AuroraMiddleware/qt5base-lts
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update most Unicode data to version 10.0

Browse Source 
The text segmentation data is not being updated in this change,
as it requires additional code changes. Updating those will
come in a follow-up commit.

Change-Id: I5d6b6bc96044e8dd0c25cf6f79756e7f68bf6e7c
Reviewed-by: Konstantin Ritt <ritt.ks@gmail.com>
Reviewed-by: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@qt.io>
This commit is contained in:
Lars Knoll 2017-12-12 09:47:53 +01:00
parent 2b2b9c9962
commit 8bfabb34de
16 changed files with 8905 additions and 5375 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/corelib/tools/qchar.h
View File

@ -296,6 +296,20 @@ public:
Script_OldHungarian,
Script_SignWriting,
// Unicode 9.0 additions
Script_Adlam,
Script_Bhaiksuki,
Script_Marchen,
Script_Newa,
Script_Osage,
Script_Tangut,
// Unicode 10.0 additions
Script_MasaramGondi,
Script_Nushu,
Script_Soyombo,
Script_ZanabazarSquare,
ScriptCount
};
@ -387,7 +401,9 @@ public:
Unicode_6_2,
Unicode_6_3,
Unicode_7_0,
Unicode_8_0
Unicode_8_0,
Unicode_9_0,
Unicode_10_0
};
// ****** WHEN ADDING FUNCTIONS, CONSIDER ADDING TO QCharRef TOO

11008
src/corelib/tools/qunicodetables.cpp
View File

File diff suppressed because it is too large Load Diff

4
src/corelib/tools/qunicodetables_p.h
View File

@ -37,7 +37,7 @@
**
****************************************************************************/
/* This file is autogenerated from the Unicode 8.0 database. Do not edit */
/* This file is autogenerated from the Unicode 10.0 database. Do not edit */
//
// W A R N I N G
@ -59,7 +59,7 @@
QT_BEGIN_NAMESPACE
#define UNICODE_DATA_VERSION QChar::Unicode_8_0
#define UNICODE_DATA_VERSION QChar::Unicode_10_0
namespace QUnicodeTables {

16
src/gui/text/qharfbuzzng.cpp
View File

@ -202,7 +202,21 @@ static const hb_script_t _qtscript_to_hbscript[] = {
HB_SCRIPT_HATRAN,
HB_SCRIPT_MULTANI,
HB_SCRIPT_OLD_HUNGARIAN,
HB_SCRIPT_SIGNWRITING
HB_SCRIPT_SIGNWRITING,
// Unicode 9.0 additions
HB_SCRIPT_ADLAM,
HB_SCRIPT_BHAIKSUKI,
HB_SCRIPT_MARCHEN,
HB_SCRIPT_NEWA,
HB_SCRIPT_OSAGE,
HB_SCRIPT_TANGUT,
// Unicode 10.0 additions
HB_SCRIPT_MASARAM_GONDI,
HB_SCRIPT_NUSHU,
HB_SCRIPT_SOYOMBO,
HB_SCRIPT_ZANABAZAR_SQUARE
};
Q_STATIC_ASSERT(QChar::ScriptCount == sizeof(_qtscript_to_hbscript) / sizeof(_qtscript_to_hbscript[0]));

12
src/platformsupport/fontdatabases/fontconfig/qfontconfigdatabase.cpp
View File

@ -250,7 +250,17 @@ static const char specialLanguages[][6] = {
"", // Hatran
"", // Multani
"", // OldHungarian
"" // SignWriting
"", // SignWriting
"", // Adlam
"", // Bhaiksuki
"", // Marchen
"", // Newa
"", // Osage
"", // Tangut
"", // MasaramGondi
"", // Nushu
"", // Soyombo
"" // ZanabazarSquare
};
Q_STATIC_ASSERT(sizeof specialLanguages / sizeof *specialLanguages == QChar::ScriptCount);

125
util/unicode/data/ArabicShaping.txt
View File

@ -1,23 +1,23 @@
# ArabicShaping-8.0.0.txt
# Date: 2015-02-17, 23:33:00 GMT [RP]
# ArabicShaping-10.0.0.txt
# Date: 2017-02-16, 00:00:00 GMT [RP, KW]
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2014 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This file defines the Joining_Type and Joining_Group property
# values for Arabic, Syriac, N'Ko, Mandaic, and Manichaean positional
# shaping, repeating in machine readable form the information
# exemplified in Tables 9-3, 9-8, 9-9, 9-10, 9-14, 9-15, 9-16, 9-19,
# 9-20, 10-4, 10-5, 10-6, 10-7, and 19-5 of The Unicode Standard core
# specification. This file also defines Joining_Type values for
# Mongolian, Phags-pa, and Psalter Pahlavi positional shaping, which
# are not listed in tables in the standard.
# Mongolian, Phags-pa, Psalter Pahlavi, and Adlam positional shaping,
# which are not listed in tables in the standard.
#
# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 19.4 of
# The Unicode Standard core specification for more information.
# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 19.4, and 19.9
# of The Unicode Standard core specification for more information.
#
# Each line contains four fields, separated by a semicolon.
#
@ -50,8 +50,8 @@
# Field 3: defines the joining group (property name: Joining_Group)
#
# The values of the joining group are based schematically on character
# names. Where a schematic character name consists of two or more parts separated
# by spaces, the formal Joining_Group property value, as specified in
# names. Where a schematic character name consists of two or more parts
# separated by spaces, the formal Joining_Group property value, as specified in
# PropertyValueAliases.txt, consists of the same name parts joined by
# underscores. Hence, the entry:
#
@ -86,11 +86,11 @@
# Note: Code points that are not explicitly listed in this file are
# either of joining type T or U:
#
# - Those that not explicitly listed that are of General Category Mn, Me, or Cf
# - Those that are not explicitly listed and that are of General Category Mn, Me, or Cf
# have joining type T.
# - All others not explicitly listed have joining type U.
#
# For an explicit listing of characters of joining type T, see
# For an explicit listing of all characters of joining type T, see
# the derived property file DerivedJoiningType.txt.
#
# #############################################################
@ -413,6 +413,20 @@
0857; MANDAIC KAD; U; No_Joining_Group
0858; MANDAIC AIN; U; No_Joining_Group
# Syriac Supplement Characters
0860; MALAYALAM NGA; D; MALAYALAM NGA
0861; MALAYALAM JA; U; MALAYALAM JA
0862; MALAYALAM NYA; D; MALAYALAM NYA
0863; MALAYALAM TTA; D; MALAYALAM TTA
0864; MALAYALAM NNA; D; MALAYALAM NNA
0865; MALAYALAM NNNA; D; MALAYALAM NNNA
0866; MALAYALAM BHA; U; MALAYALAM BHA
0867; MALAYALAM RA; R; MALAYALAM RA
0868; MALAYALAM LLA; D; MALAYALAM LLA
0869; MALAYALAM LLLA; R; MALAYALAM LLLA
086A; MALAYALAM SSA; R; MALAYALAM SSA
# Arabic Extended-A Characters
08A0; DOTLESS BEH WITH V BELOW; D; BEH
@ -436,6 +450,15 @@
08B2; REH WITH DOT AND INVERTED V ABOVE; R; REH
08B3; AIN WITH 3 DOTS BELOW; D; AIN
08B4; KAF WITH DOT BELOW; D; KAF
08B6; BEH WITH MEEM ABOVE; D; BEH
08B7; DOTLESS BEH WITH 3 DOTS BELOW AND MEEM ABOVE; D; BEH
08B8; DOTLESS BEH WITH TEH ABOVE; D; BEH
08B9; REH WITH NOON ABOVE; R; REH
08BA; YEH WITH NOON ABOVE; D; YEH
08BB; AFRICAN FEH; D; AFRICAN FEH
08BC; AFRICAN QAF; D; AFRICAN QAF
08BD; AFRICAN NOON; D; AFRICAN NOON
08E2; ARABIC DISPUTED END OF AYAH; U; No_Joining_Group
# Mongolian Characters
@ -536,8 +559,8 @@
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
1885; MONGOLIAN ALI GALI BALUDA; T; No_Joining_Group
1886; MONGOLIAN ALI GALI THREE BALUDA; T; 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
@ -578,6 +601,7 @@
200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
200D; ZERO WIDTH JOINER; C; No_Joining_Group
202F; NARROW NO-BREAK SPACE; U; 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
@ -711,4 +735,75 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group
10BAE; PSALTER PAHLAVI TWENTY; D; No_Joining_Group
10BAF; PSALTER PAHLAVI HUNDRED; U; No_Joining_Group
# Adlam Characters
1E900;ADLAM CAPITAL ALIF; D; No_Joining_Group
1E901;ADLAM CAPITAL DAALI; D; No_Joining_Group
1E902;ADLAM CAPITAL LAAM; D; No_Joining_Group
1E903;ADLAM CAPITAL MIIM; D; No_Joining_Group
1E904;ADLAM CAPITAL BA; D; No_Joining_Group
1E905;ADLAM CAPITAL SINNYIIYHE; D; No_Joining_Group
1E906;ADLAM CAPITAL PE; D; No_Joining_Group
1E907;ADLAM CAPITAL BHE; D; No_Joining_Group
1E908;ADLAM CAPITAL RA; D; No_Joining_Group
1E909;ADLAM CAPITAL E; D; No_Joining_Group
1E90A;ADLAM CAPITAL FA; D; No_Joining_Group
1E90B;ADLAM CAPITAL I; D; No_Joining_Group
1E90C;ADLAM CAPITAL O; D; No_Joining_Group
1E90D;ADLAM CAPITAL DHA; D; No_Joining_Group
1E90E;ADLAM CAPITAL YHE; D; No_Joining_Group
1E90F;ADLAM CAPITAL WAW; D; No_Joining_Group
1E910;ADLAM CAPITAL NUN; D; No_Joining_Group
1E911;ADLAM CAPITAL KAF; D; No_Joining_Group
1E912;ADLAM CAPITAL YA; D; No_Joining_Group
1E913;ADLAM CAPITAL U; D; No_Joining_Group
1E914;ADLAM CAPITAL JIIM; D; No_Joining_Group
1E915;ADLAM CAPITAL CHI; D; No_Joining_Group
1E916;ADLAM CAPITAL HA; D; No_Joining_Group
1E917;ADLAM CAPITAL QAAF; D; No_Joining_Group
1E918;ADLAM CAPITAL GA; D; No_Joining_Group
1E919;ADLAM CAPITAL NYA; D; No_Joining_Group
1E91A;ADLAM CAPITAL TU; D; No_Joining_Group
1E91B;ADLAM CAPITAL NHA; D; No_Joining_Group
1E91C;ADLAM CAPITAL VA; D; No_Joining_Group
1E91D;ADLAM CAPITAL KHA; D; No_Joining_Group
1E91E;ADLAM CAPITAL GBE; D; No_Joining_Group
1E91F;ADLAM CAPITAL ZAL; D; No_Joining_Group
1E920;ADLAM CAPITAL KPO; D; No_Joining_Group
1E921;ADLAM CAPITAL SHA; D; No_Joining_Group
1E922;ADLAM SMALL ALIF; D; No_Joining_Group
1E923;ADLAM SMALL DAALI; D; No_Joining_Group
1E924;ADLAM SMALL LAAM; D; No_Joining_Group
1E925;ADLAM SMALL MIIM; D; No_Joining_Group
1E926;ADLAM SMALL BA; D; No_Joining_Group
1E927;ADLAM SMALL SINNYIIYHE; D; No_Joining_Group
1E928;ADLAM SMALL PE; D; No_Joining_Group
1E929;ADLAM SMALL BHE; D; No_Joining_Group
1E92A;ADLAM SMALL RA; D; No_Joining_Group
1E92B;ADLAM SMALL E; D; No_Joining_Group
1E92C;ADLAM SMALL FA; D; No_Joining_Group
1E92D;ADLAM SMALL I; D; No_Joining_Group
1E92E;ADLAM SMALL O; D; No_Joining_Group
1E92F;ADLAM SMALL DHA; D; No_Joining_Group
1E930;ADLAM SMALL YHE; D; No_Joining_Group
1E931;ADLAM SMALL WAW; D; No_Joining_Group
1E932;ADLAM SMALL NUN; D; No_Joining_Group
1E933;ADLAM SMALL KAF; D; No_Joining_Group
1E934;ADLAM SMALL YA; D; No_Joining_Group
1E935;ADLAM SMALL U; D; No_Joining_Group
1E936;ADLAM SMALL JIIM; D; No_Joining_Group
1E937;ADLAM SMALL CHI; D; No_Joining_Group
1E938;ADLAM SMALL HA; D; No_Joining_Group
1E939;ADLAM SMALL QAAF; D; No_Joining_Group
1E93A;ADLAM SMALL GA; D; No_Joining_Group
1E93B;ADLAM SMALL NYA; D; No_Joining_Group
1E93C;ADLAM SMALL TU; D; No_Joining_Group
1E93D;ADLAM SMALL NHA; D; No_Joining_Group
1E93E;ADLAM SMALL VA; D; No_Joining_Group
1E93F;ADLAM SMALL KHA; D; No_Joining_Group
1E940;ADLAM SMALL GBE; D; No_Joining_Group
1E941;ADLAM SMALL ZAL; D; No_Joining_Group
1E942;ADLAM SMALL KPO; D; No_Joining_Group
1E943;ADLAM SMALL SHA; D; No_Joining_Group
# EOF

30
util/unicode/data/BidiMirroring.txt
View File

@ -1,32 +1,34 @@
# BidiMirroring-8.0.0.txt
# Date: 2015-01-20, 18:30:00 GMT [KW, LI]
# BidiMirroring-10.0.0.txt
# Date: 2017-04-12, 17:30:00 GMT [KW, LI]
# © 2017 Unicode®, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Bidi_Mirroring_Glyph Property
#
#
# This file is an informative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2015 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 8.0.0.
#
# The repertoire covered by the file is Unicode 10.0.0.
#
# The file contains a list of lines with mappings from one code point
# to another one for character-based mirroring.
# Note that for "real" mirroring, a rendering engine needs to select
# appropriate alternative glyphs, and that many Unicode characters do not
# have a mirror-image Unicode character.
#
#
# Each mapping line contains two fields, separated by a semicolon (';').
# Each of the two fields contains a code point represented as a
# variable-length hexadecimal value with 4 to 6 digits.
# A comment indicates where the characters are "BEST FIT" mirroring.
#
# Code points for which Bidi_Mirrored=Yes, but for which no appropriate
#
# Code points for which Bidi_Mirrored=Yes, but for which no appropriate
# characters exist with mirrored glyphs, are
# listed as comments at the end of the file.
#
@ -36,14 +38,14 @@
# point has the default value for the Bidi_Mirroring_Glyph property,
# that means that no other character exists whose glyph is suitable
# for character-based mirroring.
#
#
# For information on bidi mirroring, see UAX #9: Unicode Bidirectional Algorithm,
# at http://www.unicode.org/unicode/reports/tr9/
#
#
# 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 subsequent versions by Ken Whistler and Laurentiu Iancu.
#
#
# ############################################################
#
# Property: Bidi_Mirroring_Glyph

30
util/unicode/data/Blocks.txt
View File

@ -1,9 +1,9 @@
# Blocks-8.0.0.txt
# Date: 2014-11-10, 23:04:00 GMT [KW]
# Blocks-10.0.0.txt
# Date: 2017-04-12, 17:30:00 GMT [KW]
# © 2017 Unicode®, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Format:
@ -14,12 +14,12 @@
# Note: When comparing block names, casing, whitespace, hyphens,
# and underbars are ignored.
# For example, "Latin Extended-A" and "latin extended a" are equivalent.
# For more information on the comparison of property values,
# For more information on the comparison of property values,
# see UAX #44: http://www.unicode.org/reports/tr44/
#
# All block ranges start with a value where (cp MOD 16) = 0,
# and end with a value where (cp MOD 16) = 15. In other words,
# the last hexadecimal digit of the start of range is ...0
# the last hexadecimal digit of the start of range is ...0
# and the last hexadecimal digit of the end of range is ...F.
# This constraint on block ranges guarantees that allocations
# are done in terms of whole columns, and that code chart display
@ -51,6 +51,7 @@
07C0..07FF; NKo
0800..083F; Samaritan
0840..085F; Mandaic
0860..086F; Syriac Supplement
08A0..08FF; Arabic Extended-A
0900..097F; Devanagari
0980..09FF; Bengali
@ -93,6 +94,7 @@
1BC0..1BFF; Batak
1C00..1C4F; Lepcha
1C50..1C7F; Ol Chiki
1C80..1C8F; Cyrillic Extended-C
1CC0..1CCF; Sundanese Supplement
1CD0..1CFF; Vedic Extensions
1D00..1D7F; Phonetic Extensions
@ -209,6 +211,7 @@ FFF0..FFFF; Specials
10400..1044F; Deseret
10450..1047F; Shavian
10480..104AF; Osmanya
104B0..104FF; Osage
10500..1052F; Elbasan
10530..1056F; Caucasian Albanian
10600..1077F; Linear A
@ -243,13 +246,20 @@ FFF0..FFFF; Specials
11280..112AF; Multani
112B0..112FF; Khudawadi
11300..1137F; Grantha
11400..1147F; Newa
11480..114DF; Tirhuta
11580..115FF; Siddham
11600..1165F; Modi
11660..1167F; Mongolian Supplement
11680..116CF; Takri
11700..1173F; Ahom
118A0..118FF; Warang Citi
11A00..11A4F; Zanabazar Square
11A50..11AAF; Soyombo
11AC0..11AFF; Pau Cin Hau
11C00..11C6F; Bhaiksuki
11C70..11CBF; Marchen
11D00..11D5F; Masaram Gondi
12000..123FF; Cuneiform
12400..1247F; Cuneiform Numbers and Punctuation
12480..1254F; Early Dynastic Cuneiform
@ -260,7 +270,12 @@ FFF0..FFFF; Specials
16AD0..16AFF; Bassa Vah
16B00..16B8F; Pahawh Hmong
16F00..16F9F; Miao
16FE0..16FFF; Ideographic Symbols and Punctuation
17000..187FF; Tangut
18800..18AFF; Tangut Components
1B000..1B0FF; Kana Supplement
1B100..1B12F; Kana Extended-A
1B170..1B2FF; Nushu
1BC00..1BC9F; Duployan
1BCA0..1BCAF; Shorthand Format Controls
1D000..1D0FF; Byzantine Musical Symbols
@ -270,7 +285,9 @@ FFF0..FFFF; Specials
1D360..1D37F; Counting Rod Numerals
1D400..1D7FF; Mathematical Alphanumeric Symbols
1D800..1DAAF; Sutton SignWriting
1E000..1E02F; Glagolitic Supplement
1E800..1E8DF; Mende Kikakui
1E900..1E95F; Adlam
1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
1F000..1F02F; Mahjong Tiles
1F030..1F09F; Domino Tiles
@ -289,6 +306,7 @@ FFF0..FFFF; Specials
2A700..2B73F; CJK Unified Ideographs Extension C
2B740..2B81F; CJK Unified Ideographs Extension D
2B820..2CEAF; CJK Unified Ideographs Extension E
2CEB0..2EBEF; CJK Unified Ideographs Extension F
2F800..2FA1F; CJK Compatibility Ideographs Supplement
E0000..E007F; Tags
E0100..E01EF; Variation Selectors Supplement

93
util/unicode/data/CaseFolding.txt
View File

@ -1,10 +1,11 @@
# CaseFolding-8.0.0.txt
# Date: 2015-01-13, 18:16:36 GMT [MD]
# CaseFolding-10.0.0.txt
# Date: 2017-04-14, 05:40:18 GMT
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Case Folding Properties
#
@ -23,7 +24,7 @@
#
# NOTE: case folding does not preserve normalization formats!
#
# For information on case folding, including how to have case folding
# For information on case folding, including how to have case folding
# preserve normalization formats, see Section 3.13 Default Case Algorithms in
# The Unicode Standard.
#
@ -593,6 +594,15 @@
13FB; C; 13F3; # CHEROKEE SMALL LETTER YU
13FC; C; 13F4; # CHEROKEE SMALL LETTER YV
13FD; C; 13F5; # CHEROKEE SMALL LETTER MV
1C80; C; 0432; # CYRILLIC SMALL LETTER ROUNDED VE
1C81; C; 0434; # CYRILLIC SMALL LETTER LONG-LEGGED DE
1C82; C; 043E; # CYRILLIC SMALL LETTER NARROW O
1C83; C; 0441; # CYRILLIC SMALL LETTER WIDE ES
1C84; C; 0442; # CYRILLIC SMALL LETTER TALL TE
1C85; C; 0442; # CYRILLIC SMALL LETTER THREE-LEGGED TE
1C86; C; 044A; # CYRILLIC SMALL LETTER TALL HARD SIGN
1C87; C; 0463; # CYRILLIC SMALL LETTER TALL YAT
1C88; C; A64B; # CYRILLIC SMALL LETTER UNBLENDED UK
1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW
1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE
1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW
@ -1163,6 +1173,7 @@ A7AA; C; 0266; # LATIN CAPITAL LETTER H WITH HOOK
A7AB; C; 025C; # LATIN CAPITAL LETTER REVERSED OPEN E
A7AC; C; 0261; # LATIN CAPITAL LETTER SCRIPT G
A7AD; C; 026C; # LATIN CAPITAL LETTER L WITH BELT
A7AE; C; 026A; # LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0; C; 029E; # LATIN CAPITAL LETTER TURNED K
A7B1; C; 0287; # LATIN CAPITAL LETTER TURNED T
A7B2; C; 029D; # LATIN CAPITAL LETTER J WITH CROSSED-TAIL
@ -1327,6 +1338,42 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
10425; C; 1044D; # DESERET CAPITAL LETTER ENG
10426; C; 1044E; # DESERET CAPITAL LETTER OI
10427; C; 1044F; # DESERET CAPITAL LETTER EW
104B0; C; 104D8; # OSAGE CAPITAL LETTER A
104B1; C; 104D9; # OSAGE CAPITAL LETTER AI
104B2; C; 104DA; # OSAGE CAPITAL LETTER AIN
104B3; C; 104DB; # OSAGE CAPITAL LETTER AH
104B4; C; 104DC; # OSAGE CAPITAL LETTER BRA
104B5; C; 104DD; # OSAGE CAPITAL LETTER CHA
104B6; C; 104DE; # OSAGE CAPITAL LETTER EHCHA
104B7; C; 104DF; # OSAGE CAPITAL LETTER E
104B8; C; 104E0; # OSAGE CAPITAL LETTER EIN
104B9; C; 104E1; # OSAGE CAPITAL LETTER HA
104BA; C; 104E2; # OSAGE CAPITAL LETTER HYA
104BB; C; 104E3; # OSAGE CAPITAL LETTER I
104BC; C; 104E4; # OSAGE CAPITAL LETTER KA
104BD; C; 104E5; # OSAGE CAPITAL LETTER EHKA
104BE; C; 104E6; # OSAGE CAPITAL LETTER KYA
104BF; C; 104E7; # OSAGE CAPITAL LETTER LA
104C0; C; 104E8; # OSAGE CAPITAL LETTER MA
104C1; C; 104E9; # OSAGE CAPITAL LETTER NA
104C2; C; 104EA; # OSAGE CAPITAL LETTER O
104C3; C; 104EB; # OSAGE CAPITAL LETTER OIN
104C4; C; 104EC; # OSAGE CAPITAL LETTER PA
104C5; C; 104ED; # OSAGE CAPITAL LETTER EHPA
104C6; C; 104EE; # OSAGE CAPITAL LETTER SA
104C7; C; 104EF; # OSAGE CAPITAL LETTER SHA
104C8; C; 104F0; # OSAGE CAPITAL LETTER TA
104C9; C; 104F1; # OSAGE CAPITAL LETTER EHTA
104CA; C; 104F2; # OSAGE CAPITAL LETTER TSA
104CB; C; 104F3; # OSAGE CAPITAL LETTER EHTSA
104CC; C; 104F4; # OSAGE CAPITAL LETTER TSHA
104CD; C; 104F5; # OSAGE CAPITAL LETTER DHA
104CE; C; 104F6; # OSAGE CAPITAL LETTER U
104CF; C; 104F7; # OSAGE CAPITAL LETTER WA
104D0; C; 104F8; # OSAGE CAPITAL LETTER KHA
104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA
104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA
104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA
10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A
10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA
10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB
@ -1410,5 +1457,39 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
118BD; C; 118DD; # WARANG CITI CAPITAL LETTER SSUU
118BE; C; 118DE; # WARANG CITI CAPITAL LETTER SII
118BF; C; 118DF; # WARANG CITI CAPITAL LETTER VIYO
1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF
1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI
1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM
1E903; C; 1E925; # ADLAM CAPITAL LETTER MIIM
1E904; C; 1E926; # ADLAM CAPITAL LETTER BA
1E905; C; 1E927; # ADLAM CAPITAL LETTER SINNYIIYHE
1E906; C; 1E928; # ADLAM CAPITAL LETTER PE
1E907; C; 1E929; # ADLAM CAPITAL LETTER BHE
1E908; C; 1E92A; # ADLAM CAPITAL LETTER RA
1E909; C; 1E92B; # ADLAM CAPITAL LETTER E
1E90A; C; 1E92C; # ADLAM CAPITAL LETTER FA
1E90B; C; 1E92D; # ADLAM CAPITAL LETTER I
1E90C; C; 1E92E; # ADLAM CAPITAL LETTER O
1E90D; C; 1E92F; # ADLAM CAPITAL LETTER DHA
1E90E; C; 1E930; # ADLAM CAPITAL LETTER YHE
1E90F; C; 1E931; # ADLAM CAPITAL LETTER WAW
1E910; C; 1E932; # ADLAM CAPITAL LETTER NUN
1E911; C; 1E933; # ADLAM CAPITAL LETTER KAF
1E912; C; 1E934; # ADLAM CAPITAL LETTER YA
1E913; C; 1E935; # ADLAM CAPITAL LETTER U
1E914; C; 1E936; # ADLAM CAPITAL LETTER JIIM
1E915; C; 1E937; # ADLAM CAPITAL LETTER CHI
1E916; C; 1E938; # ADLAM CAPITAL LETTER HA
1E917; C; 1E939; # ADLAM CAPITAL LETTER QAAF
1E918; C; 1E93A; # ADLAM CAPITAL LETTER GA
1E919; C; 1E93B; # ADLAM CAPITAL LETTER NYA
1E91A; C; 1E93C; # ADLAM CAPITAL LETTER TU
1E91B; C; 1E93D; # ADLAM CAPITAL LETTER NHA
1E91C; C; 1E93E; # ADLAM CAPITAL LETTER VA
1E91D; C; 1E93F; # ADLAM CAPITAL LETTER KHA
1E91E; C; 1E940; # ADLAM CAPITAL LETTER GBE
1E91F; C; 1E941; # ADLAM CAPITAL LETTER ZAL
1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO
1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA
#
# EOF

124
util/unicode/data/DerivedAge.txt
View File

@ -1,10 +1,11 @@
# DerivedAge-8.0.0.txt
# Date: 2015-02-13, 13:30:18 GMT [MD]
# DerivedAge-10.0.0.txt
# Date: 2017-04-14, 05:40:18 GMT
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Unicode Character Database: Derived Property Data
# This file shows when various code points were first assigned in Unicode.
@ -12,7 +13,7 @@
# Notes:
#
# - The term 'assigned' means that a previously reserved code point was assigned
# to be a character (graphic, format, control, or private-use);
# to be a character (graphic, format, control, or private-use);
# a noncharacter code point; or a surrogate code point.
# For more information, see The Unicode Standard Section 2.4
#
@ -1535,4 +1536,115 @@ FE2E..FE2F ; 8.0 # [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILL
# Total code points: 7716
# ================================================
# Age=V9_0
# Newly assigned in Unicode 9.0.0 (June, 2016)
08B6..08BD ; 9.0 # [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1 ; 9.0 # [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E2 ; 9.0 # ARABIC DISPUTED END OF AYAH
0C80 ; 9.0 # KANNADA SIGN SPACING CANDRABINDU
0D4F ; 9.0 # MALAYALAM SIGN PARA
0D54..0D56 ; 9.0 # [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D58..0D5E ; 9.0 # [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH
0D76..0D78 ; 9.0 # [3] MALAYALAM FRACTION ONE SIXTEENTH..MALAYALAM FRACTION THREE SIXTEENTHS
1C80..1C88 ; 9.0 # [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1DFB ; 9.0 # COMBINING DELETION MARK
23FB..23FE ; 9.0 # [4] POWER SYMBOL..POWER SLEEP SYMBOL
2E43..2E44 ; 9.0 # [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK
A7AE ; 9.0 # LATIN CAPITAL LETTER SMALL CAPITAL I
A8C5 ; 9.0 # SAURASHTRA SIGN CANDRABINDU
1018D..1018E ; 9.0 # [2] GREEK INDICTION SIGN..NOMISMA SIGN
104B0..104D3 ; 9.0 # [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
104D8..104FB ; 9.0 # [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
1123E ; 9.0 # KHOJKI SIGN SUKUN
11400..11459 ; 9.0 # [90] NEWA LETTER A..NEWA DIGIT NINE
1145B ; 9.0 # NEWA PLACEHOLDER MARK
1145D ; 9.0 # NEWA INSERTION SIGN
11660..1166C ; 9.0 # [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
11C00..11C08 ; 9.0 # [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C36 ; 9.0 # [45] BHAIKSUKI LETTER E..BHAIKSUKI VOWEL SIGN VOCALIC L
11C38..11C45 ; 9.0 # [14] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI GAP FILLER-2
11C50..11C6C ; 9.0 # [29] BHAIKSUKI DIGIT ZERO..BHAIKSUKI HUNDREDS UNIT MARK
11C70..11C8F ; 9.0 # [32] MARCHEN HEAD MARK..MARCHEN LETTER A
11C92..11CA7 ; 9.0 # [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
11CA9..11CB6 ; 9.0 # [14] MARCHEN SUBJOINED LETTER YA..MARCHEN SIGN CANDRABINDU
16FE0 ; 9.0 # TANGUT ITERATION MARK
17000..187EC ; 9.0 # [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; 9.0 # [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1E000..1E006 ; 9.0 # [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E008..1E018 ; 9.0 # [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E01B..1E021 ; 9.0 # [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024 ; 9.0 # [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A ; 9.0 # [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
1E900..1E94A ; 9.0 # [75] ADLAM CAPITAL LETTER ALIF..ADLAM NUKTA
1E950..1E959 ; 9.0 # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1E95E..1E95F ; 9.0 # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
1F19B..1F1AC ; 9.0 # [18] SQUARED THREE D..SQUARED VOD
1F23B ; 9.0 # SQUARED CJK UNIFIED IDEOGRAPH-914D
1F57A ; 9.0 # MAN DANCING
1F5A4 ; 9.0 # BLACK HEART
1F6D1..1F6D2 ; 9.0 # [2] OCTAGONAL SIGN..SHOPPING TROLLEY
1F6F4..1F6F6 ; 9.0 # [3] SCOOTER..CANOE
1F919..1F91E ; 9.0 # [6] CALL ME HAND..HAND WITH INDEX AND MIDDLE FINGERS CROSSED
1F920..1F927 ; 9.0 # [8] FACE WITH COWBOY HAT..SNEEZING FACE
1F930 ; 9.0 # PREGNANT WOMAN
1F933..1F93E ; 9.0 # [12] SELFIE..HANDBALL
1F940..1F94B ; 9.0 # [12] WILTED FLOWER..MARTIAL ARTS UNIFORM
1F950..1F95E ; 9.0 # [15] CROISSANT..PANCAKES
1F985..1F991 ; 9.0 # [13] EAGLE..SQUID
# Total code points: 7500
# ================================================
# Age=V10_0
# Newly assigned in Unicode 10.0.0 (June, 2017)
0860..086A ; 10.0 # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
09FC..09FD ; 10.0 # [2] BENGALI LETTER VEDIC ANUSVARA..BENGALI ABBREVIATION SIGN
0AFA..0AFF ; 10.0 # [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0D00 ; 10.0 # MALAYALAM SIGN COMBINING ANUSVARA ABOVE
0D3B..0D3C ; 10.0 # [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
1CF7 ; 10.0 # VEDIC SIGN ATIKRAMA
1DF6..1DF9 ; 10.0 # [4] COMBINING KAVYKA ABOVE RIGHT..COMBINING WIDE INVERTED BRIDGE BELOW
20BF ; 10.0 # BITCOIN SIGN
23FF ; 10.0 # OBSERVER EYE SYMBOL
2BD2 ; 10.0 # GROUP MARK
2E45..2E49 ; 10.0 # [5] INVERTED LOW KAVYKA..DOUBLE STACKED COMMA
312E ; 10.0 # BOPOMOFO LETTER O WITH DOT ABOVE
9FD6..9FEA ; 10.0 # [21] CJK UNIFIED IDEOGRAPH-9FD6..CJK UNIFIED IDEOGRAPH-9FEA
1032D..1032F ; 10.0 # [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE
11A00..11A47 ; 10.0 # [72] ZANABAZAR SQUARE LETTER A..ZANABAZAR SQUARE SUBJOINER
11A50..11A83 ; 10.0 # [52] SOYOMBO LETTER A..SOYOMBO LETTER KSSA
11A86..11A9C ; 10.0 # [23] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO MARK DOUBLE SHAD
11A9E..11AA2 ; 10.0 # [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
11D00..11D06 ; 10.0 # [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; 10.0 # [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D36 ; 10.0 # [44] MASARAM GONDI LETTER AU..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; 10.0 # MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; 10.0 # [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D47 ; 10.0 # [9] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI RA-KARA
11D50..11D59 ; 10.0 # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
16FE1 ; 10.0 # NUSHU ITERATION MARK
1B002..1B11E ; 10.0 # [285] HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; 10.0 # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1F260..1F265 ; 10.0 # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
1F6D3..1F6D4 ; 10.0 # [2] STUPA..PAGODA
1F6F7..1F6F8 ; 10.0 # [2] SLED..FLYING SAUCER
1F900..1F90B ; 10.0 # [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
1F91F ; 10.0 # I LOVE YOU HAND SIGN
1F928..1F92F ; 10.0 # [8] FACE WITH ONE EYEBROW RAISED..SHOCKED FACE WITH EXPLODING HEAD
1F931..1F932 ; 10.0 # [2] BREAST-FEEDING..PALMS UP TOGETHER
1F94C ; 10.0 # CURLING STONE
1F95F..1F96B ; 10.0 # [13] DUMPLING..CANNED FOOD
1F992..1F997 ; 10.0 # [6] GIRAFFE FACE..CRICKET
1F9D0..1F9E6 ; 10.0 # [23] FACE WITH MONOCLE..SOCKS
2CEB0..2EBE0 ; 10.0 # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
# Total code points: 8518
# EOF

110
util/unicode/data/DerivedNormalizationProps.txt
View File

@ -1,10 +1,11 @@
# DerivedNormalizationProps-8.0.0.txt
# Date: 2015-02-13, 13:30:23 GMT [MD]
# DerivedNormalizationProps-10.0.0.txt
# Date: 2017-02-14, 04:26:07 GMT
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
# ================================================
@ -1679,12 +1680,12 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
1F16A..1F16B ; NFKD_QC; N # So [2] RAISED MC SIGN..RAISED MD SIGN
1F190 ; NFKD_QC; N # So SQUARE DJ
1F200..1F202 ; NFKD_QC; N # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA
1F210..1F23A ; NFKD_QC; N # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F210..1F23B ; NFKD_QC; N # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248 ; NFKD_QC; N # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; NFKD_QC; N # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 16893
# Total code points: 16894
# ================================================
@ -2082,12 +2083,12 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI
1F16A..1F16B ; NFKC_QC; N # So [2] RAISED MC SIGN..RAISED MD SIGN
1F190 ; NFKC_QC; N # So SQUARE DJ
1F200..1F202 ; NFKC_QC; N # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA
1F210..1F23A ; NFKC_QC; N # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F210..1F23B ; NFKC_QC; N # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248 ; NFKC_QC; N # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; NFKC_QC; N # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 4793
# Total code points: 4794
# ================================================
@ -3513,6 +3514,14 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON
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
1C80 ; NFKC_CF; 0432 # L& CYRILLIC SMALL LETTER ROUNDED VE
1C81 ; NFKC_CF; 0434 # L& CYRILLIC SMALL LETTER LONG-LEGGED DE
1C82 ; NFKC_CF; 043E # L& CYRILLIC SMALL LETTER NARROW O
1C83 ; NFKC_CF; 0441 # L& CYRILLIC SMALL LETTER WIDE ES
1C84..1C85 ; NFKC_CF; 0442 # L& [2] CYRILLIC SMALL LETTER TALL TE..CYRILLIC SMALL LETTER THREE-LEGGED TE
1C86 ; NFKC_CF; 044A # L& CYRILLIC SMALL LETTER TALL HARD SIGN
1C87 ; NFKC_CF; 0463 # L& CYRILLIC SMALL LETTER TALL YAT
1C88 ; NFKC_CF; A64B # L& CYRILLIC SMALL LETTER UNBLENDED UK
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
@ -5263,6 +5272,7 @@ A7AA ; NFKC_CF; 0266 # L& LATIN CAPITAL LETTER H WITH H
A7AB ; NFKC_CF; 025C # L& LATIN CAPITAL LETTER REVERSED OPEN E
A7AC ; NFKC_CF; 0261 # L& LATIN CAPITAL LETTER SCRIPT G
A7AD ; NFKC_CF; 026C # L& LATIN CAPITAL LETTER L WITH BELT
A7AE ; NFKC_CF; 026A # L& LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0 ; NFKC_CF; 029E # L& LATIN CAPITAL LETTER TURNED K
A7B1 ; NFKC_CF; 0287 # L& LATIN CAPITAL LETTER TURNED T
A7B2 ; NFKC_CF; 029D # L& LATIN CAPITAL LETTER J WITH CROSSED-TAIL
@ -6731,6 +6741,42 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF
10425 ; NFKC_CF; 1044D # L& DESERET CAPITAL LETTER ENG
10426 ; NFKC_CF; 1044E # L& DESERET CAPITAL LETTER OI
10427 ; NFKC_CF; 1044F # L& DESERET CAPITAL LETTER EW
104B0 ; NFKC_CF; 104D8 # L& OSAGE CAPITAL LETTER A
104B1 ; NFKC_CF; 104D9 # L& OSAGE CAPITAL LETTER AI
104B2 ; NFKC_CF; 104DA # L& OSAGE CAPITAL LETTER AIN
104B3 ; NFKC_CF; 104DB # L& OSAGE CAPITAL LETTER AH
104B4 ; NFKC_CF; 104DC # L& OSAGE CAPITAL LETTER BRA
104B5 ; NFKC_CF; 104DD # L& OSAGE CAPITAL LETTER CHA
104B6 ; NFKC_CF; 104DE # L& OSAGE CAPITAL LETTER EHCHA
104B7 ; NFKC_CF; 104DF # L& OSAGE CAPITAL LETTER E
104B8 ; NFKC_CF; 104E0 # L& OSAGE CAPITAL LETTER EIN
104B9 ; NFKC_CF; 104E1 # L& OSAGE CAPITAL LETTER HA
104BA ; NFKC_CF; 104E2 # L& OSAGE CAPITAL LETTER HYA
104BB ; NFKC_CF; 104E3 # L& OSAGE CAPITAL LETTER I
104BC ; NFKC_CF; 104E4 # L& OSAGE CAPITAL LETTER KA
104BD ; NFKC_CF; 104E5 # L& OSAGE CAPITAL LETTER EHKA
104BE ; NFKC_CF; 104E6 # L& OSAGE CAPITAL LETTER KYA
104BF ; NFKC_CF; 104E7 # L& OSAGE CAPITAL LETTER LA
104C0 ; NFKC_CF; 104E8 # L& OSAGE CAPITAL LETTER MA
104C1 ; NFKC_CF; 104E9 # L& OSAGE CAPITAL LETTER NA
104C2 ; NFKC_CF; 104EA # L& OSAGE CAPITAL LETTER O
104C3 ; NFKC_CF; 104EB # L& OSAGE CAPITAL LETTER OIN
104C4 ; NFKC_CF; 104EC # L& OSAGE CAPITAL LETTER PA
104C5 ; NFKC_CF; 104ED # L& OSAGE CAPITAL LETTER EHPA
104C6 ; NFKC_CF; 104EE # L& OSAGE CAPITAL LETTER SA
104C7 ; NFKC_CF; 104EF # L& OSAGE CAPITAL LETTER SHA
104C8 ; NFKC_CF; 104F0 # L& OSAGE CAPITAL LETTER TA
104C9 ; NFKC_CF; 104F1 # L& OSAGE CAPITAL LETTER EHTA
104CA ; NFKC_CF; 104F2 # L& OSAGE CAPITAL LETTER TSA
104CB ; NFKC_CF; 104F3 # L& OSAGE CAPITAL LETTER EHTSA
104CC ; NFKC_CF; 104F4 # L& OSAGE CAPITAL LETTER TSHA
104CD ; NFKC_CF; 104F5 # L& OSAGE CAPITAL LETTER DHA
104CE ; NFKC_CF; 104F6 # L& OSAGE CAPITAL LETTER U
104CF ; NFKC_CF; 104F7 # L& OSAGE CAPITAL LETTER WA
104D0 ; NFKC_CF; 104F8 # L& OSAGE CAPITAL LETTER KHA
104D1 ; NFKC_CF; 104F9 # L& OSAGE CAPITAL LETTER GHA
104D2 ; NFKC_CF; 104FA # L& OSAGE CAPITAL LETTER ZA
104D3 ; NFKC_CF; 104FB # L& OSAGE CAPITAL LETTER ZHA
10C80 ; NFKC_CF; 10CC0 # L& OLD HUNGARIAN CAPITAL LETTER A
10C81 ; NFKC_CF; 10CC1 # L& OLD HUNGARIAN CAPITAL LETTER AA
10C82 ; NFKC_CF; 10CC2 # L& OLD HUNGARIAN CAPITAL LETTER EB
@ -7819,6 +7865,40 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF
1D7FD ; NFKC_CF; 0037 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN
1D7FE ; NFKC_CF; 0038 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT
1D7FF ; NFKC_CF; 0039 # Nd MATHEMATICAL MONOSPACE DIGIT NINE
1E900 ; NFKC_CF; 1E922 # L& ADLAM CAPITAL LETTER ALIF
1E901 ; NFKC_CF; 1E923 # L& ADLAM CAPITAL LETTER DAALI
1E902 ; NFKC_CF; 1E924 # L& ADLAM CAPITAL LETTER LAAM
1E903 ; NFKC_CF; 1E925 # L& ADLAM CAPITAL LETTER MIIM
1E904 ; NFKC_CF; 1E926 # L& ADLAM CAPITAL LETTER BA
1E905 ; NFKC_CF; 1E927 # L& ADLAM CAPITAL LETTER SINNYIIYHE
1E906 ; NFKC_CF; 1E928 # L& ADLAM CAPITAL LETTER PE
1E907 ; NFKC_CF; 1E929 # L& ADLAM CAPITAL LETTER BHE
1E908 ; NFKC_CF; 1E92A # L& ADLAM CAPITAL LETTER RA
1E909 ; NFKC_CF; 1E92B # L& ADLAM CAPITAL LETTER E
1E90A ; NFKC_CF; 1E92C # L& ADLAM CAPITAL LETTER FA
1E90B ; NFKC_CF; 1E92D # L& ADLAM CAPITAL LETTER I
1E90C ; NFKC_CF; 1E92E # L& ADLAM CAPITAL LETTER O
1E90D ; NFKC_CF; 1E92F # L& ADLAM CAPITAL LETTER DHA
1E90E ; NFKC_CF; 1E930 # L& ADLAM CAPITAL LETTER YHE
1E90F ; NFKC_CF; 1E931 # L& ADLAM CAPITAL LETTER WAW
1E910 ; NFKC_CF; 1E932 # L& ADLAM CAPITAL LETTER NUN
1E911 ; NFKC_CF; 1E933 # L& ADLAM CAPITAL LETTER KAF
1E912 ; NFKC_CF; 1E934 # L& ADLAM CAPITAL LETTER YA
1E913 ; NFKC_CF; 1E935 # L& ADLAM CAPITAL LETTER U
1E914 ; NFKC_CF; 1E936 # L& ADLAM CAPITAL LETTER JIIM
1E915 ; NFKC_CF; 1E937 # L& ADLAM CAPITAL LETTER CHI
1E916 ; NFKC_CF; 1E938 # L& ADLAM CAPITAL LETTER HA
1E917 ; NFKC_CF; 1E939 # L& ADLAM CAPITAL LETTER QAAF
1E918 ; NFKC_CF; 1E93A # L& ADLAM CAPITAL LETTER GA
1E919 ; NFKC_CF; 1E93B # L& ADLAM CAPITAL LETTER NYA
1E91A ; NFKC_CF; 1E93C # L& ADLAM CAPITAL LETTER TU
1E91B ; NFKC_CF; 1E93D # L& ADLAM CAPITAL LETTER NHA
1E91C ; NFKC_CF; 1E93E # L& ADLAM CAPITAL LETTER VA
1E91D ; NFKC_CF; 1E93F # L& ADLAM CAPITAL LETTER KHA
1E91E ; NFKC_CF; 1E940 # L& ADLAM CAPITAL LETTER GBE
1E91F ; NFKC_CF; 1E941 # L& ADLAM CAPITAL LETTER ZAL
1E920 ; NFKC_CF; 1E942 # L& ADLAM CAPITAL LETTER KPO
1E921 ; NFKC_CF; 1E943 # L& ADLAM CAPITAL LETTER SHA
1EE00 ; NFKC_CF; 0627 # Lo ARABIC MATHEMATICAL ALEF
1EE01 ; NFKC_CF; 0628 # Lo ARABIC MATHEMATICAL BEH
1EE02 ; NFKC_CF; 062C # Lo ARABIC MATHEMATICAL JEEM
@ -8083,6 +8163,7 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF
1F238 ; NFKC_CF; 7533 # So SQUARED CJK UNIFIED IDEOGRAPH-7533
1F239 ; NFKC_CF; 5272 # So SQUARED CJK UNIFIED IDEOGRAPH-5272
1F23A ; NFKC_CF; 55B6 # So SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F23B ; NFKC_CF; 914D # So SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240 ; NFKC_CF; 3014 672C 3015 # So TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C
1F241 ; NFKC_CF; 3014 4E09 3015 # So TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E09
1F242 ; NFKC_CF; 3014 4E8C 3015 # So TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E8C
@ -8634,7 +8715,7 @@ 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: 10146
# Total code points: 10227
# ================================================
@ -8972,6 +9053,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-
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
1C80..1C88 ; Changes_When_NFKC_Casefolded # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
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
@ -9389,7 +9471,7 @@ A7A2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER K W
A7A4 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE
A7A6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
A7A8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
A7AA..A7AD ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT
A7AA..A7AE ; Changes_When_NFKC_Casefolded # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B4 ; Changes_When_NFKC_Casefolded # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA
A7B6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER OMEGA
A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
@ -9519,6 +9601,7 @@ FFE9..FFEC ; Changes_When_NFKC_Casefolded # Sm [4] HALFWIDTH LEFTWARDS ARRO
FFED..FFEE ; Changes_When_NFKC_Casefolded # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE
FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserved-FFF8>
10400..10427 ; Changes_When_NFKC_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW
104B0..104D3 ; Changes_When_NFKC_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
10C80..10CB2 ; Changes_When_NFKC_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
118A0..118BF ; Changes_When_NFKC_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
1BCA0..1BCA3 ; Changes_When_NFKC_Casefolded # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
@ -9566,6 +9649,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserv
1D7C3 ; Changes_When_NFKC_Casefolded # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL
1D7C4..1D7CB ; Changes_When_NFKC_Casefolded # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
1D7CE..1D7FF ; Changes_When_NFKC_Casefolded # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
1E900..1E921 ; Changes_When_NFKC_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA
1EE00..1EE03 ; Changes_When_NFKC_Casefolded # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
1EE05..1EE1F ; Changes_When_NFKC_Casefolded # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
1EE21..1EE22 ; Changes_When_NFKC_Casefolded # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
@ -9605,7 +9689,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserv
1F16A..1F16B ; Changes_When_NFKC_Casefolded # So [2] RAISED MC SIGN..RAISED MD SIGN
1F190 ; Changes_When_NFKC_Casefolded # So SQUARE DJ
1F200..1F202 ; Changes_When_NFKC_Casefolded # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA
1F210..1F23A ; Changes_When_NFKC_Casefolded # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F210..1F23B ; Changes_When_NFKC_Casefolded # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248 ; Changes_When_NFKC_Casefolded # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; Changes_When_NFKC_Casefolded # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
2F800..2FA1D ; Changes_When_NFKC_Casefolded # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
@ -9617,6 +9701,6 @@ 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: 10146
# Total code points: 10227
# EOF

16
util/unicode/data/NormalizationCorrections.txt
View File

@ -1,12 +1,14 @@
# NormalizationCorrections-8.0.0.txt
# Date: 2015-03-07, 01:30:00 GMT [KW, LI]
# NormalizationCorrections-10.0.0.txt
# Date: 2017-04-13, 01:00:00 GMT [KW, LI]
# © 2017 Unicode®, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# The normalization stability policy of the Unicode Consortium
# ordinarily precludes any change to the decomposition
# for any character, once established in a relevant version
@ -25,7 +27,7 @@
#
# Currently this list has exactly six entries in it, one for the
# typo found and corrected in Corrigendum #3, and five for
# the typos and misidentifications found and corrected in
# the typos and misidentifications found and corrected in
# Corrigendum #4. All efforts
# will be made to keep the entries limited to just those fixes.
#
@ -35,7 +37,7 @@
# Field 2: Corrected decomposition
# Field 3: Version of Unicode for which the correction was
# entered into UnicodeData.txt, in n.n.n format.
# Comment: Indicates the Unicode Corrigendum which documents
# Comment: Indicates the Unicode Corrigendum which documents
# the correction
#
# For more information, see UAX #15, Unicode Normalization Forms.

250
util/unicode/data/Scripts.txt
View File

@ -1,10 +1,11 @@
# Scripts-8.0.0.txt
# Date: 2015-03-11, 22:29:42 GMT [MD]
# Scripts-10.0.0.txt
# Date: 2017-03-11, 06:40:37 GMT
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
# For more information, see:
# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/
# Especially the sections:
@ -92,10 +93,10 @@
0605 ; Common # Cf ARABIC NUMBER MARK ABOVE
060C ; Common # Po ARABIC COMMA
061B ; Common # Po ARABIC SEMICOLON
061C ; Common # Cf ARABIC LETTER MARK
061F ; Common # Po ARABIC QUESTION MARK
0640 ; Common # Lm ARABIC TATWEEL
06DD ; Common # Cf ARABIC END OF AYAH
08E2 ; Common # Cf ARABIC DISPUTED END OF AYAH
0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
0FD5..0FD8 ; Common # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS
@ -110,6 +111,7 @@
1CEE..1CF1 ; Common # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
1CF7 ; Common # Mc VEDIC SIGN ATIKRAMA
2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE
200B ; Common # Cf ZERO WIDTH SPACE
200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
@ -153,7 +155,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
20A0..20BE ; Common # Sc [31] EURO-CURRENCY SIGN..LARI SIGN
20A0..20BF ; Common # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN
2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Common # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA
@ -223,8 +225,7 @@
239B..23B3 ; Common # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM
23B4..23DB ; Common # So [40] TOP SQUARE BRACKET..FUSE
23DC..23E1 ; Common # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET
23E2..23FA ; Common # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD
2400..2426 ; Common # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
23E2..2426 ; Common # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A ; Common # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..249B ; Common # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
249C..24E9 ; Common # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
@ -309,7 +310,7 @@
2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD1 ; Common # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
2BCA..2BD2 ; Common # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER
2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET
@ -348,6 +349,7 @@
2E40 ; Common # Pd DOUBLE HYPHEN
2E41 ; Common # Po REVERSED COMMA
2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E49 ; Common # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
3000 ; Common # Zs IDEOGRAPHIC SPACE
3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK
@ -572,19 +574,18 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F100..1F10C ; Common # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ
1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN
1F170..1F19A ; Common # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS
1F170..1F1AC ; Common # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD
1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA
1F210..1F23A ; Common # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F210..1F23B ; Common # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248 ; Common # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; Common # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
1F260..1F265 ; Common # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA
1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
1F400..1F579 ; Common # So [378] RAT..JOYSTICK
1F57B..1F5A3 ; Common # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
1F5A5..1F6D0 ; Common # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP
1F400..1F6D4 ; Common # So [725] RAT..PAGODA
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F3 ; Common # So [4] SATELLITE..PASSENGER SHIP
1F6F0..1F6F8 ; Common # So [9] SATELLITE..FLYING SAUCER
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D4 ; Common # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@ -592,13 +593,17 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F910..1F918 ; Common # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
1F980..1F984 ; Common # So [5] CRAB..UNICORN FACE
1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL
1F940..1F94C ; Common # So [13] WILTED FLOWER..CURLING STONE
1F950..1F96B ; Common # So [28] CROISSANT..CANNED FOOD
1F980..1F997 ; Common # So [24] CRAB..CRICKET
1F9C0 ; Common # So CHEESE WEDGE
1F9D0..1F9E6 ; Common # So [23] FACE WITH MONOCLE..SOCKS
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 7179
# Total code points: 7363
# ================================================
@ -641,7 +646,7 @@ A770 ; Latin # Lm MODIFIER LETTER US
A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T
A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT
A790..A7AD ; Latin # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT
A790..A7AE ; Latin # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I
A7B0..A7B7 ; Latin # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA
A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
@ -654,7 +659,7 @@ FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S
FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
# Total code points: 1349
# Total code points: 1350
# ================================================
@ -708,13 +713,13 @@ AB65 ; Greek # L& GREEK LETTER SMALL CAPITAL OMEGA
10175..10178 ; Greek # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN
10179..10189 ; Greek # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN
1018A..1018B ; Greek # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN
1018C ; Greek # So GREEK SINUSOID SIGN
1018C..1018E ; Greek # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN
101A0 ; Greek # So GREEK SYMBOL TAU RHO
1D200..1D241 ; Greek # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D242..1D244 ; Greek # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1D245 ; Greek # So GREEK MUSICAL LEIMMA
# Total code points: 516
# Total code points: 518
# ================================================
@ -724,6 +729,7 @@ AB65 ; Greek # L& GREEK LETTER SMALL CAPITAL OMEGA
0487 ; Cyrillic # Mn COMBINING CYRILLIC POKRYTIE
0488..0489 ; Cyrillic # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
048A..052F ; Cyrillic # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER
1C80..1C88 ; Cyrillic # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
1D2B ; Cyrillic # L& CYRILLIC LETTER SMALL CAPITAL EL
1D78 ; Cyrillic # Lm MODIFIER LETTER CYRILLIC EN
2DE0..2DFF ; Cyrillic # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
@ -740,7 +746,7 @@ A69C..A69D ; Cyrillic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER
A69E..A69F ; Cyrillic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
# Total code points: 434
# Total code points: 443
# ================================================
@ -791,6 +797,7 @@ 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
@ -815,6 +822,8 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V
0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE
08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; Arabic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1 ; Arabic # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA
FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW
@ -862,7 +871,7 @@ 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: 1257
# Total code points: 1280
# ================================================
@ -873,8 +882,9 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
0712..072F ; Syriac # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
0730..074A ; Syriac # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
074D..074F ; Syriac # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE
0860..086A ; Syriac # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
# Total code points: 77
# Total code points: 88
# ================================================
@ -944,8 +954,10 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
09F4..09F9 ; Bengali # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN
09FA ; Bengali # So BENGALI ISSHAR
09FB ; Bengali # Sc BENGALI GANDA MARK
09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA
09FD ; Bengali # Po BENGALI ABBREVIATION SIGN
# Total code points: 93
# Total code points: 95
# ================================================
@ -998,8 +1010,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
0AF9 ; Gujarati # Lo GUJARATI LETTER ZHA
0AFA..0AFF ; Gujarati # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
# Total code points: 85
# Total code points: 91
# ================================================
@ -1086,6 +1099,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
# ================================================
0C80 ; Kannada # Lo KANNADA SIGN SPACING CANDRABINDU
0C81 ; Kannada # Mn KANNADA SIGN CANDRABINDU
0C82..0C83 ; Kannada # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA
0C85..0C8C ; Kannada # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
@ -1109,15 +1123,16 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
# Total code points: 87
# Total code points: 88
# ================================================
0D01 ; Malayalam # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01 ; Malayalam # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Malayalam # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C ; Malayalam # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; Malayalam # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A ; Malayalam # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3B..0D3C ; Malayalam # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3D ; Malayalam # Lo MALAYALAM SIGN AVAGRAHA
0D3E..0D40 ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; Malayalam # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
@ -1125,15 +1140,18 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
0D4A..0D4C ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU
0D4D ; Malayalam # Mn MALAYALAM SIGN VIRAMA
0D4E ; Malayalam # Lo MALAYALAM LETTER DOT REPH
0D4F ; Malayalam # So MALAYALAM SIGN PARA
0D54..0D56 ; Malayalam # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D57 ; Malayalam # Mc MALAYALAM AU LENGTH MARK
0D58..0D5E ; Malayalam # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH
0D5F..0D61 ; Malayalam # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D62..0D63 ; Malayalam # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
0D66..0D6F ; Malayalam # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE
0D70..0D75 ; Malayalam # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS
0D70..0D78 ; Malayalam # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS
0D79 ; Malayalam # So MALAYALAM DATE MARK
0D7A..0D7F ; Malayalam # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
# Total code points: 100
# Total code points: 117
# ================================================
@ -1436,21 +1454,24 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT
1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI
1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
1844..1877 ; Mongolian # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA
1880..18A8 ; Mongolian # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA
1880..1884 ; Mongolian # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
1885..1886 ; Mongolian # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
1887..18A8 ; Mongolian # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA
18A9 ; Mongolian # Mn MONGOLIAN LETTER ALI GALI DAGALGA
18AA ; Mongolian # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA
11660..1166C ; Mongolian # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
# Total code points: 153
# Total code points: 166
# ================================================
3041..3096 ; Hiragana # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE
309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK
309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI
1B001 ; Hiragana # Lo HIRAGANA LETTER ARCHAIC YE
1B001..1B11E ; Hiragana # Lo [286] HIRAGANA LETTER ARCHAIC YE..HENTAIGANA LETTER N-MU-MO-2
1F200 ; Hiragana # So SQUARE HIRAGANA HOKA
# Total code points: 91
# Total code points: 376
# ================================================
@ -1469,10 +1490,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
# ================================================
02EA..02EB ; Bopomofo # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK
3105..312D ; Bopomofo # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; Bopomofo # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
31A0..31BA ; Bopomofo # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
# Total code points: 70
# Total code points: 71
# ================================================
@ -1485,16 +1506,17 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK
3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY
303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK
3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FD5 ; Han # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; Han # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D
FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 81734
# Total code points: 89228
# ================================================
@ -1509,8 +1531,9 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
10300..1031F ; Old_Italic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10320..10323 ; Old_Italic # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY
1032D..1032F ; Old_Italic # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE
# Total code points: 36
# Total code points: 39
# ================================================
@ -1542,8 +1565,8 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE
1CED ; Inherited # Mn VEDIC SIGN TIRYAK
1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE
1CF8..1CF9 ; Inherited # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1DC0..1DF5 ; Inherited # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
1DFC..1DFF ; Inherited # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1DC0..1DF9 ; Inherited # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
1DFB..1DFF ; Inherited # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER
20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0 ; Inherited # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
@ -1562,7 +1585,7 @@ FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CON
1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 563
# Total code points: 568
# ================================================
@ -1705,8 +1728,13 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
2C00..2C2E ; Glagolitic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; Glagolitic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
1E000..1E006 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
1E008..1E018 ; Glagolitic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
1E01B..1E021 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
1E023..1E024 ; Glagolitic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
1E026..1E02A ; Glagolitic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
# Total code points: 94
# Total code points: 132
# ================================================
@ -1872,11 +1900,11 @@ A62A..A62B ; Vai # Lo [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO
A880..A881 ; Saurashtra # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA
A882..A8B3 ; Saurashtra # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
A8B4..A8C3 ; Saurashtra # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU
A8C4 ; Saurashtra # Mn SAURASHTRA SIGN VIRAMA
A8C4..A8C5 ; Saurashtra # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU
A8CE..A8CF ; Saurashtra # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A8D0..A8D9 ; Saurashtra # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE
# Total code points: 81
# Total code points: 82
# ================================================
@ -2314,8 +2342,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11235 ; Khojki # Mc KHOJKI SIGN VIRAMA
11236..11237 ; Khojki # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
11238..1123D ; Khojki # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
1123E ; Khojki # Mn KHOJKI SIGN SUKUN
# Total code points: 61
# Total code points: 62
# ================================================
@ -2536,4 +2565,129 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 672
# ================================================
1E900..1E943 ; Adlam # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
1E944..1E94A ; Adlam # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
1E950..1E959 ; Adlam # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
1E95E..1E95F ; Adlam # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
# Total code points: 87
# ================================================
11C00..11C08 ; Bhaiksuki # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; Bhaiksuki # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
11C2F ; Bhaiksuki # Mc BHAIKSUKI VOWEL SIGN AA
11C30..11C36 ; Bhaiksuki # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
11C38..11C3D ; Bhaiksuki # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
11C3E ; Bhaiksuki # Mc BHAIKSUKI SIGN VISARGA
11C3F ; Bhaiksuki # Mn BHAIKSUKI SIGN VIRAMA
11C40 ; Bhaiksuki # Lo BHAIKSUKI SIGN AVAGRAHA
11C41..11C45 ; Bhaiksuki # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2
11C50..11C59 ; Bhaiksuki # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
11C5A..11C6C ; Bhaiksuki # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK
# Total code points: 97
# ================================================
11C70..11C71 ; Marchen # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD
11C72..11C8F ; Marchen # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
11C92..11CA7 ; Marchen # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA
11CA9 ; Marchen # Mc MARCHEN SUBJOINED LETTER YA
11CAA..11CB0 ; Marchen # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
11CB1 ; Marchen # Mc MARCHEN VOWEL SIGN I
11CB2..11CB3 ; Marchen # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB4 ; Marchen # Mc MARCHEN VOWEL SIGN O
11CB5..11CB6 ; Marchen # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
# Total code points: 68
# ================================================
11400..11434 ; Newa # Lo [53] NEWA LETTER A..NEWA LETTER HA
11435..11437 ; Newa # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II
11438..1143F ; Newa # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI
11440..11441 ; Newa # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU
11442..11444 ; Newa # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA
11445 ; Newa # Mc NEWA SIGN VISARGA
11446 ; Newa # Mn NEWA SIGN NUKTA
11447..1144A ; Newa # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI
1144B..1144F ; Newa # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN
11450..11459 ; Newa # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE
1145B ; Newa # Po NEWA PLACEHOLDER MARK
1145D ; Newa # Po NEWA INSERTION SIGN
# Total code points: 92
# ================================================
104B0..104D3 ; Osage # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA
104D8..104FB ; Osage # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA
# Total code points: 72
# ================================================
16FE0 ; Tangut # Lm TANGUT ITERATION MARK
17000..187EC ; Tangut # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; Tangut # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
# Total code points: 6881
# ================================================
11D00..11D06 ; Masaram_Gondi # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; Masaram_Gondi # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; Masaram_Gondi # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D31..11D36 ; Masaram_Gondi # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; Masaram_Gondi # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; Masaram_Gondi # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D45 ; Masaram_Gondi # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
11D46 ; Masaram_Gondi # Lo MASARAM GONDI REPHA
11D47 ; Masaram_Gondi # Mn MASARAM GONDI RA-KARA
11D50..11D59 ; Masaram_Gondi # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
# Total code points: 75
# ================================================
16FE1 ; Nushu # Lm NUSHU ITERATION MARK
1B170..1B2FB ; Nushu # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
# Total code points: 397
# ================================================
11A50 ; Soyombo # Lo SOYOMBO LETTER A
11A51..11A56 ; Soyombo # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A57..11A58 ; Soyombo # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
11A59..11A5B ; Soyombo # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A5C..11A83 ; Soyombo # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; Soyombo # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11A8A..11A96 ; Soyombo # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA
11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11A9A..11A9C ; Soyombo # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
# Total code points: 80
# ================================================
11A00 ; Zanabazar_Square # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; Zanabazar_Square # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; Zanabazar_Square # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32 ; Zanabazar_Square # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A33..11A38 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; Zanabazar_Square # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3A ; Zanabazar_Square # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A3B..11A3E ; Zanabazar_Square # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A3F..11A46 ; Zanabazar_Square # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK
11A47 ; Zanabazar_Square # Mn ZANABAZAR SQUARE SUBJOINER
# Total code points: 72
# EOF

13
util/unicode/data/SpecialCasing.txt
View File

@ -1,10 +1,11 @@
# SpecialCasing-8.0.0.txt
# Date: 2014-12-16, 23:08:04 GMT [MD]
# SpecialCasing-10.0.0.txt
# Date: 2017-04-14, 05:40:43 GMT
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
# For documentation, see http://www.unicode.org/reports/tr44/
# For documentation, see http://www.unicode.org/reports/tr44/
#
# Special Casing
#
@ -196,7 +197,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
# ================================================================================
# Conditional Mappings
# The remainder of this file provides conditional casing data used to produce
# The remainder of this file provides conditional casing data used to produce
# full case mappings.
# ================================================================================
# Language-Insensitive Mappings

2411
util/unicode/data/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff

20
util/unicode/main.cpp
View File

@ -38,8 +38,8 @@
#include <private/qunicodetables_p.h>
#endif
#define DATA_VERSION_S "8.0"
#define DATA_VERSION_STR "QChar::Unicode_8_0"
#define DATA_VERSION_S "10.0"
#define DATA_VERSION_STR "QChar::Unicode_10_0"
static QHash<QByteArray, QChar::UnicodeVersion> age_map;
@ -67,6 +67,8 @@ static void initAgeMap()
{ QChar::Unicode_6_3, "6.3" },
{ QChar::Unicode_7_0, "7.0" },
{ QChar::Unicode_8_0, "8.0" },
{ QChar::Unicode_9_0, "9.0" },
{ QChar::Unicode_10_0, "10.0" },
{ QChar::Unicode_Unassigned, 0 }
};
AgeMap *d = ageMap;
@ -722,6 +724,20 @@ static void initScriptMap()
{ QChar::Script_Multani, "Multani" },
{ QChar::Script_OldHungarian, "OldHungarian" },
{ QChar::Script_SignWriting, "SignWriting" },
// 9.0
{ QChar::Script_Adlam, "Adlam" },
{ QChar::Script_Bhaiksuki, "Bhaiksuki" },
{ QChar::Script_Marchen, "Marchen" },
{ QChar::Script_Newa, "Newa" },
{ QChar::Script_Osage, "Osage" },
{ QChar::Script_Tangut, "Tangut" },
// 10.0
{ QChar::Script_MasaramGondi, "MasaramGondi" },
{ QChar::Script_Nushu, "Nushu" },
{ QChar::Script_Soyombo, "Soyombo" },
{ QChar::Script_ZanabazarSquare, "ZanabazarSquare" },
// unhandled
{ QChar::Script_Unknown, 0 }
};