (bc), Bidi_Mirrored (Bidi_M), +# and Bidi_Mirroring_Glyph (bmg), as follows: two characters, A and B, +# form a bracket pair if A has gc=Ps and B has gc=Pe, both have bc=ON and +# Bidi_M=Y, and bmg of A is B. Bidi_Paired_Bracket (bpb) maps A to B and +# vice versa, and their Bidi_Paired_Bracket_Type (bpt) property values are +# Open (o) and Close (c), respectively. +# +# For legacy reasons, the characters U+FD3E ORNATE LEFT PARENTHESIS and +# U+FD3F ORNATE RIGHT PARENTHESIS do not mirror in bidirectional display +# and therefore do not form a bracket pair. +# +# The Unicode property value stability policy guarantees that characters +# which have bpt=o or bpt=c also have bc=ON and Bidi_M=Y. As a result, an +# implementation can optimize the lookup of the Bidi_Paired_Bracket_Type +# property values Open and Close by restricting the processing to characters +# with bc=ON. +# +# The format of the file is three fields separated by a semicolon. +# Field 0: Unicode code point value, represented as a hexadecimal value +# Field 1: Bidi_Paired_Bracket property value, a code point value or <none> +# Field 2: Bidi_Paired_Bracket_Type property value, one of the following: +# o Open +# c Close +# n None +# The names of the characters in field 0 are given in comments at the end +# of each line. +# +# For information on bidirectional paired brackets, see UAX #9: Unicode +# Bidirectional Algorithm, at http://www.unicode.org/unicode/reports/tr9/ +# +# This file was originally created by Andrew Glass and Laurentiu Iancu +# for Unicode 6.3. + +0028; 0029; o # LEFT PARENTHESIS +0029; 0028; c # RIGHT PARENTHESIS +005B; 005D; o # LEFT SQUARE BRACKET +005D; 005B; c # RIGHT SQUARE BRACKET +007B; 007D; o # LEFT CURLY BRACKET +007D; 007B; c # RIGHT CURLY BRACKET +0F3A; 0F3B; o # TIBETAN MARK GUG RTAGS GYON +0F3B; 0F3A; c # TIBETAN MARK GUG RTAGS GYAS +0F3C; 0F3D; o # TIBETAN MARK ANG KHANG GYON +0F3D; 0F3C; c # TIBETAN MARK ANG KHANG GYAS +169B; 169C; o # OGHAM FEATHER MARK +169C; 169B; c # OGHAM REVERSED FEATHER MARK +2045; 2046; o # LEFT SQUARE BRACKET WITH QUILL +2046; 2045; c # RIGHT SQUARE BRACKET WITH QUILL +207D; 207E; o # SUPERSCRIPT LEFT PARENTHESIS +207E; 207D; c # SUPERSCRIPT RIGHT PARENTHESIS +208D; 208E; o # SUBSCRIPT LEFT PARENTHESIS +208E; 208D; c # SUBSCRIPT RIGHT PARENTHESIS +2308; 2309; o # LEFT CEILING +2309; 2308; c # RIGHT CEILING +230A; 230B; o # LEFT FLOOR +230B; 230A; c # RIGHT FLOOR +2329; 232A; o # LEFT-POINTING ANGLE BRACKET +232A; 2329; c # RIGHT-POINTING ANGLE BRACKET +2768; 2769; o # MEDIUM LEFT PARENTHESIS ORNAMENT +2769; 2768; c # MEDIUM RIGHT PARENTHESIS ORNAMENT +276A; 276B; o # MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT +276B; 276A; c # MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT +276C; 276D; o # MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT +276D; 276C; c # MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT +276E; 276F; o # HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT +276F; 276E; c # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT +2770; 2771; o # HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT +2771; 2770; c # HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT +2772; 2773; o # LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT +2773; 2772; c # LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT +2774; 2775; o # MEDIUM LEFT CURLY BRACKET ORNAMENT +2775; 2774; c # MEDIUM RIGHT CURLY BRACKET ORNAMENT +27C5; 27C6; o # LEFT S-SHAPED BAG DELIMITER +27C6; 27C5; c # RIGHT S-SHAPED BAG DELIMITER +27E6; 27E7; o # MATHEMATICAL LEFT WHITE SQUARE BRACKET +27E7; 27E6; c # MATHEMATICAL RIGHT WHITE SQUARE BRACKET +27E8; 27E9; o # MATHEMATICAL LEFT ANGLE BRACKET +27E9; 27E8; c # MATHEMATICAL RIGHT ANGLE BRACKET +27EA; 27EB; o # MATHEMATICAL LEFT DOUBLE ANGLE BRACKET +27EB; 27EA; c # MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET +27EC; 27ED; o # MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET +27ED; 27EC; c # MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET +27EE; 27EF; o # MATHEMATICAL LEFT FLATTENED PARENTHESIS +27EF; 27EE; c # MATHEMATICAL RIGHT FLATTENED PARENTHESIS +2983; 2984; o # LEFT WHITE CURLY BRACKET +2984; 2983; c # RIGHT WHITE CURLY BRACKET +2985; 2986; o # LEFT WHITE PARENTHESIS +2986; 2985; c # RIGHT WHITE PARENTHESIS +2987; 2988; o # Z NOTATION LEFT IMAGE BRACKET +2988; 2987; c # Z NOTATION RIGHT IMAGE BRACKET +2989; 298A; o # Z NOTATION LEFT BINDING BRACKET +298A; 2989; c # Z NOTATION RIGHT BINDING BRACKET +298B; 298C; o # LEFT SQUARE BRACKET WITH UNDERBAR +298C; 298B; c # RIGHT SQUARE BRACKET WITH UNDERBAR +298D; 2990; o # LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +298E; 298F; c # RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +298F; 298E; o # LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +2990; 298D; c # RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +2991; 2992; o # LEFT ANGLE BRACKET WITH DOT +2992; 2991; c # RIGHT ANGLE BRACKET WITH DOT +2993; 2994; o # LEFT ARC LESS-THAN BRACKET +2994; 2993; c # RIGHT ARC GREATER-THAN BRACKET +2995; 2996; o # DOUBLE LEFT ARC GREATER-THAN BRACKET +2996; 2995; c # DOUBLE RIGHT ARC LESS-THAN BRACKET +2997; 2998; o # LEFT BLACK TORTOISE SHELL BRACKET +2998; 2997; c # RIGHT BLACK TORTOISE SHELL BRACKET +29D8; 29D9; o # LEFT WIGGLY FENCE +29D9; 29D8; c # RIGHT WIGGLY FENCE +29DA; 29DB; o # LEFT DOUBLE WIGGLY FENCE +29DB; 29DA; c # RIGHT DOUBLE WIGGLY FENCE +29FC; 29FD; o # LEFT-POINTING CURVED ANGLE BRACKET +29FD; 29FC; c # RIGHT-POINTING CURVED ANGLE BRACKET +2E22; 2E23; o # TOP LEFT HALF BRACKET +2E23; 2E22; c # TOP RIGHT HALF BRACKET +2E24; 2E25; o # BOTTOM LEFT HALF BRACKET +2E25; 2E24; c # BOTTOM RIGHT HALF BRACKET +2E26; 2E27; o # LEFT SIDEWAYS U BRACKET +2E27; 2E26; c # RIGHT SIDEWAYS U BRACKET +2E28; 2E29; o # LEFT DOUBLE PARENTHESIS +2E29; 2E28; c # RIGHT DOUBLE PARENTHESIS +3008; 3009; o # LEFT ANGLE BRACKET +3009; 3008; c # RIGHT ANGLE BRACKET +300A; 300B; o # LEFT DOUBLE ANGLE BRACKET +300B; 300A; c # RIGHT DOUBLE ANGLE BRACKET +300C; 300D; o # LEFT CORNER BRACKET +300D; 300C; c # RIGHT CORNER BRACKET +300E; 300F; o # LEFT WHITE CORNER BRACKET +300F; 300E; c # RIGHT WHITE CORNER BRACKET +3010; 3011; o # LEFT BLACK LENTICULAR BRACKET +3011; 3010; c # RIGHT BLACK LENTICULAR BRACKET +3014; 3015; o # LEFT TORTOISE SHELL BRACKET +3015; 3014; c # RIGHT TORTOISE SHELL BRACKET +3016; 3017; o # LEFT WHITE LENTICULAR BRACKET +3017; 3016; c # RIGHT WHITE LENTICULAR BRACKET +3018; 3019; o # LEFT WHITE TORTOISE SHELL BRACKET +3019; 3018; c # RIGHT WHITE TORTOISE SHELL BRACKET +301A; 301B; o # LEFT WHITE SQUARE BRACKET +301B; 301A; c # RIGHT WHITE SQUARE BRACKET +FE59; FE5A; o # SMALL LEFT PARENTHESIS +FE5A; FE59; c # SMALL RIGHT PARENTHESIS +FE5B; FE5C; o # SMALL LEFT CURLY BRACKET +FE5C; FE5B; c # SMALL RIGHT CURLY BRACKET +FE5D; FE5E; o # SMALL LEFT TORTOISE SHELL BRACKET +FE5E; FE5D; c # SMALL RIGHT TORTOISE SHELL BRACKET +FF08; FF09; o # FULLWIDTH LEFT PARENTHESIS +FF09; FF08; c # FULLWIDTH RIGHT PARENTHESIS +FF3B; FF3D; o # FULLWIDTH LEFT SQUARE BRACKET +FF3D; FF3B; c # FULLWIDTH RIGHT SQUARE BRACKET +FF5B; FF5D; o # FULLWIDTH LEFT CURLY BRACKET +FF5D; FF5B; c # FULLWIDTH RIGHT CURLY BRACKET +FF5F; FF60; o # FULLWIDTH LEFT WHITE PARENTHESIS +FF60; FF5F; c # FULLWIDTH RIGHT WHITE PARENTHESIS +FF62; FF63; o # HALFWIDTH LEFT CORNER BRACKET +FF63; FF62; c # HALFWIDTH RIGHT CORNER BRACKET + +# EOF diff --git a/lib/unicore/BidiMirroring.txt b/lib/unicore/BidiMirroring.txt index ec41b76937..d97c0dd961 100644 --- a/lib/unicore/BidiMirroring.txt +++ b/lib/unicore/BidiMirroring.txt @@ -1,19 +1,19 @@ -# BidiMirroring-6.2.0.txt -# Date: 2012-05-15, 24:19:00 GMT [KW, LI] +# BidiMirroring-6.3.0.txt +# 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 -2773; 2772 # LIGHT RIGHT TORTOISE SHELL BRACKET +2772; 2773 # LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT +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 diff --git a/lib/unicore/Blocks.txt b/lib/unicore/Blocks.txt index 6a06ab1445..d45ab0cff2 100644 --- a/lib/unicore/Blocks.txt +++ b/lib/unicore/Blocks.txt @@ -1,5 +1,5 @@ -# Blocks-6.2.0.txt -# Date: 2012-05-14, 22:42:00 GMT [KW, LI] +# Blocks-6.3.0.txt +# Date: 2012-12-02, 09:45:00 GMT [KW, LI] # # Unicode Character Database # Copyright (c) 1991-2012 Unicode, Inc. diff --git a/lib/unicore/CJKRadicals.txt b/lib/unicore/CJKRadicals.txt index 53c6731aac..23efcd7dec 100644 --- a/lib/unicore/CJKRadicals.txt +++ b/lib/unicore/CJKRadicals.txt @@ -1,30 +1,32 @@ -# CJKRadicals-6.2.0.txt -# Date: 2012-05-15, 21:08:00 GMT [RC, KW] +# CJKRadicals-6.3.0.txt +# Date: 2012-12-03, 01:57:00 GMT [RC, KW, LI] # # Unicode Character Database # Copyright (c) 1991-2012 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr38/ +# For documentation, see UAX #38: Unicode Han Database (Unihan), +# at http://www.unicode.org/reports/tr38/ # # Mapping from radical numbers to characters. # # This data file provides a mapping from the radical numbers used # in the kRSUnicode property to the corresponding character -# in the CJK Radical block or the CJK Radicals Supplement block, as -# well as to a CJK Unified Ideograph which is formed from that radical +# in the Kangxi Radicals block or the CJK Radicals Supplement block, as +# well as to a CJK unified ideograph which is formed from that radical # only. # # There is one line per radical number. Each line contains three # fields, separated by a semicolon (';'). The first field is the -# radical number. The second field is the CJK Radical character. The third -# field is the CJK Unified Ideograph. +# radical number. The second field is the CJK radical character. The third +# field is the CJK unified ideograph. # -# Radical numbers match the regular expression [0-9]{1,3}\'? +# Radical numbers match the regular expression [1-9][0-9]{0,2}\'? # and in particular they can end with a U+0027 ' APOSTROPHE. # # This file was created for Unicode 5.2 by Richard Cook. # Updated for Unicode 6.0 by Richard Cook. # Updated for Unicode 6.1 and 6.2 by Ken Whistler. +# Updated for Unicode 6.3 by Ken Whistler and Laurentiu Iancu. # # #################################################### @@ -240,8 +242,8 @@ 194; 2FC1; 9B3C 195; 2FC2; 9B5A 195'; 2EE5; 9C7C -196'; 2EE6; 9E1F 196; 2FC3; 9CE5 +196'; 2EE6; 9E1F 197; 2FC4; 9E75 197'; 2EE7; 5364 198; 2FC5; 9E7F diff --git a/lib/unicore/CaseFolding.txt b/lib/unicore/CaseFolding.txt index df1813d2ad..cf5779f407 100644 --- a/lib/unicore/CaseFolding.txt +++ b/lib/unicore/CaseFolding.txt @@ -1,8 +1,8 @@ -# CaseFolding-6.2.0.txt -# Date: 2012-08-14, 17:54:49 GMT [MD] +# CaseFolding-6.3.0.txt +# 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/ # diff --git a/lib/unicore/CompositionExclusions.txt b/lib/unicore/CompositionExclusions.txt index cd19f42255..e7858bda74 100644 --- a/lib/unicore/CompositionExclusions.txt +++ b/lib/unicore/CompositionExclusions.txt @@ -1,5 +1,5 @@ -# CompositionExclusions-6.2.0.txt -# Date: 2012-05-15, 22:21:00 GMT [KW, LI] +# CompositionExclusions-6.3.0.txt +# Date: 2012-12-11, 11:23:00 GMT [KW, LI] # # This file lists the characters for the Composition Exclusion Table # defined in UAX #15, Unicode Normalization Forms. diff --git a/lib/unicore/DAge.txt b/lib/unicore/DAge.txt index 0629232a21..6a77b82ecc 100644 --- a/lib/unicore/DAge.txt +++ b/lib/unicore/DAge.txt @@ -1,8 +1,8 @@ -# DerivedAge-6.2.0.txt -# Date: 2012-09-20, 21:30:39 GMT [MD] +# DerivedAge-6.3.0.txt +# 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 diff --git a/lib/unicore/DCoreProperties.txt b/lib/unicore/DCoreProperties.txt index 395004c09b..b332311662 100644 --- a/lib/unicore/DCoreProperties.txt +++ b/lib/unicore/DCoreProperties.txt @@ -1,8 +1,8 @@ -# DerivedCoreProperties-6.2.0.txt -# Date: 2012-05-20, 00:42:31 GMT [MD] +# DerivedCoreProperties-6.3.0.txt +# Date: 2013-09-25, 18:58:40 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/ @@ -83,7 +83,10 @@ 21DD ; Math # So RIGHTWARDS SQUIGGLE ARROW 21E4..21E5 ; Math # So [2] LEFTWARDS ARROW TO BAR..RIGHTWARDS ARROW TO BAR 21F4..22FF ; Math # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP -2308..230B ; Math # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; Math # Ps LEFT CEILING +2309 ; Math # Pe RIGHT CEILING +230A ; Math # Ps LEFT FLOOR +230B ; Math # Pe RIGHT FLOOR 2320..2321 ; Math # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 237C ; Math # Sm RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW 239B..23B3 ; Math # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM @@ -643,7 +646,8 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 19C8..19C9 ; Alphabetic # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2 1A00..1A16 ; Alphabetic # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A17..1A18 ; Alphabetic # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; Alphabetic # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; Alphabetic # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; Alphabetic # Mn BUGINESE VOWEL SIGN AE 1A20..1A54 ; Alphabetic # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; Alphabetic # Mc TAI THAM CONSONANT SIGN MEDIAL RA 1A56 ; Alphabetic # Mn TAI THAM CONSONANT SIGN MEDIAL LA @@ -2326,7 +2330,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH # ================================================ # Derived Property: Cased (Cased) -# As defined by Unicode Standard Definition D120 +# As defined by Unicode Standard Definition D135 # C has the Lowercase or Uppercase property or has a General_Category value of Titlecase_Letter. 0041..005A ; Cased # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -2466,9 +2470,9 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN # ================================================ # Derived Property: Case_Ignorable (CI) -# As defined by Unicode Standard Definition D121 +# As defined by Unicode Standard Definition D136 # C is defined to be case-ignorable if -# Word_Break(C) = MidLetter or MidNumLet, or +# Word_Break(C) = MidLetter or MidNumLet or Single_Quote, or # General_Category(C) = Nonspacing_Mark (Mn), Enclosing_Mark (Me), Format (Cf), Modifier_Letter (Lm), or Modifier_Symbol (Sk). 0027 ; Case_Ignorable # Po APOSTROPHE @@ -2509,6 +2513,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 05F4 ; Case_Ignorable # Po HEBREW PUNCTUATION GERSHAYIM 0600..0604 ; Case_Ignorable # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT 0610..061A ; Case_Ignorable # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; Case_Ignorable # Cf ARABIC LETTER MARK 0640 ; Case_Ignorable # Lm ARABIC TATWEEL 064B..065F ; Case_Ignorable # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; Case_Ignorable # Mn ARABIC LETTER SUPERSCRIPT ALEF @@ -2630,6 +2635,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 17D7 ; Case_Ignorable # Lm KHMER SIGN LEK TOO 17DD ; Case_Ignorable # Mn KHMER SIGN ATTHACAN 180B..180D ; Case_Ignorable # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180E ; Case_Ignorable # Cf MONGOLIAN VOWEL SEPARATOR 1843 ; Case_Ignorable # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 18A9 ; Case_Ignorable # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Case_Ignorable # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -2637,6 +2643,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1932 ; Case_Ignorable # Mn LIMBU SMALL LETTER ANUSVARA 1939..193B ; Case_Ignorable # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; Case_Ignorable # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; Case_Ignorable # Mn BUGINESE VOWEL SIGN AE 1A56 ; Case_Ignorable # Mn TAI THAM CONSONANT SIGN MEDIAL LA 1A58..1A5E ; Case_Ignorable # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA 1A60 ; Case_Ignorable # Mn TAI THAM SIGN SAKOT @@ -2685,7 +2692,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 2027 ; Case_Ignorable # Po HYPHENATION POINT 202A..202E ; Case_Ignorable # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Case_Ignorable # Cf [5] WORD JOINER..INVISIBLE PLUS -206A..206F ; Case_Ignorable # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2066..206F ; Case_Ignorable # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 2071 ; Case_Ignorable # Lm SUPERSCRIPT LATIN SMALL LETTER I 207F ; Case_Ignorable # Lm SUPERSCRIPT LATIN SMALL LETTER N 2090..209C ; Case_Ignorable # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T @@ -2805,13 +2812,13 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1799 +# Total code points: 1806 # ================================================ # Derived Property: Changes_When_Lowercased (CWL) # Characters whose normalized forms are not stable under a toLowercase mapping. -# For more information, see D124 in Section 3.13, "Default Case Algorithms". +# For more information, see D139 in Section 3.13, "Default Case Algorithms". # Changes_When_Lowercased(X) is true when toLowercase(toNFD(X)) != toNFD(X) 0041..005A ; Changes_When_Lowercased # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -3392,7 +3399,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE # Derived Property: Changes_When_Uppercased (CWU) # Characters whose normalized forms are not stable under a toUppercase mapping. -# For more information, see D125 in Section 3.13, "Default Case Algorithms". +# For more information, see D140 in Section 3.13, "Default Case Algorithms". # Changes_When_Uppercased(X) is true when toUppercase(toNFD(X)) != toNFD(X) 0061..007A ; Changes_When_Uppercased # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z @@ -3988,7 +3995,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER # Derived Property: Changes_When_Titlecased (CWT) # Characters whose normalized forms are not stable under a toTitlecase mapping. -# For more information, see D126 in Section 3.13, "Default Case Algorithms". +# For more information, see D141 in Section 3.13, "Default Case Algorithms". # Changes_When_Titlecased(X) is true when toTitlecase(toNFD(X)) != toNFD(X) 0061..007A ; Changes_When_Titlecased # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z @@ -4585,7 +4592,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER # Derived Property: Changes_When_Casefolded (CWCF) # Characters whose normalized forms are not stable under case folding. -# For more information, see D127 in Section 3.13, "Default Case Algorithms". +# For more information, see D142 in Section 3.13, "Default Case Algorithms". # Changes_When_Casefolded(X) is true when toCasefold(toNFD(X)) != toNFD(X) 0041..005A ; Changes_When_Casefolded # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -5177,7 +5184,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE # Derived Property: Changes_When_Casemapped (CWCM) # Characters whose normalized forms are not stable under case mapping. -# For more information, see D128 in Section 3.13, "Default Case Algorithms". +# For more information, see D143 in Section 3.13, "Default Case Algorithms". # Changes_When_Casemapped(X) is true when CWL(X), or CWT(X), or CWU(X) 0041..005A ; Changes_When_Casemapped # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -6307,7 +6314,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 19DA ; ID_Continue # No NEW TAI LUE THAM DIGIT ONE 1A00..1A16 ; ID_Continue # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A17..1A18 ; ID_Continue # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; ID_Continue # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; ID_Continue # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; ID_Continue # Mn BUGINESE VOWEL SIGN AE 1A20..1A54 ; ID_Continue # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; ID_Continue # Mc TAI THAM CONSONANT SIGN MEDIAL RA 1A56 ; ID_Continue # Mn TAI THAM CONSONANT SIGN MEDIAL LA @@ -7831,7 +7839,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 19DA ; XID_Continue # No NEW TAI LUE THAM DIGIT ONE 1A00..1A16 ; XID_Continue # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A17..1A18 ; XID_Continue # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; XID_Continue # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; XID_Continue # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; XID_Continue # Mn BUGINESE VOWEL SIGN AE 1A20..1A54 ; XID_Continue # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; XID_Continue # Mc TAI THAM CONSONANT SIGN MEDIAL RA 1A56 ; XID_Continue # Mn TAI THAM CONSONANT SIGN MEDIAL LA @@ -8356,14 +8365,16 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO 00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN 034F ; Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER +061C ; Default_Ignorable_Code_Point # Cf ARABIC LETTER MARK 115F..1160 ; Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER 17B4..17B5 ; Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180E ; Default_Ignorable_Code_Point # Cf MONGOLIAN VOWEL SEPARATOR 200B..200F ; Default_Ignorable_Code_Point # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK 202A..202E ; Default_Ignorable_Code_Point # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Default_Ignorable_Code_Point # Cf [5] WORD JOINER..INVISIBLE PLUS -2065..2069 ; Default_Ignorable_Code_Point # Cn [5] <reserved-2065>..<reserved-2069> -206A..206F ; Default_Ignorable_Code_Point # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2065 ; Default_Ignorable_Code_Point # Cn <reserved-2065> +2066..206F ; Default_Ignorable_Code_Point # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 3164 ; Default_Ignorable_Code_Point # Lo HANGUL FILLER FE00..FE0F ; Default_Ignorable_Code_Point # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FEFF ; Default_Ignorable_Code_Point # Cf ZERO WIDTH NO-BREAK SPACE @@ -8378,7 +8389,7 @@ E0080..E00FF ; Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reser E0100..E01EF ; Default_Ignorable_Code_Point # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 4167 +# Total code points: 4169 # ================================================ @@ -8521,6 +8532,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 1932 ; Grapheme_Extend # Mn LIMBU SMALL LETTER ANUSVARA 1939..193B ; Grapheme_Extend # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; Grapheme_Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; Grapheme_Extend # Mn BUGINESE VOWEL SIGN AE 1A56 ; Grapheme_Extend # Mn TAI THAM CONSONANT SIGN MEDIAL LA 1A58..1A5E ; Grapheme_Extend # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA 1A60 ; Grapheme_Extend # Mn TAI THAM SIGN SAKOT @@ -8629,7 +8641,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1D242..1D244 ; Grapheme_Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1317 +# Total code points: 1318 # ================================================ @@ -9077,7 +9089,6 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1800..1805 ; Grapheme_Base # Po [6] MONGOLIAN BIRGA..MONGOLIAN FOUR DOTS 1806 ; Grapheme_Base # Pd MONGOLIAN TODO SOFT HYPHEN 1807..180A ; Grapheme_Base # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU -180E ; Grapheme_Base # Zs MONGOLIAN VOWEL SEPARATOR 1810..1819 ; Grapheme_Base # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; Grapheme_Base # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Grapheme_Base # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -9103,7 +9114,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 19DA ; Grapheme_Base # No NEW TAI LUE THAM DIGIT ONE 19DE..19FF ; Grapheme_Base # So [34] NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A16 ; Grapheme_Base # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA -1A19..1A1B ; Grapheme_Base # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; Grapheme_Base # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O 1A1E..1A1F ; Grapheme_Base # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 1A20..1A54 ; Grapheme_Base # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; Grapheme_Base # Mc TAI THAM CONSONANT SIGN MEDIAL RA @@ -9286,7 +9297,10 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 21D5..21F3 ; Grapheme_Base # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW 21F4..22FF ; Grapheme_Base # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP 2300..2307 ; Grapheme_Base # So [8] DIAMETER SIGN..WAVY LINE -2308..230B ; Grapheme_Base # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; Grapheme_Base # Ps LEFT CEILING +2309 ; Grapheme_Base # Pe RIGHT CEILING +230A ; Grapheme_Base # Ps LEFT FLOOR +230B ; Grapheme_Base # Pe RIGHT FLOOR 230C..231F ; Grapheme_Base # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER 2320..2321 ; Grapheme_Base # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2322..2328 ; Grapheme_Base # So [7] FROWN..KEYBOARD @@ -9980,7 +9994,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 108661 +# Total code points: 108659 # ================================================ diff --git a/lib/unicore/DNormalizationProps.txt b/lib/unicore/DNormalizationProps.txt index 2ecd8e22ff..e59d17715d 100644 --- a/lib/unicore/DNormalizationProps.txt +++ b/lib/unicore/DNormalizationProps.txt @@ -1,8 +1,8 @@ -# DerivedNormalizationProps-6.2.0.txt -# Date: 2012-05-23, 20:34:48 GMT [MD] +# DerivedNormalizationProps-6.3.0.txt +# 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> -206A..206F ; NFKC_CF; # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2065 ; NFKC_CF; # Cn <reserved-2065> +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> -206A..206F ; Changes_When_NFKC_Casefolded # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2065 ; Changes_When_NFKC_Casefolded # Cn <reserved-2065> +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 diff --git a/lib/unicore/EastAsianWidth.txt b/lib/unicore/EastAsianWidth.txt index 949f7ff392..e38e8c4bc2 100644 --- a/lib/unicore/EastAsianWidth.txt +++ b/lib/unicore/EastAsianWidth.txt @@ -1,39 +1,40 @@ -# EastAsianWidth-6.2.0.txt -# Date: 2012-05-15, 18:30:00 GMT [KW] +# EastAsianWidth-6.3.0.txt +# Date: 2013-02-05, 20:09:00 GMT [KW, LI] # # East Asian Width Properties # # 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 # # The format is two fields separated by a semicolon. # Field 0: Unicode value -# Field 1: East Asian Width property, consisting of one of the following values: +# Field 1: East_Asian_Width property, consisting of one of the following values: # "N", "A", "H", "W", "F", "Na" -# - All code points, assigned or unassigned, that are not listed +# - All code points, assigned or unassigned, that are not listed # explicitly are given the value "N". # The unassigned code points that default to "W" 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 +# - 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 #11: East Asian Width, for more information. +# For more information, see UAX #11: East Asian Width, +# at http://www.unicode.org/reports/tr11/ # # @missing: 0000..10FFFF; N 0000;N # <control> @@ -1547,6 +1548,7 @@ 0619;N # ARABIC SMALL DAMMA 061A;N # ARABIC SMALL KASRA 061B;N # ARABIC SEMICOLON +061C;N # ARABIC LETTER MARK 061E;N # ARABIC TRIPLE DOT PUNCTUATION MARK 061F;N # ARABIC QUESTION MARK 0620;N # ARABIC LETTER KASHMIRI YEH @@ -7154,6 +7156,10 @@ 2062;N # INVISIBLE TIMES 2063;N # INVISIBLE SEPARATOR 2064;N # INVISIBLE PLUS +2066;N # LEFT-TO-RIGHT ISOLATE +2067;N # RIGHT-TO-LEFT ISOLATE +2068;N # FIRST STRONG ISOLATE +2069;N # POP DIRECTIONAL ISOLATE 206A;N # INHIBIT SYMMETRIC SWAPPING 206B;N # ACTIVATE SYMMETRIC SWAPPING 206C;N # INHIBIT ARABIC FORM SHAPING diff --git a/lib/unicore/EmojiSources.txt b/lib/unicore/EmojiSources.txt index cf0f6cbf26..a573b95f53 100644 --- a/lib/unicore/EmojiSources.txt +++ b/lib/unicore/EmojiSources.txt @@ -1,5 +1,5 @@ -# EmojiSources-6.2.0.txt -# Date: 2012-03-08, 21:21:00 GMT [MS, KW] +# EmojiSources-6.3.0.txt +# Date: 2012-12-11, 11:07:00 GMT [MS, KW] # # Unicode Character Database # Copyright (c) 1991-2012 Unicode, Inc. @@ -16,8 +16,7 @@ # additional data columns providing mappings for additional vendors. # # Created for Unicode 6.0 by Markus Scherer. -# Updated for Unicode 6.1 by Ken Whistler (no changes to mappings). -# Updated for Unicode 6.2 by Ken Whistler (no changes to mappings). +# Updated for Unicode 6.1, 6.2, and 6.3 by Ken Whistler (no changes to mappings). # # Format: Semicolon-delimited file with a fixed number of fields. # The number of fields may increase in the future. diff --git a/lib/unicore/HangulSyllableType.txt b/lib/unicore/HangulSyllableType.txt index a4db00b2f3..6c9962fa68 100644 --- a/lib/unicore/HangulSyllableType.txt +++ b/lib/unicore/HangulSyllableType.txt @@ -1,8 +1,8 @@ -# HangulSyllableType-6.2.0.txt -# Date: 2012-05-23, 20:34:56 GMT [MD] +# HangulSyllableType-6.3.0.txt +# 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/ diff --git a/lib/unicore/Index.txt b/lib/unicore/Index.txt index c9885ac30e..d8bd3d3282 100644 --- a/lib/unicore/Index.txt +++ b/lib/unicore/Index.txt @@ -258,6 +258,7 @@ arabic kashida 0640 Arabic Koranic Annotation Signs 06D6 arabic letter hamzah on ha 06C0 ARABIC LETTER HEH WITH YEH ABOVE 06C0 +ARABIC LETTER MARK 061C Arabic Letters, Extended 0671 Arabic Letters, Extended 0750 ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM FDFD @@ -1521,6 +1522,7 @@ direct product 2299 direct sum 2295 Directional Format Characters 202A DIRECTIONAL FORMATTING, POP 202C +DIRECTIONAL ISOLATE, POP 2069 DISCONTINUOUS UNDERLINE SYMBOL 2382 discretionary hyphen 00AD disjunction 2228 @@ -1978,6 +1980,7 @@ finite surjection 2901 finite surjective injection 2918 FIRE 1F525 FIRST QUARTER MOON 263D +FIRST STRONG ISOLATE 2068 FISH 1F41F Fish Tails 297C FISH, TROPICAL 1F420 @@ -2627,6 +2630,10 @@ IPA Extensions 0250 IPA, Diacritics for 0346 iranian currency FDFC irish punt 00A3 +ISOLATE, FIRST STRONG 2068 +ISOLATE, LEFT-TO-RIGHT 2066 +ISOLATE, POP DIRECTIONAL 2069 +ISOLATE, RIGHT-TO-LEFT 2067 isotech entity ⧜ 29DC israeli currency 20AA ISSHAR, BENGALI 09FA @@ -2973,6 +2980,7 @@ LEFT-POINTING ANGLE BRACKET 2329 LEFT-POINTING ANGLE QUOTATION MARK, SINGLE 2039 LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 00AB LEFT-TO-RIGHT EMBEDDING 202A +LEFT-TO-RIGHT ISOLATE 2066 LEFT-TO-RIGHT MARK 200E LEFT-TO-RIGHT OVERRIDE 202D leftward tab 21E4 @@ -3916,6 +3924,7 @@ Polytonic Greek, Precomposed 1F00 POO, PILE OF 1F4A9 POODLE 1F429 POP DIRECTIONAL FORMATTING 202C +POP DIRECTIONAL ISOLATE 2069 pork (on menus) 1F416 Portrait and Role Symbols 1F464 POSITION INDICATOR 2316 @@ -4303,6 +4312,7 @@ RIGHT-POINTING ANGLE BRACKET 232A RIGHT-POINTING ANGLE QUOTATION MARK, SINGLE 203A RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 00BB RIGHT-TO-LEFT EMBEDDING 202B +RIGHT-TO-LEFT ISOLATE 2067 RIGHT-TO-LEFT MARK 200F RIGHT-TO-LEFT OVERRIDE 202E RIGHTHAND INTERIOR PRODUCT 2A3D diff --git a/lib/unicore/IndicMatraCategory.txt b/lib/unicore/IndicMatraCategory.txt index 03a043ed87..04cb93296c 100644 --- a/lib/unicore/IndicMatraCategory.txt +++ b/lib/unicore/IndicMatraCategory.txt @@ -1,16 +1,16 @@ -# IndicMatraCategory-6.2.0.txt -# Date: 2012-05-15, 21:10:00 GMT [KW] +# IndicMatraCategory-6.3.0.txt +# Date: 2013-01-02, 08:33:00 GMT [KW, LI] # # 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 UAX #44. +# For documentation, see UAX #44, at http://www.unicode.org/reports/tr44/ # # This file defines the following provisional property: # # Indic_Matra_Category enumerated property # -# NB: Provisional properties and data files have no associated stability +# NB: Provisional properties and data files have no associated stability # guarantees. They are provided in part to determine the possible usefulness # of a property or other data and to encourage analysis and further investigation # which may result in their improvement. Provisional properties and @@ -47,7 +47,7 @@ # 4. Matra display may be contextually determined. This is # notable, for example, in the Tamil script, where the shape # and placement of -u and -uu vowels depends strongly on -# which consonant they adjoin. +# which consonant they adjoin. # # Format: # Field 0 Code Point or Code Point Range @@ -210,7 +210,7 @@ AAEE ; Left # Mc MEETEI MAYEK VOWEL SIGN AU # model, these left-side vowels occur first in the backing store (before # the consonant letter) and are not reordered during text rendering. # -# [Derivation: Logical_Order_Exception=True] +# [Derivation: Logical_Order_Exception=Yes] 0E40..0E44 ; Visual_Order_Left # Lo [5] THAI CHARACTER SARA E..THAI CHARACTER SARA AI MAIMALAI 0EC0..0EC4 ; Visual_Order_Left # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI diff --git a/lib/unicore/IndicSyllabicCategory.txt b/lib/unicore/IndicSyllabicCategory.txt index fd03ea335b..31f2e4b9b3 100644 --- a/lib/unicore/IndicSyllabicCategory.txt +++ b/lib/unicore/IndicSyllabicCategory.txt @@ -1,16 +1,16 @@ -# IndicSyllabicCategory-6.2.0.txt -# Date: 2012-05-15, 21:12:00 GMT [KW] +# IndicSyllabicCategory-6.3.0.txt +# Date: 2013-08-01, 21:17:00 GMT [KW, LI] # # 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 UAX #44. +# For documentation, see UAX #44, at http://www.unicode.org/reports/tr44/ # # This file defines the following provisional property: # # Indic_Syllabic_Category enumerated property # -# NB: Provisional properties and data files have no associated stability +# NB: Provisional properties and data files have no associated stability # guarantees. They are provided in part to determine the possible usefulness # of a property or other data and to encourage analysis and further investigation # which may result in their improvement. Provisional properties and @@ -89,18 +89,18 @@ 17C6 ; Bindu # Mn KHMER SIGN NIKAHIT 1932 ; Bindu # Mn LIMBU SMALL LETTER ANUSVARA 1B00..1B02 ; Bindu # Mn [3] BALINESE SIGN ULU RICEM..BALINESE SIGN CECEK -A80B ; Bindu # Mn SYLOTI NAGRI SIGN ANUSVARA -A873 ; Bindu # Lo PHAGS-PA LETTER CANDRABINDU -A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 1B80 ; Bindu # Mn SUNDANESE SIGN PANYECEK 1C34..1C35 ; Bindu # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG +A80B ; Bindu # Mn SYLOTI NAGRI SIGN ANUSVARA +A873 ; Bindu # Lo PHAGS-PA LETTER CANDRABINDU A880 ; Bindu # Mc SAURASHTRA SIGN ANUSVARA +A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 10A0E ; Bindu # Mn KHAROSHTHI SIGN ANUSVARA 11000 ; Bindu # Mc BRAHMI SIGN CANDRABINDU 11001 ; Bindu # Mn BRAHMI SIGN ANUSVARA 11080..11081 ; Bindu # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA -11100..11101 ; Bindu # Mn CHAKMA SIGN CANDRABINDU..CHAKMA SIGN ANUSVARA -11180..11181 ; Bindu # Mn SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +11100..11101 ; Bindu # Mn [2] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN ANUSVARA +11180..11181 ; Bindu # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA 116AB ; Bindu # Mn TAKRI SIGN ANUSVARA # ================================================ @@ -222,7 +222,7 @@ ABED ; Virama # Mn MEETEI MAYEK APUN IYEK 10A3F ; Virama # Mn KHAROSHTHI VIRAMA 11046 ; Virama # Mn BRAHMI VIRAMA 110B9 ; Virama # Mn KAITHI SIGN VIRAMA -11133..11134 ; Virama # Mn CHAKMA VIRAMA..CHAKMA MAAYYAA +11133..11134 ; Virama # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA 111C0 ; Virama # Mc SHARADA SIGN VIRAMA 116B6 ; Virama # Mn TAKRI SIGN VIRAMA @@ -309,7 +309,7 @@ ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA 0941..0948 ; Vowel_Dependent # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI 0949..094C ; Vowel_Dependent # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU 094E..094F ; Vowel_Dependent # Mc [2] DEVANAGARI VOWEL SIGN PRISHTHAMATRA E..DEVANAGARI VOWEL SIGN AW -0955..0957 ; Vowel_Dependent # Mn DEVANAGARI VOWEL SIGN CANDRA LONG E..DEVANAGARI VOWEL SIGN UUE +0955..0957 ; Vowel_Dependent # Mn [3] DEVANAGARI VOWEL SIGN CANDRA LONG E..DEVANAGARI VOWEL SIGN UUE 0962..0963 ; Vowel_Dependent # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL 09BE..09C0 ; Vowel_Dependent # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II 09C1..09C4 ; Vowel_Dependent # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR @@ -508,7 +508,7 @@ A926..A92A ; Vowel # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O # [Not derivable] -0915..0939 ; Consonant # Lo [35] DEVANAGARI LETTER KA..DEVANAGARI LETTER HA +0915..0939 ; Consonant # Lo [37] DEVANAGARI LETTER KA..DEVANAGARI LETTER HA 0958..095F ; Consonant # Lo [8] DEVANAGARI LETTER QA..DEVANAGARI LETTER YYA 0979..097F ; Consonant # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA 0995..09A8 ; Consonant # Lo [20] BENGALI LETTER KA..BENGALI LETTER NA @@ -612,7 +612,7 @@ A892..A8B3 ; Consonant # Lo [34] SAURASHTRA LETTER KA..SAURASHTRA LETTER LLA A90A..A921 ; Consonant # Lo [24] KAYAH LI LETTER KA..KAYAH LI LETTER CA A930..A946 ; Consonant # Lo [23] REJANG LETTER KA..REJANG LETTER A A989..A98B ; Consonant # Lo [3] JAVANESE LETTER PA CEREK..JAVANESE LETTER NGA LELET RASWADI -A98F..A9B2 ; Consonant # Lo [34] JAVANESE LETTER KA..JAVANESE LETTER HA +A98F..A9B2 ; Consonant # Lo [36] JAVANESE LETTER KA..JAVANESE LETTER HA AA06..AA28 ; Consonant # Lo [35] CHAM LETTER KA..CHAM LETTER HA AA60..AA6F ; Consonant # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA AA71..AA73 ; Consonant # Lo [3] MYANMAR LETTER KHAMTI XA..MYAMNAR LETTER KHAMTI RA @@ -693,7 +693,7 @@ A9BD ; Consonant_Subjoined # Mc JAVANESE CONSONANT SIGN KERET 1082 ; Consonant_Medial # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA 1A55 ; Consonant_Medial # Mc TAI THAM CONSONANT SIGN MEDIAL RA 1A56 ; Consonant_Medial # Mn TAI THAM CONSONANT SIGN MEDIAL LA -A9BE..A9BF ; Consonant_Medial # Mc JAVANESE CONSONANT SIGN PENGKAL..JAVANESE CONSONANT SIGN CAKRA +A9BE..A9BF ; Consonant_Medial # Mc [2] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE CONSONANT SIGN CAKRA AA33..AA34 ; Consonant_Medial # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA AA35..AA36 ; Consonant_Medial # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA diff --git a/lib/unicore/Jamo.txt b/lib/unicore/Jamo.txt index ee32f6e6c1..f288681812 100644 --- a/lib/unicore/Jamo.txt +++ b/lib/unicore/Jamo.txt @@ -1,14 +1,14 @@ -# Jamo-6.2.0.txt -# Date: 2012-05-15, 22:23:00 GMT [KW, LI] +# Jamo-6.3.0.txt +# Date: 2013-01-02, 08:35:00 GMT [KW, LI] # # 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/ # # This file defines the Jamo_Short_Name property. # -# See Section 3.12 of The Unicode Standard, Version 6.2 +# See Section 3.12 of The Unicode Standard, Version 6.3 # for more information. # # Each line contains two fields, separated by a semicolon. diff --git a/lib/unicore/LineBreak.txt b/lib/unicore/LineBreak.txt index e309836b0e..8a72cabf78 100644 --- a/lib/unicore/LineBreak.txt +++ b/lib/unicore/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 diff --git a/lib/unicore/NameAliases.txt b/lib/unicore/NameAliases.txt index 482fb92be4..4d5d1e231e 100644 --- a/lib/unicore/NameAliases.txt +++ b/lib/unicore/NameAliases.txt @@ -1,10 +1,10 @@ -# NameAliases-6.2.0.txt -# Date: 2012-05-15, 18:44:00 GMT [KW] +# NameAliases-6.3.0.txt +# Date: 2013-02-05, 23:33:00 GMT [KW] # # This file is a normative contributory data file in the # Unicode Character Database. # -# Copyright (c) 2005-2012 Unicode, Inc. +# Copyright (c) 2005-2013 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # This file defines the formal name aliases for Unicode characters. @@ -216,6 +216,7 @@ 01A2;LATIN CAPITAL LETTER GHA;correction 01A3;LATIN SMALL LETTER GHA;correction 034F;CGJ;abbreviation +061C;ALM;abbreviation 0709;SYRIAC SUBLINEAR COLON SKEWED LEFT;correction 0CDE;KANNADA LETTER LLLA;correction 0E9D;LAO LETTER FO FON;correction @@ -240,6 +241,10 @@ 202F;NNBSP;abbreviation 205F;MMSP;abbreviation 2060;WJ;abbreviation +2066;LRI;abbreviation +2067;RLI;abbreviation +2068;FSI;abbreviation +2069;PDI;abbreviation 2118;WEIERSTRASS ELLIPTIC FUNCTION;correction 2448;MICR ON US SYMBOL;correction 2449;MICR DASH SYMBOL;correction @@ -264,6 +269,8 @@ FE0F;VS16;abbreviation FEFF;BYTE ORDER MARK;alternate FEFF;BOM;abbreviation FEFF;ZWNBSP;abbreviation +122D4;CUNEIFORM SIGN NU11 TENU;correction +122D5;CUNEIFORM SIGN NU11 OVER NU11 BUR OVER BUR;correction 1D0C5;BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS;correction E0100;VS17;abbreviation E0101;VS18;abbreviation diff --git a/lib/unicore/NamedSequences.txt b/lib/unicore/NamedSequences.txt index 040acdb6c3..e1ae2b740e 100644 --- a/lib/unicore/NamedSequences.txt +++ b/lib/unicore/NamedSequences.txt @@ -1,5 +1,5 @@ -# NamedSequences-6.2.0.txt -# Date: 2012-05-15, 21:23:00 GMT [KW] +# NamedSequences-6.3.0.txt +# Date: 2012-11-14, 21:51:00 GMT [KW] # # Unicode Character Database # Copyright (c) 1991-2012 Unicode, Inc. @@ -104,8 +104,23 @@ LATIN SMALL LETTER SCHWA WITH ACUTE;0259 0301 LATIN SMALL LETTER HOOKED SCHWA WITH GRAVE;025A 0300 LATIN SMALL LETTER HOOKED SCHWA WITH ACUTE;025A 0301 +# Entries for Uyghur and Chagatai. +# Provisional: N/A, Approved: 2012-11-08 + +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH ALEF;0626 0627 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH WAW;0626 0648 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH ALEF MAKSURA;0626 0649 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH OE;0626 06C6 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH U;0626 06C7 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH YU;0626 06C8 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH E;0626 06D0 +ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH AE;0626 06D5 +ARABIC SEQUENCE NOON WITH KEHEH;0646 06A9 + # Entry for a Bangla entity. # Provisional: 2009-08-10, Approved 2010-05-14 +# +# Note that this same sequence is also used for the ASSAMESE LETTER KSSA. BENGALI LETTER KHINYA;0995 09CD 09B7 diff --git a/lib/unicore/NamedSqProv.txt b/lib/unicore/NamedSqProv.txt index 7d87629e01..2f245a2dac 100644 --- a/lib/unicore/NamedSqProv.txt +++ b/lib/unicore/NamedSqProv.txt @@ -1,8 +1,8 @@ -# NamedSequencesProv-6.2.0.txt -# Date: 2012-05-15, 21:29:00 GMT [KW] +# NamedSequencesProv-6.3.0.txt +# Date: 2013-01-02, 08:37:00 GMT [KW] # # 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/ # diff --git a/lib/unicore/NamesList.txt b/lib/unicore/NamesList.txt index 17bd45b0a4..3db6a95b8c 100644 --- a/lib/unicore/NamesList.txt +++ b/lib/unicore/NamesList.txt @@ -1,17 +1,49 @@ ; charset=UTF-8 -@@@ The Unicode Standard 6.2 -@@@+ U62M120808.lst - Unicode 6.2 names list, third delta (converted to UTF-8). - Updated more annotations in the Bengali block. - Added clarifying annotations for 0342. - Updated alias for 1110E. +@@@ The Unicode Standard 6.3.0 +@@@+ U63M130730.lst + Unicode 6.3.0 names list, fourteenth delta. + Updated annotation for U+A980. + Move subhead for U+200C to include U+200B. + Commented out alt glyph lines for 222B, 222C. + Updated annotations for U+3001 and U+FF0C. + Merged with applicable annotations from DAM1 text. + Added annotation for 06BA. + Added notice about spelling of Oriya as Odia. + Added aliases for 09F0 and 09F1. + Added annotations and xrefs for 0022, 0027, 05F3, 05F4. + Tweaked annotations for 0022, 0027. + Added subhead for new bidi format controls at 2066. + Added formal name aliases for 122D4 and 122D5. + Update xref for 2EE7. + Added xrefs for 2696, 1F40F, 264E, 2648. + Added notice for Bengali block. + Adjustments for adding 061C to repertoire. + Added annotation for A9CF. + Added annotations for 2592. + Added annotation for 111C4. + Updated aliases for FEFF. + Added xrefs for 2294 and 2A03. + Added xrefs for 002D and 2043. + Updated annotations for noncharacters, consistent with Corrigendum #9. + Updated annotation for 0024. + Updated annotation for 0B83. + Added annotation for 06AA. + Updated notice at 2500. + Updated subheads for various Jamo blocks. + Updated annotations and cross-references for several math characters. + Updated casing for two Assamese annotations. + Removed extraneous tab in entry for 1F4AE. + Added several explicit standardized variant summary headers. + Added notice about the exceptional bidi behavior of FD3E and FD3F. + Added xrefs for diamonds and squares related to modal logic. + Removed obelus as alias for 2020. This file is semi-automatically derived from UnicodeData.txt and a set of manually created annotations using a script to select or suppress information from the data file. The rules used for this process are aimed at readability for the human reader, at the expense of some details; therefore, this file should not be parsed for machine-readable information. -@+ 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 @@ 0000 C0 Controls and Basic Latin (Basic Latin) 007F @@+ @@ -112,9 +144,11 @@ 0022 QUOTATION MARK * neutral (vertical), used as opening or closing quotation mark * preferred characters in English for paired quotation marks are 201C & 201D + * 05F4 is preferred for gershayim when writing Hebrew x (modifier letter double prime - 02BA) x (combining double acute accent - 030B) x (combining double vertical line above - 030E) + x (hebrew punctuation gershayim - 05F4) x (double prime - 2033) x (ditto mark - 3003) 0023 NUMBER SIGN @@ -127,7 +161,7 @@ = milréis, escudo * used for many peso currencies in Latin America and elsewhere * glyph may have one or two vertical bars - * other currency symbol characters: 20A0-20BA + * other currency symbol characters start at 20A0 x (currency sign - 00A4) x (peso sign - 20B1) x (heavy dollar sign - 1F4B2) @@ -145,10 +179,12 @@ * neutral (vertical) glyph with mixed usage * 2019 is preferred for apostrophe * preferred characters in English for paired quotation marks are 2018 & 2019 + * 05F3 is preferred for geresh when writing Hebrew x (modifier letter prime - 02B9) x (modifier letter apostrophe - 02BC) x (modifier letter vertical line - 02C8) x (combining acute accent - 0301) + x (hebrew punctuation geresh - 05F3) x (prime - 2032) x (latin small letter saltillo - A78C) 0028 LEFT PARENTHESIS @@ -177,6 +213,7 @@ x (non-breaking hyphen - 2011) x (figure dash - 2012) x (en dash - 2013) + x (hyphen bullet - 2043) x (minus sign - 2212) x (roman uncia sign - 10191) 002E FULL STOP @@ -223,6 +260,7 @@ ~ 0039 FE0F emoji style @ ASCII punctuation and symbols 003A COLON + * also used to denote division or scale; for that mathematical use 2236 is preferred x (armenian full stop - 0589) x (hebrew punctuation sof pasuq - 05C3) x (ratio - 2236) @@ -409,7 +447,7 @@ @ Control character 007F <control> = DELETE -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 0080 C1 Controls and Latin-1 Supplement (Latin-1 Supplement) 00FF @ C1 controls @+ Alias names are those for ISO/IEC 6429:1992. @@ -573,6 +611,7 @@ = midpoint (in typography) = Georgian comma = Greek middle dot (ano teleia) + * also used as a raised decimal point or to denote multiplication; for multiplication 22C5 is preferred x (greek ano teleia - 0387) x (runic single punctuation - 16EB) x (bullet - 2022) @@ -750,8 +789,15 @@ : 006F 0308 @ Mathematical operator 00F7 DIVISION SIGN + = obelus + * occasionally used as an alternate, more visually distinct version of 2212 or 2011 in some contexts + * historically used as a punctuation mark to denote questionable passages in manuscripts + x (syriac harklean obelus - 070B) + x (commercial minus sign - 2052) + x (minus sign - 2212) x (division slash - 2215) x (divides - 2223) + x (ratio - 2236) x (heavy division sign - 2797) @ Letters 00F8 LATIN SMALL LETTER O WITH STROKE @@ -2549,6 +2595,7 @@ 0360 COMBINING DOUBLE TILDE 0361 COMBINING DOUBLE INVERTED BREVE = ligature tie + x (combining ligature left half - FE20) 0362 COMBINING DOUBLE RIGHTWARDS ARROW BELOW * IPA: sliding articulation @ Medieval superscript letter diacritics @@ -3588,7 +3635,9 @@ = tsvey yudn @ Additional punctuation 05F3 HEBREW PUNCTUATION GERESH + x (apostrophe - 0027) 05F4 HEBREW PUNCTUATION GERSHAYIM + x (quotation mark - 0022) @@ 0600 Arabic 06FF @@+ @ Subtending marks @@ -3652,6 +3701,10 @@ * also used with Thaana and Syriac in modern text x (semicolon - 003B) x (turned semicolon - 2E35) +@ Format character +061C ARABIC LETTER MARK + * commonly abbreviated ALM +@ Punctuation 061E ARABIC TRIPLE DOT PUNCTUATION MARK 061F ARABIC QUESTION MARK * also used with Thaana and Syriac in modern text @@ -3919,6 +3972,7 @@ 06A9 ARABIC LETTER KEHEH * Persian, Urdu, ... 06AA ARABIC LETTER SWASH KAF + * represents a letter distinct from Arabic KAF (0643) in Sindhi 06AB ARABIC LETTER KAF WITH RING * Pashto * may appear like an Arabic KAF (0643) with a ring below the base @@ -3950,6 +4004,7 @@ 06B9 ARABIC LETTER NOON WITH DOT BELOW 06BA ARABIC LETTER NOON GHUNNA * Urdu + * dotless in all contextual forms 06BB ARABIC LETTER RNOON * Sindhi 06BC ARABIC LETTER NOON WITH RING @@ -4105,6 +4160,7 @@ * placed at the end of an incomplete word 070B SYRIAC HARKLEAN OBELUS * marks the beginning of a phrase, word, or morpheme that has a marginal note + x (division sign - 00F7) 070C SYRIAC HARKLEAN METOBELUS * marks the end of a section with a marginal note 070D SYRIAC HARKLEAN ASTERISCUS @@ -4575,8 +4631,9 @@ 08FB ARABIC DOUBLE RIGHT ARROWHEAD ABOVE 08FC ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT 08FD ARABIC RIGHT ARROWHEAD ABOVE WITH DOT -@ Extended vowel sign for Philippine languages +@ Extended vowel signs 08FE ARABIC DAMMA WITH DOT + * Philippine languages @@ 0900 Devanagari 097F @@+ @ Various signs @@ -4781,6 +4838,7 @@ 097E DEVANAGARI LETTER DDDA 097F DEVANAGARI LETTER BBA @@ 0980 Bengali 09FF +@+ The Bengali script is also known as Bangla. In Assam, the preferred name of the script is Asamiya or Assamese. The Assamese language has also been written historically using distinct regional scripts known as Kamrupi. @ Various signs 0981 BENGALI SIGN CANDRABINDU 0982 BENGALI SIGN ANUSVARA @@ -4894,7 +4952,9 @@ 09EF BENGALI DIGIT NINE @ Additions for Assamese 09F0 BENGALI LETTER RA WITH MIDDLE DIAGONAL + = Assamese letter ra 09F1 BENGALI LETTER RA WITH LOWER DIAGONAL + = Assamese letter wa = bengali letter va with lower diagonal (1.0) @ Currency signs 09F2 BENGALI RUPEE MARK @@ -5148,6 +5208,7 @@ 0AF1 GUJARATI RUPEE SIGN * preferred spelling is 0AB0 0AC2 0AF0 @@ 0B00 Oriya 0B7F +@+ As of 2012, the name "Oriya" for this script and language is officially spelled "Odia" in India. That change in spelling does not affect the Unicode block or character names, which are constrained by stability guarantees. @ Various signs 0B01 ORIYA SIGN CANDRABINDU 0B02 ORIYA SIGN ANUSVARA @@ -5283,7 +5344,7 @@ * not used in Tamil 0B83 TAMIL SIGN VISARGA = aytham - * in fonts which display the Tamil pulli as a ring shape, the glyph for aytham also uses rings + * just as for the Tamil pulli, the glyph for aytham may use either dots or rings @ Independent vowels 0B85 TAMIL LETTER A 0B86 TAMIL LETTER AA @@ -5393,6 +5454,7 @@ @ Various signs 0C01 TELUGU SIGN CANDRABINDU = arasunna + * indicates a contextually elided nasal 0C02 TELUGU SIGN ANUSVARA = sunna 0C03 TELUGU SIGN VISARGA @@ -6906,6 +6968,7 @@ 1112 HANGUL CHOSEONG HIEUH = H * voiceless glottal fricative +@ Old initial consonants 1113 HANGUL CHOSEONG NIEUN-KIYEOK 1114 HANGUL CHOSEONG SSANGNIEUN 1115 HANGUL CHOSEONG NIEUN-TIKEUT @@ -7040,6 +7103,7 @@ = YI 1175 HANGUL JUNGSEONG I = I +@ Old medial vowels 1176 HANGUL JUNGSEONG A-O 1177 HANGUL JUNGSEONG A-U 1178 HANGUL JUNGSEONG YA-O @@ -7147,6 +7211,7 @@ = P 11C2 HANGUL JONGSEONG HIEUH = H +@ Old final consonants 11C3 HANGUL JONGSEONG KIYEOK-RIEUL 11C4 HANGUL JONGSEONG KIYEOK-SIOS-KIYEOK 11C5 HANGUL JONGSEONG NIEUN-KIYEOK @@ -9203,7 +9268,7 @@ 18A8 MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9 MONGOLIAN LETTER ALI GALI DAGALGA 18AA MONGOLIAN LETTER MANCHU ALI GALI LHA -@~ Standarized Variation Sequences +@~ Standardized Variation Sequences @+ Unlike other blocks, these variation sequences use the script-specific variation selectors for Mongolian. @@ 18B0 Unified Canadian Aboriginal Syllabics Extended 18FF @ Syllables for Moose Cree @@ -11873,10 +11938,10 @@ * thinner than a thin space * in traditional typography, the thinnest space available # 0020 space +@ Format characters 200B ZERO WIDTH SPACE * commonly abbreviated ZWSP * this character is intended for invisible word separation and for line break control; it has no width, but its presence between two characters does not prevent increased letter spacing in justification -@ Format characters 200C ZERO WIDTH NON-JOINER * commonly abbreviated ZWNJ 200D ZERO WIDTH JOINER @@ -11954,7 +12019,7 @@ * has same semantic as 201C, but differs in appearance @ General punctuation 2020 DAGGER - = obelisk, obelus, long cross + = obelisk, long cross, oblong cross x (turned dagger - 2E38) 2021 DOUBLE DAGGER = diesis, double obelisk @@ -12086,6 +12151,7 @@ x (right semidirect product - 22CC) 2042 ASTERISM 2043 HYPHEN BULLET + x (hyphen-minus - 002D) 2044 FRACTION SLASH = solidus (in typography) * for composing arbitrary fractions @@ -12125,6 +12191,7 @@ * used in Finno-Ugric Phonetic Alphabet to indicate a related borrowed form with different sound x (percent sign - 0025) x (arabic percent sign - 066A) + x (division sign - 00F7) 2053 SWUNG DASH x (tilde - 007E) 2054 INVERTED UNDERTIE @@ -12182,6 +12249,11 @@ * contiguity operator indicating that adjacent mathematical symbols form a list, e.g. when no visible comma is used between multiple indices 2064 INVISIBLE PLUS * contiguity operator indicating addition +@ Format characters +2066 LEFT-TO-RIGHT ISOLATE +2067 RIGHT-TO-LEFT ISOLATE +2068 FIRST STRONG ISOLATE +2069 POP DIRECTIONAL ISOLATE @ Deprecated @+ Use of these characters is strongly discouraged. 206A INHIBIT SYMMETRIC SWAPPING @@ -12190,7 +12262,7 @@ 206D ACTIVATE ARABIC FORM SHAPING 206E NATIONAL DIGIT SHAPES 206F NOMINAL DIGIT SHAPES -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2070 Superscripts and Subscripts 209F @ Superscripts @+ See also superscript Latin letters in the Spacing Modifier Letters block starting at 02B0. @@ -12695,7 +12767,7 @@ x (greek small letter digamma - 03DD) @ Biblical editorial symbol 214F SYMBOL FOR SAMARITAN SOURCE -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2150 Number Forms 218F @ Fractions @+ Other fraction number forms are found in the Latin-1 Supplement block. @@ -13024,7 +13096,7 @@ 21FD LEFTWARDS OPEN-HEADED ARROW 21FE RIGHTWARDS OPEN-HEADED ARROW 21FF LEFT RIGHT OPEN-HEADED ARROW -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2200 Mathematical Operators 22FF @@+ @ Miscellaneous mathematical symbols @@ -13161,10 +13233,10 @@ 222B INTEGRAL x (latin small letter esh - 0283) ;experimenting with variant syntax - ~ 222B ALT1 slanted style +; ~ 222B ALT1 slanted style 222C DOUBLE INTEGRAL ;experimenting with variant syntax - ~ 222C ALT1 slanted style +; ~ 222C ALT1 slanted style # 222B 222B 222D TRIPLE INTEGRAL x (quadruple integral operator - 2A0C) @@ -13185,6 +13257,7 @@ 2235 BECAUSE @ Relations 2236 RATIO + * preferred to 003A for denotation of division or scale in mathematical use x (colon - 003A) 2237 PROPORTION @ Operator @@ -13359,6 +13432,7 @@ x (n-ary square intersection operator - 2A05) ~ 2293 FE00 with serifs 2294 SQUARE CUP + x (n-ary square union operator - 2A06) ~ 2294 FE00 with serifs 2295 CIRCLED PLUS = direct sum @@ -13477,6 +13551,7 @@ x (white diamond - 25C7) x (black small diamond - 2B29) 22C5 DOT OPERATOR + * preferred to 00B7 for denotation of multiplication x (middle dot - 00B7) 22C6 STAR OPERATOR * APL @@ -13565,10 +13640,7 @@ 22FD CONTAINS WITH OVERBAR 22FE SMALL CONTAINS WITH OVERBAR 22FF Z NOTATION BAG MEMBERSHIP -@@~ Alternative Glyph Listing -@+ Experimental listing -@~ Standarized Variation Sequences -@+ Experimental listing +@~ Standardized Variation Sequences @@ 2300 Miscellaneous Technical 23FF @ Miscellaneous technical 2300 DIAMETER SIGN @@ -14005,7 +14077,7 @@ 23F2 TIMER CLOCK 23F3 HOURGLASS WITH FLOWING SAND x (hourglass - 231B) -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2400 Control Pictures 243F @+ The diagonal lettering glyphs are only exemplary; alternate representations may be, and often are used in the visible display of control codes. @ Graphic pictures for control codes @@ -14401,9 +14473,9 @@ @ Additional white on black circled number 24FF NEGATIVE CIRCLED DIGIT ZERO x (dingbat negative circled digit one - 2776) -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2500 Box Drawing 257F -@+ All of these characters are intended for compatibility with old sets oriented toward character cell graphics. +@+ All of these characters are intended for compatibility with character cell graphic sets in use prior to 1990. @ Light and heavy solid lines 2500 BOX DRAWINGS LIGHT HORIZONTAL = Videotex Mosaic DG 15 @@ -14593,7 +14665,9 @@ 2591 LIGHT SHADE * 25% 2592 MEDIUM SHADE + = speckles fill, dotted fill * 50% + * used in mapping to cp949 2593 DARK SHADE * 75% @ Block elements @@ -14622,6 +14696,7 @@ = alchemical symbol for salt * may be used to represent a missing ideograph x (combining enclosing square - 20DE) + x (white medium square - 25FB) x (ballot box - 2610) x (white large square - 2B1C) x (geta mark - 3013) @@ -14704,6 +14779,7 @@ x (combining enclosing diamond - 20DF) x (diamond operator - 22C4) x (white diamond suit - 2662) + x (white concave-sided diamond - 27E1) x (white medium diamond - 2B26) x (alchemical symbol for soap - 1F754) 25C8 WHITE DIAMOND CONTAINING BLACK SMALL DIAMOND @@ -14791,6 +14867,7 @@ 25FB WHITE MEDIUM SQUARE = always (modal operator) x (white square - 25A1) + x (white square with leftwards tick - 27E4) ~ 25FB FE0E text style ~ 25FB FE0F emoji style 25FC BLACK MEDIUM SQUARE @@ -14807,8 +14884,7 @@ ~ 25FE FE0F emoji style 25FF LOWER RIGHT TRIANGLE x (right triangle - 22BF) -@~ Standarized Variation Sequences -@+ Emoji style variants include rendering of characters in ways not achievable with traditional or even digital typography. The sample glyphs shown here cannot faithfully represent the range of intended appearances. +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2600 Miscellaneous Symbols 26FF @@+ @ Weather and astrological symbols @@ -14994,6 +15070,7 @@ 2647 PLUTO @ Zodiacal symbols 2648 ARIES + x (ram - 1F40F) ~ 2648 FE0E text style ~ 2648 FE0F emoji style 2649 TAURUS @@ -15013,6 +15090,7 @@ ~ 264D FE0E text style ~ 264D FE0F emoji style 264E LIBRA + x (scales - 2696) x (alchemical symbol for sublimation - 1F75E) ~ 264E FE0E text style ~ 264E FE0F emoji style @@ -15168,6 +15246,7 @@ x (caduceus - 2624) 2696 SCALES = legal term, jurisprudence + x (libra - 264E) 2697 ALEMBIC = chemical term, chemistry x (alchemical symbol for retort - 1F76D) @@ -15444,7 +15523,7 @@ x (teacup without handle - 1F375) 26FF WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE = Japanese self-defence force site -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2700 Dingbats 27BF @+ ITC Zapf dingbats series 100. Some of the ITC Zapf dingbats have been unified with geometric shape characters. Gaps in the chart have subsequently been filled with other dingbat-like symbols. x (black telephone - 260E) @@ -15747,7 +15826,7 @@ 27BE OPEN-OUTLINED RIGHTWARDS ARROW @ Miscellaneous 27BF DOUBLE CURLY LOOP -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 27C0 Miscellaneous Mathematical Symbols-A 27EF @ Miscellaneous symbols 27C0 THREE DIMENSIONAL ANGLE @@ -15840,6 +15919,7 @@ x (lozenge - 25CA) 27E1 WHITE CONCAVE-SIDED DIAMOND = never (modal operator) + x (white diamond - 25C7) 27E2 WHITE CONCAVE-SIDED DIAMOND WITH LEFTWARDS TICK = was never (modal operator) 27E3 WHITE CONCAVE-SIDED DIAMOND WITH RIGHTWARDS TICK @@ -15847,6 +15927,7 @@ 27E4 WHITE SQUARE WITH LEFTWARDS TICK = was always (modal operator) x (white square - 25A1) + x (white medium square - 25FB) 27E5 WHITE SQUARE WITH RIGHTWARDS TICK = will always be (modal operator) @ Mathematical brackets @@ -16371,7 +16452,7 @@ 297D RIGHT FISH TAIL 297E UP FISH TAIL 297F DOWN FISH TAIL -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2980 Miscellaneous Mathematical Symbols-B 29FF @ Miscellaneous mathematical symbols 2980 TRIPLE VERTICAL BAR DELIMITER @@ -16606,6 +16687,7 @@ x (circled times - 2297) x (heavy circled saltire - 2B59) 2A03 N-ARY UNION OPERATOR WITH DOT + x (multiset multiplication - 228D) 2A04 N-ARY UNION OPERATOR WITH PLUS x (multiset union - 228E) 2A05 N-ARY SQUARE INTERSECTION OPERATOR @@ -17188,7 +17270,7 @@ 2B59 HEAVY CIRCLED SALTIRE = police station x (n-ary circled times operator - 2A02) -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 2C00 Glagolitic 2C5F @ Capital letters 2C00 GLAGOLITIC CAPITAL LETTER AZU @@ -18113,7 +18195,7 @@ 2EE6 CJK RADICAL C-SIMPLIFIED BIRD x 9E1F 2EE7 CJK RADICAL C-SIMPLIFIED SALT - x 9E75 + x 5364 2EE8 CJK RADICAL SIMPLIFIED WHEAT x 9EA6 2EE9 CJK RADICAL SIMPLIFIED YELLOW @@ -18590,7 +18672,9 @@ x (space - 0020) # <wide> 0020 3001 IDEOGRAPHIC COMMA + * in Chinese, delimits items in a list or series x (comma - 002C) + x (fullwidth comma - FF0C) 3002 IDEOGRAPHIC FULL STOP x (full stop - 002E) 3003 DITTO MARK @@ -18726,7 +18810,7 @@ * visual indicator that the following ideograph is to be taken as a variant of the intended character 303F IDEOGRAPHIC HALF FILL SPACE * visual indicator of a screen space for half of an ideograph -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 3040 Hiragana 309F @ Hiragana letters 3041 HIRAGANA LETTER SMALL A @@ -19060,7 +19144,7 @@ 312D BOPOMOFO LETTER IH * for analytic representation of apical vowel @@ 3130 Hangul Compatibility Jamo 318F -@ Modern letters +@ Consonant letters 3131 HANGUL LETTER KIYEOK # 1100 hangul choseong kiyeok 3132 HANGUL LETTER SSANGKIYEOK @@ -19123,6 +19207,7 @@ 314E HANGUL LETTER HIEUH * voiceless glottal fricative # 1112 hangul choseong hieuh +@ Vowel letters 314F HANGUL LETTER A # 1161 hangul jungseong a 3150 HANGUL LETTER AE @@ -19169,7 +19254,7 @@ 3164 HANGUL FILLER = chaeum # 1160 hangul jungseong filler -@ Old letters +@ Old consonant letters 3165 HANGUL LETTER SSANGNIEUN # 1114 hangul choseong ssangnieun 3166 HANGUL LETTER NIEUN-TIKEUT @@ -19242,6 +19327,7 @@ 3186 HANGUL LETTER YEORINHIEUH * glottal stop # 1159 hangul choseong yeorinhieuh +@ Old vowel letters 3187 HANGUL LETTER YO-YA # 1184 hangul jungseong yo-ya 3188 HANGUL LETTER YO-YAE @@ -19990,7 +20076,7 @@ # <circle> 30F1 32FE CIRCLED KATAKANA WO # <circle> 30F2 -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 3300 CJK Compatibility 33FF @ Squared Katakana words 3300 SQUARE APAATO @@ -23270,7 +23356,7 @@ A953 REJANG VIRAMA @ Punctuation A95F REJANG SECTION MARK @@ A960 Hangul Jamo Extended-A A97F -@ Initial consonants +@ Old initial consonants A960 HANGUL CHOSEONG TIKEUT-MIEUM A961 HANGUL CHOSEONG TIKEUT-PIEUP A962 HANGUL CHOSEONG TIKEUT-SIOS @@ -23303,7 +23389,7 @@ A97C HANGUL CHOSEONG SSANGYEORINHIEUH @@ A980 Javanese A9DF @ Various signs A980 JAVANESE SIGN PANYANGGA - = ardhacandra + = candrabindu A981 JAVANESE SIGN CECAK = anusvara A982 JAVANESE SIGN LAYAR @@ -23426,6 +23512,7 @@ A9CC JAVANESE PADA PISELEH A9CD JAVANESE TURNED PADA PISELEH @ Syllable reduplicator A9CF JAVANESE PANGRANGKEP + * also used in Buginese x (arabic-indic digit two - 0662) @ Digits A9D0 JAVANESE DIGIT ZERO @@ -23848,7 +23935,7 @@ ABF9 MEETEI MAYEK DIGIT NINE = mapal @@ AC00 Hangul Syllables D7A3 @@ D7B0 Hangul Jamo Extended-B D7FF -@ Medial vowels +@ Old medial vowels D7B0 HANGUL JUNGSEONG O-YEO D7B1 HANGUL JUNGSEONG O-O-I D7B2 HANGUL JUNGSEONG YO-A @@ -23872,7 +23959,7 @@ D7C3 HANGUL JUNGSEONG I-YU D7C4 HANGUL JUNGSEONG I-I D7C5 HANGUL JUNGSEONG ARAEA-A D7C6 HANGUL JUNGSEONG ARAEA-E -@ Final consonants +@ Old final consonants D7CB HANGUL JONGSEONG NIEUN-RIEUL D7CC HANGUL JONGSEONG NIEUN-CHIEUCH D7CD HANGUL JONGSEONG SSANGTIKEUT @@ -24886,6 +24973,7 @@ FAD8 CJK COMPATIBILITY IDEOGRAPH-FAD8 : 9F43 FAD9 CJK COMPATIBILITY IDEOGRAPH-FAD9 : 9F8E +@~ Standardized Variation Sequences @@ FB00 Alphabetic Presentation Forms FB4F @ Latin ligatures @+ See the Basic Latin block starting at 0020 @@ -25964,6 +26052,7 @@ FD3C ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM FD3D ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM # <isolated> 0627 064B @ Punctuation +@+ For legacy reasons, these parentheses do not mirror in bidirectional display and do not have the Bidi_Paired_Bracket property. FD3E ORNATE LEFT PARENTHESIS FD3F ORNATE RIGHT PARENTHESIS @ Ligatures (three elements) @@ -26204,7 +26293,7 @@ FDC6 ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM FDC7 ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM # <final> 0646 062C 064A @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. FDD0 <not a character> FDD1 <not a character> FDD2 <not a character> @@ -26760,7 +26849,8 @@ FEFC ARABIC LIGATURE LAM WITH ALEF FINAL FORM # <final> 0644 0627 @ Special FEFF ZERO WIDTH NO-BREAK SPACE - = BYTE ORDER MARK (BOM), ZWNBSP + % BYTE ORDER MARK + = BOM, ZWNBSP * may be used to detect byte order by contrast with the noncharacter code point FFFE * use as an indication of non-breaking is deprecated; see 2060 instead x (zero width space - 200B) @@ -26792,6 +26882,8 @@ FF0A FULLWIDTH ASTERISK FF0B FULLWIDTH PLUS SIGN # <wide> 002B FF0C FULLWIDTH COMMA + * in Chinese, indicates a pause + x (ideographic comma - 3001) # <wide> 002C FF0D FULLWIDTH HYPHEN-MINUS # <wide> 002D @@ -27249,13 +27341,11 @@ FFFD REPLACEMENT CHARACTER * used to replace an incoming character whose value is unknown or unrepresentable in Unicode * compare the use of 001A as a control character to indicate the substitute function @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. FFFE <not a character> - * the value FFFE is guaranteed not to be a Unicode character at all - * may be used to detect byte order by contrast with FEFF which is a character + * may be used to detect byte order by contrast with FEFF x (zero width no-break space - FEFF) FFFF <not a character> - * the value FFFF is guaranteed not to be a Unicode character at all @@ 10000 Linear B Syllabary 1007F @@+ @ Basic syllables @@ -29299,6 +29389,8 @@ FFFF <not a character> 111C2 SHARADA SIGN JIHVAMULIYA 111C3 SHARADA SIGN UPADHMANIYA 111C4 SHARADA OM + * use of this character is discouraged + * recommended sequence is 1118F 11180 @ Punctuation 111C5 SHARADA DANDA 111C6 SHARADA DOUBLE DANDA @@ -30117,7 +30209,9 @@ FFFF <not a character> 122D2 CUNEIFORM SIGN SHINIG 122D3 CUNEIFORM SIGN SHIR 122D4 CUNEIFORM SIGN SHIR TENU + % CUNEIFORM SIGN NU11 TENU 122D5 CUNEIFORM SIGN SHIR OVER SHIR BUR OVER BUR + % CUNEIFORM SIGN NU11 OVER NU11 BUR OVER BUR 122D6 CUNEIFORM SIGN SHITA 122D7 CUNEIFORM SIGN SHU 122D8 CUNEIFORM SIGN SHU OVER INVERTED SHU @@ -35793,7 +35887,7 @@ FFFF <not a character> 1F02A MAHJONG TILE JOKER = baida 1F02B MAHJONG TILE BACK -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 1F030 Domino Tiles 1F09F @ Horizontal tiles 1F030 DOMINO TILE HORIZONTAL BACK @@ -36323,7 +36417,7 @@ FFFF <not a character> 1F1FD REGIONAL INDICATOR SYMBOL LETTER X 1F1FE REGIONAL INDICATOR SYMBOL LETTER Y 1F1FF REGIONAL INDICATOR SYMBOL LETTER Z -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 1F200 Enclosed Ideographic Supplement 1F2FF @ Squared hiragana from ARIB STD B24 1F200 SQUARE HIRAGANA HOKA @@ -36512,7 +36606,7 @@ FFFF <not a character> 1F251 CIRCLED IDEOGRAPH ACCEPT = accept sign # <circle> 53EF -@~ Standardized Variation Sequences +@~ !{FE0E FE0F} Standardized Variation Sequences @@ 1F300 Miscellaneous Symbols and Pictographs 1F5FF @ Weather, landscape, and sky symbols 1F300 CYCLONE @@ -36830,6 +36924,7 @@ FFFF <not a character> * seventh of the signs of the Asian zodiac 1F40F RAM * eighth of the signs of the Asian zodiac + x (aries - 2648) 1F410 GOAT * eighth of the signs of the Asian zodiac, used in Vietnam 1F411 SHEEP @@ -37718,12 +37813,10 @@ FFFF <not a character> = uncia semis x (ounce sign - 2125) @@ 1FF80 Unassigned 1FFFF -@ Not character codes -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@ Noncharacters +@+ These codes are intended for process-internal uses. 1FFFE <not a character> - * the value 1FFFE is guaranteed not to be a Unicode character at all 1FFFF <not a character> - * the value 1FFFF is guaranteed not to be a Unicode character at all @@ 20000 CJK Unified Ideographs Extension B 2A6D6 @@ 2A700 CJK Unified Ideographs Extension C 2B734 @@ 2B740 CJK Unified Ideographs Extension D 2B81D @@ -38824,90 +38917,67 @@ FFFF <not a character> : 9F3B 2FA1D CJK COMPATIBILITY IDEOGRAPH-2FA1D : 2A600 +@~ Standardized Variation Sequences @@ 2FF80 Unassigned 2FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 2FFFE <not a character> - * the value 2FFFE is guaranteed not to be a Unicode character at all 2FFFF <not a character> - * the value 2FFFF is guaranteed not to be a Unicode character at all @@ 3FF80 Unassigned 3FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 3FFFE <not a character> - * the value 3FFFE is guaranteed not to be a Unicode character at all 3FFFF <not a character> - * the value 3FFFF is guaranteed not to be a Unicode character at all @@ 4FF80 Unassigned 4FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 4FFFE <not a character> - * the value 4FFFE is guaranteed not to be a Unicode character at all 4FFFF <not a character> - * the value 4FFFF is guaranteed not to be a Unicode character at all @@ 5FF80 Unassigned 5FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 5FFFE <not a character> - * the value 5FFFE is guaranteed not to be a Unicode character at all 5FFFF <not a character> - * the value 5FFFF is guaranteed not to be a Unicode character at all @@ 6FF80 Unassigned 6FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 6FFFE <not a character> - * the value 6FFFE is guaranteed not to be a Unicode character at all 6FFFF <not a character> - * the value 6FFFF is guaranteed not to be a Unicode character at all @@ 7FF80 Unassigned 7FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 7FFFE <not a character> - * the value 7FFFE is guaranteed not to be a Unicode character at all 7FFFF <not a character> - * the value 7FFFF is guaranteed not to be a Unicode character at all @@ 8FF80 Unassigned 8FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 8FFFE <not a character> - * the value 8FFFE is guaranteed not to be a Unicode character at all 8FFFF <not a character> - * the value 8FFFF is guaranteed not to be a Unicode character at all @@ 9FF80 Unassigned 9FFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 9FFFE <not a character> - * the value 9FFFE is guaranteed not to be a Unicode character at all 9FFFF <not a character> - * the value 9FFFF is guaranteed not to be a Unicode character at all @@ AFF80 Unassigned AFFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. AFFFE <not a character> - * the value AFFFE is guaranteed not to be a Unicode character at all AFFFF <not a character> - * the value AFFFF is guaranteed not to be a Unicode character at all @@ BFF80 Unassigned BFFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. BFFFE <not a character> - * the value BFFFE is guaranteed not to be a Unicode character at all BFFFF <not a character> - * the value BFFFF is guaranteed not to be a Unicode character at all @@ CFF80 Unassigned CFFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. CFFFE <not a character> - * the value CFFFE is guaranteed not to be a Unicode character at all CFFFF <not a character> - * the value CFFFF is guaranteed not to be a Unicode character at all @@ DFF80 Unassigned DFFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. DFFFE <not a character> - * the value DFFFE is guaranteed not to be a Unicode character at all DFFFF <not a character> - * the value DFFFF is guaranteed not to be a Unicode character at all @@ E0000 Tags E007F @+ Tag characters are deprecated, and their use is strongly discouraged. @ Tag identifiers @@ -39255,24 +39325,18 @@ E01EE VARIATION SELECTOR-255 E01EF VARIATION SELECTOR-256 @@ EFF80 Unassigned EFFFF @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. EFFFE <not a character> - * the value EFFFE is guaranteed not to be a Unicode character at all EFFFF <not a character> - * the value EFFFF is guaranteed not to be a Unicode character at all @@ FFF80 Supplementary Private Use Area-A FFFFF @+ The entire plane is dedicated to private use with the exception of the last two code points. @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. FFFFE <not a character> - * the value FFFFE is guaranteed not to be a Unicode character at all FFFFF <not a character> - * the value FFFFF is guaranteed not to be a Unicode character at all @@ 10FF80 Supplementary Private Use Area-B 10FFFF @+ The entire plane is dedicated to private use with the exception of the last two code points. @ Noncharacters -@+ These codes are intended for process-internal uses, but are not permitted for interchange. +@+ These codes are intended for process-internal uses. 10FFFE <not a character> - * the value 10FFFE is guaranteed not to be a Unicode character at all 10FFFF <not a character> - * the value 10FFFF is guaranteed not to be a Unicode character at all diff --git a/lib/unicore/NormalizationCorrections.txt b/lib/unicore/NormalizationCorrections.txt index b53bb408a5..aea94ca33e 100644 --- a/lib/unicore/NormalizationCorrections.txt +++ b/lib/unicore/NormalizationCorrections.txt @@ -1,10 +1,10 @@ -# NormalizationCorrections-6.2.0.txt -# Date: 2012-05-15, 22:25:00 GMT [KW, LI] +# NormalizationCorrections-6.3.0.txt +# 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 diff --git a/lib/unicore/PropList.txt b/lib/unicore/PropList.txt index 9ce7eec971..78aef6a4da 100644 --- a/lib/unicore/PropList.txt +++ b/lib/unicore/PropList.txt @@ -1,8 +1,8 @@ -# PropList-6.2.0.txt -# Date: 2012-05-23, 20:34:59 GMT [MD] +# PropList-6.3.0.txt +# Date: 2013-09-25, 18:58:50 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/ @@ -13,7 +13,6 @@ 0085 ; White_Space # Cc <control-0085> 00A0 ; White_Space # Zs NO-BREAK SPACE 1680 ; White_Space # Zs OGHAM SPACE MARK -180E ; White_Space # Zs MONGOLIAN VOWEL SEPARATOR 2000..200A ; White_Space # Zs [11] EN QUAD..HAIR SPACE 2028 ; White_Space # Zl LINE SEPARATOR 2029 ; White_Space # Zp PARAGRAPH SEPARATOR @@ -21,14 +20,16 @@ 205F ; White_Space # Zs MEDIUM MATHEMATICAL SPACE 3000 ; White_Space # Zs IDEOGRAPHIC SPACE -# Total code points: 26 +# Total code points: 25 # ================================================ +061C ; Bidi_Control # Cf ARABIC LETTER MARK 200E..200F ; Bidi_Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; Bidi_Control # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2066..2069 ; Bidi_Control # Cf [4] LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE -# Total code points: 7 +# Total code points: 12 # ================================================ @@ -230,6 +231,10 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 21D5..21DB ; Other_Math # So [7] UP DOWN DOUBLE ARROW..RIGHTWARDS TRIPLE ARROW 21DD ; Other_Math # So RIGHTWARDS SQUIGGLE ARROW 21E4..21E5 ; Other_Math # So [2] LEFTWARDS ARROW TO BAR..RIGHTWARDS ARROW TO BAR +2308 ; Other_Math # Ps LEFT CEILING +2309 ; Other_Math # Pe RIGHT CEILING +230A ; Other_Math # Ps LEFT FLOOR +230B ; Other_Math # Pe RIGHT FLOOR 23B4..23B5 ; Other_Math # So [2] TOP SQUARE BRACKET..BOTTOM SQUARE BRACKET 23B7 ; Other_Math # So RADICAL SYMBOL BOTTOM 23D0 ; Other_Math # So VERTICAL LINE EXTENSION @@ -358,7 +363,7 @@ FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT 1EEA5..1EEA9 ; Other_Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; Other_Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# Total code points: 1358 +# Total code points: 1362 # ================================================ @@ -538,7 +543,8 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 19B0..19C0 ; Other_Alphabetic # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY 19C8..19C9 ; Other_Alphabetic # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2 1A17..1A18 ; Other_Alphabetic # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; Other_Alphabetic # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; Other_Alphabetic # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; Other_Alphabetic # Mn BUGINESE VOWEL SIGN AE 1A55 ; Other_Alphabetic # Mc TAI THAM CONSONANT SIGN MEDIAL RA 1A56 ; Other_Alphabetic # Mn TAI THAM CONSONANT SIGN MEDIAL LA 1A57 ; Other_Alphabetic # Mc TAI THAM CONSONANT SIGN LA TANG LAI @@ -966,7 +972,7 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C 034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER 115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER 17B4..17B5 ; Other_Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA -2065..2069 ; Other_Default_Ignorable_Code_Point # Cn [5] <reserved-2065>..<reserved-2069> +2065 ; Other_Default_Ignorable_Code_Point # Cn <reserved-2065> 3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER FFF0..FFF8 ; Other_Default_Ignorable_Code_Point # Cn [9] <reserved-FFF0>..<reserved-FFF8> @@ -975,7 +981,7 @@ E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] <reserved-E0002>.. E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reserved-E00FF> E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 3780 +# Total code points: 3776 # ================================================ @@ -1210,7 +1216,10 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 21D5..21F3 ; Pattern_Syntax # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW 21F4..22FF ; Pattern_Syntax # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP 2300..2307 ; Pattern_Syntax # So [8] DIAMETER SIGN..WAVY LINE -2308..230B ; Pattern_Syntax # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; Pattern_Syntax # Ps LEFT CEILING +2309 ; Pattern_Syntax # Pe RIGHT CEILING +230A ; Pattern_Syntax # Ps LEFT FLOOR +230B ; Pattern_Syntax # Pe RIGHT FLOOR 230C..231F ; Pattern_Syntax # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER 2320..2321 ; Pattern_Syntax # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2322..2328 ; Pattern_Syntax # So [7] FROWN..KEYBOARD diff --git a/lib/unicore/PropValueAliases.txt b/lib/unicore/PropValueAliases.txt index d9048fb32f..12a3f1d1cb 100644 --- a/lib/unicore/PropValueAliases.txt +++ b/lib/unicore/PropValueAliases.txt @@ -1,8 +1,8 @@ -# PropertyValueAliases-6.2.0.txt -# Date: 2012-08-14, 16:05:11 GMT [MD] +# PropertyValueAliases-6.3.0.txt +# Date: 2013-08-27, 16:02:08 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/ # @@ -32,13 +32,14 @@ # # Loose matching should be applied to all property names and property values, with # the exception of String Property values. With loose matching of property names and -# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property -# values, numeric equivalencies are applied: thus "01.00" is equivalent to "1". +# values, the case distinctions, whitespace, hyphens, and '_' are ignored. +# For Numeric Property values, numeric equivalence is applied: thus "01.00" +# is equivalent to "1". # # NOTE: Property value names are NOT unique across properties. For example: # # AL means Arabic Letter for the Bidi_Class property, and -# AL means Above_Left for the Combining_Class property, and +# AL means Above_Left for the Canonical_Combining_Class property, and # AL means Alphabetic for the Line_Break property. # # In addition, some property names may be the same as some property value names. @@ -74,6 +75,7 @@ age; 5.2 ; V5_2 age; 6.0 ; V6_0 age; 6.1 ; V6_1 age; 6.2 ; V6_2 +age; 6.3 ; V6_3 age; NA ; Unassigned # Alphabetic (Alpha) @@ -91,14 +93,18 @@ bc ; CS ; Common_Separator bc ; EN ; European_Number bc ; ES ; European_Separator bc ; ET ; European_Terminator +bc ; FSI ; First_Strong_Isolate bc ; L ; Left_To_Right bc ; LRE ; Left_To_Right_Embedding +bc ; LRI ; Left_To_Right_Isolate bc ; LRO ; Left_To_Right_Override bc ; NSM ; Nonspacing_Mark bc ; ON ; Other_Neutral bc ; PDF ; Pop_Directional_Format +bc ; PDI ; Pop_Directional_Isolate bc ; R ; Right_To_Left bc ; RLE ; Right_To_Left_Embedding +bc ; RLI ; Right_To_Left_Isolate bc ; RLO ; Right_To_Left_Override bc ; S ; Segment_Separator bc ; WS ; White_Space @@ -117,6 +123,17 @@ Bidi_M; Y ; Yes ; T # @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none> +# Bidi_Paired_Bracket (bpb) + +# @missing: 0000..10FFFF; Bidi_Paired_Bracket; <none> + +# Bidi_Paired_Bracket_Type (bpt) + +# @missing: 0000..10FFFF; Bidi_Paired_Bracket_Type; n +bpt; c ; Close +bpt; n ; None +bpt; o ; Open + # Block (blk) blk; Aegean_Numbers ; Aegean_Numbers @@ -1186,9 +1203,11 @@ WSpace; Y ; Yes ; T # Word_Break (WB) WB ; CR ; CR +WB ; DQ ; Double_Quote WB ; EX ; ExtendNumLet WB ; Extend ; Extend WB ; FO ; Format +WB ; HL ; Hebrew_Letter WB ; KA ; Katakana WB ; LE ; ALetter WB ; LF ; LF @@ -1198,6 +1217,7 @@ WB ; MN ; MidNum WB ; NL ; Newline WB ; NU ; Numeric WB ; RI ; Regional_Indicator +WB ; SQ ; Single_Quote WB ; XX ; Other # XID_Continue (XIDC) diff --git a/lib/unicore/PropertyAliases.txt b/lib/unicore/PropertyAliases.txt index 81a063b1f6..587dcd3eb1 100644 --- a/lib/unicore/PropertyAliases.txt +++ b/lib/unicore/PropertyAliases.txt @@ -1,8 +1,8 @@ -# PropertyAliases-6.2.0.txt -# Date: 2012-05-20, 17:41:20 GMT [MD] +# PropertyAliases-6.3.0.txt +# Date: 2013-03-05, 21:40:52 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/ # @@ -74,6 +74,7 @@ uc ; Uppercase_Mapping # Miscellaneous Properties # ================================================ bmg ; Bidi_Mirroring_Glyph +bpb ; Bidi_Paired_Bracket cjkIICore ; kIICore cjkIRG_GSource ; kIRG_GSource cjkIRG_HSource ; kIRG_HSource @@ -103,6 +104,7 @@ sc ; Script # Enumerated Properties # ================================================ bc ; Bidi_Class +bpt ; Bidi_Paired_Bracket_Type ccc ; Canonical_Combining_Class dt ; Decomposition_Type ea ; East_Asian_Width @@ -186,6 +188,6 @@ XO_NFKC ; Expands_On_NFKC XO_NFKD ; Expands_On_NFKD # ================================================ -# Total: 115 +# Total: 117 # EOF diff --git a/lib/unicore/README.perl b/lib/unicore/README.perl index 1633b55de0..56d98fa012 100644 --- a/lib/unicore/README.perl +++ b/lib/unicore/README.perl @@ -113,7 +113,7 @@ mv Unihan_Variants.txt UnihanVariants.txt # which needs to be updated if there are changes. A quick way to check if # there have been changes would be to see if the number of such characters # listed in perluniprops.pod (generated by running mktables) for the property -# \p{White_Space} is no longer 26. Further investigation would then be +# \p{White_Space} is no longer 25. Further investigation would then be # necessary to classify the new characters as horizontal and vertical. # # The code in regexec.c for the \X match construct is intimately tied to the diff --git a/lib/unicore/ReadMe.txt b/lib/unicore/ReadMe.txt index 370cbd0801..f970223790 100644 --- a/lib/unicore/ReadMe.txt +++ b/lib/unicore/ReadMe.txt @@ -1,7 +1,7 @@ -# Date: 2012-09-24, 22:40:00 GMT [KW] +# Date: 2013-09-27, 23:05:00 GMT [KW] # # 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 NamesList.html, @@ -9,7 +9,7 @@ # UAX #44, "Unicode Character Database." # -This directory contains final data files -for the Unicode Character Database (UCD) for Unicode 6.2.0. +This directory contains the final data files +for the Unicode Character Database (UCD) for Unicode 6.3.0. diff --git a/lib/unicore/ScriptExtensions.txt b/lib/unicore/ScriptExtensions.txt index 5bff07ece0..a651e2993f 100644 --- a/lib/unicore/ScriptExtensions.txt +++ b/lib/unicore/ScriptExtensions.txt @@ -1,8 +1,8 @@ -# ScriptExtensions-6.2.0.txt -# Date: 2012-08-13, 20:52:17 GMT [MD] +# ScriptExtensions-6.3.0.txt +# Date: 2013-03-02, 16:07:55 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/ # The Script_Extensions property indicates which characters are commonly used @@ -90,6 +90,14 @@ FDFD ; Arab Thaa # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHE # ================================================ +# Script_Extensions=Bugi Java + +A9CF ; Bugi Java # Lm JAVANESE PANGRANGKEP + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Cprt Linb 10100..10102 ; Cprt Linb # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK @@ -108,6 +116,14 @@ FDFD ; Arab Thaa # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHE # ================================================ +# Script_Extensions=Deva Kthi + +0966..096F ; Deva Kthi # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE + +# Total code points: 10 + +# ================================================ + # Script_Extensions=Deva Latn 0951..0952 ; Deva Latn # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA @@ -151,9 +167,26 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW 060C ; Arab Syrc Thaa # Po ARABIC COMMA 061B ; Arab Syrc Thaa # Po ARABIC SEMICOLON +061C ; Arab Syrc Thaa # Cf ARABIC LETTER MARK 061F ; Arab Syrc Thaa # Po ARABIC QUESTION MARK -# Total code points: 3 +# Total code points: 4 + +# ================================================ + +# Script_Extensions=Beng Cakm Sylo + +09E6..09EF ; Beng Cakm Sylo # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE + +# Total code points: 10 + +# ================================================ + +# Script_Extensions=Cakm Mymr Tale + +1040..1049 ; Cakm Mymr Tale # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE + +# Total code points: 10 # ================================================ diff --git a/lib/unicore/Scripts.txt b/lib/unicore/Scripts.txt index 1a8e7229cc..b69716c7a6 100644 --- a/lib/unicore/Scripts.txt +++ b/lib/unicore/Scripts.txt @@ -1,8 +1,8 @@ -# Scripts-6.2.0.txt -# Date: 2012-06-04, 17:21:29 GMT [MD] +# Scripts-6.3.0.txt +# 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 # ================================================ diff --git a/lib/unicore/SpecialCasing.txt b/lib/unicore/SpecialCasing.txt index 994043f01b..016a756eb0 100644 --- a/lib/unicore/SpecialCasing.txt +++ b/lib/unicore/SpecialCasing.txt @@ -1,8 +1,8 @@ -# SpecialCasing-6.2.0.txt -# Date: 2012-05-23, 20:35:15 GMT [MD] +# SpecialCasing-6.3.0.txt +# 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/) # diff --git a/lib/unicore/StandardizedVariants.txt b/lib/unicore/StandardizedVariants.txt index 179726550e..5ebe52381c 100644 --- a/lib/unicore/StandardizedVariants.txt +++ b/lib/unicore/StandardizedVariants.txt @@ -1,5 +1,5 @@ -# StandardizedVariants-6.2.0.txt -# Date: 2012-05-15, 21:53:00 GMT [KW, LI] +# StandardizedVariants-6.3.0.txt +# Date: 2012-11-14, 21:34:00 GMT [KW, LI] # # Specification of the variation sequences that are defined in the # Unicode Standard. @@ -21,7 +21,7 @@ # # For more information on standardized variation sequences, # see Section 16.4, Variation Selectors, -# in The Unicode Standard, Version 6.2. +# in The Unicode Standard, Version 6.3. # # For more information on the Ideographic Variation Database, # see http://www.unicode.org/ivd/ @@ -362,4 +362,1015 @@ A868 FE00; phags-pa letter reversed shaping subjoined ya; # PHAGS-PA SUBJOINED L 1F22F FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-6307 1F22F FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-6307 +# CJK compatibility ideographs + +# Note: In the entries for CJK compatibility ideographs, field 1 +# has the name of the respective CJK compatibility +# ideograph. The visual appearance of that CJK compatibility ideograph +# is the intended visual appearance of the base CJK unified ideograph +# followed by the variation selector in each sequence defined. + +349E FE00; CJK COMPATIBILITY IDEOGRAPH-2F80C; +34B9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F813; +34BB FE00; CJK COMPATIBILITY IDEOGRAPH-2F9CA; +34DF FE00; CJK COMPATIBILITY IDEOGRAPH-2F81F; +3515 FE00; CJK COMPATIBILITY IDEOGRAPH-2F824; +36EE FE00; CJK COMPATIBILITY IDEOGRAPH-2F867; +36FC FE00; CJK COMPATIBILITY IDEOGRAPH-2F868; +3781 FE00; CJK COMPATIBILITY IDEOGRAPH-2F876; +382F FE00; CJK COMPATIBILITY IDEOGRAPH-2F883; +3862 FE00; CJK COMPATIBILITY IDEOGRAPH-2F888; +387C FE00; CJK COMPATIBILITY IDEOGRAPH-2F88A; +38C7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F896; +38E3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F89B; +391C FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A2; +393A FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A1; +3A2E FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C2; +3A6C FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C7; +3AE4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D1; +3B08 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D0; +3B19 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8CE; +3B49 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8DE; +3B9D FE00; CJK COMPATIBILITY IDEOGRAPH-FAD2; +3B9D FE01; CJK COMPATIBILITY IDEOGRAPH-2F8E7; +3C18 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8EE; +3C4E FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F2; +3D33 FE00; CJK COMPATIBILITY IDEOGRAPH-2F90A; +3D96 FE00; CJK COMPATIBILITY IDEOGRAPH-2F916; +3EAC FE00; CJK COMPATIBILITY IDEOGRAPH-2F92A; +3EB8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F92C; +3EB8 FE01; CJK COMPATIBILITY IDEOGRAPH-2F92D; +3F1B FE00; CJK COMPATIBILITY IDEOGRAPH-2F933; +3FFC FE00; CJK COMPATIBILITY IDEOGRAPH-2F93E; +4008 FE00; CJK COMPATIBILITY IDEOGRAPH-2F93F; +4018 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD3; +4039 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD4; +4039 FE01; CJK COMPATIBILITY IDEOGRAPH-2F949; +4046 FE00; CJK COMPATIBILITY IDEOGRAPH-2F94B; +4096 FE00; CJK COMPATIBILITY IDEOGRAPH-2F94C; +40E3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F951; +412F FE00; CJK COMPATIBILITY IDEOGRAPH-2F958; +4202 FE00; CJK COMPATIBILITY IDEOGRAPH-2F960; +4227 FE00; CJK COMPATIBILITY IDEOGRAPH-2F964; +42A0 FE00; CJK COMPATIBILITY IDEOGRAPH-2F967; +4301 FE00; CJK COMPATIBILITY IDEOGRAPH-2F96D; +4334 FE00; CJK COMPATIBILITY IDEOGRAPH-2F971; +4359 FE00; CJK COMPATIBILITY IDEOGRAPH-2F974; +43D5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F981; +43D9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D7; +440B FE00; CJK COMPATIBILITY IDEOGRAPH-2F984; +446B FE00; CJK COMPATIBILITY IDEOGRAPH-2F98E; +452B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A7; +455D FE00; CJK COMPATIBILITY IDEOGRAPH-2F9AE; +4561 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9AF; +456B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B2; +45D7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9BF; +45F9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C2; +4635 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C8; +46BE FE00; CJK COMPATIBILITY IDEOGRAPH-2F9CD; +46C7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9CE; +4995 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9EF; +49E6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F2; +4A6E FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F8; +4A76 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F9; +4AB2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9FC; +4B33 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA03; +4BCE FE00; CJK COMPATIBILITY IDEOGRAPH-2FA08; +4CCE FE00; CJK COMPATIBILITY IDEOGRAPH-2FA0D; +4CED FE00; CJK COMPATIBILITY IDEOGRAPH-2FA0E; +4CF8 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA11; +4D56 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA16; +4E0D FE00; CJK COMPATIBILITY IDEOGRAPH-F967; +4E26 FE00; CJK COMPATIBILITY IDEOGRAPH-FA70; +4E32 FE00; CJK COMPATIBILITY IDEOGRAPH-F905; +4E38 FE00; CJK COMPATIBILITY IDEOGRAPH-2F801; +4E39 FE00; CJK COMPATIBILITY IDEOGRAPH-F95E; +4E3D FE00; CJK COMPATIBILITY IDEOGRAPH-2F800; +4E41 FE00; CJK COMPATIBILITY IDEOGRAPH-2F802; +4E82 FE00; CJK COMPATIBILITY IDEOGRAPH-F91B; +4E86 FE00; CJK COMPATIBILITY IDEOGRAPH-F9BA; +4EAE FE00; CJK COMPATIBILITY IDEOGRAPH-F977; +4EC0 FE00; CJK COMPATIBILITY IDEOGRAPH-F9FD; +4ECC FE00; CJK COMPATIBILITY IDEOGRAPH-2F819; +4EE4 FE00; CJK COMPATIBILITY IDEOGRAPH-F9A8; +4F60 FE00; CJK COMPATIBILITY IDEOGRAPH-2F804; +4F80 FE00; CJK COMPATIBILITY IDEOGRAPH-FA73; +4F86 FE00; CJK COMPATIBILITY IDEOGRAPH-F92D; +4F8B FE00; CJK COMPATIBILITY IDEOGRAPH-F9B5; +4FAE FE00; CJK COMPATIBILITY IDEOGRAPH-FA30; +4FAE FE01; CJK COMPATIBILITY IDEOGRAPH-2F805; +4FBB FE00; CJK COMPATIBILITY IDEOGRAPH-2F806; +4FBF FE00; CJK COMPATIBILITY IDEOGRAPH-F965; +5002 FE00; CJK COMPATIBILITY IDEOGRAPH-2F807; +502B FE00; CJK COMPATIBILITY IDEOGRAPH-F9D4; +507A FE00; CJK COMPATIBILITY IDEOGRAPH-2F808; +5099 FE00; CJK COMPATIBILITY IDEOGRAPH-2F809; +50CF FE00; CJK COMPATIBILITY IDEOGRAPH-2F80B; +50DA FE00; CJK COMPATIBILITY IDEOGRAPH-F9BB; +50E7 FE00; CJK COMPATIBILITY IDEOGRAPH-FA31; +50E7 FE01; CJK COMPATIBILITY IDEOGRAPH-2F80A; +5140 FE00; CJK COMPATIBILITY IDEOGRAPH-FA0C; +5145 FE00; CJK COMPATIBILITY IDEOGRAPH-FA74; +514D FE00; CJK COMPATIBILITY IDEOGRAPH-FA32; +514D FE01; CJK COMPATIBILITY IDEOGRAPH-2F80E; +5154 FE00; CJK COMPATIBILITY IDEOGRAPH-2F80F; +5164 FE00; CJK COMPATIBILITY IDEOGRAPH-2F810; +5167 FE00; CJK COMPATIBILITY IDEOGRAPH-2F814; +5168 FE00; CJK COMPATIBILITY IDEOGRAPH-FA72; +5169 FE00; CJK COMPATIBILITY IDEOGRAPH-F978; +516D FE00; CJK COMPATIBILITY IDEOGRAPH-F9D1; +5177 FE00; CJK COMPATIBILITY IDEOGRAPH-2F811; +5180 FE00; CJK COMPATIBILITY IDEOGRAPH-FA75; +518D FE00; CJK COMPATIBILITY IDEOGRAPH-2F815; +5192 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D2; +5195 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D3; +5197 FE00; CJK COMPATIBILITY IDEOGRAPH-2F817; +51A4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F818; +51AC FE00; CJK COMPATIBILITY IDEOGRAPH-2F81A; +51B5 FE00; CJK COMPATIBILITY IDEOGRAPH-FA71; +51B5 FE01; CJK COMPATIBILITY IDEOGRAPH-2F81B; +51B7 FE00; CJK COMPATIBILITY IDEOGRAPH-F92E; +51C9 FE00; CJK COMPATIBILITY IDEOGRAPH-F979; +51CC FE00; CJK COMPATIBILITY IDEOGRAPH-F955; +51DC FE00; CJK COMPATIBILITY IDEOGRAPH-F954; +51DE FE00; CJK COMPATIBILITY IDEOGRAPH-FA15; +51F5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F81D; +5203 FE00; CJK COMPATIBILITY IDEOGRAPH-2F81E; +5207 FE00; CJK COMPATIBILITY IDEOGRAPH-FA00; +5207 FE01; CJK COMPATIBILITY IDEOGRAPH-2F850; +5217 FE00; CJK COMPATIBILITY IDEOGRAPH-F99C; +5229 FE00; CJK COMPATIBILITY IDEOGRAPH-F9DD; +523A FE00; CJK COMPATIBILITY IDEOGRAPH-F9FF; +523B FE00; CJK COMPATIBILITY IDEOGRAPH-2F820; +5246 FE00; CJK COMPATIBILITY IDEOGRAPH-2F821; +5272 FE00; CJK COMPATIBILITY IDEOGRAPH-2F822; +5277 FE00; CJK COMPATIBILITY IDEOGRAPH-2F823; +5289 FE00; CJK COMPATIBILITY IDEOGRAPH-F9C7; +529B FE00; CJK COMPATIBILITY IDEOGRAPH-F98A; +52A3 FE00; CJK COMPATIBILITY IDEOGRAPH-F99D; +52B3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F992; +52C7 FE00; CJK COMPATIBILITY IDEOGRAPH-FA76; +52C7 FE01; CJK COMPATIBILITY IDEOGRAPH-2F825; +52C9 FE00; CJK COMPATIBILITY IDEOGRAPH-FA33; +52C9 FE01; CJK COMPATIBILITY IDEOGRAPH-2F826; +52D2 FE00; CJK COMPATIBILITY IDEOGRAPH-F952; +52DE FE00; CJK COMPATIBILITY IDEOGRAPH-F92F; +52E4 FE00; CJK COMPATIBILITY IDEOGRAPH-FA34; +52E4 FE01; CJK COMPATIBILITY IDEOGRAPH-2F827; +52F5 FE00; CJK COMPATIBILITY IDEOGRAPH-F97F; +52FA FE00; CJK COMPATIBILITY IDEOGRAPH-FA77; +52FA FE01; CJK COMPATIBILITY IDEOGRAPH-2F828; +5305 FE00; CJK COMPATIBILITY IDEOGRAPH-2F829; +5306 FE00; CJK COMPATIBILITY IDEOGRAPH-2F82A; +5317 FE00; CJK COMPATIBILITY IDEOGRAPH-F963; +5317 FE01; CJK COMPATIBILITY IDEOGRAPH-2F82B; +533F FE00; CJK COMPATIBILITY IDEOGRAPH-F9EB; +5349 FE00; CJK COMPATIBILITY IDEOGRAPH-2F82C; +5351 FE00; CJK COMPATIBILITY IDEOGRAPH-FA35; +5351 FE01; CJK COMPATIBILITY IDEOGRAPH-2F82D; +535A FE00; CJK COMPATIBILITY IDEOGRAPH-2F82E; +5373 FE00; CJK COMPATIBILITY IDEOGRAPH-2F82F; +5375 FE00; CJK COMPATIBILITY IDEOGRAPH-F91C; +537D FE00; CJK COMPATIBILITY IDEOGRAPH-2F830; +537F FE00; CJK COMPATIBILITY IDEOGRAPH-2F831; +537F FE01; CJK COMPATIBILITY IDEOGRAPH-2F832; +537F FE02; CJK COMPATIBILITY IDEOGRAPH-2F833; +53C3 FE00; CJK COMPATIBILITY IDEOGRAPH-F96B; +53CA FE00; CJK COMPATIBILITY IDEOGRAPH-2F836; +53DF FE00; CJK COMPATIBILITY IDEOGRAPH-2F837; +53E5 FE00; CJK COMPATIBILITY IDEOGRAPH-F906; +53EB FE00; CJK COMPATIBILITY IDEOGRAPH-2F839; +53F1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F83A; +5406 FE00; CJK COMPATIBILITY IDEOGRAPH-2F83B; +540F FE00; CJK COMPATIBILITY IDEOGRAPH-F9DE; +541D FE00; CJK COMPATIBILITY IDEOGRAPH-F9ED; +5438 FE00; CJK COMPATIBILITY IDEOGRAPH-2F83D; +5442 FE00; CJK COMPATIBILITY IDEOGRAPH-F980; +5448 FE00; CJK COMPATIBILITY IDEOGRAPH-2F83E; +5468 FE00; CJK COMPATIBILITY IDEOGRAPH-2F83F; +549E FE00; CJK COMPATIBILITY IDEOGRAPH-2F83C; +54A2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F840; +54BD FE00; CJK COMPATIBILITY IDEOGRAPH-F99E; +54F6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F841; +5510 FE00; CJK COMPATIBILITY IDEOGRAPH-2F842; +5553 FE00; CJK COMPATIBILITY IDEOGRAPH-2F843; +5555 FE00; CJK COMPATIBILITY IDEOGRAPH-FA79; +5563 FE00; CJK COMPATIBILITY IDEOGRAPH-2F844; +5584 FE00; CJK COMPATIBILITY IDEOGRAPH-2F845; +5584 FE01; CJK COMPATIBILITY IDEOGRAPH-2F846; +5587 FE00; CJK COMPATIBILITY IDEOGRAPH-F90B; +5599 FE00; CJK COMPATIBILITY IDEOGRAPH-FA7A; +5599 FE01; CJK COMPATIBILITY IDEOGRAPH-2F847; +559D FE00; CJK COMPATIBILITY IDEOGRAPH-FA36; +559D FE01; CJK COMPATIBILITY IDEOGRAPH-FA78; +55AB FE00; CJK COMPATIBILITY IDEOGRAPH-2F848; +55B3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F849; +55C0 FE00; CJK COMPATIBILITY IDEOGRAPH-FA0D; +55C2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F84A; +55E2 FE00; CJK COMPATIBILITY IDEOGRAPH-FA7B; +5606 FE00; CJK COMPATIBILITY IDEOGRAPH-FA37; +5606 FE01; CJK COMPATIBILITY IDEOGRAPH-2F84C; +5651 FE00; CJK COMPATIBILITY IDEOGRAPH-2F84E; +5668 FE00; CJK COMPATIBILITY IDEOGRAPH-FA38; +5674 FE00; CJK COMPATIBILITY IDEOGRAPH-2F84F; +56F9 FE00; CJK COMPATIBILITY IDEOGRAPH-F9A9; +5716 FE00; CJK COMPATIBILITY IDEOGRAPH-2F84B; +5717 FE00; CJK COMPATIBILITY IDEOGRAPH-2F84D; +578B FE00; CJK COMPATIBILITY IDEOGRAPH-2F855; +57CE FE00; CJK COMPATIBILITY IDEOGRAPH-2F852; +57F4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F853; +580D FE00; CJK COMPATIBILITY IDEOGRAPH-2F854; +5831 FE00; CJK COMPATIBILITY IDEOGRAPH-2F857; +5832 FE00; CJK COMPATIBILITY IDEOGRAPH-2F856; +5840 FE00; CJK COMPATIBILITY IDEOGRAPH-FA39; +585A FE00; CJK COMPATIBILITY IDEOGRAPH-FA10; +585A FE01; CJK COMPATIBILITY IDEOGRAPH-FA7C; +585E FE00; CJK COMPATIBILITY IDEOGRAPH-F96C; +58A8 FE00; CJK COMPATIBILITY IDEOGRAPH-FA3A; +58AC FE00; CJK COMPATIBILITY IDEOGRAPH-2F858; +58B3 FE00; CJK COMPATIBILITY IDEOGRAPH-FA7D; +58D8 FE00; CJK COMPATIBILITY IDEOGRAPH-F94A; +58DF FE00; CJK COMPATIBILITY IDEOGRAPH-F942; +58EE FE00; CJK COMPATIBILITY IDEOGRAPH-2F851; +58F2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F85A; +58F7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F85B; +5906 FE00; CJK COMPATIBILITY IDEOGRAPH-2F85C; +591A FE00; CJK COMPATIBILITY IDEOGRAPH-2F85D; +5922 FE00; CJK COMPATIBILITY IDEOGRAPH-2F85E; +5944 FE00; CJK COMPATIBILITY IDEOGRAPH-FA7E; +5948 FE00; CJK COMPATIBILITY IDEOGRAPH-F90C; +5951 FE00; CJK COMPATIBILITY IDEOGRAPH-F909; +5954 FE00; CJK COMPATIBILITY IDEOGRAPH-FA7F; +5962 FE00; CJK COMPATIBILITY IDEOGRAPH-2F85F; +5973 FE00; CJK COMPATIBILITY IDEOGRAPH-F981; +59D8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F865; +59EC FE00; CJK COMPATIBILITY IDEOGRAPH-2F862; +5A1B FE00; CJK COMPATIBILITY IDEOGRAPH-2F863; +5A27 FE00; CJK COMPATIBILITY IDEOGRAPH-2F864; +5A62 FE00; CJK COMPATIBILITY IDEOGRAPH-FA80; +5A66 FE00; CJK COMPATIBILITY IDEOGRAPH-2F866; +5AB5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F986; +5B08 FE00; CJK COMPATIBILITY IDEOGRAPH-2F869; +5B28 FE00; CJK COMPATIBILITY IDEOGRAPH-FA81; +5B3E FE00; CJK COMPATIBILITY IDEOGRAPH-2F86A; +5B3E FE01; CJK COMPATIBILITY IDEOGRAPH-2F86B; +5B85 FE00; CJK COMPATIBILITY IDEOGRAPH-FA04; +5BC3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F86D; +5BD8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F86E; +5BE7 FE00; CJK COMPATIBILITY IDEOGRAPH-F95F; +5BE7 FE01; CJK COMPATIBILITY IDEOGRAPH-F9AA; +5BE7 FE02; CJK COMPATIBILITY IDEOGRAPH-2F86F; +5BEE FE00; CJK COMPATIBILITY IDEOGRAPH-F9BC; +5BF3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F870; +5BFF FE00; CJK COMPATIBILITY IDEOGRAPH-2F872; +5C06 FE00; CJK COMPATIBILITY IDEOGRAPH-2F873; +5C22 FE00; CJK COMPATIBILITY IDEOGRAPH-2F875; +5C3F FE00; CJK COMPATIBILITY IDEOGRAPH-F9BD; +5C60 FE00; CJK COMPATIBILITY IDEOGRAPH-2F877; +5C62 FE00; CJK COMPATIBILITY IDEOGRAPH-F94B; +5C64 FE00; CJK COMPATIBILITY IDEOGRAPH-FA3B; +5C65 FE00; CJK COMPATIBILITY IDEOGRAPH-F9DF; +5C6E FE00; CJK COMPATIBILITY IDEOGRAPH-FA3C; +5C6E FE01; CJK COMPATIBILITY IDEOGRAPH-2F878; +5C8D FE00; CJK COMPATIBILITY IDEOGRAPH-2F87A; +5CC0 FE00; CJK COMPATIBILITY IDEOGRAPH-2F879; +5D19 FE00; CJK COMPATIBILITY IDEOGRAPH-F9D5; +5D43 FE00; CJK COMPATIBILITY IDEOGRAPH-2F87C; +5D50 FE00; CJK COMPATIBILITY IDEOGRAPH-F921; +5D6B FE00; CJK COMPATIBILITY IDEOGRAPH-2F87F; +5D6E FE00; CJK COMPATIBILITY IDEOGRAPH-2F87E; +5D7C FE00; CJK COMPATIBILITY IDEOGRAPH-2F880; +5DB2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F4; +5DBA FE00; CJK COMPATIBILITY IDEOGRAPH-F9AB; +5DE1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F881; +5DE2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F882; +5DFD FE00; CJK COMPATIBILITY IDEOGRAPH-2F884; +5E28 FE00; CJK COMPATIBILITY IDEOGRAPH-2F885; +5E3D FE00; CJK COMPATIBILITY IDEOGRAPH-2F886; +5E69 FE00; CJK COMPATIBILITY IDEOGRAPH-2F887; +5E74 FE00; CJK COMPATIBILITY IDEOGRAPH-F98E; +5EA6 FE00; CJK COMPATIBILITY IDEOGRAPH-FA01; +5EB0 FE00; CJK COMPATIBILITY IDEOGRAPH-2F88B; +5EB3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F88C; +5EB6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F88D; +5EC9 FE00; CJK COMPATIBILITY IDEOGRAPH-F9A2; +5ECA FE00; CJK COMPATIBILITY IDEOGRAPH-F928; +5ECA FE01; CJK COMPATIBILITY IDEOGRAPH-2F88E; +5ED2 FE00; CJK COMPATIBILITY IDEOGRAPH-FA82; +5ED3 FE00; CJK COMPATIBILITY IDEOGRAPH-FA0B; +5ED9 FE00; CJK COMPATIBILITY IDEOGRAPH-FA83; +5EEC FE00; CJK COMPATIBILITY IDEOGRAPH-F982; +5EFE FE00; CJK COMPATIBILITY IDEOGRAPH-2F890; +5F04 FE00; CJK COMPATIBILITY IDEOGRAPH-F943; +5F22 FE00; CJK COMPATIBILITY IDEOGRAPH-2F894; +5F22 FE01; CJK COMPATIBILITY IDEOGRAPH-2F895; +5F53 FE00; CJK COMPATIBILITY IDEOGRAPH-2F874; +5F62 FE00; CJK COMPATIBILITY IDEOGRAPH-2F899; +5F69 FE00; CJK COMPATIBILITY IDEOGRAPH-FA84; +5F6B FE00; CJK COMPATIBILITY IDEOGRAPH-2F89A; +5F8B FE00; CJK COMPATIBILITY IDEOGRAPH-F9D8; +5F9A FE00; CJK COMPATIBILITY IDEOGRAPH-2F89C; +5FA9 FE00; CJK COMPATIBILITY IDEOGRAPH-F966; +5FAD FE00; CJK COMPATIBILITY IDEOGRAPH-FA85; +5FCD FE00; CJK COMPATIBILITY IDEOGRAPH-2F89D; +5FD7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F89E; +5FF5 FE00; CJK COMPATIBILITY IDEOGRAPH-F9A3; +5FF9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F89F; +6012 FE00; CJK COMPATIBILITY IDEOGRAPH-F960; +601C FE00; CJK COMPATIBILITY IDEOGRAPH-F9AC; +6075 FE00; CJK COMPATIBILITY IDEOGRAPH-FA6B; +6081 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A0; +6094 FE00; CJK COMPATIBILITY IDEOGRAPH-FA3D; +6094 FE01; CJK COMPATIBILITY IDEOGRAPH-2F8A3; +60C7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A5; +60D8 FE00; CJK COMPATIBILITY IDEOGRAPH-FA86; +60E1 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B9; +6108 FE00; CJK COMPATIBILITY IDEOGRAPH-FA88; +6144 FE00; CJK COMPATIBILITY IDEOGRAPH-F9D9; +6148 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A6; +614C FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A7; +614C FE01; CJK COMPATIBILITY IDEOGRAPH-2F8A9; +614E FE00; CJK COMPATIBILITY IDEOGRAPH-FA87; +614E FE01; CJK COMPATIBILITY IDEOGRAPH-2F8A8; +6160 FE00; CJK COMPATIBILITY IDEOGRAPH-FA8A; +6168 FE00; CJK COMPATIBILITY IDEOGRAPH-FA3E; +617A FE00; CJK COMPATIBILITY IDEOGRAPH-2F8AA; +618E FE00; CJK COMPATIBILITY IDEOGRAPH-FA3F; +618E FE01; CJK COMPATIBILITY IDEOGRAPH-FA89; +618E FE02; CJK COMPATIBILITY IDEOGRAPH-2F8AB; +6190 FE00; CJK COMPATIBILITY IDEOGRAPH-F98F; +61A4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8AD; +61AF FE00; CJK COMPATIBILITY IDEOGRAPH-2F8AE; +61B2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8AC; +61DE FE00; CJK COMPATIBILITY IDEOGRAPH-2F8AF; +61F2 FE00; CJK COMPATIBILITY IDEOGRAPH-FA40; +61F2 FE01; CJK COMPATIBILITY IDEOGRAPH-FA8B; +61F2 FE02; CJK COMPATIBILITY IDEOGRAPH-2F8B0; +61F6 FE00; CJK COMPATIBILITY IDEOGRAPH-F90D; +61F6 FE01; CJK COMPATIBILITY IDEOGRAPH-2F8B1; +6200 FE00; CJK COMPATIBILITY IDEOGRAPH-F990; +6210 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B2; +621B FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B3; +622E FE00; CJK COMPATIBILITY IDEOGRAPH-F9D2; +6234 FE00; CJK COMPATIBILITY IDEOGRAPH-FA8C; +625D FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B4; +62B1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B5; +62C9 FE00; CJK COMPATIBILITY IDEOGRAPH-F925; +62CF FE00; CJK COMPATIBILITY IDEOGRAPH-F95B; +62D3 FE00; CJK COMPATIBILITY IDEOGRAPH-FA02; +62D4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B6; +62FC FE00; CJK COMPATIBILITY IDEOGRAPH-2F8BA; +62FE FE00; CJK COMPATIBILITY IDEOGRAPH-F973; +633D FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B9; +6350 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B7; +6368 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8BB; +637B FE00; CJK COMPATIBILITY IDEOGRAPH-F9A4; +6383 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8BC; +63A0 FE00; CJK COMPATIBILITY IDEOGRAPH-F975; +63A9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C1; +63C4 FE00; CJK COMPATIBILITY IDEOGRAPH-FA8D; +63C5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C0; +63E4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8BD; +641C FE00; CJK COMPATIBILITY IDEOGRAPH-FA8E; +6422 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8BF; +6452 FE00; CJK COMPATIBILITY IDEOGRAPH-FA8F; +6469 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C3; +6477 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C6; +647E FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C4; +649A FE00; CJK COMPATIBILITY IDEOGRAPH-F991; +649D FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C5; +64C4 FE00; CJK COMPATIBILITY IDEOGRAPH-F930; +654F FE00; CJK COMPATIBILITY IDEOGRAPH-FA41; +654F FE01; CJK COMPATIBILITY IDEOGRAPH-2F8C8; +6556 FE00; CJK COMPATIBILITY IDEOGRAPH-FA90; +656C FE00; CJK COMPATIBILITY IDEOGRAPH-2F8C9; +6578 FE00; CJK COMPATIBILITY IDEOGRAPH-F969; +6599 FE00; CJK COMPATIBILITY IDEOGRAPH-F9BE; +65C5 FE00; CJK COMPATIBILITY IDEOGRAPH-F983; +65E2 FE00; CJK COMPATIBILITY IDEOGRAPH-FA42; +65E3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8CB; +6613 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E0; +6649 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8CD; +6674 FE00; CJK COMPATIBILITY IDEOGRAPH-FA12; +6674 FE01; CJK COMPATIBILITY IDEOGRAPH-FA91; +6688 FE00; CJK COMPATIBILITY IDEOGRAPH-F9C5; +6691 FE00; CJK COMPATIBILITY IDEOGRAPH-FA43; +6691 FE01; CJK COMPATIBILITY IDEOGRAPH-2F8CF; +669C FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D5; +66B4 FE00; CJK COMPATIBILITY IDEOGRAPH-FA06; +66C6 FE00; CJK COMPATIBILITY IDEOGRAPH-F98B; +66F4 FE00; CJK COMPATIBILITY IDEOGRAPH-F901; +66F8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8CC; +6700 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D4; +6717 FE00; CJK COMPATIBILITY IDEOGRAPH-F929; +6717 FE01; CJK COMPATIBILITY IDEOGRAPH-FA92; +6717 FE02; CJK COMPATIBILITY IDEOGRAPH-2F8D8; +671B FE00; CJK COMPATIBILITY IDEOGRAPH-FA93; +671B FE01; CJK COMPATIBILITY IDEOGRAPH-2F8D9; +6721 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8DA; +674E FE00; CJK COMPATIBILITY IDEOGRAPH-F9E1; +6753 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8DC; +6756 FE00; CJK COMPATIBILITY IDEOGRAPH-FA94; +675E FE00; CJK COMPATIBILITY IDEOGRAPH-2F8DB; +677B FE00; CJK COMPATIBILITY IDEOGRAPH-F9C8; +6785 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E0; +6797 FE00; CJK COMPATIBILITY IDEOGRAPH-F9F4; +67F3 FE00; CJK COMPATIBILITY IDEOGRAPH-F9C9; +67FA FE00; CJK COMPATIBILITY IDEOGRAPH-2F8DF; +6817 FE00; CJK COMPATIBILITY IDEOGRAPH-F9DA; +681F FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E5; +6852 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E1; +6881 FE00; CJK COMPATIBILITY IDEOGRAPH-F97A; +6885 FE00; CJK COMPATIBILITY IDEOGRAPH-FA44; +6885 FE01; CJK COMPATIBILITY IDEOGRAPH-2F8E2; +688E FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E4; +68A8 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E2; +6914 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E6; +6942 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E8; +69A3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E9; +69EA FE00; CJK COMPATIBILITY IDEOGRAPH-2F8EA; +6A02 FE00; CJK COMPATIBILITY IDEOGRAPH-F914; +6A02 FE01; CJK COMPATIBILITY IDEOGRAPH-F95C; +6A02 FE02; CJK COMPATIBILITY IDEOGRAPH-F9BF; +6A13 FE00; CJK COMPATIBILITY IDEOGRAPH-F94C; +6AA8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8EB; +6AD3 FE00; CJK COMPATIBILITY IDEOGRAPH-F931; +6ADB FE00; CJK COMPATIBILITY IDEOGRAPH-2F8ED; +6B04 FE00; CJK COMPATIBILITY IDEOGRAPH-F91D; +6B21 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8EF; +6B54 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F1; +6B72 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F3; +6B77 FE00; CJK COMPATIBILITY IDEOGRAPH-F98C; +6B79 FE00; CJK COMPATIBILITY IDEOGRAPH-FA95; +6B9F FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F4; +6BAE FE00; CJK COMPATIBILITY IDEOGRAPH-F9A5; +6BBA FE00; CJK COMPATIBILITY IDEOGRAPH-F970; +6BBA FE01; CJK COMPATIBILITY IDEOGRAPH-FA96; +6BBA FE02; CJK COMPATIBILITY IDEOGRAPH-2F8F5; +6BBB FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F6; +6C4E FE00; CJK COMPATIBILITY IDEOGRAPH-2F8FA; +6C67 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8FE; +6C88 FE00; CJK COMPATIBILITY IDEOGRAPH-F972; +6CBF FE00; CJK COMPATIBILITY IDEOGRAPH-2F8FC; +6CCC FE00; CJK COMPATIBILITY IDEOGRAPH-F968; +6CCD FE00; CJK COMPATIBILITY IDEOGRAPH-2F8FD; +6CE5 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E3; +6D16 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8FF; +6D1B FE00; CJK COMPATIBILITY IDEOGRAPH-F915; +6D1E FE00; CJK COMPATIBILITY IDEOGRAPH-FA05; +6D34 FE00; CJK COMPATIBILITY IDEOGRAPH-2F907; +6D3E FE00; CJK COMPATIBILITY IDEOGRAPH-2F900; +6D41 FE00; CJK COMPATIBILITY IDEOGRAPH-F9CA; +6D41 FE01; CJK COMPATIBILITY IDEOGRAPH-FA97; +6D41 FE02; CJK COMPATIBILITY IDEOGRAPH-2F902; +6D69 FE00; CJK COMPATIBILITY IDEOGRAPH-2F903; +6D6A FE00; CJK COMPATIBILITY IDEOGRAPH-F92A; +6D77 FE00; CJK COMPATIBILITY IDEOGRAPH-FA45; +6D77 FE01; CJK COMPATIBILITY IDEOGRAPH-2F901; +6D78 FE00; CJK COMPATIBILITY IDEOGRAPH-2F904; +6D85 FE00; CJK COMPATIBILITY IDEOGRAPH-2F905; +6DCB FE00; CJK COMPATIBILITY IDEOGRAPH-F9F5; +6DDA FE00; CJK COMPATIBILITY IDEOGRAPH-F94D; +6DEA FE00; CJK COMPATIBILITY IDEOGRAPH-F9D6; +6DF9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F90E; +6E1A FE00; CJK COMPATIBILITY IDEOGRAPH-FA46; +6E2F FE00; CJK COMPATIBILITY IDEOGRAPH-2F908; +6E6E FE00; CJK COMPATIBILITY IDEOGRAPH-2F909; +6E9C FE00; CJK COMPATIBILITY IDEOGRAPH-F9CB; +6EBA FE00; CJK COMPATIBILITY IDEOGRAPH-F9EC; +6EC7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F90C; +6ECB FE00; CJK COMPATIBILITY IDEOGRAPH-FA99; +6ECB FE01; CJK COMPATIBILITY IDEOGRAPH-2F90B; +6ED1 FE00; CJK COMPATIBILITY IDEOGRAPH-F904; +6EDB FE00; CJK COMPATIBILITY IDEOGRAPH-FA98; +6F0F FE00; CJK COMPATIBILITY IDEOGRAPH-F94E; +6F22 FE00; CJK COMPATIBILITY IDEOGRAPH-FA47; +6F22 FE01; CJK COMPATIBILITY IDEOGRAPH-FA9A; +6F23 FE00; CJK COMPATIBILITY IDEOGRAPH-F992; +6F6E FE00; CJK COMPATIBILITY IDEOGRAPH-2F90F; +6FC6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F912; +6FEB FE00; CJK COMPATIBILITY IDEOGRAPH-F922; +6FFE FE00; CJK COMPATIBILITY IDEOGRAPH-F984; +701B FE00; CJK COMPATIBILITY IDEOGRAPH-2F915; +701E FE00; CJK COMPATIBILITY IDEOGRAPH-FA9B; +701E FE01; CJK COMPATIBILITY IDEOGRAPH-2F914; +7039 FE00; CJK COMPATIBILITY IDEOGRAPH-2F913; +704A FE00; CJK COMPATIBILITY IDEOGRAPH-2F917; +7070 FE00; CJK COMPATIBILITY IDEOGRAPH-2F835; +7077 FE00; CJK COMPATIBILITY IDEOGRAPH-2F919; +707D FE00; CJK COMPATIBILITY IDEOGRAPH-2F918; +7099 FE00; CJK COMPATIBILITY IDEOGRAPH-F9FB; +70AD FE00; CJK COMPATIBILITY IDEOGRAPH-2F91A; +70C8 FE00; CJK COMPATIBILITY IDEOGRAPH-F99F; +70D9 FE00; CJK COMPATIBILITY IDEOGRAPH-F916; +7145 FE00; CJK COMPATIBILITY IDEOGRAPH-2F91C; +7149 FE00; CJK COMPATIBILITY IDEOGRAPH-F993; +716E FE00; CJK COMPATIBILITY IDEOGRAPH-FA48; +716E FE01; CJK COMPATIBILITY IDEOGRAPH-FA9C; +719C FE00; CJK COMPATIBILITY IDEOGRAPH-2F91E; +71CE FE00; CJK COMPATIBILITY IDEOGRAPH-F9C0; +71D0 FE00; CJK COMPATIBILITY IDEOGRAPH-F9EE; +7210 FE00; CJK COMPATIBILITY IDEOGRAPH-F932; +721B FE00; CJK COMPATIBILITY IDEOGRAPH-F91E; +7228 FE00; CJK COMPATIBILITY IDEOGRAPH-2F920; +722B FE00; CJK COMPATIBILITY IDEOGRAPH-FA49; +7235 FE00; CJK COMPATIBILITY IDEOGRAPH-FA9E; +7235 FE01; CJK COMPATIBILITY IDEOGRAPH-2F921; +7250 FE00; CJK COMPATIBILITY IDEOGRAPH-2F922; +7262 FE00; CJK COMPATIBILITY IDEOGRAPH-F946; +7280 FE00; CJK COMPATIBILITY IDEOGRAPH-2F924; +7295 FE00; CJK COMPATIBILITY IDEOGRAPH-2F925; +72AF FE00; CJK COMPATIBILITY IDEOGRAPH-FA9F; +72C0 FE00; CJK COMPATIBILITY IDEOGRAPH-F9FA; +72FC FE00; CJK COMPATIBILITY IDEOGRAPH-F92B; +732A FE00; CJK COMPATIBILITY IDEOGRAPH-FA16; +732A FE01; CJK COMPATIBILITY IDEOGRAPH-FAA0; +7375 FE00; CJK COMPATIBILITY IDEOGRAPH-F9A7; +737A FE00; CJK COMPATIBILITY IDEOGRAPH-2F928; +7387 FE00; CJK COMPATIBILITY IDEOGRAPH-F961; +7387 FE01; CJK COMPATIBILITY IDEOGRAPH-F9DB; +738B FE00; CJK COMPATIBILITY IDEOGRAPH-2F929; +73A5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F92B; +73B2 FE00; CJK COMPATIBILITY IDEOGRAPH-F9AD; +73DE FE00; CJK COMPATIBILITY IDEOGRAPH-F917; +7406 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E4; +7409 FE00; CJK COMPATIBILITY IDEOGRAPH-F9CC; +7422 FE00; CJK COMPATIBILITY IDEOGRAPH-FA4A; +7447 FE00; CJK COMPATIBILITY IDEOGRAPH-2F92E; +745C FE00; CJK COMPATIBILITY IDEOGRAPH-2F92F; +7469 FE00; CJK COMPATIBILITY IDEOGRAPH-F9AE; +7471 FE00; CJK COMPATIBILITY IDEOGRAPH-FAA1; +7471 FE01; CJK COMPATIBILITY IDEOGRAPH-2F930; +7485 FE00; CJK COMPATIBILITY IDEOGRAPH-2F931; +7489 FE00; CJK COMPATIBILITY IDEOGRAPH-F994; +7498 FE00; CJK COMPATIBILITY IDEOGRAPH-F9EF; +74CA FE00; CJK COMPATIBILITY IDEOGRAPH-2F932; +7506 FE00; CJK COMPATIBILITY IDEOGRAPH-FAA2; +7524 FE00; CJK COMPATIBILITY IDEOGRAPH-2F934; +753B FE00; CJK COMPATIBILITY IDEOGRAPH-FAA3; +753E FE00; CJK COMPATIBILITY IDEOGRAPH-2F936; +7559 FE00; CJK COMPATIBILITY IDEOGRAPH-F9CD; +7565 FE00; CJK COMPATIBILITY IDEOGRAPH-F976; +7570 FE00; CJK COMPATIBILITY IDEOGRAPH-F962; +7570 FE01; CJK COMPATIBILITY IDEOGRAPH-2F938; +75E2 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E5; +7610 FE00; CJK COMPATIBILITY IDEOGRAPH-2F93A; +761D FE00; CJK COMPATIBILITY IDEOGRAPH-FAA4; +761F FE00; CJK COMPATIBILITY IDEOGRAPH-FAA5; +7642 FE00; CJK COMPATIBILITY IDEOGRAPH-F9C1; +7669 FE00; CJK COMPATIBILITY IDEOGRAPH-F90E; +76CA FE00; CJK COMPATIBILITY IDEOGRAPH-FA17; +76CA FE01; CJK COMPATIBILITY IDEOGRAPH-FAA6; +76DB FE00; CJK COMPATIBILITY IDEOGRAPH-FAA7; +76E7 FE00; CJK COMPATIBILITY IDEOGRAPH-F933; +76F4 FE00; CJK COMPATIBILITY IDEOGRAPH-FAA8; +76F4 FE01; CJK COMPATIBILITY IDEOGRAPH-2F940; +7701 FE00; CJK COMPATIBILITY IDEOGRAPH-F96D; +771E FE00; CJK COMPATIBILITY IDEOGRAPH-2F945; +771F FE00; CJK COMPATIBILITY IDEOGRAPH-2F946; +771F FE01; CJK COMPATIBILITY IDEOGRAPH-2F947; +7740 FE00; CJK COMPATIBILITY IDEOGRAPH-FAAA; +774A FE00; CJK COMPATIBILITY IDEOGRAPH-FAA9; +774A FE01; CJK COMPATIBILITY IDEOGRAPH-2F948; +778B FE00; CJK COMPATIBILITY IDEOGRAPH-2F94A; +77A7 FE00; CJK COMPATIBILITY IDEOGRAPH-FA9D; +784E FE00; CJK COMPATIBILITY IDEOGRAPH-2F94E; +786B FE00; CJK COMPATIBILITY IDEOGRAPH-F9CE; +788C FE00; CJK COMPATIBILITY IDEOGRAPH-F93B; +788C FE01; CJK COMPATIBILITY IDEOGRAPH-2F94F; +7891 FE00; CJK COMPATIBILITY IDEOGRAPH-FA4B; +78CA FE00; CJK COMPATIBILITY IDEOGRAPH-F947; +78CC FE00; CJK COMPATIBILITY IDEOGRAPH-FAAB; +78CC FE01; CJK COMPATIBILITY IDEOGRAPH-2F950; +78FB FE00; CJK COMPATIBILITY IDEOGRAPH-F964; +792A FE00; CJK COMPATIBILITY IDEOGRAPH-F985; +793C FE00; CJK COMPATIBILITY IDEOGRAPH-FA18; +793E FE00; CJK COMPATIBILITY IDEOGRAPH-FA4C; +7948 FE00; CJK COMPATIBILITY IDEOGRAPH-FA4E; +7949 FE00; CJK COMPATIBILITY IDEOGRAPH-FA4D; +7950 FE00; CJK COMPATIBILITY IDEOGRAPH-FA4F; +7956 FE00; CJK COMPATIBILITY IDEOGRAPH-FA50; +7956 FE01; CJK COMPATIBILITY IDEOGRAPH-2F953; +795D FE00; CJK COMPATIBILITY IDEOGRAPH-FA51; +795E FE00; CJK COMPATIBILITY IDEOGRAPH-FA19; +7965 FE00; CJK COMPATIBILITY IDEOGRAPH-FA1A; +797F FE00; CJK COMPATIBILITY IDEOGRAPH-F93C; +798D FE00; CJK COMPATIBILITY IDEOGRAPH-FA52; +798E FE00; CJK COMPATIBILITY IDEOGRAPH-FA53; +798F FE00; CJK COMPATIBILITY IDEOGRAPH-FA1B; +798F FE01; CJK COMPATIBILITY IDEOGRAPH-2F956; +79AE FE00; CJK COMPATIBILITY IDEOGRAPH-F9B6; +79CA FE00; CJK COMPATIBILITY IDEOGRAPH-F995; +79EB FE00; CJK COMPATIBILITY IDEOGRAPH-2F957; +7A1C FE00; CJK COMPATIBILITY IDEOGRAPH-F956; +7A40 FE00; CJK COMPATIBILITY IDEOGRAPH-FA54; +7A40 FE01; CJK COMPATIBILITY IDEOGRAPH-2F959; +7A4A FE00; CJK COMPATIBILITY IDEOGRAPH-2F95A; +7A4F FE00; CJK COMPATIBILITY IDEOGRAPH-2F95B; +7A81 FE00; CJK COMPATIBILITY IDEOGRAPH-FA55; +7AB1 FE00; CJK COMPATIBILITY IDEOGRAPH-FAAC; +7ACB FE00; CJK COMPATIBILITY IDEOGRAPH-F9F7; +7AEE FE00; CJK COMPATIBILITY IDEOGRAPH-2F95F; +7B20 FE00; CJK COMPATIBILITY IDEOGRAPH-F9F8; +7BC0 FE00; CJK COMPATIBILITY IDEOGRAPH-FA56; +7BC0 FE01; CJK COMPATIBILITY IDEOGRAPH-FAAD; +7BC6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F962; +7BC9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F963; +7C3E FE00; CJK COMPATIBILITY IDEOGRAPH-F9A6; +7C60 FE00; CJK COMPATIBILITY IDEOGRAPH-F944; +7C7B FE00; CJK COMPATIBILITY IDEOGRAPH-FAAE; +7C92 FE00; CJK COMPATIBILITY IDEOGRAPH-F9F9; +7CBE FE00; CJK COMPATIBILITY IDEOGRAPH-FA1D; +7CD2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F966; +7CD6 FE00; CJK COMPATIBILITY IDEOGRAPH-FA03; +7CE3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F969; +7CE7 FE00; CJK COMPATIBILITY IDEOGRAPH-F97B; +7CE8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F968; +7D00 FE00; CJK COMPATIBILITY IDEOGRAPH-2F96A; +7D10 FE00; CJK COMPATIBILITY IDEOGRAPH-F9CF; +7D22 FE00; CJK COMPATIBILITY IDEOGRAPH-F96A; +7D2F FE00; CJK COMPATIBILITY IDEOGRAPH-F94F; +7D5B FE00; CJK COMPATIBILITY IDEOGRAPH-FAAF; +7D63 FE00; CJK COMPATIBILITY IDEOGRAPH-2F96C; +7DA0 FE00; CJK COMPATIBILITY IDEOGRAPH-F93D; +7DBE FE00; CJK COMPATIBILITY IDEOGRAPH-F957; +7DC7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F96E; +7DF4 FE00; CJK COMPATIBILITY IDEOGRAPH-F996; +7DF4 FE01; CJK COMPATIBILITY IDEOGRAPH-FA57; +7DF4 FE02; CJK COMPATIBILITY IDEOGRAPH-FAB0; +7E02 FE00; CJK COMPATIBILITY IDEOGRAPH-2F96F; +7E09 FE00; CJK COMPATIBILITY IDEOGRAPH-FA58; +7E37 FE00; CJK COMPATIBILITY IDEOGRAPH-F950; +7E41 FE00; CJK COMPATIBILITY IDEOGRAPH-FA59; +7E45 FE00; CJK COMPATIBILITY IDEOGRAPH-2F970; +7F3E FE00; CJK COMPATIBILITY IDEOGRAPH-FAB1; +7F72 FE00; CJK COMPATIBILITY IDEOGRAPH-FA5A; +7F79 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E6; +7F7A FE00; CJK COMPATIBILITY IDEOGRAPH-2F976; +7F85 FE00; CJK COMPATIBILITY IDEOGRAPH-F90F; +7F95 FE00; CJK COMPATIBILITY IDEOGRAPH-2F978; +7F9A FE00; CJK COMPATIBILITY IDEOGRAPH-F9AF; +7FBD FE00; CJK COMPATIBILITY IDEOGRAPH-FA1E; +7FFA FE00; CJK COMPATIBILITY IDEOGRAPH-2F979; +8001 FE00; CJK COMPATIBILITY IDEOGRAPH-F934; +8005 FE00; CJK COMPATIBILITY IDEOGRAPH-FA5B; +8005 FE01; CJK COMPATIBILITY IDEOGRAPH-FAB2; +8005 FE02; CJK COMPATIBILITY IDEOGRAPH-2F97A; +8046 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B0; +8060 FE00; CJK COMPATIBILITY IDEOGRAPH-2F97D; +806F FE00; CJK COMPATIBILITY IDEOGRAPH-F997; +8070 FE00; CJK COMPATIBILITY IDEOGRAPH-2F97F; +807E FE00; CJK COMPATIBILITY IDEOGRAPH-F945; +808B FE00; CJK COMPATIBILITY IDEOGRAPH-F953; +80AD FE00; CJK COMPATIBILITY IDEOGRAPH-2F8D6; +80B2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F982; +8103 FE00; CJK COMPATIBILITY IDEOGRAPH-2F983; +813E FE00; CJK COMPATIBILITY IDEOGRAPH-2F985; +81D8 FE00; CJK COMPATIBILITY IDEOGRAPH-F926; +81E8 FE00; CJK COMPATIBILITY IDEOGRAPH-F9F6; +81ED FE00; CJK COMPATIBILITY IDEOGRAPH-FA5C; +8201 FE00; CJK COMPATIBILITY IDEOGRAPH-2F893; +8201 FE01; CJK COMPATIBILITY IDEOGRAPH-2F98B; +8204 FE00; CJK COMPATIBILITY IDEOGRAPH-2F98C; +8218 FE00; CJK COMPATIBILITY IDEOGRAPH-FA6D; +826F FE00; CJK COMPATIBILITY IDEOGRAPH-F97C; +8279 FE00; CJK COMPATIBILITY IDEOGRAPH-FA5D; +8279 FE01; CJK COMPATIBILITY IDEOGRAPH-FA5E; +828B FE00; CJK COMPATIBILITY IDEOGRAPH-2F990; +8291 FE00; CJK COMPATIBILITY IDEOGRAPH-2F98F; +829D FE00; CJK COMPATIBILITY IDEOGRAPH-2F991; +82B1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F993; +82B3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F994; +82BD FE00; CJK COMPATIBILITY IDEOGRAPH-2F995; +82E5 FE00; CJK COMPATIBILITY IDEOGRAPH-F974; +82E5 FE01; CJK COMPATIBILITY IDEOGRAPH-2F998; +82E6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F996; +831D FE00; CJK COMPATIBILITY IDEOGRAPH-2F999; +8323 FE00; CJK COMPATIBILITY IDEOGRAPH-2F99C; +8336 FE00; CJK COMPATIBILITY IDEOGRAPH-F9FE; +8352 FE00; CJK COMPATIBILITY IDEOGRAPH-FAB3; +8353 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A0; +8363 FE00; CJK COMPATIBILITY IDEOGRAPH-2F99A; +83AD FE00; CJK COMPATIBILITY IDEOGRAPH-2F99B; +83BD FE00; CJK COMPATIBILITY IDEOGRAPH-2F99D; +83C9 FE00; CJK COMPATIBILITY IDEOGRAPH-F93E; +83CA FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A1; +83CC FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A2; +83DC FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A3; +83E7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F99E; +83EF FE00; CJK COMPATIBILITY IDEOGRAPH-FAB4; +83F1 FE00; CJK COMPATIBILITY IDEOGRAPH-F958; +843D FE00; CJK COMPATIBILITY IDEOGRAPH-F918; +8449 FE00; CJK COMPATIBILITY IDEOGRAPH-F96E; +8457 FE00; CJK COMPATIBILITY IDEOGRAPH-FA5F; +8457 FE01; CJK COMPATIBILITY IDEOGRAPH-2F99F; +84EE FE00; CJK COMPATIBILITY IDEOGRAPH-F999; +84F1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A8; +84F3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A9; +84FC FE00; CJK COMPATIBILITY IDEOGRAPH-F9C2; +8516 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9AA; +8564 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9AC; +85CD FE00; CJK COMPATIBILITY IDEOGRAPH-F923; +85FA FE00; CJK COMPATIBILITY IDEOGRAPH-F9F0; +8606 FE00; CJK COMPATIBILITY IDEOGRAPH-F935; +8612 FE00; CJK COMPATIBILITY IDEOGRAPH-FA20; +862D FE00; CJK COMPATIBILITY IDEOGRAPH-F91F; +863F FE00; CJK COMPATIBILITY IDEOGRAPH-F910; +8650 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B3; +865C FE00; CJK COMPATIBILITY IDEOGRAPH-F936; +865C FE01; CJK COMPATIBILITY IDEOGRAPH-2F9B4; +8667 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B5; +8669 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B6; +8688 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B8; +86A9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B7; +86E2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9BA; +870E FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B9; +8728 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9BC; +876B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9BD; +8779 FE00; CJK COMPATIBILITY IDEOGRAPH-FAB5; +8779 FE01; CJK COMPATIBILITY IDEOGRAPH-2F9BB; +8786 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9BE; +87BA FE00; CJK COMPATIBILITY IDEOGRAPH-F911; +87E1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C0; +8801 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C1; +881F FE00; CJK COMPATIBILITY IDEOGRAPH-F927; +884C FE00; CJK COMPATIBILITY IDEOGRAPH-FA08; +8860 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C3; +8863 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C4; +88C2 FE00; CJK COMPATIBILITY IDEOGRAPH-F9A0; +88CF FE00; CJK COMPATIBILITY IDEOGRAPH-F9E7; +88D7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C6; +88DE FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C7; +88E1 FE00; CJK COMPATIBILITY IDEOGRAPH-F9E8; +88F8 FE00; CJK COMPATIBILITY IDEOGRAPH-F912; +88FA FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C9; +8910 FE00; CJK COMPATIBILITY IDEOGRAPH-FA60; +8941 FE00; CJK COMPATIBILITY IDEOGRAPH-FAB6; +8964 FE00; CJK COMPATIBILITY IDEOGRAPH-F924; +8986 FE00; CJK COMPATIBILITY IDEOGRAPH-FAB7; +898B FE00; CJK COMPATIBILITY IDEOGRAPH-FA0A; +8996 FE00; CJK COMPATIBILITY IDEOGRAPH-FA61; +8996 FE01; CJK COMPATIBILITY IDEOGRAPH-FAB8; +8AA0 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9CF; +8AAA FE00; CJK COMPATIBILITY IDEOGRAPH-F96F; +8AAA FE01; CJK COMPATIBILITY IDEOGRAPH-F9A1; +8ABF FE00; CJK COMPATIBILITY IDEOGRAPH-FAB9; +8ACB FE00; CJK COMPATIBILITY IDEOGRAPH-FABB; +8AD2 FE00; CJK COMPATIBILITY IDEOGRAPH-F97D; +8AD6 FE00; CJK COMPATIBILITY IDEOGRAPH-F941; +8AED FE00; CJK COMPATIBILITY IDEOGRAPH-FABE; +8AED FE01; CJK COMPATIBILITY IDEOGRAPH-2F9D0; +8AF8 FE00; CJK COMPATIBILITY IDEOGRAPH-FA22; +8AF8 FE01; CJK COMPATIBILITY IDEOGRAPH-FABA; +8AFE FE00; CJK COMPATIBILITY IDEOGRAPH-F95D; +8AFE FE01; CJK COMPATIBILITY IDEOGRAPH-FABD; +8B01 FE00; CJK COMPATIBILITY IDEOGRAPH-FA62; +8B01 FE01; CJK COMPATIBILITY IDEOGRAPH-FABC; +8B39 FE00; CJK COMPATIBILITY IDEOGRAPH-FA63; +8B39 FE01; CJK COMPATIBILITY IDEOGRAPH-FABF; +8B58 FE00; CJK COMPATIBILITY IDEOGRAPH-F9FC; +8B80 FE00; CJK COMPATIBILITY IDEOGRAPH-F95A; +8B8A FE00; CJK COMPATIBILITY IDEOGRAPH-FAC0; +8B8A FE01; CJK COMPATIBILITY IDEOGRAPH-2F9D1; +8C48 FE00; CJK COMPATIBILITY IDEOGRAPH-F900; +8C55 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D2; +8CAB FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D4; +8CC1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D5; +8CC2 FE00; CJK COMPATIBILITY IDEOGRAPH-F948; +8CC8 FE00; CJK COMPATIBILITY IDEOGRAPH-F903; +8CD3 FE00; CJK COMPATIBILITY IDEOGRAPH-FA64; +8D08 FE00; CJK COMPATIBILITY IDEOGRAPH-FA65; +8D08 FE01; CJK COMPATIBILITY IDEOGRAPH-FAC1; +8D1B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D6; +8D77 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D7; +8DBC FE00; CJK COMPATIBILITY IDEOGRAPH-2F9DB; +8DCB FE00; CJK COMPATIBILITY IDEOGRAPH-2F9DA; +8DEF FE00; CJK COMPATIBILITY IDEOGRAPH-F937; +8DF0 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9DC; +8ECA FE00; CJK COMPATIBILITY IDEOGRAPH-F902; +8ED4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9DE; +8F26 FE00; CJK COMPATIBILITY IDEOGRAPH-F998; +8F2A FE00; CJK COMPATIBILITY IDEOGRAPH-F9D7; +8F38 FE00; CJK COMPATIBILITY IDEOGRAPH-FAC2; +8F38 FE01; CJK COMPATIBILITY IDEOGRAPH-2F9DF; +8F3B FE00; CJK COMPATIBILITY IDEOGRAPH-FA07; +8F62 FE00; CJK COMPATIBILITY IDEOGRAPH-F98D; +8F9E FE00; CJK COMPATIBILITY IDEOGRAPH-2F98D; +8FB0 FE00; CJK COMPATIBILITY IDEOGRAPH-F971; +8FB6 FE00; CJK COMPATIBILITY IDEOGRAPH-FA66; +9023 FE00; CJK COMPATIBILITY IDEOGRAPH-F99A; +9038 FE00; CJK COMPATIBILITY IDEOGRAPH-FA25; +9038 FE01; CJK COMPATIBILITY IDEOGRAPH-FA67; +9072 FE00; CJK COMPATIBILITY IDEOGRAPH-FAC3; +907C FE00; CJK COMPATIBILITY IDEOGRAPH-F9C3; +908F FE00; CJK COMPATIBILITY IDEOGRAPH-F913; +9094 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E2; +90CE FE00; CJK COMPATIBILITY IDEOGRAPH-F92C; +90DE FE00; CJK COMPATIBILITY IDEOGRAPH-FA2E; +90F1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E3; +90FD FE00; CJK COMPATIBILITY IDEOGRAPH-FA26; +9111 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E4; +911B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E6; +916A FE00; CJK COMPATIBILITY IDEOGRAPH-F919; +9199 FE00; CJK COMPATIBILITY IDEOGRAPH-FAC4; +91B4 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B7; +91CC FE00; CJK COMPATIBILITY IDEOGRAPH-F9E9; +91CF FE00; CJK COMPATIBILITY IDEOGRAPH-F97E; +91D1 FE00; CJK COMPATIBILITY IDEOGRAPH-F90A; +9234 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B1; +9238 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E7; +9276 FE00; CJK COMPATIBILITY IDEOGRAPH-FAC5; +927C FE00; CJK COMPATIBILITY IDEOGRAPH-2F9EA; +92D7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E8; +92D8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E9; +9304 FE00; CJK COMPATIBILITY IDEOGRAPH-F93F; +934A FE00; CJK COMPATIBILITY IDEOGRAPH-F99B; +93F9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9EB; +9415 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9EC; +958B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9EE; +95AD FE00; CJK COMPATIBILITY IDEOGRAPH-F986; +95B7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F0; +962E FE00; CJK COMPATIBILITY IDEOGRAPH-F9C6; +964B FE00; CJK COMPATIBILITY IDEOGRAPH-F951; +964D FE00; CJK COMPATIBILITY IDEOGRAPH-FA09; +9675 FE00; CJK COMPATIBILITY IDEOGRAPH-F959; +9678 FE00; CJK COMPATIBILITY IDEOGRAPH-F9D3; +967C FE00; CJK COMPATIBILITY IDEOGRAPH-FAC6; +9686 FE00; CJK COMPATIBILITY IDEOGRAPH-F9DC; +96A3 FE00; CJK COMPATIBILITY IDEOGRAPH-F9F1; +96B7 FE00; CJK COMPATIBILITY IDEOGRAPH-FA2F; +96B8 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B8; +96C3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F3; +96E2 FE00; CJK COMPATIBILITY IDEOGRAPH-F9EA; +96E3 FE00; CJK COMPATIBILITY IDEOGRAPH-FA68; +96E3 FE01; CJK COMPATIBILITY IDEOGRAPH-FAC7; +96F6 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B2; +96F7 FE00; CJK COMPATIBILITY IDEOGRAPH-F949; +9723 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F5; +9732 FE00; CJK COMPATIBILITY IDEOGRAPH-F938; +9748 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B3; +9756 FE00; CJK COMPATIBILITY IDEOGRAPH-FA1C; +9756 FE01; CJK COMPATIBILITY IDEOGRAPH-FAC8; +97DB FE00; CJK COMPATIBILITY IDEOGRAPH-FAC9; +97E0 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9FA; +97FF FE00; CJK COMPATIBILITY IDEOGRAPH-FA69; +97FF FE01; CJK COMPATIBILITY IDEOGRAPH-FACA; +980B FE00; CJK COMPATIBILITY IDEOGRAPH-FACB; +980B FE01; CJK COMPATIBILITY IDEOGRAPH-2F9FE; +980B FE02; CJK COMPATIBILITY IDEOGRAPH-2F9FF; +9818 FE00; CJK COMPATIBILITY IDEOGRAPH-F9B4; +9829 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA00; +983B FE00; CJK COMPATIBILITY IDEOGRAPH-FA6A; +983B FE01; CJK COMPATIBILITY IDEOGRAPH-FACC; +985E FE00; CJK COMPATIBILITY IDEOGRAPH-F9D0; +98E2 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA02; +98EF FE00; CJK COMPATIBILITY IDEOGRAPH-FA2A; +98FC FE00; CJK COMPATIBILITY IDEOGRAPH-FA2B; +9928 FE00; CJK COMPATIBILITY IDEOGRAPH-FA2C; +9929 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA04; +99A7 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA05; +99C2 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA06; +99F1 FE00; CJK COMPATIBILITY IDEOGRAPH-F91A; +99FE FE00; CJK COMPATIBILITY IDEOGRAPH-2FA07; +9A6A FE00; CJK COMPATIBILITY IDEOGRAPH-F987; +9B12 FE00; CJK COMPATIBILITY IDEOGRAPH-FACD; +9B12 FE01; CJK COMPATIBILITY IDEOGRAPH-2FA0A; +9B6F FE00; CJK COMPATIBILITY IDEOGRAPH-F939; +9C40 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA0B; +9C57 FE00; CJK COMPATIBILITY IDEOGRAPH-F9F2; +9CFD FE00; CJK COMPATIBILITY IDEOGRAPH-2FA0C; +9D67 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA0F; +9DB4 FE00; CJK COMPATIBILITY IDEOGRAPH-FA2D; +9DFA FE00; CJK COMPATIBILITY IDEOGRAPH-F93A; +9E1E FE00; CJK COMPATIBILITY IDEOGRAPH-F920; +9E7F FE00; CJK COMPATIBILITY IDEOGRAPH-F940; +9E97 FE00; CJK COMPATIBILITY IDEOGRAPH-F988; +9E9F FE00; CJK COMPATIBILITY IDEOGRAPH-F9F3; +9EBB FE00; CJK COMPATIBILITY IDEOGRAPH-2FA15; +9ECE FE00; CJK COMPATIBILITY IDEOGRAPH-F989; +9EF9 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA17; +9EFE FE00; CJK COMPATIBILITY IDEOGRAPH-2FA18; +9F05 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA19; +9F0F FE00; CJK COMPATIBILITY IDEOGRAPH-2FA1A; +9F16 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA1B; +9F3B FE00; CJK COMPATIBILITY IDEOGRAPH-2FA1C; +9F43 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD8; +9F8D FE00; CJK COMPATIBILITY IDEOGRAPH-F9C4; +9F8E FE00; CJK COMPATIBILITY IDEOGRAPH-FAD9; +9F9C FE00; CJK COMPATIBILITY IDEOGRAPH-F907; +9F9C FE01; CJK COMPATIBILITY IDEOGRAPH-F908; +9F9C FE02; CJK COMPATIBILITY IDEOGRAPH-FACE; +20122 FE00; CJK COMPATIBILITY IDEOGRAPH-2F803; +2051C FE00; CJK COMPATIBILITY IDEOGRAPH-2F812; +20525 FE00; CJK COMPATIBILITY IDEOGRAPH-2F91B; +2054B FE00; CJK COMPATIBILITY IDEOGRAPH-2F816; +2063A FE00; CJK COMPATIBILITY IDEOGRAPH-2F80D; +20804 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D9; +208DE FE00; CJK COMPATIBILITY IDEOGRAPH-2F9DD; +20A2C FE00; CJK COMPATIBILITY IDEOGRAPH-2F834; +20B63 FE00; CJK COMPATIBILITY IDEOGRAPH-2F838; +214E4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F859; +216A8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F860; +216EA FE00; CJK COMPATIBILITY IDEOGRAPH-2F861; +219C8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F86C; +21B18 FE00; CJK COMPATIBILITY IDEOGRAPH-2F871; +21D0B FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F8; +21DE4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F87B; +21DE6 FE00; CJK COMPATIBILITY IDEOGRAPH-2F87D; +22183 FE00; CJK COMPATIBILITY IDEOGRAPH-2F889; +2219F FE00; CJK COMPATIBILITY IDEOGRAPH-2F939; +22331 FE00; CJK COMPATIBILITY IDEOGRAPH-2F891; +22331 FE01; CJK COMPATIBILITY IDEOGRAPH-2F892; +226D4 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8A4; +22844 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD0; +2284A FE00; CJK COMPATIBILITY IDEOGRAPH-FACF; +22B0C FE00; CJK COMPATIBILITY IDEOGRAPH-2F8B8; +22BF1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8BE; +2300A FE00; CJK COMPATIBILITY IDEOGRAPH-2F8CA; +232B8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F897; +2335F FE00; CJK COMPATIBILITY IDEOGRAPH-2F980; +23393 FE00; CJK COMPATIBILITY IDEOGRAPH-2F989; +2339C FE00; CJK COMPATIBILITY IDEOGRAPH-2F98A; +233C3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8DD; +233D5 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD1; +2346D FE00; CJK COMPATIBILITY IDEOGRAPH-2F8E3; +236A3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8EC; +238A7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F0; +23A8D FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F7; +23AFA FE00; CJK COMPATIBILITY IDEOGRAPH-2F8F9; +23CBC FE00; CJK COMPATIBILITY IDEOGRAPH-2F8FB; +23D1E FE00; CJK COMPATIBILITY IDEOGRAPH-2F906; +23ED1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F90D; +23F5E FE00; CJK COMPATIBILITY IDEOGRAPH-2F910; +23F8E FE00; CJK COMPATIBILITY IDEOGRAPH-2F911; +24263 FE00; CJK COMPATIBILITY IDEOGRAPH-2F91D; +242EE FE00; CJK COMPATIBILITY IDEOGRAPH-FA6C; +243AB FE00; CJK COMPATIBILITY IDEOGRAPH-2F91F; +24608 FE00; CJK COMPATIBILITY IDEOGRAPH-2F923; +24735 FE00; CJK COMPATIBILITY IDEOGRAPH-2F926; +24814 FE00; CJK COMPATIBILITY IDEOGRAPH-2F927; +24C36 FE00; CJK COMPATIBILITY IDEOGRAPH-2F935; +24C92 FE00; CJK COMPATIBILITY IDEOGRAPH-2F937; +24FA1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F93B; +24FB8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F93C; +25044 FE00; CJK COMPATIBILITY IDEOGRAPH-2F93D; +250F2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F942; +250F3 FE00; CJK COMPATIBILITY IDEOGRAPH-2F941; +25119 FE00; CJK COMPATIBILITY IDEOGRAPH-2F943; +25133 FE00; CJK COMPATIBILITY IDEOGRAPH-2F944; +25249 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD5; +2541D FE00; CJK COMPATIBILITY IDEOGRAPH-2F94D; +25626 FE00; CJK COMPATIBILITY IDEOGRAPH-2F952; +2569A FE00; CJK COMPATIBILITY IDEOGRAPH-2F954; +256C5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F955; +2597C FE00; CJK COMPATIBILITY IDEOGRAPH-2F95C; +25AA7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F95D; +25AA7 FE01; CJK COMPATIBILITY IDEOGRAPH-2F95E; +25BAB FE00; CJK COMPATIBILITY IDEOGRAPH-2F961; +25C80 FE00; CJK COMPATIBILITY IDEOGRAPH-2F965; +25CD0 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD6; +25F86 FE00; CJK COMPATIBILITY IDEOGRAPH-2F96B; +261DA FE00; CJK COMPATIBILITY IDEOGRAPH-2F898; +26228 FE00; CJK COMPATIBILITY IDEOGRAPH-2F972; +26247 FE00; CJK COMPATIBILITY IDEOGRAPH-2F973; +262D9 FE00; CJK COMPATIBILITY IDEOGRAPH-2F975; +2633E FE00; CJK COMPATIBILITY IDEOGRAPH-2F977; +264DA FE00; CJK COMPATIBILITY IDEOGRAPH-2F97B; +26523 FE00; CJK COMPATIBILITY IDEOGRAPH-2F97C; +265A8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F97E; +267A7 FE00; CJK COMPATIBILITY IDEOGRAPH-2F987; +267B5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F988; +26B3C FE00; CJK COMPATIBILITY IDEOGRAPH-2F997; +26C36 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A4; +26CD5 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A6; +26D6B FE00; CJK COMPATIBILITY IDEOGRAPH-2F9A5; +26F2C FE00; CJK COMPATIBILITY IDEOGRAPH-2F9AD; +26FB1 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B0; +270D2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9B1; +273CA FE00; CJK COMPATIBILITY IDEOGRAPH-2F9AB; +27667 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9C5; +278AE FE00; CJK COMPATIBILITY IDEOGRAPH-2F9CB; +27966 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9CC; +27CA8 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D3; +27ED3 FE00; CJK COMPATIBILITY IDEOGRAPH-FAD7; +27F2F FE00; CJK COMPATIBILITY IDEOGRAPH-2F9D8; +285D2 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E0; +285ED FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E1; +2872E FE00; CJK COMPATIBILITY IDEOGRAPH-2F9E5; +28BFA FE00; CJK COMPATIBILITY IDEOGRAPH-2F9ED; +28D77 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F1; +29145 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F6; +291DF FE00; CJK COMPATIBILITY IDEOGRAPH-2F81C; +2921A FE00; CJK COMPATIBILITY IDEOGRAPH-2F9F7; +2940A FE00; CJK COMPATIBILITY IDEOGRAPH-2F9FB; +29496 FE00; CJK COMPATIBILITY IDEOGRAPH-2F9FD; +295B6 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA01; +29B30 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA09; +2A0CE FE00; CJK COMPATIBILITY IDEOGRAPH-2FA10; +2A105 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA12; +2A20E FE00; CJK COMPATIBILITY IDEOGRAPH-2FA13; +2A291 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA14; +2A392 FE00; CJK COMPATIBILITY IDEOGRAPH-2F88F; +2A600 FE00; CJK COMPATIBILITY IDEOGRAPH-2FA1D; + # EOF diff --git a/lib/unicore/UnicodeData.txt b/lib/unicore/UnicodeData.txt index 086379eb4f..9fffa71a1e 100644 --- a/lib/unicore/UnicodeData.txt +++ b/lib/unicore/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;;;;; -2309;RIGHT CEILING;Sm;0;ON;;;;;Y;;;;; -230A;LEFT FLOOR;Sm;0;ON;;;;;Y;;;;; -230B;RIGHT FLOOR;Sm;0;ON;;;;;Y;;;;; +2308;LEFT CEILING;Ps;0;ON;;;;;Y;;;;; +2309;RIGHT CEILING;Pe;0;ON;;;;;Y;;;;; +230A;LEFT FLOOR;Ps;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;;;;; -12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;-1;N;;;;; +12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;2;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;;;;; diff --git a/lib/unicore/auxiliary/GCBTest.txt b/lib/unicore/auxiliary/GCBTest.txt index 90e15fed3e..88a98e7127 100644 --- a/lib/unicore/auxiliary/GCBTest.txt +++ b/lib/unicore/auxiliary/GCBTest.txt @@ -1,8 +1,8 @@ -# GraphemeBreakTest-6.2.0.txt -# Date: 2012-08-22, 12:41:15 GMT [MD] +# GraphemeBreakTest-6.3.0.txt +# 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/ # diff --git a/lib/unicore/auxiliary/GraphemeBreakProperty.txt b/lib/unicore/auxiliary/GraphemeBreakProperty.txt index 948faa9d5c..55556e0c58 100644 --- a/lib/unicore/auxiliary/GraphemeBreakProperty.txt +++ b/lib/unicore/auxiliary/GraphemeBreakProperty.txt @@ -1,8 +1,8 @@ -# GraphemeBreakProperty-6.2.0.txt -# Date: 2012-08-13, 19:12:02 GMT [MD] +# GraphemeBreakProperty-6.3.0.txt +# 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> -206A..206F ; Control # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2065 ; Control # Cn <reserved-2065> +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 # ================================================ diff --git a/lib/unicore/auxiliary/SentenceBreakProperty.txt b/lib/unicore/auxiliary/SentenceBreakProperty.txt index f29dc4e199..d714d59d3a 100644 --- a/lib/unicore/auxiliary/SentenceBreakProperty.txt +++ b/lib/unicore/auxiliary/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 # ================================================ diff --git a/lib/unicore/auxiliary/WordBreakProperty.txt b/lib/unicore/auxiliary/WordBreakProperty.txt index 2caa16b46b..ad2b10992c 100644 --- a/lib/unicore/auxiliary/WordBreakProperty.txt +++ b/lib/unicore/auxiliary/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 # ================================================ diff --git a/lib/unicore/extracted/DBidiClass.txt b/lib/unicore/extracted/DBidiClass.txt index eac65b659e..226ffff6d3 100644 --- a/lib/unicore/extracted/DBidiClass.txt +++ b/lib/unicore/extracted/DBidiClass.txt @@ -1,8 +1,8 @@ -# DerivedBidiClass-6.2.0.txt -# Date: 2012-05-20, 00:42:30 GMT [MD] +# DerivedBidiClass-6.3.0.txt +# Date: 2013-07-05, 14:08:43 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/ @@ -47,6 +47,15 @@ # U+1E800 - U+1EDFF, # U+1EF00 - U+1EFFF # +# The unassigned code points that default to ET are in the range: +# [\u20A0-\u20CF] +# +# Currency Symbols: U+20A0 - U+20CF +# +# The unassigned code points that default to BN have one of the following properties: +# Default_Ignorable_Code_Point +# Noncharacter_Code_Point +# # For all other cases: # All code points not explicitly listed for Bidi_Class @@ -392,7 +401,7 @@ 19D0..19D9 ; L # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE 19DA ; L # No NEW TAI LUE THAM DIGIT ONE 1A00..1A16 ; L # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA -1A19..1A1B ; L # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; L # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O 1A1E..1A1F ; L # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 1A20..1A54 ; L # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; L # Mc TAI THAM CONSONANT SIGN MEDIAL RA @@ -807,8 +816,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; L # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 858959 code points not listed here. -# Total code points: 1098530 +# The above property value applies to 858938 code points not listed here. +# Total code points: 1098508 # ================================================ @@ -972,6 +981,7 @@ FF0D ; ES # Pd FULLWIDTH HYPHEN-MINUS 17DB ; ET # Sc KHMER CURRENCY SYMBOL RIEL 2030..2034 ; ET # Po [5] PER MILLE SIGN..TRIPLE PRIME 20A0..20BA ; ET # Sc [27] EURO-CURRENCY SIGN..TURKISH LIRA SIGN +20BB..20CF ; ET # Cn [21] <reserved-20BB>..<reserved-20CF> 212E ; ET # So ESTIMATED SYMBOL 2213 ; ET # Sm MINUS-OR-PLUS SIGN A838 ; ET # Sc NORTH INDIC RUPEE MARK @@ -985,7 +995,7 @@ FF05 ; ET # Po FULLWIDTH PERCENT SIGN FFE0..FFE1 ; ET # Sc [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN FFE5..FFE6 ; ET # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN -# Total code points: 66 +# Total code points: 87 # ================================================ @@ -1048,13 +1058,12 @@ FF1A ; CS # Po FULLWIDTH COLON 000C ; WS # Cc <control-000C> 0020 ; WS # Zs SPACE 1680 ; WS # Zs OGHAM SPACE MARK -180E ; WS # Zs MONGOLIAN VOWEL SEPARATOR 2000..200A ; WS # Zs [11] EN QUAD..HAIR SPACE 2028 ; WS # Zl LINE SEPARATOR 205F ; WS # Zs MEDIUM MATHEMATICAL SPACE 3000 ; WS # Zs IDEOGRAPHIC SPACE -# Total code points: 18 +# Total code points: 17 # ================================================ @@ -1207,7 +1216,10 @@ FF1A ; CS # Po FULLWIDTH COLON 21F4..2211 ; ON # Sm [30] RIGHT ARROW WITH SMALL CIRCLE..N-ARY SUMMATION 2214..22FF ; ON # Sm [236] DOT PLUS..Z NOTATION BAG MEMBERSHIP 2300..2307 ; ON # So [8] DIAMETER SIGN..WAVY LINE -2308..230B ; ON # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; ON # Ps LEFT CEILING +2309 ; ON # Pe RIGHT CEILING +230A ; ON # Ps LEFT FLOOR +230B ; ON # Pe RIGHT FLOOR 230C..231F ; ON # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER 2320..2321 ; ON # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2322..2328 ; ON # So [7] FROWN..KEYBOARD @@ -1532,9 +1544,10 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 007F..0084 ; BN # Cc [6] <control-007F>..<control-0084> 0086..009F ; BN # Cc [26] <control-0086>..<control-009F> 00AD ; BN # Cf SOFT HYPHEN +180E ; BN # Cf MONGOLIAN VOWEL SEPARATOR 200B..200D ; BN # Cf [3] ZERO WIDTH SPACE..ZERO WIDTH JOINER 2060..2064 ; BN # Cf [5] WORD JOINER..INVISIBLE PLUS -2065..2069 ; BN # Cn [5] <reserved-2065>..<reserved-2069> +2065 ; BN # Cn <reserved-2065> 206A..206F ; BN # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES FDD0..FDEF ; BN # Cn [32] <noncharacter-FDD0>..<noncharacter-FDEF> FEFF ; BN # Cf ZERO WIDTH NO-BREAK SPACE @@ -1563,7 +1576,7 @@ EFFFE..EFFFF ; BN # Cn [2] <noncharacter-EFFFE>..<noncharacter-EFFFF> FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 10FFFE..10FFFF; BN # Cn [2] <noncharacter-10FFFE>..<noncharacter-10FFFF> -# Total code points: 4015 +# Total code points: 4012 # ================================================ @@ -1689,6 +1702,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 1932 ; NSM # Mn LIMBU SMALL LETTER ANUSVARA 1939..193B ; NSM # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; NSM # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; NSM # Mn BUGINESE VOWEL SIGN AE 1A56 ; NSM # Mn TAI THAM CONSONANT SIGN MEDIAL LA 1A58..1A5E ; NSM # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA 1A60 ; NSM # Mn TAI THAM SIGN SAKOT @@ -1792,7 +1806,7 @@ FE20..FE26 ; NSM # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOININ 1D242..1D244 ; NSM # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1290 +# Total code points: 1291 # ================================================ @@ -1803,7 +1817,8 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 060B ; AL # Sc AFGHANI SIGN 060D ; AL # Po ARABIC DATE SEPARATOR 061B ; AL # Po ARABIC SEMICOLON -061C..061D ; AL # Cn [2] <reserved-061C>..<reserved-061D> +061C ; AL # Cf ARABIC LETTER MARK +061D ; AL # Cn <reserved-061D> 061E..061F ; AL # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK 0620..063F ; AL # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; AL # Lm ARABIC TATWEEL @@ -1958,4 +1973,36 @@ FEFD..FEFE ; AL # Cn [2] <reserved-FEFD>..<reserved-FEFE> # Total code points: 1 +# ================================================ + +# Bidi_Class=Left_To_Right_Isolate + +2066 ; LRI # Cf LEFT-TO-RIGHT ISOLATE + +# Total code points: 1 + +# ================================================ + +# Bidi_Class=Right_To_Left_Isolate + +2067 ; RLI # Cf RIGHT-TO-LEFT ISOLATE + +# Total code points: 1 + +# ================================================ + +# Bidi_Class=First_Strong_Isolate + +2068 ; FSI # Cf FIRST STRONG ISOLATE + +# Total code points: 1 + +# ================================================ + +# Bidi_Class=Pop_Directional_Isolate + +2069 ; PDI # Cf POP DIRECTIONAL ISOLATE + +# Total code points: 1 + # EOF diff --git a/lib/unicore/extracted/DBinaryProperties.txt b/lib/unicore/extracted/DBinaryProperties.txt index 815904296d..efa356aa68 100644 --- a/lib/unicore/extracted/DBinaryProperties.txt +++ b/lib/unicore/extracted/DBinaryProperties.txt @@ -1,8 +1,8 @@ -# DerivedBinaryProperties-6.2.0.txt -# Date: 2012-05-23, 20:34:43 GMT [MD] +# DerivedBinaryProperties-6.3.0.txt +# Date: 2013-07-05, 14:08:44 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/ @@ -60,7 +60,10 @@ 22D0..22D1 ; Bidi_Mirrored # Sm [2] DOUBLE SUBSET..DOUBLE SUPERSET 22D6..22ED ; Bidi_Mirrored # Sm [24] LESS-THAN WITH DOT..DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL 22F0..22FF ; Bidi_Mirrored # Sm [16] UP RIGHT DIAGONAL ELLIPSIS..Z NOTATION BAG MEMBERSHIP -2308..230B ; Bidi_Mirrored # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; Bidi_Mirrored # Ps LEFT CEILING +2309 ; Bidi_Mirrored # Pe RIGHT CEILING +230A ; Bidi_Mirrored # Ps LEFT FLOOR +230B ; Bidi_Mirrored # Pe RIGHT FLOOR 2320..2321 ; Bidi_Mirrored # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2329 ; Bidi_Mirrored # Ps LEFT-POINTING ANGLE BRACKET 232A ; Bidi_Mirrored # Pe RIGHT-POINTING ANGLE BRACKET diff --git a/lib/unicore/extracted/DCombiningClass.txt b/lib/unicore/extracted/DCombiningClass.txt index 36aed6ae62..bb5804b151 100644 --- a/lib/unicore/extracted/DCombiningClass.txt +++ b/lib/unicore/extracted/DCombiningClass.txt @@ -1,8 +1,8 @@ -# DerivedCombiningClass-6.2.0.txt -# Date: 2012-08-13, 19:56:56 GMT [MD] +# DerivedCombiningClass-6.3.0.txt +# Date: 2013-07-05, 14:08:44 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/ @@ -135,6 +135,7 @@ 060C..060D ; 0 # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR 060E..060F ; 0 # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 061B ; 0 # Po ARABIC SEMICOLON +061C ; 0 # Cf ARABIC LETTER MARK 061E..061F ; 0 # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK 0620..063F ; 0 # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; 0 # Lm ARABIC TATWEEL @@ -543,7 +544,7 @@ 1806 ; 0 # Pd MONGOLIAN TODO SOFT HYPHEN 1807..180A ; 0 # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; 0 # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE -180E ; 0 # Zs MONGOLIAN VOWEL SEPARATOR +180E ; 0 # Cf MONGOLIAN VOWEL SEPARATOR 1810..1819 ; 0 # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; 0 # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; 0 # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -572,7 +573,8 @@ 19DA ; 0 # No NEW TAI LUE THAM DIGIT ONE 19DE..19FF ; 0 # So [34] NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A16 ; 0 # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA -1A19..1A1B ; 0 # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; 0 # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; 0 # Mn BUGINESE VOWEL SIGN AE 1A1E..1A1F ; 0 # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 1A20..1A54 ; 0 # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; 0 # Mc TAI THAM CONSONANT SIGN MEDIAL RA @@ -705,7 +707,7 @@ 2055..205E ; 0 # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS 205F ; 0 # Zs MEDIUM MATHEMATICAL SPACE 2060..2064 ; 0 # Cf [5] WORD JOINER..INVISIBLE PLUS -206A..206F ; 0 # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2066..206F ; 0 # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 2070 ; 0 # No SUPERSCRIPT ZERO 2071 ; 0 # Lm SUPERSCRIPT LATIN SMALL LETTER I 2074..2079 ; 0 # No [6] SUPERSCRIPT FOUR..SUPERSCRIPT NINE @@ -778,7 +780,10 @@ 21D5..21F3 ; 0 # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW 21F4..22FF ; 0 # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP 2300..2307 ; 0 # So [8] DIAMETER SIGN..WAVY LINE -2308..230B ; 0 # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; 0 # Ps LEFT CEILING +2309 ; 0 # Pe RIGHT CEILING +230A ; 0 # Ps LEFT FLOOR +230B ; 0 # Pe RIGHT FLOOR 230C..231F ; 0 # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER 2320..2321 ; 0 # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2322..2328 ; 0 # So [7] FROWN..KEYBOARD @@ -1514,7 +1519,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; 0 # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 866462 code points not listed here. +# The above property value applies to 866457 code points not listed here. # Total code points: 1113459 # ================================================ diff --git a/lib/unicore/extracted/DDecompositionType.txt b/lib/unicore/extracted/DDecompositionType.txt index cb66baf3be..a10099974c 100644 --- a/lib/unicore/extracted/DDecompositionType.txt +++ b/lib/unicore/extracted/DDecompositionType.txt @@ -1,8 +1,8 @@ -# DerivedDecompositionType-6.2.0.txt -# Date: 2012-05-23, 20:34:46 GMT [MD] +# DerivedDecompositionType-6.3.0.txt +# Date: 2012-12-20, 22:18:23 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/ diff --git a/lib/unicore/extracted/DEastAsianWidth.txt b/lib/unicore/extracted/DEastAsianWidth.txt index 5d76aa63e3..c50dbe6d26 100644 --- a/lib/unicore/extracted/DEastAsianWidth.txt +++ b/lib/unicore/extracted/DEastAsianWidth.txt @@ -1,8 +1,8 @@ -# DerivedEastAsianWidth-6.2.0.txt -# Date: 2012-05-20, 00:42:33 GMT [MD] +# DerivedEastAsianWidth-6.3.0.txt +# Date: 2013-07-05, 14:08:45 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/ @@ -139,6 +139,7 @@ 060E..060F ; N # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 0610..061A ; N # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061B ; N # Po ARABIC SEMICOLON +061C ; N # Cf ARABIC LETTER MARK 061E..061F ; N # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK 0620..063F ; N # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; N # Lm ARABIC TATWEEL @@ -583,7 +584,7 @@ 1806 ; N # Pd MONGOLIAN TODO SOFT HYPHEN 1807..180A ; N # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; N # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE -180E ; N # Zs MONGOLIAN VOWEL SEPARATOR +180E ; N # Cf MONGOLIAN VOWEL SEPARATOR 1810..1819 ; N # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; N # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; N # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -615,7 +616,8 @@ 19DE..19FF ; N # So [34] NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A16 ; N # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A17..1A18 ; N # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; N # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; N # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; N # Mn BUGINESE VOWEL SIGN AE 1A1E..1A1F ; N # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 1A20..1A54 ; N # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; N # Mc TAI THAM CONSONANT SIGN MEDIAL RA @@ -762,7 +764,7 @@ 2055..205E ; N # Po [10] FLOWER PUNCTUATION MARK..VERTICAL FOUR DOTS 205F ; N # Zs MEDIUM MATHEMATICAL SPACE 2060..2064 ; N # Cf [5] WORD JOINER..INVISIBLE PLUS -206A..206F ; N # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2066..206F ; N # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 2070 ; N # No SUPERSCRIPT ZERO 2071 ; N # Lm SUPERSCRIPT LATIN SMALL LETTER I 2075..2079 ; N # No [5] SUPERSCRIPT FIVE..SUPERSCRIPT NINE @@ -870,7 +872,10 @@ 22A6..22BE ; N # Sm [25] ASSERTION..RIGHT ANGLE WITH ARC 22C0..22FF ; N # Sm [64] N-ARY LOGICAL AND..Z NOTATION BAG MEMBERSHIP 2300..2307 ; N # So [8] DIAMETER SIGN..WAVY LINE -2308..230B ; N # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; N # Ps LEFT CEILING +2309 ; N # Pe RIGHT CEILING +230A ; N # Ps LEFT FLOOR +230B ; N # Pe RIGHT FLOOR 230C..2311 ; N # So [6] BOTTOM RIGHT CROP..SQUARE LOZENGE 2313..231F ; N # So [13] SEGMENT..BOTTOM RIGHT CORNER 2320..2321 ; N # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL @@ -1466,7 +1471,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 782917 code points not listed here. +# The above property value applies to 782912 code points not listed here. # Total code points: 801894 # ================================================ diff --git a/lib/unicore/extracted/DGeneralCategory.txt b/lib/unicore/extracted/DGeneralCategory.txt index 546a677137..202b5d233f 100644 --- a/lib/unicore/extracted/DGeneralCategory.txt +++ b/lib/unicore/extracted/DGeneralCategory.txt @@ -1,8 +1,8 @@ -# DerivedGeneralCategory-6.2.0.txt -# Date: 2012-05-20, 00:42:34 GMT [MD] +# DerivedGeneralCategory-6.3.0.txt +# Date: 2013-07-05, 14:08:45 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/ @@ -29,7 +29,7 @@ 05EB..05EF ; Cn # [5] <reserved-05EB>..<reserved-05EF> 05F5..05FF ; Cn # [11] <reserved-05F5>..<reserved-05FF> 0605 ; Cn # <reserved-0605> -061C..061D ; Cn # [2] <reserved-061C>..<reserved-061D> +061D ; Cn # <reserved-061D> 070E ; Cn # <reserved-070E> 074B..074C ; Cn # [2] <reserved-074B>..<reserved-074C> 07B2..07BF ; Cn # [14] <reserved-07B2>..<reserved-07BF> @@ -271,7 +271,7 @@ 1FF0..1FF1 ; Cn # [2] <reserved-1FF0>..<reserved-1FF1> 1FF5 ; Cn # <reserved-1FF5> 1FFF ; Cn # <reserved-1FFF> -2065..2069 ; Cn # [5] <reserved-2065>..<reserved-2069> +2065 ; Cn # <reserved-2065> 2072..2073 ; Cn # [2] <reserved-2072>..<reserved-2073> 208F ; Cn # <reserved-208F> 209D..209F ; Cn # [3] <reserved-209D>..<reserved-209F> @@ -554,7 +554,7 @@ E01F0..EFFFF ; Cn # [65040] <reserved-E01F0>..<noncharacter-EFFFF> FFFFE..FFFFF ; Cn # [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 10FFFE..10FFFF; Cn # [2] <noncharacter-10FFFE>..<noncharacter-10FFFF> -# Total code points: 864414 +# Total code points: 864409 # ================================================ @@ -2368,6 +2368,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1932 ; Mn # LIMBU SMALL LETTER ANUSVARA 1939..193B ; Mn # [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; Mn # [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; Mn # BUGINESE VOWEL SIGN AE 1A56 ; Mn # TAI THAM CONSONANT SIGN MEDIAL LA 1A58..1A5E ; Mn # [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA 1A60 ; Mn # TAI THAM SIGN SAKOT @@ -2468,7 +2469,7 @@ FE20..FE26 ; Mn # [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MA 1D242..1D244 ; Mn # [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1280 +# Total code points: 1281 # ================================================ @@ -2551,7 +2552,7 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL 1933..1938 ; Mc # [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA 19B0..19C0 ; Mc # [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY 19C8..19C9 ; Mc # [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2 -1A19..1A1B ; Mc # [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; Mc # [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O 1A55 ; Mc # TAI THAM CONSONANT SIGN MEDIAL RA 1A57 ; Mc # TAI THAM CONSONANT SIGN LA TANG LAI 1A61 ; Mc # TAI THAM VOWEL SIGN A @@ -2612,7 +2613,7 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 1D165..1D166 ; Mc # [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D..1D172 ; Mc # [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 -# Total code points: 353 +# Total code points: 352 # ================================================ @@ -2738,13 +2739,12 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 0020 ; Zs # SPACE 00A0 ; Zs # NO-BREAK SPACE 1680 ; Zs # OGHAM SPACE MARK -180E ; Zs # MONGOLIAN VOWEL SEPARATOR 2000..200A ; Zs # [11] EN QUAD..HAIR SPACE 202F ; Zs # NARROW NO-BREAK SPACE 205F ; Zs # MEDIUM MATHEMATICAL SPACE 3000 ; Zs # IDEOGRAPHIC SPACE -# Total code points: 18 +# Total code points: 17 # ================================================ @@ -2777,12 +2777,14 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 00AD ; Cf # SOFT HYPHEN 0600..0604 ; Cf # [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT +061C ; Cf # ARABIC LETTER MARK 06DD ; Cf # ARABIC END OF AYAH 070F ; Cf # SYRIAC ABBREVIATION MARK +180E ; Cf # MONGOLIAN VOWEL SEPARATOR 200B..200F ; Cf # [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK 202A..202E ; Cf # [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Cf # [5] WORD JOINER..INVISIBLE PLUS -206A..206F ; Cf # [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2066..206F ; Cf # [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES FEFF ; Cf # ZERO WIDTH NO-BREAK SPACE FFF9..FFFB ; Cf # [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR 110BD ; Cf # KAITHI NUMBER SIGN @@ -2790,7 +2792,7 @@ FFF9..FFFB ; Cf # [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION E0001 ; Cf # LANGUAGE TAG E0020..E007F ; Cf # [96] TAG SPACE..CANCEL TAG -# Total code points: 139 +# Total code points: 145 # ================================================ @@ -2848,6 +2850,8 @@ FF0D ; Pd # FULLWIDTH HYPHEN-MINUS 2045 ; Ps # LEFT SQUARE BRACKET WITH QUILL 207D ; Ps # SUPERSCRIPT LEFT PARENTHESIS 208D ; Ps # SUBSCRIPT LEFT PARENTHESIS +2308 ; Ps # LEFT CEILING +230A ; Ps # LEFT FLOOR 2329 ; Ps # LEFT-POINTING ANGLE BRACKET 2768 ; Ps # MEDIUM LEFT PARENTHESIS ORNAMENT 276A ; Ps # MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT @@ -2910,7 +2914,7 @@ FF5B ; Ps # FULLWIDTH LEFT CURLY BRACKET FF5F ; Ps # FULLWIDTH LEFT WHITE PARENTHESIS FF62 ; Ps # HALFWIDTH LEFT CORNER BRACKET -# Total code points: 72 +# Total code points: 74 # ================================================ @@ -2925,6 +2929,8 @@ FF62 ; Ps # HALFWIDTH LEFT CORNER BRACKET 2046 ; Pe # RIGHT SQUARE BRACKET WITH QUILL 207E ; Pe # SUPERSCRIPT RIGHT PARENTHESIS 208E ; Pe # SUBSCRIPT RIGHT PARENTHESIS +2309 ; Pe # RIGHT CEILING +230B ; Pe # RIGHT FLOOR 232A ; Pe # RIGHT-POINTING ANGLE BRACKET 2769 ; Pe # MEDIUM RIGHT PARENTHESIS ORNAMENT 276B ; Pe # MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT @@ -2987,7 +2993,7 @@ FF5D ; Pe # FULLWIDTH RIGHT CURLY BRACKET FF60 ; Pe # FULLWIDTH RIGHT WHITE PARENTHESIS FF63 ; Pe # HALFWIDTH RIGHT CORNER BRACKET -# Total code points: 71 +# Total code points: 73 # ================================================ @@ -3175,7 +3181,6 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 21D2 ; Sm # RIGHTWARDS DOUBLE ARROW 21D4 ; Sm # LEFT RIGHT DOUBLE ARROW 21F4..22FF ; Sm # [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP -2308..230B ; Sm # [4] LEFT CEILING..RIGHT FLOOR 2320..2321 ; Sm # [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 237C ; Sm # RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW 239B..23B3 ; Sm # [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM @@ -3214,7 +3219,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 1D7C3 ; Sm # MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1EEF0..1EEF1 ; Sm # [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 952 +# Total code points: 948 # ================================================ diff --git a/lib/unicore/extracted/DJoinGroup.txt b/lib/unicore/extracted/DJoinGroup.txt index c1efad76c1..9d7ae3bebd 100644 --- a/lib/unicore/extracted/DJoinGroup.txt +++ b/lib/unicore/extracted/DJoinGroup.txt @@ -1,8 +1,8 @@ -# DerivedJoiningGroup-6.2.0.txt -# Date: 2012-05-23, 20:34:47 GMT [MD] +# DerivedJoiningGroup-6.3.0.txt +# Date: 2012-12-20, 22:18:24 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/ diff --git a/lib/unicore/extracted/DJoinType.txt b/lib/unicore/extracted/DJoinType.txt index f8cfd1d41d..5cc2818529 100644 --- a/lib/unicore/extracted/DJoinType.txt +++ b/lib/unicore/extracted/DJoinType.txt @@ -1,8 +1,8 @@ -# DerivedJoiningType-6.2.0.txt -# Date: 2012-05-23, 20:34:48 GMT [MD] +# DerivedJoiningType-6.3.0.txt +# Date: 2013-03-02, 16:07:37 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/ @@ -21,9 +21,10 @@ 0640 ; C # Lm ARABIC TATWEEL 07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU 200D ; C # Cf ZERO WIDTH JOINER -# Total code points: 3 +# Total code points: 4 # ================================================ @@ -65,8 +66,15 @@ 0855 ; D # Lo MANDAIC LETTER AT 08A0 ; D # Lo ARABIC LETTER BEH WITH SMALL V BELOW 08A2..08A9 ; D # Lo [8] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; D # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA -# Total code points: 215 +# Total code points: 389 # ================================================ @@ -111,6 +119,14 @@ # ================================================ +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA + +# Total code points: 1 + +# ================================================ + # Joining_Type=Transparent 00AD ; T # Cf SOFT HYPHEN @@ -123,6 +139,7 @@ 05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C7 ; T # Mn HEBREW POINT QAMATS QATAN 0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK 064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF 06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN @@ -237,6 +254,7 @@ 1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA 1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE 1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA 1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA 1A60 ; T # Mn TAI THAM SIGN SAKOT @@ -351,6 +369,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1423 +# Total code points: 1425 # EOF diff --git a/lib/unicore/extracted/DLineBreak.txt b/lib/unicore/extracted/DLineBreak.txt index fb1fe48f44..1f3c47fc40 100644 --- a/lib/unicore/extracted/DLineBreak.txt +++ b/lib/unicore/extracted/DLineBreak.txt @@ -1,8 +1,8 @@ -# DerivedLineBreak-6.2.0.txt -# Date: 2012-08-13, 19:20:17 GMT [MD] +# DerivedLineBreak-6.3.0.txt +# Date: 2013-07-05, 14:08:46 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/ @@ -23,8 +23,8 @@ E000..F8FF ; XX # Co [6400] <private-use-E000>..<private-use-F8FF> F0000..FFFFD ; XX # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; XX # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 780869 code points not listed here. -# Total code points: 918337 +# The above property value applies to 780843 code points not listed here. +# Total code points: 918311 # ================================================ @@ -245,7 +245,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 0F0C ; GL # Po TIBETAN MARK DELIMITER TSHEG BSTAR 0F12 ; GL # Po TIBETAN MARK RGYA GRAM SHAD 0FD9..0FDA ; GL # Po [2] TIBETAN MARK LEADING MCHAN RTAGS..TIBETAN MARK TRAILING MCHAN RTAGS -180E ; GL # Zs MONGOLIAN VOWEL SEPARATOR +180E ; GL # Cf MONGOLIAN VOWEL SEPARATOR 2007 ; GL # Zs FIGURE SPACE 2011 ; GL # Pd NON-BREAKING HYPHEN 202F ; GL # Zs NARROW NO-BREAK SPACE @@ -348,6 +348,7 @@ FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION 20A0..20A6 ; PR # Sc [7] EURO-CURRENCY SIGN..NAIRA SIGN 20A8..20B5 ; PR # Sc [14] RUPEE SIGN..CEDI SIGN 20B7..20BA ; PR # Sc [4] SPESMILO SIGN..TURKISH LIRA SIGN +20BB..20CF ; PR # Cn [21] <reserved-20BB>..<reserved-20CF> 2116 ; PR # So NUMERO SIGN 2212..2213 ; PR # Sm [2] MINUS SIGN..MINUS-OR-PLUS SIGN FE69 ; PR # Sc SMALL DOLLAR SIGN @@ -355,7 +356,7 @@ FF04 ; PR # Sc FULLWIDTH DOLLAR SIGN FFE1 ; PR # Sc FULLWIDTH POUND SIGN FFE5..FFE6 ; PR # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN -# Total code points: 46 +# Total code points: 67 # ================================================ @@ -871,7 +872,10 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 22A6..22BE ; AL # Sm [25] ASSERTION..RIGHT ANGLE WITH ARC 22C0..22FF ; AL # Sm [64] N-ARY LOGICAL AND..Z NOTATION BAG MEMBERSHIP 2300..2307 ; AL # So [8] DIAMETER SIGN..WAVY LINE -2308..230B ; AL # Sm [4] LEFT CEILING..RIGHT FLOOR +2308 ; AL # Ps LEFT CEILING +2309 ; AL # Pe RIGHT CEILING +230A ; AL # Ps LEFT FLOOR +230B ; AL # Pe RIGHT FLOOR 230C..2311 ; AL # So [6] BOTTOM RIGHT CROP..SQUARE LOZENGE 2313..2319 ; AL # So [7] SEGMENT..TURNED NOT SIGN 231C..231F ; AL # So [4] TOP LEFT CORNER..BOTTOM RIGHT CORNER @@ -1269,7 +1273,6 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 2E9B..2EF3 ; ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE 2FF0..2FFB ; ID # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID -3000 ; ID # Zs IDEOGRAPHIC SPACE 3003 ; ID # Po DITTO MARK 3004 ; ID # So JAPANESE INDUSTRIAL STANDARD SYMBOL 3006 ; ID # Lo IDEOGRAPHIC CLOSING MARK @@ -1278,7 +1281,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 3020 ; ID # So POSTAL MARK FACE 3021..3029 ; ID # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE 3030 ; ID # Pd WAVY DASH -3031..3035 ; ID # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF +3031..3034 ; ID # Lm [4] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT WITH VOICED SOUND MARK UPPER HALF 3036..3037 ; ID # So [2] CIRCLED POSTAL MARK..IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL 3038..303A ; ID # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 303D ; ID # Po PART ALTERNATION MARK @@ -1414,7 +1417,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 2FA1E..2FFFD ; ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD ; ID # Cn [65534] <reserved-30000>..<reserved-3FFFD> -# Total code points: 162700 +# Total code points: 162698 # ================================================ @@ -1452,6 +1455,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 05C4..05C5 ; CM # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C7 ; CM # Mn HEBREW POINT QAMATS QATAN 0610..061A ; CM # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; CM # Cf ARABIC LETTER MARK 064B..065F ; CM # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW 0670 ; CM # Mn ARABIC LETTER SUPERSCRIPT ALEF 06D6..06DC ; CM # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN @@ -1591,7 +1595,8 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1933..1938 ; CM # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA 1939..193B ; CM # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; CM # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U -1A19..1A1B ; CM # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A19..1A1A ; CM # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; CM # Mn BUGINESE VOWEL SIGN AE 1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH @@ -1636,7 +1641,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1DFC..1DFF ; CM # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200F ; CM # Cf [4] ZERO WIDTH NON-JOINER..RIGHT-TO-LEFT MARK 202A..202E ; CM # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE -206A..206F ; CM # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2066..206F ; CM # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 20D0..20DC ; CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; CM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; CM # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1647,6 +1652,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 2DE0..2DFF ; CM # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS 302A..302D ; CM # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK 302E..302F ; CM # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK +3035 ; CM # Lm VERTICAL KANA REPEAT MARK LOWER HALF 3099..309A ; CM # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK A66F ; CM # Mn COMBINING CYRILLIC VZMET A670..A672 ; CM # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN @@ -1744,7 +1750,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1628 +# Total code points: 1634 # ================================================ @@ -1815,6 +1821,7 @@ A874..A875 ; BB # Po [2] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA DOUBLE HEAD MA 2E2A..2E2D ; BA # Po [4] TWO DOTS OVER ONE DOT PUNCTUATION..FIVE DOT MARK 2E30..2E31 ; BA # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT 2E33..2E34 ; BA # Po [2] RAISED DOT..RAISED COMMA +3000 ; BA # Zs IDEOGRAPHIC SPACE A4FE..A4FF ; BA # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D ; BA # Po VAI COMMA A60F ; BA # Po VAI QUESTION MARK @@ -1839,7 +1846,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 111C8 ; BA # Po SHARADA SEPARATOR 12470..12473 ; BA # Po [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON -# Total code points: 151 +# Total code points: 152 # ================================================ diff --git a/lib/unicore/extracted/DNumType.txt b/lib/unicore/extracted/DNumType.txt index 23d2186a99..2833d054c6 100644 --- a/lib/unicore/extracted/DNumType.txt +++ b/lib/unicore/extracted/DNumType.txt @@ -1,8 +1,8 @@ -# DerivedNumericType-6.2.0.txt -# Date: 2012-08-13, 19:20:20 GMT [MD] +# DerivedNumericType-6.3.0.txt +# Date: 2012-12-20, 22:18:26 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/ diff --git a/lib/unicore/extracted/DNumValues.txt b/lib/unicore/extracted/DNumValues.txt index 517bede77b..488f632952 100644 --- a/lib/unicore/extracted/DNumValues.txt +++ b/lib/unicore/extracted/DNumValues.txt @@ -1,8 +1,8 @@ -# DerivedNumericValues-6.2.0.txt -# Date: 2012-08-13, 19:20:22 GMT [MD] +# DerivedNumericValues-6.3.0.txt +# Date: 2012-12-20, 22:18:26 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/ @@ -33,12 +33,6 @@ # ================================================ -12456..12457 ; -1.0 ; ; -1 # Nl [2] CUNEIFORM NUMERIC SIGN NIGIDAMIN..CUNEIFORM NUMERIC SIGN NIGIDAESH - -# Total code points: 2 - -# ================================================ - 0F33 ; -0.5 ; ; -1/2 # No TIBETAN DIGIT HALF ZERO # Total code points: 1 @@ -461,6 +455,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 12435 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO BURU 1244A ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO ASH TENU 12450 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO BAN2 +12456 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN NIGIDAMIN 12459 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO ESHE3 1D361 ; 2.0 ; ; 2 # No COUNTING ROD UNIT DIGIT TWO 1D7D0 ; 2.0 ; ; 2 # Nd MATHEMATICAL BOLD DIGIT TWO @@ -471,7 +466,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1F103 ; 2.0 ; ; 2 # No DIGIT TWO COMMA 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 100 +# Total code points: 101 # ================================================ @@ -565,6 +560,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 1243A..1243B ; 3.0 ; ; 3 # Nl [2] CUNEIFORM NUMERIC SIGN THREE VARIANT FORM ESH16..CUNEIFORM NUMERIC SIGN THREE VARIANT FORM ESH21 1244B ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE ASH TENU 12451 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE BAN2 +12457 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN NIGIDAESH 1D362 ; 3.0 ; ; 3 # No COUNTING ROD UNIT DIGIT THREE 1D7D1 ; 3.0 ; ; 3 # Nd MATHEMATICAL BOLD DIGIT THREE 1D7DB ; 3.0 ; ; 3 # Nd MATHEMATICAL DOUBLE-STRUCK DIGIT THREE @@ -577,7 +573,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 102 +# Total code points: 103 # ================================================ diff --git a/lib/unicore/mktables b/lib/unicore/mktables index c2fd22f7e3..9fd86e6d97 100644 --- a/lib/unicore/mktables +++ b/lib/unicore/mktables @@ -805,9 +805,9 @@ my $v_version = pack "C*", split /\./, $string_version; # v string # are known to not match any code points in some versions of Unicode, but that # may change in the future so they should be matchable, hence an empty file is # generated for them. -my @tables_that_may_be_empty = ( - 'Joining_Type=Left_Joining', - ); +my @tables_that_may_be_empty; +push @tables_that_may_be_empty, 'Joining_Type=Left_Joining' + if $v_version lt v6.3.0; push @tables_that_may_be_empty, 'Script=Common' if $v_version le v4.0.1; push @tables_that_may_be_empty, 'Title' if $v_version lt v2.0.0; push @tables_that_may_be_empty, 'Script=Katakana_Or_Hiragana' @@ -17701,6 +17701,13 @@ my @input_file_objects = ( Has_Missings_Defaults => $NOT_IGNORED, Skip => "Provisional; for the analysis and processing of Indic scripts", ), + Input_file->new('BidiBrackets.txt', v6.3.0, + Properties => [ 'Bidi_Paired_Bracket', 'Bidi_Paired_Bracket_Type' ], + Has_Missings_Defaults => $NO_DEFAULTS, + ), + Input_file->new("BidiCharacterTest.txt", v6.3.0, + Skip => 'Validation Tests', + ), ); # End of all the preliminaries. diff --git a/pod/perldelta.pod b/pod/perldelta.pod index afc74275a4..38577010a2 100644 --- a/pod/perldelta.pod +++ b/pod/perldelta.pod @@ -27,6 +27,13 @@ here, but most should go in the L</Performance Enhancements> section. [ List each enhancement as a =head2 entry ] +=head2 Unicode 6.3 now supported + +Perl now supports and is shipped with Unicode 6.3 (though Perl may be +recompiled with any previous Unicode release as well). A detailed +list of Unicode 6.3 changes is at +L<http://www.unicode.org/versions/Unicode6.3.0/>. + =head1 Security XXX Any security-related notices go here. In particular, any security diff --git a/pod/perlrecharclass.pod b/pod/perlrecharclass.pod index 611d6c6098..0a168a073b 100644 --- a/pod/perlrecharclass.pod +++ b/pod/perlrecharclass.pod @@ -285,7 +285,7 @@ starting in Perl v5.18, but prior to that, the sole difference was that the vertical tab (C<"\cK">) was not matched by C<\s>. The following table is a complete listing of characters matched by -C<\s>, C<\h> and C<\v> as of Unicode 6.0. +C<\s>, C<\h> and C<\v> as of Unicode 6.3. The first column gives the Unicode code point of the character (in hex format), the second column gives the (Unicode) name. The third column indicates @@ -301,7 +301,6 @@ effect that changes the C<\s> matching). 0x0085 NEXT LINE (NEL) vs [2] 0x00a0 NO-BREAK SPACE h s [2] 0x1680 OGHAM SPACE MARK h s - 0x180e MONGOLIAN VOWEL SEPARATOR h s 0x2000 EN QUAD h s 0x2001 EM QUAD h s 0x2002 EN SPACE h s diff --git a/regcharclass.h b/regcharclass.h index 58262073a1..8b175fd1b8 100644 --- a/regcharclass.h +++ b/regcharclass.h @@ -115,9 +115,7 @@ ( ( 0xC2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 ) \ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( 0x80 <= NATIVE_TO_LATIN1(((U8*)s)[2]) && NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -133,9 +131,7 @@ ( ( 0xC2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 ) \ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( 0x80 <= NATIVE_TO_LATIN1(((U8*)s)[2]) && NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -160,9 +156,7 @@ : ( 0xC2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 ) \ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -176,9 +170,7 @@ : ( 0xC2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 ) \ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( 0x80 <= NATIVE_TO_LATIN1(((U8*)s)[2]) && NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -204,9 +196,7 @@ /*** GENERATED CODE ***/ #define is_HORIZWS_high(s) \ ( ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -217,9 +207,7 @@ #define is_HORIZWS_high_safe(s,e) \ ( ((e)-(s) > 2) ? \ ( ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( 0x80 <= NATIVE_TO_LATIN1(((U8*)s)[2]) && NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -233,18 +221,16 @@ ( 0x20 == NATIVE_TO_UNI(cp) || ( 0x20 < NATIVE_TO_UNI(cp) && \ ( 0xA0 == NATIVE_TO_UNI(cp) || ( 0xA0 < NATIVE_TO_UNI(cp) && \ ( 0x1680 == NATIVE_TO_UNI(cp) || ( 0x1680 < NATIVE_TO_UNI(cp) && \ -( 0x180E == NATIVE_TO_UNI(cp) || ( 0x180E < NATIVE_TO_UNI(cp) && \ ( ( 0x2000 <= NATIVE_TO_UNI(cp) && NATIVE_TO_UNI(cp) <= 0x200A ) || ( 0x200A < NATIVE_TO_UNI(cp) &&\ ( 0x202F == NATIVE_TO_UNI(cp) || ( 0x202F < NATIVE_TO_UNI(cp) && \ -( 0x205F == NATIVE_TO_UNI(cp) || 0x3000 == NATIVE_TO_UNI(cp) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) +( 0x205F == NATIVE_TO_UNI(cp) || 0x3000 == NATIVE_TO_UNI(cp) ) ) ) ) ) ) ) ) ) ) ) ) ) /*** GENERATED CODE ***/ #define is_HORIZWS_cp_high(cp) \ ( 0x1680 == NATIVE_TO_UNI(cp) || ( 0x1680 < NATIVE_TO_UNI(cp) && \ -( 0x180E == NATIVE_TO_UNI(cp) || ( 0x180E < NATIVE_TO_UNI(cp) && \ ( ( 0x2000 <= NATIVE_TO_UNI(cp) && NATIVE_TO_UNI(cp) <= 0x200A ) || ( 0x200A < NATIVE_TO_UNI(cp) &&\ ( 0x202F == NATIVE_TO_UNI(cp) || ( 0x202F < NATIVE_TO_UNI(cp) && \ -( 0x205F == NATIVE_TO_UNI(cp) || 0x3000 == NATIVE_TO_UNI(cp) ) ) ) ) ) ) ) ) ) +( 0x205F == NATIVE_TO_UNI(cp) || 0x3000 == NATIVE_TO_UNI(cp) ) ) ) ) ) ) ) /* VERTWS: Vertical Whitespace: \v \V @@ -369,9 +355,7 @@ ( ( 0xC2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x85 == NATIVE_TO_LATIN1(((U8*)s)[1]) || 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 )\ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( 0x80 <= NATIVE_TO_LATIN1(((U8*)s)[2]) && NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || ( NATIVE_TO_LATIN1(((U8*)s)[2]) & 0xFE ) == 0xA8 || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -385,9 +369,7 @@ : ( 0xC2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x85 == NATIVE_TO_LATIN1(((U8*)s)[1]) || 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 )\ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || ( NATIVE_TO_LATIN1(((U8*)s)[2]) & 0xFE ) == 0xA8 || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -397,9 +379,7 @@ /*** GENERATED CODE ***/ #define is_XPERLSPACE_high(s) \ ( ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ - ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ - ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 ) \ - : ( ( 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x8E == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ + ( ( ( 0x9A == NATIVE_TO_LATIN1(((U8*)s)[1]) ) && ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ) ? 3 : 0 )\ : ( 0xE2 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x80 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( ( NATIVE_TO_LATIN1(((U8*)s)[2]) <= 0x8A ) || ( NATIVE_TO_LATIN1(((U8*)s)[2]) & 0xFE ) == 0xA8 || 0xAF == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ @@ -409,12 +389,11 @@ /*** GENERATED CODE ***/ #define is_XPERLSPACE_cp_high(cp) \ ( 0x1680 == NATIVE_TO_UNI(cp) || ( 0x1680 < NATIVE_TO_UNI(cp) && \ -( 0x180E == NATIVE_TO_UNI(cp) || ( 0x180E < NATIVE_TO_UNI(cp) && \ ( ( 0x2000 <= NATIVE_TO_UNI(cp) && NATIVE_TO_UNI(cp) <= 0x200A ) || ( 0x200A < NATIVE_TO_UNI(cp) &&\ ( 0x2028 == NATIVE_TO_UNI(cp) || ( 0x2028 < NATIVE_TO_UNI(cp) && \ ( 0x2029 == NATIVE_TO_UNI(cp) || ( 0x2029 < NATIVE_TO_UNI(cp) && \ ( 0x202F == NATIVE_TO_UNI(cp) || ( 0x202F < NATIVE_TO_UNI(cp) && \ -( 0x205F == NATIVE_TO_UNI(cp) || 0x3000 == NATIVE_TO_UNI(cp) ) ) ) ) ) ) ) ) ) ) ) ) ) +( 0x205F == NATIVE_TO_UNI(cp) || 0x3000 == NATIVE_TO_UNI(cp) ) ) ) ) ) ) ) ) ) ) ) /* REPLACEMENT: Unicode REPLACEMENT CHARACTER @@ -575,6 +554,8 @@ #define is_QUOTEMETA_high(s) \ ( ( 0xCD == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x8F == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 ) \ +: ( 0xD8 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ + ( ( 0x9C == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? 2 : 0 ) \ : ( 0xE1 == NATIVE_TO_LATIN1(((U8*)s)[0]) ) ? \ ( ( 0x85 == NATIVE_TO_LATIN1(((U8*)s)[1]) ) ? \ ( ( 0x9F == NATIVE_TO_LATIN1(((U8*)s)[2]) || 0xA0 == NATIVE_TO_LATIN1(((U8*)s)[2]) ) ? 3 : 0 )\ diff --git a/t/op/split_unicode.t b/t/op/split_unicode.t index 887adcc11f..bb50620e0e 100644 --- a/t/op/split_unicode.t +++ b/t/op/split_unicode.t @@ -3,7 +3,7 @@ BEGIN { require './test.pl'; skip_all_if_miniperl("no dynamic loading on miniperl, no File::Spec (used by charnames)"); - plan(tests => 151); + plan(tests => 145); } { @@ -28,7 +28,6 @@ BEGIN { ord("\N{NO-BREAK SPACE}"), # Zs NO-BREAK SPACE 0x1680, # Zs OGHAM SPACE MARK - 0x180E, # Zs MONGOLIAN VOWEL SEPARATOR 0x2000..0x200A, # Zs [11] EN QUAD..HAIR SPACE 0x2028, # Zl LINE SEPARATOR 0x2029, # Zp PARAGRAPH SEPARATOR diff --git a/t/re/pat_advanced.t b/t/re/pat_advanced.t index 6d9ca2fdeb..d7ef8e93db 100644 --- a/t/re/pat_advanced.t +++ b/t/re/pat_advanced.t @@ -636,14 +636,14 @@ sub run_tests { ok "<\x{100}\x{00A0}>" =~ /<\x{100}\s>/, '\x{00A0} in \s'; ok "<\x{00A0}>" =~ /<\h>/, '\x{00A0} in \h'; } - my @h = map {sprintf "%05x" => $_} 0x01680, 0x0180E, 0x02000 .. 0x0200A, + my @h = map {sprintf "%05x" => $_} 0x01680, 0x02000 .. 0x0200A, 0x0202F, 0x0205F, 0x03000; my @v = map {sprintf "%05x" => $_} 0x02028, 0x02029; my @H = map {sprintf "%05x" => $_} 0x01361, 0x0200B, 0x02408, 0x02420, - 0x0303F, 0xE0020; + 0x0303F, 0xE0020, 0x180E; my @V = map {sprintf "%05x" => $_} 0x0008A .. 0x0008D, 0x00348, 0x10100, - 0xE005F, 0xE007C; + 0xE005F, 0xE007C, 0x180E; for my $hex (@h) { my $str = eval qq ["<\\x{$hex}>"]; @@ -1613,7 +1613,7 @@ sub run_tests { { # Various whitespace special patterns - my @h = map {chr $_} 0x09, 0x20, 0xa0, 0x1680, 0x180e, 0x2000, + my @h = map {chr $_} 0x09, 0x20, 0xa0, 0x1680, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, 0x2006, 0x2007, 0x2008, 0x2009, 0x200a, 0x202f, 0x205f, 0x3000; |