walkero
/
pcre2
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Update Unicode tables to 8.0.0.

This commit is contained in:
Philip.Hazel 2015-07-17 15:44:51 +00:00
parent 7b4b853b81
commit d702527628
17 changed files with 5067 additions and 2634 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ChangeLog
View File

@ -43,6 +43,9 @@ possessive. This is a very minor optimization.
11. A possessively repeated conditional group that could match an empty string,
for example, /(?(R))*+/, was incorrectly compiled.
12. The Unicode tables have been updated to Unicode 8.0.0 (thanks to Christian
Persch).
Version 10.20 30-June-2015
--------------------------

6
doc/pcre2api.3
View File

@ -1,4 +1,4 @@
.TH PCRE2API 3 "22 April 2015" "PCRE2 10.20"
.TH PCRE2API 3 "17 July 2015" "PCRE2 10.21"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.sp
@ -905,7 +905,7 @@ The \fIwhere\fP argument should point to a buffer that is at least 24 code
units long. (The exact length required can be found by calling
\fBpcre2_config()\fP with \fBwhere\fP set to NULL.) If PCRE2 has been compiled
without Unicode support, the buffer is filled with the text "Unicode not
supported". Otherwise, the Unicode version string (for example, "7.0.0") is
supported". Otherwise, the Unicode version string (for example, "8.0.0") is
inserted. The number of code units used is returned. This is the length of the
string plus one unit for the terminating zero.
.sp
@ -2939,6 +2939,6 @@ Cambridge, England.
.rs
.sp
.nf
Last updated: 22 April 2015
Last updated: 17 July 2015
Copyright (c) 1997-2015 University of Cambridge.
.fi

10
doc/pcre2pattern.3
View File

@ -1,4 +1,4 @@
.TH PCRE2PATTERN 3 "13 June 2015" "PCRE2 10.20"
.TH PCRE2PATTERN 3 "17 July 2015" "PCRE2 10.21"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION DETAILS"
@ -738,6 +738,8 @@ example:
Those that are not part of an identified script are lumped together as
"Common". The current list of scripts is:
.P
Ahom,
Anatolian_Hieroglyphs,
Arabic,
Armenian,
Avestan,
@ -778,6 +780,7 @@ Gurmukhi,
Han,
Hangul,
Hanunoo,
Hatran,
Hebrew,
Hiragana,
Imperial_Aramaic,
@ -814,12 +817,14 @@ Miao,
Modi,
Mongolian,
Mro,
Multani,
Myanmar,
Nabataean,
New_Tai_Lue,
Nko,
Ogham,
Ol_Chiki,
Old_Hungarian,
Old_Italic,
Old_North_Arabian,
Old_Permic,
@ -841,6 +846,7 @@ Saurashtra,
Sharada,
Shavian,
Siddham,
SignWriting,
Sinhala,
Sora_Sompeng,
Sundanese,
@ -3361,6 +3367,6 @@ Cambridge, England.
.rs
.sp
.nf
Last updated: 13 June 2015
Last updated: 17 July 2015
Copyright (c) 1997-2015 University of Cambridge.
.fi

10
doc/pcre2syntax.3
View File

@ -1,4 +1,4 @@
.TH PCRE2SYNTAX 3 "13 June 2015" "PCRE2 10.20"
.TH PCRE2SYNTAX 3 "17 July 2015" "PCRE2 10.21"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@ -159,6 +159,8 @@ at release 5.18.
.SH "SCRIPT NAMES FOR \ep AND \eP"
.rs
.sp
Ahom,
Anatolian_Hieroglyphs,
Arabic,
Armenian,
Avestan,
@ -199,6 +201,7 @@ Gurmukhi,
Han,
Hangul,
Hanunoo,
Hatran,
Hebrew,
Hiragana,
Imperial_Aramaic,
@ -235,12 +238,14 @@ Miao,
Modi,
Mongolian,
Mro,
Multani,
Myanmar,
Nabataean,
New_Tai_Lue,
Nko,
Ogham,
Ol_Chiki,
Old_Hungarian,
Old_Italic,
Old_North_Arabian,
Old_Permic,
@ -262,6 +267,7 @@ Saurashtra,
Sharada,
Shavian,
Siddham,
SignWriting,
Sinhala,
Sora_Sompeng,
Sundanese,
@ -570,6 +576,6 @@ Cambridge, England.
.rs
.sp
.nf
Last updated: 13 June 2015
Last updated: 17 July 2015
Copyright (c) 1997-2015 University of Cambridge.
.fi

6
maint/GenerateUtt.py
View File

@ -22,6 +22,7 @@
# Comment modified by PH 13-May-2014 to update to PCRE2 file names.
# Script updated to Python 3 by running it through the 2to3 converter.
# Added script names for Unicode 7.0.0, 20-June-2014.
# Added script names for Unicode 8.0.0, 19-June-2015.
script_names = ['Arabic', 'Armenian', 'Bengali', 'Bopomofo', 'Braille', 'Buginese', 'Buhid', 'Canadian_Aboriginal', \
'Cherokee', 'Common', 'Coptic', 'Cypriot', 'Cyrillic', 'Deseret', 'Devanagari', 'Ethiopic', 'Georgian', \
@ -47,7 +48,10 @@ script_names = ['Arabic', 'Armenian', 'Bengali', 'Bopomofo', 'Braille', 'Bugines
'Bassa_Vah', 'Caucasian_Albanian', 'Duployan', 'Elbasan', 'Grantha', 'Khojki', 'Khudawadi',
'Linear_A', 'Mahajani', 'Manichaean', 'Mende_Kikakui', 'Modi', 'Mro', 'Nabataean',
'Old_North_Arabian', 'Old_Permic', 'Pahawh_Hmong', 'Palmyrene', 'Psalter_Pahlavi',
'Pau_Cin_Hau', 'Siddham', 'Tirhuta', 'Warang_Citi'
'Pau_Cin_Hau', 'Siddham', 'Tirhuta', 'Warang_Citi',
# New for Unicode 8.0.0
'Ahom', 'Anatolian_Hieroglyphs', 'Hatran', 'Multani', 'Old_Hungarian',
'SignWriting'
]
category_names = ['Cc', 'Cf', 'Cn', 'Co', 'Cs', 'Ll', 'Lm', 'Lo', 'Lt', 'Lu',

6
maint/MultiStage2.py
View File

@ -121,6 +121,7 @@
# 03-June-2014: Updated for Python 3
# 20-June-2014: Updated for Unicode 7.0.0
# 12-August-2014: Updated to put Unicode version into the file
# 19-June-2015: Updated for Unicode 8.0.0
##############################################################################
@ -330,7 +331,10 @@ script_names = ['Arabic', 'Armenian', 'Bengali', 'Bopomofo', 'Braille', 'Bugines
'Bassa_Vah', 'Caucasian_Albanian', 'Duployan', 'Elbasan', 'Grantha', 'Khojki', 'Khudawadi',
'Linear_A', 'Mahajani', 'Manichaean', 'Mende_Kikakui', 'Modi', 'Mro', 'Nabataean',
'Old_North_Arabian', 'Old_Permic', 'Pahawh_Hmong', 'Palmyrene', 'Psalter_Pahlavi',
'Pau_Cin_Hau', 'Siddham', 'Tirhuta', 'Warang_Citi'
'Pau_Cin_Hau', 'Siddham', 'Tirhuta', 'Warang_Citi',
# New for Unicode 8.0.0
'Ahom', 'Anatolian_Hieroglyphs', 'Hatran', 'Multani', 'Old_Hungarian',
'SignWriting'
]
category_names = ['Cc', 'Cf', 'Cn', 'Co', 'Cs', 'Ll', 'Lm', 'Lo', 'Lt', 'Lu',

147
maint/Unicode.tables/CaseFolding.txt
View File

@ -1,8 +1,8 @@
# CaseFolding-7.0.0.txt
# Date: 2014-04-09, 20:00:56 GMT [MD]
# CaseFolding-8.0.0.txt
# Date: 2015-01-13, 18:16:36 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# 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/
#
@ -587,6 +587,12 @@
10C5; C; 2D25; # GEORGIAN CAPITAL LETTER HOE
10C7; C; 2D27; # GEORGIAN CAPITAL LETTER YN
10CD; C; 2D2D; # GEORGIAN CAPITAL LETTER AEN
13F8; C; 13F0; # CHEROKEE SMALL LETTER YE
13F9; C; 13F1; # CHEROKEE SMALL LETTER YI
13FA; C; 13F2; # CHEROKEE SMALL LETTER YO
13FB; C; 13F3; # CHEROKEE SMALL LETTER YU
13FC; C; 13F4; # CHEROKEE SMALL LETTER YV
13FD; C; 13F5; # CHEROKEE SMALL LETTER MV
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
@ -1159,6 +1165,90 @@ A7AC; C; 0261; # LATIN CAPITAL LETTER SCRIPT G
A7AD; C; 026C; # LATIN CAPITAL LETTER L WITH BELT
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
A7B3; C; AB53; # LATIN CAPITAL LETTER CHI
A7B4; C; A7B5; # LATIN CAPITAL LETTER BETA
A7B6; C; A7B7; # LATIN CAPITAL LETTER OMEGA
AB70; C; 13A0; # CHEROKEE SMALL LETTER A
AB71; C; 13A1; # CHEROKEE SMALL LETTER E
AB72; C; 13A2; # CHEROKEE SMALL LETTER I
AB73; C; 13A3; # CHEROKEE SMALL LETTER O
AB74; C; 13A4; # CHEROKEE SMALL LETTER U
AB75; C; 13A5; # CHEROKEE SMALL LETTER V
AB76; C; 13A6; # CHEROKEE SMALL LETTER GA
AB77; C; 13A7; # CHEROKEE SMALL LETTER KA
AB78; C; 13A8; # CHEROKEE SMALL LETTER GE
AB79; C; 13A9; # CHEROKEE SMALL LETTER GI
AB7A; C; 13AA; # CHEROKEE SMALL LETTER GO
AB7B; C; 13AB; # CHEROKEE SMALL LETTER GU
AB7C; C; 13AC; # CHEROKEE SMALL LETTER GV
AB7D; C; 13AD; # CHEROKEE SMALL LETTER HA
AB7E; C; 13AE; # CHEROKEE SMALL LETTER HE
AB7F; C; 13AF; # CHEROKEE SMALL LETTER HI
AB80; C; 13B0; # CHEROKEE SMALL LETTER HO
AB81; C; 13B1; # CHEROKEE SMALL LETTER HU
AB82; C; 13B2; # CHEROKEE SMALL LETTER HV
AB83; C; 13B3; # CHEROKEE SMALL LETTER LA
AB84; C; 13B4; # CHEROKEE SMALL LETTER LE
AB85; C; 13B5; # CHEROKEE SMALL LETTER LI
AB86; C; 13B6; # CHEROKEE SMALL LETTER LO
AB87; C; 13B7; # CHEROKEE SMALL LETTER LU
AB88; C; 13B8; # CHEROKEE SMALL LETTER LV
AB89; C; 13B9; # CHEROKEE SMALL LETTER MA
AB8A; C; 13BA; # CHEROKEE SMALL LETTER ME
AB8B; C; 13BB; # CHEROKEE SMALL LETTER MI
AB8C; C; 13BC; # CHEROKEE SMALL LETTER MO
AB8D; C; 13BD; # CHEROKEE SMALL LETTER MU
AB8E; C; 13BE; # CHEROKEE SMALL LETTER NA
AB8F; C; 13BF; # CHEROKEE SMALL LETTER HNA
AB90; C; 13C0; # CHEROKEE SMALL LETTER NAH
AB91; C; 13C1; # CHEROKEE SMALL LETTER NE
AB92; C; 13C2; # CHEROKEE SMALL LETTER NI
AB93; C; 13C3; # CHEROKEE SMALL LETTER NO
AB94; C; 13C4; # CHEROKEE SMALL LETTER NU
AB95; C; 13C5; # CHEROKEE SMALL LETTER NV
AB96; C; 13C6; # CHEROKEE SMALL LETTER QUA
AB97; C; 13C7; # CHEROKEE SMALL LETTER QUE
AB98; C; 13C8; # CHEROKEE SMALL LETTER QUI
AB99; C; 13C9; # CHEROKEE SMALL LETTER QUO
AB9A; C; 13CA; # CHEROKEE SMALL LETTER QUU
AB9B; C; 13CB; # CHEROKEE SMALL LETTER QUV
AB9C; C; 13CC; # CHEROKEE SMALL LETTER SA
AB9D; C; 13CD; # CHEROKEE SMALL LETTER S
AB9E; C; 13CE; # CHEROKEE SMALL LETTER SE
AB9F; C; 13CF; # CHEROKEE SMALL LETTER SI
ABA0; C; 13D0; # CHEROKEE SMALL LETTER SO
ABA1; C; 13D1; # CHEROKEE SMALL LETTER SU
ABA2; C; 13D2; # CHEROKEE SMALL LETTER SV
ABA3; C; 13D3; # CHEROKEE SMALL LETTER DA
ABA4; C; 13D4; # CHEROKEE SMALL LETTER TA
ABA5; C; 13D5; # CHEROKEE SMALL LETTER DE
ABA6; C; 13D6; # CHEROKEE SMALL LETTER TE
ABA7; C; 13D7; # CHEROKEE SMALL LETTER DI
ABA8; C; 13D8; # CHEROKEE SMALL LETTER TI
ABA9; C; 13D9; # CHEROKEE SMALL LETTER DO
ABAA; C; 13DA; # CHEROKEE SMALL LETTER DU
ABAB; C; 13DB; # CHEROKEE SMALL LETTER DV
ABAC; C; 13DC; # CHEROKEE SMALL LETTER DLA
ABAD; C; 13DD; # CHEROKEE SMALL LETTER TLA
ABAE; C; 13DE; # CHEROKEE SMALL LETTER TLE
ABAF; C; 13DF; # CHEROKEE SMALL LETTER TLI
ABB0; C; 13E0; # CHEROKEE SMALL LETTER TLO
ABB1; C; 13E1; # CHEROKEE SMALL LETTER TLU
ABB2; C; 13E2; # CHEROKEE SMALL LETTER TLV
ABB3; C; 13E3; # CHEROKEE SMALL LETTER TSA
ABB4; C; 13E4; # CHEROKEE SMALL LETTER TSE
ABB5; C; 13E5; # CHEROKEE SMALL LETTER TSI
ABB6; C; 13E6; # CHEROKEE SMALL LETTER TSO
ABB7; C; 13E7; # CHEROKEE SMALL LETTER TSU
ABB8; C; 13E8; # CHEROKEE SMALL LETTER TSV
ABB9; C; 13E9; # CHEROKEE SMALL LETTER WA
ABBA; C; 13EA; # CHEROKEE SMALL LETTER WE
ABBB; C; 13EB; # CHEROKEE SMALL LETTER WI
ABBC; C; 13EC; # CHEROKEE SMALL LETTER WO
ABBD; C; 13ED; # CHEROKEE SMALL LETTER WU
ABBE; C; 13EE; # CHEROKEE SMALL LETTER WV
ABBF; C; 13EF; # CHEROKEE SMALL LETTER YA
FB00; F; 0066 0066; # LATIN SMALL LIGATURE FF
FB01; F; 0066 0069; # LATIN SMALL LIGATURE FI
FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL
@ -1237,6 +1327,57 @@ 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
10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A
10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA
10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB
10C83; C; 10CC3; # OLD HUNGARIAN CAPITAL LETTER AMB
10C84; C; 10CC4; # OLD HUNGARIAN CAPITAL LETTER EC
10C85; C; 10CC5; # OLD HUNGARIAN CAPITAL LETTER ENC
10C86; C; 10CC6; # OLD HUNGARIAN CAPITAL LETTER ECS
10C87; C; 10CC7; # OLD HUNGARIAN CAPITAL LETTER ED
10C88; C; 10CC8; # OLD HUNGARIAN CAPITAL LETTER AND
10C89; C; 10CC9; # OLD HUNGARIAN CAPITAL LETTER E
10C8A; C; 10CCA; # OLD HUNGARIAN CAPITAL LETTER CLOSE E
10C8B; C; 10CCB; # OLD HUNGARIAN CAPITAL LETTER EE
10C8C; C; 10CCC; # OLD HUNGARIAN CAPITAL LETTER EF
10C8D; C; 10CCD; # OLD HUNGARIAN CAPITAL LETTER EG
10C8E; C; 10CCE; # OLD HUNGARIAN CAPITAL LETTER EGY
10C8F; C; 10CCF; # OLD HUNGARIAN CAPITAL LETTER EH
10C90; C; 10CD0; # OLD HUNGARIAN CAPITAL LETTER I
10C91; C; 10CD1; # OLD HUNGARIAN CAPITAL LETTER II
10C92; C; 10CD2; # OLD HUNGARIAN CAPITAL LETTER EJ
10C93; C; 10CD3; # OLD HUNGARIAN CAPITAL LETTER EK
10C94; C; 10CD4; # OLD HUNGARIAN CAPITAL LETTER AK
10C95; C; 10CD5; # OLD HUNGARIAN CAPITAL LETTER UNK
10C96; C; 10CD6; # OLD HUNGARIAN CAPITAL LETTER EL
10C97; C; 10CD7; # OLD HUNGARIAN CAPITAL LETTER ELY
10C98; C; 10CD8; # OLD HUNGARIAN CAPITAL LETTER EM
10C99; C; 10CD9; # OLD HUNGARIAN CAPITAL LETTER EN
10C9A; C; 10CDA; # OLD HUNGARIAN CAPITAL LETTER ENY
10C9B; C; 10CDB; # OLD HUNGARIAN CAPITAL LETTER O
10C9C; C; 10CDC; # OLD HUNGARIAN CAPITAL LETTER OO
10C9D; C; 10CDD; # OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG OE
10C9E; C; 10CDE; # OLD HUNGARIAN CAPITAL LETTER RUDIMENTA OE
10C9F; C; 10CDF; # OLD HUNGARIAN CAPITAL LETTER OEE
10CA0; C; 10CE0; # OLD HUNGARIAN CAPITAL LETTER EP
10CA1; C; 10CE1; # OLD HUNGARIAN CAPITAL LETTER EMP
10CA2; C; 10CE2; # OLD HUNGARIAN CAPITAL LETTER ER
10CA3; C; 10CE3; # OLD HUNGARIAN CAPITAL LETTER SHORT ER
10CA4; C; 10CE4; # OLD HUNGARIAN CAPITAL LETTER ES
10CA5; C; 10CE5; # OLD HUNGARIAN CAPITAL LETTER ESZ
10CA6; C; 10CE6; # OLD HUNGARIAN CAPITAL LETTER ET
10CA7; C; 10CE7; # OLD HUNGARIAN CAPITAL LETTER ENT
10CA8; C; 10CE8; # OLD HUNGARIAN CAPITAL LETTER ETY
10CA9; C; 10CE9; # OLD HUNGARIAN CAPITAL LETTER ECH
10CAA; C; 10CEA; # OLD HUNGARIAN CAPITAL LETTER U
10CAB; C; 10CEB; # OLD HUNGARIAN CAPITAL LETTER UU
10CAC; C; 10CEC; # OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG UE
10CAD; C; 10CED; # OLD HUNGARIAN CAPITAL LETTER RUDIMENTA UE
10CAE; C; 10CEE; # OLD HUNGARIAN CAPITAL LETTER EV
10CAF; C; 10CEF; # OLD HUNGARIAN CAPITAL LETTER EZ
10CB0; C; 10CF0; # OLD HUNGARIAN CAPITAL LETTER EZS
10CB1; C; 10CF1; # OLD HUNGARIAN CAPITAL LETTER ENT-SHAPED SIGN
10CB2; C; 10CF2; # OLD HUNGARIAN CAPITAL LETTER US
118A0; C; 118C0; # WARANG CITI CAPITAL LETTER NGAA
118A1; C; 118C1; # WARANG CITI CAPITAL LETTER A
118A2; C; 118C2; # WARANG CITI CAPITAL LETTER WI

237
maint/Unicode.tables/DerivedGeneralCategory.txt
View File

@ -1,8 +1,8 @@
# DerivedGeneralCategory-7.0.0.txt
# Date: 2014-02-07, 18:42:12 GMT [MD]
# DerivedGeneralCategory-8.0.0.txt
# Date: 2015-02-13, 13:47:11 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# 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/
@ -37,7 +37,7 @@
083F ; Cn # <reserved-083F>
085C..085D ; Cn # [2] <reserved-085C>..<reserved-085D>
085F..089F ; Cn # [65] <reserved-085F>..<reserved-089F>
08B3..08E3 ; Cn # [49] <reserved-08B3>..<reserved-08E3>
08B5..08E2 ; Cn # [46] <reserved-08B5>..<reserved-08E2>
0984 ; Cn # <reserved-0984>
098D..098E ; Cn # [2] <reserved-098D>..<reserved-098E>
0991..0992 ; Cn # [2] <reserved-0991>..<reserved-0992>
@ -80,7 +80,8 @@
0ACE..0ACF ; Cn # [2] <reserved-0ACE>..<reserved-0ACF>
0AD1..0ADF ; Cn # [15] <reserved-0AD1>..<reserved-0ADF>
0AE4..0AE5 ; Cn # [2] <reserved-0AE4>..<reserved-0AE5>
0AF2..0B00 ; Cn # [15] <reserved-0AF2>..<reserved-0B00>
0AF2..0AF8 ; Cn # [7] <reserved-0AF2>..<reserved-0AF8>
0AFA..0B00 ; Cn # [7] <reserved-0AFA>..<reserved-0B00>
0B04 ; Cn # <reserved-0B04>
0B0D..0B0E ; Cn # [2] <reserved-0B0D>..<reserved-0B0E>
0B11..0B12 ; Cn # [2] <reserved-0B11>..<reserved-0B12>
@ -120,7 +121,7 @@
0C49 ; Cn # <reserved-0C49>
0C4E..0C54 ; Cn # [7] <reserved-0C4E>..<reserved-0C54>
0C57 ; Cn # <reserved-0C57>
0C5A..0C5F ; Cn # [6] <reserved-0C5A>..<reserved-0C5F>
0C5B..0C5F ; Cn # [5] <reserved-0C5B>..<reserved-0C5F>
0C64..0C65 ; Cn # [2] <reserved-0C64>..<reserved-0C65>
0C70..0C77 ; Cn # [8] <reserved-0C70>..<reserved-0C77>
0C80 ; Cn # <reserved-0C80>
@ -145,7 +146,7 @@
0D45 ; Cn # <reserved-0D45>
0D49 ; Cn # <reserved-0D49>
0D4F..0D56 ; Cn # [8] <reserved-0D4F>..<reserved-0D56>
0D58..0D5F ; Cn # [8] <reserved-0D58>..<reserved-0D5F>
0D58..0D5E ; Cn # [7] <reserved-0D58>..<reserved-0D5E>
0D64..0D65 ; Cn # [2] <reserved-0D64>..<reserved-0D65>
0D76..0D78 ; Cn # [3] <reserved-0D76>..<reserved-0D78>
0D80..0D81 ; Cn # [2] <reserved-0D80>..<reserved-0D81>
@ -208,7 +209,8 @@
135B..135C ; Cn # [2] <reserved-135B>..<reserved-135C>
137D..137F ; Cn # [3] <reserved-137D>..<reserved-137F>
139A..139F ; Cn # [6] <reserved-139A>..<reserved-139F>
13F5..13FF ; Cn # [11] <reserved-13F5>..<reserved-13FF>
13F6..13F7 ; Cn # [2] <reserved-13F6>..<reserved-13F7>
13FE..13FF ; Cn # [2] <reserved-13FE>..<reserved-13FF>
169D..169F ; Cn # [3] <reserved-169D>..<reserved-169F>
16F9..16FF ; Cn # [7] <reserved-16F9>..<reserved-16FF>
170D ; Cn # <reserved-170D>
@ -272,9 +274,9 @@
2072..2073 ; Cn # [2] <reserved-2072>..<reserved-2073>
208F ; Cn # <reserved-208F>
209D..209F ; Cn # [3] <reserved-209D>..<reserved-209F>
20BE..20CF ; Cn # [18] <reserved-20BE>..<reserved-20CF>
20BF..20CF ; Cn # [17] <reserved-20BF>..<reserved-20CF>
20F1..20FF ; Cn # [15] <reserved-20F1>..<reserved-20FF>
218A..218F ; Cn # [6] <reserved-218A>..<reserved-218F>
218C..218F ; Cn # [4] <reserved-218C>..<reserved-218F>
23FB..23FF ; Cn # [5] <reserved-23FB>..<reserved-23FF>
2427..243F ; Cn # [25] <reserved-2427>..<reserved-243F>
244B..245F ; Cn # [21] <reserved-244B>..<reserved-245F>
@ -282,7 +284,8 @@
2B96..2B97 ; Cn # [2] <reserved-2B96>..<reserved-2B97>
2BBA..2BBC ; Cn # [3] <reserved-2BBA>..<reserved-2BBC>
2BC9 ; Cn # <reserved-2BC9>
2BD2..2BFF ; Cn # [46] <reserved-2BD2>..<reserved-2BFF>
2BD2..2BEB ; Cn # [26] <reserved-2BD2>..<reserved-2BEB>
2BF0..2BFF ; Cn # [16] <reserved-2BF0>..<reserved-2BFF>
2C2F ; Cn # <reserved-2C2F>
2C5F ; Cn # <reserved-2C5F>
2CF4..2CF8 ; Cn # [5] <reserved-2CF4>..<reserved-2CF8>
@ -315,21 +318,19 @@
321F ; Cn # <reserved-321F>
32FF ; Cn # <reserved-32FF>
4DB6..4DBF ; Cn # [10] <reserved-4DB6>..<reserved-4DBF>
9FCD..9FFF ; Cn # [51] <reserved-9FCD>..<reserved-9FFF>
9FD6..9FFF ; Cn # [42] <reserved-9FD6>..<reserved-9FFF>
A48D..A48F ; Cn # [3] <reserved-A48D>..<reserved-A48F>
A4C7..A4CF ; Cn # [9] <reserved-A4C7>..<reserved-A4CF>
A62C..A63F ; Cn # [20] <reserved-A62C>..<reserved-A63F>
A69E ; Cn # <reserved-A69E>
A6F8..A6FF ; Cn # [8] <reserved-A6F8>..<reserved-A6FF>
A78F ; Cn # <reserved-A78F>
A7AE..A7AF ; Cn # [2] <reserved-A7AE>..<reserved-A7AF>
A7B2..A7F6 ; Cn # [69] <reserved-A7B2>..<reserved-A7F6>
A7B8..A7F6 ; Cn # [63] <reserved-A7B8>..<reserved-A7F6>
A82C..A82F ; Cn # [4] <reserved-A82C>..<reserved-A82F>
A83A..A83F ; Cn # [6] <reserved-A83A>..<reserved-A83F>
A878..A87F ; Cn # [8] <reserved-A878>..<reserved-A87F>
A8C5..A8CD ; Cn # [9] <reserved-A8C5>..<reserved-A8CD>
A8DA..A8DF ; Cn # [6] <reserved-A8DA>..<reserved-A8DF>
A8FC..A8FF ; Cn # [4] <reserved-A8FC>..<reserved-A8FF>
A8FE..A8FF ; Cn # [2] <reserved-A8FE>..<reserved-A8FF>
A954..A95E ; Cn # [11] <reserved-A954>..<reserved-A95E>
A97D..A97F ; Cn # [3] <reserved-A97D>..<reserved-A97F>
A9CE ; Cn # <reserved-A9CE>
@ -345,8 +346,7 @@ AB0F..AB10 ; Cn # [2] <reserved-AB0F>..<reserved-AB10>
AB17..AB1F ; Cn # [9] <reserved-AB17>..<reserved-AB1F>
AB27 ; Cn # <reserved-AB27>
AB2F ; Cn # <reserved-AB2F>
AB60..AB63 ; Cn # [4] <reserved-AB60>..<reserved-AB63>
AB66..ABBF ; Cn # [90] <reserved-AB66>..<reserved-ABBF>
AB66..AB6F ; Cn # [10] <reserved-AB66>..<reserved-AB6F>
ABEE..ABEF ; Cn # [2] <reserved-ABEE>..<reserved-ABEF>
ABFA..ABFF ; Cn # [6] <reserved-ABFA>..<reserved-ABFF>
D7A4..D7AF ; Cn # [12] <reserved-D7A4>..<reserved-D7AF>
@ -367,7 +367,6 @@ FD90..FD91 ; Cn # [2] <reserved-FD90>..<reserved-FD91>
FDC8..FDEF ; Cn # [40] <reserved-FDC8>..<noncharacter-FDEF>
FDFE..FDFF ; Cn # [2] <reserved-FDFE>..<reserved-FDFF>
FE1A..FE1F ; Cn # [6] <reserved-FE1A>..<reserved-FE1F>
FE2E..FE2F ; Cn # [2] <reserved-FE2E>..<reserved-FE2F>
FE53 ; Cn # <reserved-FE53>
FE67 ; Cn # <reserved-FE67>
FE6C..FE6F ; Cn # [4] <reserved-FE6C>..<reserved-FE6F>
@ -419,12 +418,14 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
1083D..1083E ; Cn # [2] <reserved-1083D>..<reserved-1083E>
10856 ; Cn # <reserved-10856>
1089F..108A6 ; Cn # [8] <reserved-1089F>..<reserved-108A6>
108B0..108FF ; Cn # [80] <reserved-108B0>..<reserved-108FF>
108B0..108DF ; Cn # [48] <reserved-108B0>..<reserved-108DF>
108F3 ; Cn # <reserved-108F3>
108F6..108FA ; Cn # [5] <reserved-108F6>..<reserved-108FA>
1091C..1091E ; Cn # [3] <reserved-1091C>..<reserved-1091E>
1093A..1093E ; Cn # [5] <reserved-1093A>..<reserved-1093E>
10940..1097F ; Cn # [64] <reserved-10940>..<reserved-1097F>
109B8..109BD ; Cn # [6] <reserved-109B8>..<reserved-109BD>
109C0..109FF ; Cn # [64] <reserved-109C0>..<reserved-109FF>
109B8..109BB ; Cn # [4] <reserved-109B8>..<reserved-109BB>
109D0..109D1 ; Cn # [2] <reserved-109D0>..<reserved-109D1>
10A04 ; Cn # <reserved-10A04>
10A07..10A0B ; Cn # [5] <reserved-10A07>..<reserved-10A0B>
10A14 ; Cn # <reserved-10A14>
@ -442,7 +443,10 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
10B92..10B98 ; Cn # [7] <reserved-10B92>..<reserved-10B98>
10B9D..10BA8 ; Cn # [12] <reserved-10B9D>..<reserved-10BA8>
10BB0..10BFF ; Cn # [80] <reserved-10BB0>..<reserved-10BFF>
10C49..10E5F ; Cn # [535] <reserved-10C49>..<reserved-10E5F>
10C49..10C7F ; Cn # [55] <reserved-10C49>..<reserved-10C7F>
10CB3..10CBF ; Cn # [13] <reserved-10CB3>..<reserved-10CBF>
10CF3..10CF9 ; Cn # [7] <reserved-10CF3>..<reserved-10CF9>
10D00..10E5F ; Cn # [352] <reserved-10D00>..<reserved-10E5F>
10E7F..10FFF ; Cn # [385] <reserved-10E7F>..<reserved-10FFF>
1104E..11051 ; Cn # [4] <reserved-1104E>..<reserved-11051>
11070..1107E ; Cn # [15] <reserved-11070>..<reserved-1107E>
@ -452,14 +456,18 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
11135 ; Cn # <reserved-11135>
11144..1114F ; Cn # [12] <reserved-11144>..<reserved-1114F>
11177..1117F ; Cn # [9] <reserved-11177>..<reserved-1117F>
111C9..111CC ; Cn # [4] <reserved-111C9>..<reserved-111CC>
111CE..111CF ; Cn # [2] <reserved-111CE>..<reserved-111CF>
111DB..111E0 ; Cn # [6] <reserved-111DB>..<reserved-111E0>
111E0 ; Cn # <reserved-111E0>
111F5..111FF ; Cn # [11] <reserved-111F5>..<reserved-111FF>
11212 ; Cn # <reserved-11212>
1123E..112AF ; Cn # [114] <reserved-1123E>..<reserved-112AF>
1123E..1127F ; Cn # [66] <reserved-1123E>..<reserved-1127F>
11287 ; Cn # <reserved-11287>
11289 ; Cn # <reserved-11289>
1128E ; Cn # <reserved-1128E>
1129E ; Cn # <reserved-1129E>
112AA..112AF ; Cn # [6] <reserved-112AA>..<reserved-112AF>
112EB..112EF ; Cn # [5] <reserved-112EB>..<reserved-112EF>
112FA..11300 ; Cn # [7] <reserved-112FA>..<reserved-11300>
112FA..112FF ; Cn # [6] <reserved-112FA>..<reserved-112FF>
11304 ; Cn # <reserved-11304>
1130D..1130E ; Cn # [2] <reserved-1130D>..<reserved-1130E>
11311..11312 ; Cn # [2] <reserved-11311>..<reserved-11312>
@ -469,7 +477,8 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
1133A..1133B ; Cn # [2] <reserved-1133A>..<reserved-1133B>
11345..11346 ; Cn # [2] <reserved-11345>..<reserved-11346>
11349..1134A ; Cn # [2] <reserved-11349>..<reserved-1134A>
1134E..11356 ; Cn # [9] <reserved-1134E>..<reserved-11356>
1134E..1134F ; Cn # [2] <reserved-1134E>..<reserved-1134F>
11351..11356 ; Cn # [6] <reserved-11351>..<reserved-11356>
11358..1135C ; Cn # [5] <reserved-11358>..<reserved-1135C>
11364..11365 ; Cn # [2] <reserved-11364>..<reserved-11365>
1136D..1136F ; Cn # [3] <reserved-1136D>..<reserved-1136F>
@ -477,18 +486,23 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
114C8..114CF ; Cn # [8] <reserved-114C8>..<reserved-114CF>
114DA..1157F ; Cn # [166] <reserved-114DA>..<reserved-1157F>
115B6..115B7 ; Cn # [2] <reserved-115B6>..<reserved-115B7>
115CA..115FF ; Cn # [54] <reserved-115CA>..<reserved-115FF>
115DE..115FF ; Cn # [34] <reserved-115DE>..<reserved-115FF>
11645..1164F ; Cn # [11] <reserved-11645>..<reserved-1164F>
1165A..1167F ; Cn # [38] <reserved-1165A>..<reserved-1167F>
116B8..116BF ; Cn # [8] <reserved-116B8>..<reserved-116BF>
116CA..1189F ; Cn # [470] <reserved-116CA>..<reserved-1189F>
116CA..116FF ; Cn # [54] <reserved-116CA>..<reserved-116FF>
1171A..1171C ; Cn # [3] <reserved-1171A>..<reserved-1171C>
1172C..1172F ; Cn # [4] <reserved-1172C>..<reserved-1172F>
11740..1189F ; Cn # [352] <reserved-11740>..<reserved-1189F>
118F3..118FE ; Cn # [12] <reserved-118F3>..<reserved-118FE>
11900..11ABF ; Cn # [448] <reserved-11900>..<reserved-11ABF>
11AF9..11FFF ; Cn # [1287] <reserved-11AF9>..<reserved-11FFF>
12399..123FF ; Cn # [103] <reserved-12399>..<reserved-123FF>
1239A..123FF ; Cn # [102] <reserved-1239A>..<reserved-123FF>
1246F ; Cn # <reserved-1246F>
12475..12FFF ; Cn # [2955] <reserved-12475>..<reserved-12FFF>
1342F..167FF ; Cn # [13265] <reserved-1342F>..<reserved-167FF>
12475..1247F ; Cn # [11] <reserved-12475>..<reserved-1247F>
12544..12FFF ; Cn # [2748] <reserved-12544>..<reserved-12FFF>
1342F..143FF ; Cn # [4049] <reserved-1342F>..<reserved-143FF>
14647..167FF ; Cn # [8633] <reserved-14647>..<reserved-167FF>
16A39..16A3F ; Cn # [7] <reserved-16A39>..<reserved-16A3F>
16A5F ; Cn # <reserved-16A5F>
16A6A..16A6D ; Cn # [4] <reserved-16A6A>..<reserved-16A6D>
@ -511,7 +525,7 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
1BCA4..1CFFF ; Cn # [4956] <reserved-1BCA4>..<reserved-1CFFF>
1D0F6..1D0FF ; Cn # [10] <reserved-1D0F6>..<reserved-1D0FF>
1D127..1D128 ; Cn # [2] <reserved-1D127>..<reserved-1D128>
1D1DE..1D1FF ; Cn # [34] <reserved-1D1DE>..<reserved-1D1FF>
1D1E9..1D1FF ; Cn # [23] <reserved-1D1E9>..<reserved-1D1FF>
1D246..1D2FF ; Cn # [186] <reserved-1D246>..<reserved-1D2FF>
1D357..1D35F ; Cn # [9] <reserved-1D357>..<reserved-1D35F>
1D372..1D3FF ; Cn # [142] <reserved-1D372>..<reserved-1D3FF>
@ -535,7 +549,9 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
1D551 ; Cn # <reserved-1D551>
1D6A6..1D6A7 ; Cn # [2] <reserved-1D6A6>..<reserved-1D6A7>
1D7CC..1D7CD ; Cn # [2] <reserved-1D7CC>..<reserved-1D7CD>
1D800..1E7FF ; Cn # [4096] <reserved-1D800>..<reserved-1E7FF>
1DA8C..1DA9A ; Cn # [15] <reserved-1DA8C>..<reserved-1DA9A>
1DAA0 ; Cn # <reserved-1DAA0>
1DAB0..1E7FF ; Cn # [3408] <reserved-1DAB0>..<reserved-1E7FF>
1E8C5..1E8C6 ; Cn # [2] <reserved-1E8C5>..<reserved-1E8C6>
1E8D7..1EDFF ; Cn # [1321] <reserved-1E8D7>..<reserved-1EDFF>
1EE04 ; Cn # <reserved-1EE04>
@ -586,16 +602,9 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
1F23B..1F23F ; Cn # [5] <reserved-1F23B>..<reserved-1F23F>
1F249..1F24F ; Cn # [7] <reserved-1F249>..<reserved-1F24F>
1F252..1F2FF ; Cn # [174] <reserved-1F252>..<reserved-1F2FF>
1F32D..1F32F ; Cn # [3] <reserved-1F32D>..<reserved-1F32F>
1F37E..1F37F ; Cn # [2] <reserved-1F37E>..<reserved-1F37F>
1F3CF..1F3D3 ; Cn # [5] <reserved-1F3CF>..<reserved-1F3D3>
1F3F8..1F3FF ; Cn # [8] <reserved-1F3F8>..<reserved-1F3FF>
1F4FF ; Cn # <reserved-1F4FF>
1F54B..1F54F ; Cn # [5] <reserved-1F54B>..<reserved-1F54F>
1F57A ; Cn # <reserved-1F57A>
1F5A4 ; Cn # <reserved-1F5A4>
1F643..1F644 ; Cn # [2] <reserved-1F643>..<reserved-1F644>
1F6D0..1F6DF ; Cn # [16] <reserved-1F6D0>..<reserved-1F6DF>
1F6D1..1F6DF ; Cn # [15] <reserved-1F6D1>..<reserved-1F6DF>
1F6ED..1F6EF ; Cn # [3] <reserved-1F6ED>..<reserved-1F6EF>
1F6F4..1F6FF ; Cn # [12] <reserved-1F6F4>..<reserved-1F6FF>
1F774..1F77F ; Cn # [12] <reserved-1F774>..<reserved-1F77F>
@ -604,10 +613,14 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF>
1F848..1F84F ; Cn # [8] <reserved-1F848>..<reserved-1F84F>
1F85A..1F85F ; Cn # [6] <reserved-1F85A>..<reserved-1F85F>
1F888..1F88F ; Cn # [8] <reserved-1F888>..<reserved-1F88F>
1F8AE..1FFFF ; Cn # [1874] <reserved-1F8AE>..<noncharacter-1FFFF>
1F8AE..1F90F ; Cn # [98] <reserved-1F8AE>..<reserved-1F90F>
1F919..1F97F ; Cn # [103] <reserved-1F919>..<reserved-1F97F>
1F985..1F9BF ; Cn # [59] <reserved-1F985>..<reserved-1F9BF>
1F9C1..1FFFF ; Cn # [1599] <reserved-1F9C1>..<noncharacter-1FFFF>
2A6D7..2A6FF ; Cn # [41] <reserved-2A6D7>..<reserved-2A6FF>
2B735..2B73F ; Cn # [11] <reserved-2B735>..<reserved-2B73F>
2B81E..2F7FF ; Cn # [16354] <reserved-2B81E>..<reserved-2F7FF>
2B81E..2B81F ; Cn # [2] <reserved-2B81E>..<reserved-2B81F>
2CEA2..2F7FF ; Cn # [10590] <reserved-2CEA2>..<reserved-2F7FF>
2FA1E..E0000 ; Cn # [722403] <reserved-2FA1E>..<reserved-E0000>
E0002..E001F ; Cn # [30] <reserved-E0002>..<reserved-E001F>
E0080..E00FF ; Cn # [128] <reserved-E0080>..<reserved-E00FF>
@ -615,7 +628,7 @@ 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: 861575
# Total code points: 853859
# ================================================
@ -896,6 +909,7 @@ FFFFE..FFFFF ; Cn # [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
10A0..10C5 ; Lu # [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10C7 ; Lu # GEORGIAN CAPITAL LETTER YN
10CD ; Lu # GEORGIAN CAPITAL LETTER AEN
13A0..13F5 ; Lu # [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
1E00 ; Lu # LATIN CAPITAL LETTER A WITH RING BELOW
1E02 ; Lu # LATIN CAPITAL LETTER B WITH DOT ABOVE
1E04 ; Lu # LATIN CAPITAL LETTER B WITH DOT BELOW
@ -1208,9 +1222,11 @@ A7A4 ; Lu # LATIN CAPITAL LETTER N WITH OBLIQUE STROKE
A7A6 ; Lu # LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
A7A8 ; Lu # LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
A7AA..A7AD ; Lu # [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT
A7B0..A7B1 ; Lu # [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
A7B0..A7B4 ; Lu # [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA
A7B6 ; Lu # LATIN CAPITAL LETTER OMEGA
FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z
10400..10427 ; Lu # [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW
10C80..10CB2 ; Lu # [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
118A0..118BF ; Lu # [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO
1D400..1D419 ; Lu # [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z
1D434..1D44D ; Lu # [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z
@ -1244,7 +1260,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP
1D790..1D7A8 ; Lu # [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA
1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA
# Total code points: 1490
# Total code points: 1631
# ================================================
@ -1520,6 +1536,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP
052D ; Ll # CYRILLIC SMALL LETTER DCHE
052F ; Ll # CYRILLIC SMALL LETTER EL WITH DESCENDER
0561..0587 ; Ll # [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN
13F8..13FD ; Ll # [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
1D00..1D2B ; Ll # [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D6B..1D77 ; Ll # [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
1D79..1D9A ; Ll # [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
@ -1839,13 +1856,17 @@ A7A3 ; Ll # LATIN SMALL LETTER K WITH OBLIQUE STROKE
A7A5 ; Ll # LATIN SMALL LETTER N WITH OBLIQUE STROKE
A7A7 ; Ll # LATIN SMALL LETTER R WITH OBLIQUE STROKE
A7A9 ; Ll # LATIN SMALL LETTER S WITH OBLIQUE STROKE
A7B5 ; Ll # LATIN SMALL LETTER BETA
A7B7 ; Ll # LATIN SMALL LETTER OMEGA
A7FA ; Ll # LATIN LETTER SMALL CAPITAL TURNED M
AB30..AB5A ; Ll # [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
AB64..AB65 ; Ll # [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA
AB60..AB65 ; Ll # [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA
AB70..ABBF ; Ll # [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
FB00..FB06 ; Ll # [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
FB13..FB17 ; Ll # [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z
10428..1044F ; Ll # [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW
10CC0..10CF2 ; Ll # [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
118C0..118DF ; Ll # [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
1D41A..1D433 ; Ll # [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z
1D44E..1D454 ; Ll # [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G
@ -1876,7 +1897,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL
1D7C4..1D7C9 ; Ll # [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL
1D7CB ; Ll # MATHEMATICAL BOLD SMALL DIGAMMA
# Total code points: 1841
# Total code points: 1984
# ================================================
@ -1984,7 +2005,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
07CA..07EA ; Lo # [33] NKO LETTER A..NKO LETTER JONA RA
0800..0815 ; Lo # [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF
0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
08A0..08B2 ; Lo # [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
08A0..08B4 ; Lo # [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
0904..0939 ; Lo # [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
093D ; Lo # DEVANAGARI SIGN AVAGRAHA
0950 ; Lo # DEVANAGARI OM
@ -2020,6 +2041,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
0ABD ; Lo # GUJARATI SIGN AVAGRAHA
0AD0 ; Lo # GUJARATI OM
0AE0..0AE1 ; Lo # [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
0AF9 ; Lo # GUJARATI LETTER ZHA
0B05..0B0C ; Lo # [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
0B0F..0B10 ; Lo # [2] ORIYA LETTER E..ORIYA LETTER AI
0B13..0B28 ; Lo # [22] ORIYA LETTER O..ORIYA LETTER NA
@ -2046,7 +2068,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
0C12..0C28 ; Lo # [23] TELUGU LETTER O..TELUGU LETTER NA
0C2A..0C39 ; Lo # [16] TELUGU LETTER PA..TELUGU LETTER HA
0C3D ; Lo # TELUGU SIGN AVAGRAHA
0C58..0C59 ; Lo # [2] TELUGU LETTER TSA..TELUGU LETTER DZA
0C58..0C5A ; Lo # [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
0C60..0C61 ; Lo # [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
0C85..0C8C ; Lo # [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L
0C8E..0C90 ; Lo # [3] KANNADA LETTER E..KANNADA LETTER AI
@ -2062,7 +2084,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
0D12..0D3A ; Lo # [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3D ; Lo # MALAYALAM SIGN AVAGRAHA
0D4E ; Lo # MALAYALAM LETTER DOT REPH
0D60..0D61 ; Lo # [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
0D5F..0D61 ; Lo # [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL
0D7A..0D7F ; Lo # [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
0D85..0D96 ; Lo # [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA
0D9A..0DB1 ; Lo # [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA
@ -2119,7 +2141,6 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
1312..1315 ; Lo # [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE
1318..135A ; Lo # [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA
1380..138F ; Lo # [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE
13A0..13F4 ; Lo # [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
1401..166C ; Lo # [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA
166F..167F ; Lo # [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W
1681..169A ; Lo # [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH
@ -2142,7 +2163,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
1950..196D ; Lo # [30] TAI LE LETTER KA..TAI LE LETTER AI
1970..1974 ; Lo # [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6
1980..19AB ; Lo # [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
19C1..19C7 ; Lo # [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
19B0..19C9 ; Lo # [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
1A00..1A16 ; Lo # [23] BUGINESE LETTER KA..BUGINESE LETTER HA
1A20..1A54 ; Lo # [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA
1B05..1B33 ; Lo # [47] BALINESE LETTER AKARA..BALINESE LETTER HA
@ -2178,7 +2199,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
31A0..31BA ; Lo # [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; Lo # [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; Lo # [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FCC ; Lo # [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
4E00..9FD5 ; Lo # [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
A000..A014 ; Lo # [21] YI SYLLABLE IT..YI SYLLABLE E
A016..A48C ; Lo # [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
A4D0..A4F7 ; Lo # [40] LISU LETTER BA..LISU LETTER OE
@ -2187,6 +2208,7 @@ A610..A61F ; Lo # [16] VAI SYLLABLE NDOLE FA..VAI SYMBOL JONG
A62A..A62B ; Lo # [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO
A66E ; Lo # CYRILLIC LETTER MULTIOCULAR O
A6A0..A6E5 ; Lo # [70] BAMUM LETTER A..BAMUM LETTER KI
A78F ; Lo # LATIN LETTER SINOLOGICAL DOT
A7F7 ; Lo # LATIN EPIGRAPHIC LETTER SIDEWAYS I
A7FB..A801 ; Lo # [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I
A803..A805 ; Lo # [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O
@ -2196,6 +2218,7 @@ A840..A873 ; Lo # [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABINDU
A882..A8B3 ; Lo # [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA
A8F2..A8F7 ; Lo # [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
A8FB ; Lo # DEVANAGARI HEADSTROKE
A8FD ; Lo # DEVANAGARI JAIN OM
A90A..A925 ; Lo # [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO
A930..A946 ; Lo # [23] REJANG LETTER KA..REJANG LETTER A
A960..A97C ; Lo # [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH
@ -2280,6 +2303,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
1083F..10855 ; Lo # [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW
10860..10876 ; Lo # [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW
10880..1089E ; Lo # [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
108E0..108F2 ; Lo # [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
108F4..108F5 ; Lo # [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
10900..10915 ; Lo # [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
10920..10939 ; Lo # [26] LYDIAN LETTER A..LYDIAN LETTER C
10980..109B7 ; Lo # [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
@ -2306,8 +2331,14 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
11183..111B2 ; Lo # [48] SHARADA LETTER A..SHARADA LETTER HA
111C1..111C4 ; Lo # [4] SHARADA SIGN AVAGRAHA..SHARADA OM
111DA ; Lo # SHARADA EKAM
111DC ; Lo # SHARADA HEADSTROKE
11200..11211 ; Lo # [18] KHOJKI LETTER A..KHOJKI LETTER JJA
11213..1122B ; Lo # [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
11280..11286 ; Lo # [7] MULTANI LETTER A..MULTANI LETTER GA
11288 ; Lo # MULTANI LETTER GHA
1128A..1128D ; Lo # [4] MULTANI LETTER CA..MULTANI LETTER JJA
1128F..1129D ; Lo # [15] MULTANI LETTER NYA..MULTANI LETTER BA
1129F..112A8 ; Lo # [10] MULTANI LETTER BHA..MULTANI LETTER RHA
112B0..112DE ; Lo # [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA
11305..1130C ; Lo # [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
1130F..11310 ; Lo # [2] GRANTHA LETTER EE..GRANTHA LETTER AI
@ -2316,18 +2347,23 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
11332..11333 ; Lo # [2] GRANTHA LETTER LA..GRANTHA LETTER LLA
11335..11339 ; Lo # [5] GRANTHA LETTER VA..GRANTHA LETTER HA
1133D ; Lo # GRANTHA SIGN AVAGRAHA
11350 ; Lo # GRANTHA OM
1135D..11361 ; Lo # [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
11480..114AF ; Lo # [48] TIRHUTA ANJI..TIRHUTA LETTER HA
114C4..114C5 ; Lo # [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG
114C7 ; Lo # TIRHUTA OM
11580..115AE ; Lo # [47] SIDDHAM LETTER A..SIDDHAM LETTER HA
115D8..115DB ; Lo # [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
11600..1162F ; Lo # [48] MODI LETTER A..MODI LETTER LLA
11644 ; Lo # MODI SIGN HUVA
11680..116AA ; Lo # [43] TAKRI LETTER A..TAKRI LETTER RRA
11700..11719 ; Lo # [26] AHOM LETTER KA..AHOM LETTER JHA
118FF ; Lo # WARANG CITI OM
11AC0..11AF8 ; Lo # [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
12000..12398 ; Lo # [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
12000..12399 ; Lo # [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12480..12543 ; Lo # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
13000..1342E ; Lo # [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
14400..14646 ; Lo # [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
16800..16A38 ; Lo # [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
16A40..16A5E ; Lo # [31] MRO LETTER TA..MRO LETTER TEK
16AD0..16AED ; Lo # [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I
@ -2378,9 +2414,10 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
20000..2A6D6 ; Lo # [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Lo # [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Lo # [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Lo # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2F800..2FA1D ; Lo # [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 99115
# Total code points: 105697
# ================================================
@ -2409,7 +2446,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
0825..0827 ; Mn # [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082D ; Mn # [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0859..085B ; Mn # [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
08E4..0902 ; Mn # [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
08E3..0902 ; Mn # [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
093A ; Mn # DEVANAGARI VOWEL SIGN OE
093C ; Mn # DEVANAGARI SIGN NUKTA
0941..0948 ; Mn # [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
@ -2552,7 +2589,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
3099..309A ; Mn # [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
A66F ; Mn # COMBINING CYRILLIC VZMET
A674..A67D ; Mn # [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
A69F ; Mn # COMBINING CYRILLIC LETTER IOTIFIED E
A69E..A69F ; Mn # [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
A6F0..A6F1 ; Mn # [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
A802 ; Mn # SYLOTI NAGRI SIGN DVISVARA
A806 ; Mn # SYLOTI NAGRI SIGN HASANTA
@ -2585,7 +2622,7 @@ ABE8 ; Mn # MEETEI MAYEK VOWEL SIGN UNAP
ABED ; Mn # MEETEI MAYEK APUN IYEK
FB1E ; Mn # HEBREW POINT JUDEO-SPANISH VARIKA
FE00..FE0F ; Mn # [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE2D ; Mn # [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
101FD ; Mn # PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
102E0 ; Mn # COPTIC EPACT THOUSANDS MARK
10376..1037A ; Mn # [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII
@ -2606,12 +2643,13 @@ FE20..FE2D ; Mn # [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MA
11173 ; Mn # MAHAJANI SIGN NUKTA
11180..11181 ; Mn # [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
111B6..111BE ; Mn # [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111CA..111CC ; Mn # [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
1122F..11231 ; Mn # [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
11234 ; Mn # KHOJKI SIGN ANUSVARA
11236..11237 ; Mn # [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
112DF ; Mn # KHUDAWADI SIGN ANUSVARA
112E3..112EA ; Mn # [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
11301 ; Mn # GRANTHA SIGN CANDRABINDU
11300..11301 ; Mn # [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
1133C ; Mn # GRANTHA SIGN NUKTA
11340 ; Mn # GRANTHA VOWEL SIGN II
11366..1136C ; Mn # [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
@ -2623,6 +2661,7 @@ FE20..FE2D ; Mn # [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MA
115B2..115B5 ; Mn # [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR
115BC..115BD ; Mn # [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
115BF..115C0 ; Mn # [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
115DC..115DD ; Mn # [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
11633..1163A ; Mn # [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
1163D ; Mn # MODI SIGN ANUSVARA
1163F..11640 ; Mn # [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA
@ -2630,6 +2669,9 @@ FE20..FE2D ; Mn # [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MA
116AD ; Mn # TAKRI VOWEL SIGN AA
116B0..116B5 ; Mn # [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
116B7 ; Mn # TAKRI SIGN NUKTA
1171D..1171F ; Mn # [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11722..11725 ; Mn # [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11727..1172B ; Mn # [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
16AF0..16AF4 ; Mn # [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Mn # [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW
@ -2639,10 +2681,16 @@ FE20..FE2D ; Mn # [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MA
1D185..1D18B ; Mn # [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D1AA..1D1AD ; Mn # [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
1D242..1D244 ; Mn # [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1DA00..1DA36 ; Mn # [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
1DA3B..1DA6C ; Mn # [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
1DA75 ; Mn # SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
1DA84 ; Mn # SIGNWRITING LOCATION HEAD NECK
1DA9B..1DA9F ; Mn # [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF ; Mn # [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
1E8D0..1E8D6 ; Mn # [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 1418
# Total code points: 1567
# ================================================
@ -2724,8 +2772,6 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL
1929..192B ; Mc # [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
1930..1931 ; Mc # [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
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..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
@ -2804,11 +2850,13 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK
116AC ; Mc # TAKRI SIGN VISARGA
116AE..116AF ; Mc # [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
116B6 ; Mc # TAKRI SIGN VIRAMA
11720..11721 ; Mc # [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
11726 ; Mc # AHOM VOWEL SIGN E
16F51..16F7E ; Mc # [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
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: 399
# Total code points: 383
# ================================================
@ -2860,12 +2908,13 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
114D0..114D9 ; Nd # [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
11650..11659 ; Nd # [10] MODI DIGIT ZERO..MODI DIGIT NINE
116C0..116C9 ; Nd # [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
11730..11739 ; Nd # [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
118E0..118E9 ; Nd # [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE
16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
# Total code points: 540
# Total code points: 550
# ================================================
@ -2926,7 +2975,11 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO
10858..1085F ; No # [8] IMPERIAL ARAMAIC NUMBER ONE..IMPERIAL ARAMAIC NUMBER TEN THOUSAND
10879..1087F ; No # [7] PALMYRENE NUMBER ONE..PALMYRENE NUMBER TWENTY
108A7..108AF ; No # [9] NABATAEAN NUMBER ONE..NABATAEAN NUMBER ONE HUNDRED
108FB..108FF ; No # [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
10916..1091B ; No # [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE
109BC..109BD ; No # [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
109C0..109CF ; No # [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
109D2..109FF ; No # [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
10A40..10A47 ; No # [8] KHAROSHTHI DIGIT ONE..KHAROSHTHI NUMBER ONE THOUSAND
10A7D..10A7E ; No # [2] OLD SOUTH ARABIAN NUMBER ONE..OLD SOUTH ARABIAN NUMBER FIFTY
10A9D..10A9F ; No # [3] OLD NORTH ARABIAN NUMBER ONE..OLD NORTH ARABIAN NUMBER TWENTY
@ -2934,16 +2987,18 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO
10B58..10B5F ; No # [8] INSCRIPTIONAL PARTHIAN NUMBER ONE..INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND
10B78..10B7F ; No # [8] INSCRIPTIONAL PAHLAVI NUMBER ONE..INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND
10BA9..10BAF ; No # [7] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER ONE HUNDRED
10CFA..10CFF ; No # [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
10E60..10E7E ; No # [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS
11052..11065 ; No # [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND
111E1..111F4 ; No # [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND
1173A..1173B ; No # [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
118EA..118F2 ; No # [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
16B5B..16B61 ; No # [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS
1D360..1D371 ; No # [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
1E8C7..1E8CF ; No # [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
1F100..1F10C ; No # [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
# Total code points: 570
# Total code points: 647
# ================================================
@ -3322,6 +3377,7 @@ A6F2..A6F7 ; Po # [6] BAMUM NJAEMLI..BAMUM QUESTION MARK
A874..A877 ; Po # [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHAD
A8CE..A8CF ; Po # [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA
A8F8..A8FA ; Po # [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
A8FC ; Po # DEVANAGARI SIGN SIDDHAM
A92E..A92F ; Po # [2] KAYAH LI SIGN CWI..KAYAH LI SIGN SHYA
A95F ; Po # REJANG SECTION MARK
A9C1..A9CD ; Po # [13] JAVANESE LEFT RERENGGAN..JAVANESE TURNED PADA PISELEH
@ -3367,20 +3423,25 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL
110BE..110C1 ; Po # [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA
11140..11143 ; Po # [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK
11174..11175 ; Po # [2] MAHAJANI ABBREVIATION SIGN..MAHAJANI SECTION MARK
111C5..111C8 ; Po # [4] SHARADA DANDA..SHARADA SEPARATOR
111C5..111C9 ; Po # [5] SHARADA DANDA..SHARADA SANDHI MARK
111CD ; Po # SHARADA SUTRA MARK
111DB ; Po # SHARADA SIGN SIDDHAM
111DD..111DF ; Po # [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2
11238..1123D ; Po # [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
112A9 ; Po # MULTANI SECTION MARK
114C6 ; Po # TIRHUTA ABBREVIATION SIGN
115C1..115C9 ; Po # [9] SIDDHAM SIGN SIDDHAM..SIDDHAM END OF TEXT MARK
115C1..115D7 ; Po # [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
11641..11643 ; Po # [3] MODI DANDA..MODI ABBREVIATION SIGN
1173C..1173E ; Po # [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
12470..12474 ; Po # [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
16A6E..16A6F ; Po # [2] MRO DANDA..MRO DOUBLE DANDA
16AF5 ; Po # BASSA VAH FULL STOP
16B37..16B3B ; Po # [5] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS FEEM
16B44 ; Po # PAHAWH HMONG SIGN XAUS
1BC9F ; Po # DUPLOYAN PUNCTUATION CHINOOK FULL STOP
1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS
# Total code points: 484
# Total code points: 513
# ================================================
@ -3467,7 +3528,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW
0BF9 ; Sc # TAMIL RUPEE SIGN
0E3F ; Sc # THAI CURRENCY SYMBOL BAHT
17DB ; Sc # KHMER CURRENCY SYMBOL RIEL
20A0..20BD ; Sc # [30] EURO-CURRENCY SIGN..RUBLE SIGN
20A0..20BE ; Sc # [31] EURO-CURRENCY SIGN..LARI SIGN
A838 ; Sc # NORTH INDIC RUPEE MARK
FDFC ; Sc # RIAL SIGN
FE69 ; Sc # SMALL DOLLAR SIGN
@ -3475,7 +3536,7 @@ FF04 ; Sc # FULLWIDTH DOLLAR SIGN
FFE0..FFE1 ; Sc # [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN
FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN
# Total code points: 52
# Total code points: 53
# ================================================
@ -3509,8 +3570,9 @@ FBB2..FBC1 ; Sk # [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELO
FF3E ; Sk # FULLWIDTH CIRCUMFLEX ACCENT
FF40 ; Sk # FULLWIDTH GRAVE ACCENT
FFE3 ; Sk # FULLWIDTH MACRON
1F3FB..1F3FF ; Sk # [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
# Total code points: 116
# Total code points: 121
# ================================================
@ -3564,6 +3626,7 @@ FFE3 ; Sk # FULLWIDTH MACRON
214A ; So # PROPERTY LINE
214C..214D ; So # [2] PER SIGN..AKTIESELSKAB
214F ; So # SYMBOL FOR SAMARITAN SOURCE
218A..218B ; So # [2] TURNED DIGIT TWO..TURNED DIGIT THREE
2195..2199 ; So # [5] UP DOWN ARROW..SOUTH WEST ARROW
219C..219F ; So # [4] LEFTWARDS WAVE ARROW..UPWARDS TWO HEADED ARROW
21A1..21A2 ; So # [2] DOWNWARDS TWO HEADED ARROW..LEFTWARDS ARROW WITH TAIL
@ -3597,6 +3660,7 @@ FFE3 ; Sk # FULLWIDTH MACRON
2B98..2BB9 ; So # [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8 ; So # [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD1 ; So # [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
2BEC..2BEF ; So # [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2CE5..2CEA ; So # [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA
2E80..2E99 ; So # [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; So # [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
@ -3636,6 +3700,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
101D0..101FC ; So # [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND
10877..10878 ; So # [2] PALMYRENE LEFT-POINTING FLEURON..PALMYRENE RIGHT-POINTING FLEURON
10AC8 ; So # MANICHAEAN SIGN UD
1173F ; So # AHOM SYMBOL VI
16B3C..16B3F ; So # [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB
16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG
1BC9C ; So # DUPLOYAN SIGN O WITH CROSS
@ -3645,10 +3710,15 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
1D16A..1D16C ; So # [3] MUSICAL SYMBOL FINGERED TREMOLO-1..MUSICAL SYMBOL FINGERED TREMOLO-3
1D183..1D184 ; So # [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
1D18C..1D1A9 ; So # [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
1D1AE..1D1DD ; So # [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS
1D1AE..1D1E8 ; So # [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
1D200..1D241 ; So # [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54
1D245 ; So # GREEK MUSICAL LEIMMA
1D300..1D356 ; So # [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D800..1D9FF ; So # [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD
1DA37..1DA3A ; So # [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE
1DA6D..1DA74 ; So # [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING
1DA76..1DA83 ; So # [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH
1DA85..1DA86 ; So # [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS
1F000..1F02B ; So # [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK
1F030..1F093 ; So # [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06
1F0A0..1F0AE ; So # [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES
@ -3662,16 +3732,10 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
1F210..1F23A ; So # [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
1F240..1F248 ; So # [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; So # [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
1F300..1F32C ; So # [45] CYCLONE..WIND BLOWING FACE
1F330..1F37D ; So # [78] CHESTNUT..FORK AND KNIFE WITH PLATE
1F380..1F3CE ; So # [79] RIBBON..RACING CAR
1F3D4..1F3F7 ; So # [36] SNOW CAPPED MOUNTAIN..LABEL
1F400..1F4FE ; So # [255] RAT..PORTABLE STEREO
1F500..1F54A ; So # [75] TWISTED RIGHTWARDS ARROWS..DOVE OF PEACE
1F550..1F579 ; So # [42] CLOCK FACE ONE OCLOCK..JOYSTICK
1F300..1F3FA ; So # [251] CYCLONE..AMPHORA
1F400..1F579 ; So # [378] RAT..JOYSTICK
1F57B..1F5A3 ; So # [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX
1F5A5..1F642 ; So # [158] DESKTOP COMPUTER..SLIGHTLY SMILING FACE
1F645..1F6CF ; So # [139] FACE WITH NO GOOD GESTURE..BED
1F5A5..1F6D0 ; So # [300] DESKTOP COMPUTER..PLACE OF WORSHIP
1F6E0..1F6EC ; So # [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F3 ; So # [4] SATELLITE..PASSENGER SHIP
1F700..1F773 ; So # [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
@ -3681,8 +3745,11 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F910..1F918 ; So # [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS
1F980..1F984 ; So # [5] CRAB..UNICORN FACE
1F9C0 ; So # CHEESE WEDGE
# Total code points: 5082
# Total code points: 5677
# ================================================

33
maint/Unicode.tables/GraphemeBreakProperty.txt
View File

@ -1,8 +1,8 @@
# GraphemeBreakProperty-7.0.0.txt
# Date: 2014-02-19, 15:51:21 GMT [MD]
# GraphemeBreakProperty-8.0.0.txt
# Date: 2015-02-13, 13:47:14 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# 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/
@ -89,7 +89,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
08E4..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA
08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA
093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE
093C ; Extend # Mn DEVANAGARI SIGN NUKTA
0941..0948 ; Extend # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
@ -250,7 +250,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
A66F ; Extend # Mn COMBINING CYRILLIC VZMET
A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK
A69F ; Extend # Mn COMBINING CYRILLIC LETTER IOTIFIED E
A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E
A6F0..A6F1 ; Extend # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
A802 ; Extend # Mn SYLOTI NAGRI SIGN DVISVARA
A806 ; Extend # Mn SYLOTI NAGRI SIGN HASANTA
@ -283,7 +283,7 @@ ABE8 ; Extend # Mn MEETEI MAYEK VOWEL SIGN UNAP
ABED ; Extend # Mn MEETEI MAYEK APUN IYEK
FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA
FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
FE20..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW
FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF
FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK
@ -305,12 +305,13 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
11173 ; Extend # Mn MAHAJANI SIGN NUKTA
11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA
111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
11234 ; Extend # Mn KHOJKI SIGN ANUSVARA
11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA
112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU
11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
1133C ; Extend # Mn GRANTHA SIGN NUKTA
1133E ; Extend # Mc GRANTHA VOWEL SIGN AA
11340 ; Extend # Mn GRANTHA VOWEL SIGN II
@ -327,6 +328,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
115B2..115B5 ; Extend # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR
115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI
1163D ; Extend # Mn MODI SIGN ANUSVARA
1163F..11640 ; Extend # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA
@ -334,6 +336,9 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
116AD ; Extend # Mn TAKRI VOWEL SIGN AA
116B0..116B5 ; Extend # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU
116B7 ; Extend # Mn TAKRI SIGN NUKTA
1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
@ -345,10 +350,16 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
1DA3B..1DA6C ; Extend # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
1DA75 ; Extend # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK
1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 1461
# Total code points: 1610
# ================================================
@ -412,8 +423,6 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
1929..192B ; SpacingMark # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA
1930..1931 ; SpacingMark # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA
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..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
@ -487,11 +496,13 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK
116AC ; SpacingMark # Mc TAKRI SIGN VISARGA
116AE..116AF ; SpacingMark # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II
116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA
11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
11726 ; SpacingMark # Mc AHOM VOWEL SIGN E
16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT
# Total code points: 331
# Total code points: 330
# ================================================

180
maint/Unicode.tables/Scripts.txt
View File

@ -1,10 +1,16 @@
# Scripts-7.0.0.txt
# Date: 2014-05-15, 00:11:35 GMT [MD]
# Scripts-8.0.0.txt
# Date: 2015-03-11, 22:29:42 GMT [MD]
#
# Unicode Character Database
# Copyright (c) 1991-2014 Unicode, Inc.
# 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 more information, see:
# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/
# Especially the sections:
# http://www.unicode.org/reports/tr24/#Assignment_Script_Values
# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values
#
# ================================================
@ -89,7 +95,6 @@
061C ; Common # Cf ARABIC LETTER MARK
061F ; Common # Po ARABIC QUESTION MARK
0640 ; Common # Lm ARABIC TATWEEL
0660..0669 ; Common # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
06DD ; Common # Cf ARABIC END OF AYAH
0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA
0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT
@ -148,7 +153,7 @@
208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS
20A0..20BD ; Common # Sc [30] EURO-CURRENCY SIGN..RUBLE SIGN
20A0..20BE ; Common # Sc [31] EURO-CURRENCY SIGN..LARI 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
@ -182,6 +187,7 @@
214F ; Common # So SYMBOL FOR SAMARITAN SOURCE
2150..215F ; Common # No [16] VULGAR FRACTION ONE SEVENTH..FRACTION NUMERATOR ONE
2189 ; Common # No VULGAR FRACTION ZERO THIRDS
218A..218B ; Common # So [2] TURNED DIGIT TWO..TURNED DIGIT THREE
2190..2194 ; Common # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW
2195..2199 ; Common # So [5] UP DOWN ARROW..SOUTH WEST ARROW
219A..219B ; Common # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE
@ -304,6 +310,7 @@
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
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
2E03 ; Common # Pf RIGHT SUBSTITUTION BRACKET
@ -512,7 +519,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1D173..1D17A ; Common # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
1D183..1D184 ; Common # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
1D18C..1D1A9 ; Common # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
1D1AE..1D1DD ; Common # So [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS
1D1AE..1D1E8 ; Common # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING
1D360..1D371 ; Common # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE
1D400..1D454 ; Common # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
@ -571,16 +578,11 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
1F210..1F23A ; Common # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6
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
1F300..1F32C ; Common # So [45] CYCLONE..WIND BLOWING FACE
1F330..1F37D ; Common # So [78] CHESTNUT..FORK AND KNIFE WITH PLATE
1F380..1F3CE ; Common # So [79] RIBBON..RACING CAR
1F3D4..1F3F7 ; Common # So [36] SNOW CAPPED MOUNTAIN..LABEL
1F400..1F4FE ; Common # So [255] RAT..PORTABLE STEREO
1F500..1F54A ; Common # So [75] TWISTED RIGHTWARDS ARROWS..DOVE OF PEACE
1F550..1F579 ; Common # So [42] CLOCK FACE ONE OCLOCK..JOYSTICK
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..1F642 ; Common # So [158] DESKTOP COMPUTER..SLIGHTLY SMILING FACE
1F645..1F6CF ; Common # So [139] FACE WITH NO GOOD GESTURE..BED
1F5A5..1F6D0 ; Common # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP
1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F3 ; Common # So [4] SATELLITE..PASSENGER SHIP
1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
@ -590,10 +592,13 @@ 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
1F9C0 ; Common # So CHEESE WEDGE
E0001 ; Common # Cf LANGUAGE TAG
E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG
# Total code points: 7129
# Total code points: 7179
# ================================================
@ -635,20 +640,21 @@ A722..A76F ; Latin # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN
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
A7B0..A7B1 ; Latin # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T
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
A7FA ; Latin # L& LATIN LETTER SMALL CAPITAL TURNED M
A7FB..A7FF ; Latin # Lo [5] LATIN EPIGRAPHIC LETTER REVERSED F..LATIN EPIGRAPHIC LETTER ARCHAIC M
AB30..AB5A ; Latin # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
AB5C..AB5F ; Latin # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
AB64 ; Latin # L& LATIN SMALL LETTER INVERTED ALPHA
AB60..AB64 ; Latin # L& [5] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER INVERTED ALPHA
FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
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: 1338
# Total code points: 1349
# ================================================
@ -731,9 +737,10 @@ A67E ; Cyrillic # Po CYRILLIC KAVYKA
A67F ; Cyrillic # Lm CYRILLIC PAYEROK
A680..A69B ; Cyrillic # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER CROSSED O
A69C..A69D ; Cyrillic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
A69F ; Cyrillic # Mn COMBINING CYRILLIC LETTER IOTIFIED E
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: 431
# Total code points: 434
# ================================================
@ -788,6 +795,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
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
0656..065F ; Arabic # Mn [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW
0660..0669 ; Arabic # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE
066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
066E..066F ; Arabic # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
0671..06D3 ; Arabic # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
@ -806,8 +814,8 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN
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..08B2 ; Arabic # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE
08E4..08FF ; Arabic # Mn [28] ARABIC CURLY FATHA..ARABIC MARK SIDEWAYS NOON GHUNNA
08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
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
FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
@ -854,7 +862,7 @@ 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: 1244
# Total code points: 1257
# ================================================
@ -902,8 +910,10 @@ A8E0..A8F1 ; Devanagari # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING
A8F2..A8F7 ; Devanagari # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA
A8F8..A8FA ; Devanagari # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET
A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
A8FC ; Devanagari # Po DEVANAGARI SIGN SIDDHAM
A8FD ; Devanagari # Lo DEVANAGARI JAIN OM
# Total code points: 152
# Total code points: 154
# ================================================
@ -987,8 +997,9 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0AE6..0AEF ; Gujarati # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN
0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN
0AF9 ; Gujarati # Lo GUJARATI LETTER ZHA
# Total code points: 84
# Total code points: 85
# ================================================
@ -1064,14 +1075,14 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0C46..0C48 ; Telugu # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
0C4A..0C4D ; Telugu # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
0C55..0C56 ; Telugu # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
0C58..0C59 ; Telugu # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA
0C58..0C5A ; Telugu # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA
0C60..0C61 ; Telugu # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL
0C62..0C63 ; Telugu # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
0C66..0C6F ; Telugu # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE
0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
0C7F ; Telugu # So TELUGU SIGN TUUMU
# Total code points: 95
# Total code points: 96
# ================================================
@ -1115,14 +1126,14 @@ A8FB ; Devanagari # Lo DEVANAGARI HEADSTROKE
0D4D ; Malayalam # Mn MALAYALAM SIGN VIRAMA
0D4E ; Malayalam # Lo MALAYALAM LETTER DOT REPH
0D57 ; Malayalam # Mc MALAYALAM AU LENGTH MARK
0D60..0D61 ; Malayalam # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL
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
0D79 ; Malayalam # So MALAYALAM DATE MARK
0D7A..0D7F ; Malayalam # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
# Total code points: 99
# Total code points: 100
# ================================================
@ -1358,9 +1369,11 @@ AB28..AB2E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO
# ================================================
13A0..13F4 ; Cherokee # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV
13A0..13F5 ; Cherokee # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
13F8..13FD ; Cherokee # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
# Total code points: 85
# Total code points: 172
# ================================================
@ -1472,15 +1485,16 @@ 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..9FCC ; Han # Lo [20941] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCC
4E00..9FD5 ; Han # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
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
2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 75963
# Total code points: 81734
# ================================================
@ -1680,9 +1694,7 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2
# ================================================
1980..19AB ; New_Tai_Lue # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA
19B0..19C0 ; New_Tai_Lue # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY
19C1..19C7 ; New_Tai_Lue # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
19C8..19C9 ; New_Tai_Lue # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2
19B0..19C9 ; New_Tai_Lue # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
19D0..19D9 ; New_Tai_Lue # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE
19DA ; New_Tai_Lue # No NEW TAI LUE THAM DIGIT ONE
19DE..19DF ; New_Tai_Lue # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV
@ -1770,11 +1782,12 @@ A828..A82B ; Syloti_Nagri # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI
# ================================================
12000..12398 ; Cuneiform # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME
12000..12399 ; Cuneiform # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; Cuneiform # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12470..12474 ; Cuneiform # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
12480..12543 ; Cuneiform # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
# Total code points: 1037
# Total code points: 1234
# ================================================
@ -2151,9 +2164,12 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# ================================================
109A0..109B7 ; Meroitic_Cursive # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA
109BC..109BD ; Meroitic_Cursive # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
109BE..109BF ; Meroitic_Cursive # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
109C0..109CF ; Meroitic_Cursive # No [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
109D2..109FF ; Meroitic_Cursive # No [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
# Total code points: 26
# Total code points: 90
# ================================================
@ -2180,12 +2196,16 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
111B6..111BE ; Sharada # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O
111BF..111C0 ; Sharada # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA
111C1..111C4 ; Sharada # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM
111C5..111C8 ; Sharada # Po [4] SHARADA DANDA..SHARADA SEPARATOR
111C5..111C9 ; Sharada # Po [5] SHARADA DANDA..SHARADA SANDHI MARK
111CA..111CC ; Sharada # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK
111CD ; Sharada # Po SHARADA SUTRA MARK
111D0..111D9 ; Sharada # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE
111DA ; Sharada # Lo SHARADA EKAM
111DB ; Sharada # Po SHARADA SIGN SIDDHAM
111DC ; Sharada # Lo SHARADA HEADSTROKE
111DD..111DF ; Sharada # Po [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2
# Total code points: 85
# Total code points: 94
# ================================================
@ -2243,7 +2263,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# ================================================
11301 ; Grantha # Mn GRANTHA SIGN CANDRABINDU
11300..11301 ; Grantha # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
11302..11303 ; Grantha # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA
11305..1130C ; Grantha # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
1130F..11310 ; Grantha # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI
@ -2258,13 +2278,14 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
11341..11344 ; Grantha # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR
11347..11348 ; Grantha # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI
1134B..1134D ; Grantha # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA
11350 ; Grantha # Lo GRANTHA OM
11357 ; Grantha # Mc GRANTHA AU LENGTH MARK
1135D..11361 ; Grantha # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL
11362..11363 ; Grantha # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL
11366..1136C ; Grantha # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX
11370..11374 ; Grantha # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA
# Total code points: 83
# Total code points: 85
# ================================================
@ -2407,9 +2428,11 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
115BC..115BD ; Siddham # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA
115BE ; Siddham # Mc SIDDHAM SIGN VISARGA
115BF..115C0 ; Siddham # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA
115C1..115C9 ; Siddham # Po [9] SIDDHAM SIGN SIDDHAM..SIDDHAM END OF TEXT MARK
115C1..115D7 ; Siddham # Po [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES
115D8..115DB ; Siddham # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U
115DC..115DD ; Siddham # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU
# Total code points: 72
# Total code points: 92
# ================================================
@ -2448,4 +2471,69 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI
# Total code points: 84
# ================================================
11700..11719 ; Ahom # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
1171D..1171F ; Ahom # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11720..11721 ; Ahom # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA
11722..11725 ; Ahom # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11726 ; Ahom # Mc AHOM VOWEL SIGN E
11727..1172B ; Ahom # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
11730..11739 ; Ahom # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
1173A..1173B ; Ahom # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
1173C..1173E ; Ahom # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI
1173F ; Ahom # So AHOM SYMBOL VI
# Total code points: 57
# ================================================
14400..14646 ; Anatolian_Hieroglyphs # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
# Total code points: 583
# ================================================
108E0..108F2 ; Hatran # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
108F4..108F5 ; Hatran # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
108FB..108FF ; Hatran # No [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
# Total code points: 26
# ================================================
11280..11286 ; Multani # Lo [7] MULTANI LETTER A..MULTANI LETTER GA
11288 ; Multani # Lo MULTANI LETTER GHA
1128A..1128D ; Multani # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
1128F..1129D ; Multani # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA
1129F..112A8 ; Multani # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA
112A9 ; Multani # Po MULTANI SECTION MARK
# Total code points: 38
# ================================================
10C80..10CB2 ; Old_Hungarian # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
10CC0..10CF2 ; Old_Hungarian # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
10CFA..10CFF ; Old_Hungarian # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
# Total code points: 108
# ================================================
1D800..1D9FF ; SignWriting # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD
1DA00..1DA36 ; SignWriting # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN
1DA37..1DA3A ; SignWriting # So [4] SIGNWRITING AIR BLOW SMALL ROTATIONS..SIGNWRITING BREATH EXHALE
1DA3B..1DA6C ; SignWriting # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT
1DA6D..1DA74 ; SignWriting # So [8] SIGNWRITING SHOULDER HIP SPINE..SIGNWRITING TORSO-FLOORPLANE TWISTING
1DA75 ; SignWriting # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS
1DA76..1DA83 ; SignWriting # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH
1DA84 ; SignWriting # Mn SIGNWRITING LOCATION HEAD NECK
1DA85..1DA86 ; SignWriting # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS
1DA87..1DA8B ; SignWriting # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS
1DA9B..1DA9F ; SignWriting # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6
1DAA1..1DAAF ; SignWriting # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16
# Total code points: 672
# EOF

2161
maint/Unicode.tables/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff

8
maint/ucptest.c
View File

@ -260,6 +260,14 @@ switch(script)
case ucp_Siddham: scriptname = US"Siddham"; break;
case ucp_Tirhuta: scriptname = US"Tirhuta"; break;
case ucp_Warang_Citi: scriptname = US"Warang_Citi"; break;
/* New for Unicode 8.0.0 */
case ucp_Ahom: scriptname = US"Ahom"; break;
case ucp_Anatolian_Hieroglyphs: scriptname = US"Anatolian_Hieroglyphs"; break;
case ucp_Hatran: scriptname = US"Hatran"; break;
case ucp_Multani: scriptname = US"Multani"; break;
case ucp_Old_Hungarian: scriptname = US"Old_Hungarian"; break;
case ucp_SignWriting: scriptname = US"SignWriting"; break;
}
printf("%04x %s: %s, %s, %s", c, typename, fulltypename, scriptname, graphbreak);

2
maint/ucptestdata/testinput1
View File

@ -34,3 +34,5 @@ findprop 11100 1113c 11680 116c0
findprop 0d 0a 0e 0711 1b04 1111 1169 11fe ae4c ad89
findprop 118a0 11ac7 16ad0
findprop 11700 14400 108e0 11280 1d800

7
maint/ucptestdata/testoutput1
View File

@ -362,3 +362,10 @@ findprop 118a0 11ac7 16ad0
118a0 Letter: Upper case letter, Warang_Citi, Other, 118c0
11ac7 Letter: Other letter, Pau_Cin_Hau, Other
16ad0 Letter: Other letter, Bassa_Vah, Other
findprop 11700 14400 108e0 11280 1d800
11700 Letter: Other letter, Ahom, Other
14400 Letter: Other letter, Anatolian_Hieroglyphs, Other
108e0 Letter: Other letter, Hatran, Other
11280 Letter: Other letter, Multani, Other
1d800 Symbol: Other symbol, SignWriting, Other

356
src/pcre2_tables.c
View File

@ -227,6 +227,8 @@ version. Like all other character and string literals that are compared against
the regular expression pattern, we must use STR_ macros instead of literal
strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Ahom0 STR_A STR_h STR_o STR_m "\0"
#define STRING_Anatolian_Hieroglyphs0 STR_A STR_n STR_a STR_t STR_o STR_l STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
#define STRING_Any0 STR_A STR_n STR_y "\0"
#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
@ -274,6 +276,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Han0 STR_H STR_a STR_n "\0"
#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
#define STRING_Hatran0 STR_H STR_a STR_t STR_r STR_a STR_n "\0"
#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
@ -321,6 +324,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Modi0 STR_M STR_o STR_d STR_i "\0"
#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
#define STRING_Mro0 STR_M STR_r STR_o "\0"
#define STRING_Multani0 STR_M STR_u STR_l STR_t STR_a STR_n STR_i "\0"
#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
#define STRING_N0 STR_N "\0"
#define STRING_Nabataean0 STR_N STR_a STR_b STR_a STR_t STR_a STR_e STR_a STR_n "\0"
@ -331,6 +335,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_No0 STR_N STR_o "\0"
#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
#define STRING_Old_Hungarian0 STR_O STR_l STR_d STR_UNDERSCORE STR_H STR_u STR_n STR_g STR_a STR_r STR_i STR_a STR_n "\0"
#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0"
#define STRING_Old_North_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_N STR_o STR_r STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
#define STRING_Old_Permic0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_m STR_i STR_c "\0"
@ -362,6 +367,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
#define STRING_Siddham0 STR_S STR_i STR_d STR_d STR_h STR_a STR_m "\0"
#define STRING_SignWriting0 STR_S STR_i STR_g STR_n STR_W STR_r STR_i STR_t STR_i STR_n STR_g "\0"
#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
#define STRING_Sk0 STR_S STR_k "\0"
#define STRING_Sm0 STR_S STR_m "\0"
@ -398,6 +404,8 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
#define STRING_Zs0 STR_Z STR_s "\0"
const char PRIV(utt_names)[] =
STRING_Ahom0
STRING_Anatolian_Hieroglyphs0
STRING_Any0
STRING_Arabic0
STRING_Armenian0
@ -445,6 +453,7 @@ const char PRIV(utt_names)[] =
STRING_Han0
STRING_Hangul0
STRING_Hanunoo0
STRING_Hatran0
STRING_Hebrew0
STRING_Hiragana0
STRING_Imperial_Aramaic0
@ -492,6 +501,7 @@ const char PRIV(utt_names)[] =
STRING_Modi0
STRING_Mongolian0
STRING_Mro0
STRING_Multani0
STRING_Myanmar0
STRING_N0
STRING_Nabataean0
@ -502,6 +512,7 @@ const char PRIV(utt_names)[] =
STRING_No0
STRING_Ogham0
STRING_Ol_Chiki0
STRING_Old_Hungarian0
STRING_Old_Italic0
STRING_Old_North_Arabian0
STRING_Old_Permic0
@ -533,6 +544,7 @@ const char PRIV(utt_names)[] =
STRING_Sharada0
STRING_Shavian0
STRING_Siddham0
STRING_SignWriting0
STRING_Sinhala0
STRING_Sk0
STRING_Sm0
@ -569,175 +581,181 @@ const char PRIV(utt_names)[] =
STRING_Zs0;
const ucp_type_table PRIV(utt)[] = {
{ 0, PT_ANY, 0 },
{ 4, PT_SC, ucp_Arabic },
{ 11, PT_SC, ucp_Armenian },
{ 20, PT_SC, ucp_Avestan },
{ 28, PT_SC, ucp_Balinese },
{ 37, PT_SC, ucp_Bamum },
{ 43, PT_SC, ucp_Bassa_Vah },
{ 53, PT_SC, ucp_Batak },
{ 59, PT_SC, ucp_Bengali },
{ 67, PT_SC, ucp_Bopomofo },
{ 76, PT_SC, ucp_Brahmi },
{ 83, PT_SC, ucp_Braille },
{ 91, PT_SC, ucp_Buginese },
{ 100, PT_SC, ucp_Buhid },
{ 106, PT_GC, ucp_C },
{ 108, PT_SC, ucp_Canadian_Aboriginal },
{ 128, PT_SC, ucp_Carian },
{ 135, PT_SC, ucp_Caucasian_Albanian },
{ 154, PT_PC, ucp_Cc },
{ 157, PT_PC, ucp_Cf },
{ 160, PT_SC, ucp_Chakma },
{ 167, PT_SC, ucp_Cham },
{ 172, PT_SC, ucp_Cherokee },
{ 181, PT_PC, ucp_Cn },
{ 184, PT_PC, ucp_Co },
{ 187, PT_SC, ucp_Common },
{ 194, PT_SC, ucp_Coptic },
{ 201, PT_PC, ucp_Cs },
{ 204, PT_SC, ucp_Cuneiform },
{ 214, PT_SC, ucp_Cypriot },
{ 222, PT_SC, ucp_Cyrillic },
{ 231, PT_SC, ucp_Deseret },
{ 239, PT_SC, ucp_Devanagari },
{ 250, PT_SC, ucp_Duployan },
{ 259, PT_SC, ucp_Egyptian_Hieroglyphs },
{ 280, PT_SC, ucp_Elbasan },
{ 288, PT_SC, ucp_Ethiopic },
{ 297, PT_SC, ucp_Georgian },
{ 306, PT_SC, ucp_Glagolitic },
{ 317, PT_SC, ucp_Gothic },
{ 324, PT_SC, ucp_Grantha },
{ 332, PT_SC, ucp_Greek },
{ 338, PT_SC, ucp_Gujarati },
{ 347, PT_SC, ucp_Gurmukhi },
{ 356, PT_SC, ucp_Han },
{ 360, PT_SC, ucp_Hangul },
{ 367, PT_SC, ucp_Hanunoo },
{ 375, PT_SC, ucp_Hebrew },
{ 382, PT_SC, ucp_Hiragana },
{ 391, PT_SC, ucp_Imperial_Aramaic },
{ 408, PT_SC, ucp_Inherited },
{ 418, PT_SC, ucp_Inscriptional_Pahlavi },
{ 440, PT_SC, ucp_Inscriptional_Parthian },
{ 463, PT_SC, ucp_Javanese },
{ 472, PT_SC, ucp_Kaithi },
{ 479, PT_SC, ucp_Kannada },
{ 487, PT_SC, ucp_Katakana },
{ 496, PT_SC, ucp_Kayah_Li },
{ 505, PT_SC, ucp_Kharoshthi },
{ 516, PT_SC, ucp_Khmer },
{ 522, PT_SC, ucp_Khojki },
{ 529, PT_SC, ucp_Khudawadi },
{ 539, PT_GC, ucp_L },
{ 541, PT_LAMP, 0 },
{ 544, PT_SC, ucp_Lao },
{ 548, PT_SC, ucp_Latin },
{ 554, PT_SC, ucp_Lepcha },
{ 561, PT_SC, ucp_Limbu },
{ 567, PT_SC, ucp_Linear_A },
{ 576, PT_SC, ucp_Linear_B },
{ 585, PT_SC, ucp_Lisu },
{ 590, PT_PC, ucp_Ll },
{ 593, PT_PC, ucp_Lm },
{ 596, PT_PC, ucp_Lo },
{ 599, PT_PC, ucp_Lt },
{ 602, PT_PC, ucp_Lu },
{ 605, PT_SC, ucp_Lycian },
{ 612, PT_SC, ucp_Lydian },
{ 619, PT_GC, ucp_M },
{ 621, PT_SC, ucp_Mahajani },
{ 630, PT_SC, ucp_Malayalam },
{ 640, PT_SC, ucp_Mandaic },
{ 648, PT_SC, ucp_Manichaean },
{ 659, PT_PC, ucp_Mc },
{ 662, PT_PC, ucp_Me },
{ 665, PT_SC, ucp_Meetei_Mayek },
{ 678, PT_SC, ucp_Mende_Kikakui },
{ 692, PT_SC, ucp_Meroitic_Cursive },
{ 709, PT_SC, ucp_Meroitic_Hieroglyphs },
{ 730, PT_SC, ucp_Miao },
{ 735, PT_PC, ucp_Mn },
{ 738, PT_SC, ucp_Modi },
{ 743, PT_SC, ucp_Mongolian },
{ 753, PT_SC, ucp_Mro },
{ 757, PT_SC, ucp_Myanmar },
{ 765, PT_GC, ucp_N },
{ 767, PT_SC, ucp_Nabataean },
{ 777, PT_PC, ucp_Nd },
{ 780, PT_SC, ucp_New_Tai_Lue },
{ 792, PT_SC, ucp_Nko },
{ 796, PT_PC, ucp_Nl },
{ 799, PT_PC, ucp_No },
{ 802, PT_SC, ucp_Ogham },
{ 808, PT_SC, ucp_Ol_Chiki },
{ 817, PT_SC, ucp_Old_Italic },
{ 828, PT_SC, ucp_Old_North_Arabian },
{ 846, PT_SC, ucp_Old_Permic },
{ 857, PT_SC, ucp_Old_Persian },
{ 869, PT_SC, ucp_Old_South_Arabian },
{ 887, PT_SC, ucp_Old_Turkic },
{ 898, PT_SC, ucp_Oriya },
{ 904, PT_SC, ucp_Osmanya },
{ 912, PT_GC, ucp_P },
{ 914, PT_SC, ucp_Pahawh_Hmong },
{ 927, PT_SC, ucp_Palmyrene },
{ 937, PT_SC, ucp_Pau_Cin_Hau },
{ 949, PT_PC, ucp_Pc },
{ 952, PT_PC, ucp_Pd },
{ 955, PT_PC, ucp_Pe },
{ 958, PT_PC, ucp_Pf },
{ 961, PT_SC, ucp_Phags_Pa },
{ 970, PT_SC, ucp_Phoenician },
{ 981, PT_PC, ucp_Pi },
{ 984, PT_PC, ucp_Po },
{ 987, PT_PC, ucp_Ps },
{ 990, PT_SC, ucp_Psalter_Pahlavi },
{ 1006, PT_SC, ucp_Rejang },
{ 1013, PT_SC, ucp_Runic },
{ 1019, PT_GC, ucp_S },
{ 1021, PT_SC, ucp_Samaritan },
{ 1031, PT_SC, ucp_Saurashtra },
{ 1042, PT_PC, ucp_Sc },
{ 1045, PT_SC, ucp_Sharada },
{ 1053, PT_SC, ucp_Shavian },
{ 1061, PT_SC, ucp_Siddham },
{ 1069, PT_SC, ucp_Sinhala },
{ 1077, PT_PC, ucp_Sk },
{ 1080, PT_PC, ucp_Sm },
{ 1083, PT_PC, ucp_So },
{ 1086, PT_SC, ucp_Sora_Sompeng },
{ 1099, PT_SC, ucp_Sundanese },
{ 1109, PT_SC, ucp_Syloti_Nagri },
{ 1122, PT_SC, ucp_Syriac },
{ 1129, PT_SC, ucp_Tagalog },
{ 1137, PT_SC, ucp_Tagbanwa },
{ 1146, PT_SC, ucp_Tai_Le },
{ 1153, PT_SC, ucp_Tai_Tham },
{ 1162, PT_SC, ucp_Tai_Viet },
{ 1171, PT_SC, ucp_Takri },
{ 1177, PT_SC, ucp_Tamil },
{ 1183, PT_SC, ucp_Telugu },
{ 1190, PT_SC, ucp_Thaana },
{ 1197, PT_SC, ucp_Thai },
{ 1202, PT_SC, ucp_Tibetan },
{ 1210, PT_SC, ucp_Tifinagh },
{ 1219, PT_SC, ucp_Tirhuta },
{ 1227, PT_SC, ucp_Ugaritic },
{ 1236, PT_SC, ucp_Vai },
{ 1240, PT_SC, ucp_Warang_Citi },
{ 1252, PT_ALNUM, 0 },
{ 1256, PT_PXSPACE, 0 },
{ 1260, PT_SPACE, 0 },
{ 1264, PT_UCNC, 0 },
{ 1268, PT_WORD, 0 },
{ 1272, PT_SC, ucp_Yi },
{ 1275, PT_GC, ucp_Z },
{ 1277, PT_PC, ucp_Zl },
{ 1280, PT_PC, ucp_Zp },
{ 1283, PT_PC, ucp_Zs }
{ 0, PT_SC, ucp_Ahom },
{ 5, PT_SC, ucp_Anatolian_Hieroglyphs },
{ 27, PT_ANY, 0 },
{ 31, PT_SC, ucp_Arabic },
{ 38, PT_SC, ucp_Armenian },
{ 47, PT_SC, ucp_Avestan },
{ 55, PT_SC, ucp_Balinese },
{ 64, PT_SC, ucp_Bamum },
{ 70, PT_SC, ucp_Bassa_Vah },
{ 80, PT_SC, ucp_Batak },
{ 86, PT_SC, ucp_Bengali },
{ 94, PT_SC, ucp_Bopomofo },
{ 103, PT_SC, ucp_Brahmi },
{ 110, PT_SC, ucp_Braille },
{ 118, PT_SC, ucp_Buginese },
{ 127, PT_SC, ucp_Buhid },
{ 133, PT_GC, ucp_C },
{ 135, PT_SC, ucp_Canadian_Aboriginal },
{ 155, PT_SC, ucp_Carian },
{ 162, PT_SC, ucp_Caucasian_Albanian },
{ 181, PT_PC, ucp_Cc },
{ 184, PT_PC, ucp_Cf },
{ 187, PT_SC, ucp_Chakma },
{ 194, PT_SC, ucp_Cham },
{ 199, PT_SC, ucp_Cherokee },
{ 208, PT_PC, ucp_Cn },
{ 211, PT_PC, ucp_Co },
{ 214, PT_SC, ucp_Common },
{ 221, PT_SC, ucp_Coptic },
{ 228, PT_PC, ucp_Cs },
{ 231, PT_SC, ucp_Cuneiform },
{ 241, PT_SC, ucp_Cypriot },
{ 249, PT_SC, ucp_Cyrillic },
{ 258, PT_SC, ucp_Deseret },
{ 266, PT_SC, ucp_Devanagari },
{ 277, PT_SC, ucp_Duployan },
{ 286, PT_SC, ucp_Egyptian_Hieroglyphs },
{ 307, PT_SC, ucp_Elbasan },
{ 315, PT_SC, ucp_Ethiopic },
{ 324, PT_SC, ucp_Georgian },
{ 333, PT_SC, ucp_Glagolitic },
{ 344, PT_SC, ucp_Gothic },
{ 351, PT_SC, ucp_Grantha },
{ 359, PT_SC, ucp_Greek },
{ 365, PT_SC, ucp_Gujarati },
{ 374, PT_SC, ucp_Gurmukhi },
{ 383, PT_SC, ucp_Han },
{ 387, PT_SC, ucp_Hangul },
{ 394, PT_SC, ucp_Hanunoo },
{ 402, PT_SC, ucp_Hatran },
{ 409, PT_SC, ucp_Hebrew },
{ 416, PT_SC, ucp_Hiragana },
{ 425, PT_SC, ucp_Imperial_Aramaic },
{ 442, PT_SC, ucp_Inherited },
{ 452, PT_SC, ucp_Inscriptional_Pahlavi },
{ 474, PT_SC, ucp_Inscriptional_Parthian },
{ 497, PT_SC, ucp_Javanese },
{ 506, PT_SC, ucp_Kaithi },
{ 513, PT_SC, ucp_Kannada },
{ 521, PT_SC, ucp_Katakana },
{ 530, PT_SC, ucp_Kayah_Li },
{ 539, PT_SC, ucp_Kharoshthi },
{ 550, PT_SC, ucp_Khmer },
{ 556, PT_SC, ucp_Khojki },
{ 563, PT_SC, ucp_Khudawadi },
{ 573, PT_GC, ucp_L },
{ 575, PT_LAMP, 0 },
{ 578, PT_SC, ucp_Lao },
{ 582, PT_SC, ucp_Latin },
{ 588, PT_SC, ucp_Lepcha },
{ 595, PT_SC, ucp_Limbu },
{ 601, PT_SC, ucp_Linear_A },
{ 610, PT_SC, ucp_Linear_B },
{ 619, PT_SC, ucp_Lisu },
{ 624, PT_PC, ucp_Ll },
{ 627, PT_PC, ucp_Lm },
{ 630, PT_PC, ucp_Lo },
{ 633, PT_PC, ucp_Lt },
{ 636, PT_PC, ucp_Lu },
{ 639, PT_SC, ucp_Lycian },
{ 646, PT_SC, ucp_Lydian },
{ 653, PT_GC, ucp_M },
{ 655, PT_SC, ucp_Mahajani },
{ 664, PT_SC, ucp_Malayalam },
{ 674, PT_SC, ucp_Mandaic },
{ 682, PT_SC, ucp_Manichaean },
{ 693, PT_PC, ucp_Mc },
{ 696, PT_PC, ucp_Me },
{ 699, PT_SC, ucp_Meetei_Mayek },
{ 712, PT_SC, ucp_Mende_Kikakui },
{ 726, PT_SC, ucp_Meroitic_Cursive },
{ 743, PT_SC, ucp_Meroitic_Hieroglyphs },
{ 764, PT_SC, ucp_Miao },
{ 769, PT_PC, ucp_Mn },
{ 772, PT_SC, ucp_Modi },
{ 777, PT_SC, ucp_Mongolian },
{ 787, PT_SC, ucp_Mro },
{ 791, PT_SC, ucp_Multani },
{ 799, PT_SC, ucp_Myanmar },
{ 807, PT_GC, ucp_N },
{ 809, PT_SC, ucp_Nabataean },
{ 819, PT_PC, ucp_Nd },
{ 822, PT_SC, ucp_New_Tai_Lue },
{ 834, PT_SC, ucp_Nko },
{ 838, PT_PC, ucp_Nl },
{ 841, PT_PC, ucp_No },
{ 844, PT_SC, ucp_Ogham },
{ 850, PT_SC, ucp_Ol_Chiki },
{ 859, PT_SC, ucp_Old_Hungarian },
{ 873, PT_SC, ucp_Old_Italic },
{ 884, PT_SC, ucp_Old_North_Arabian },
{ 902, PT_SC, ucp_Old_Permic },
{ 913, PT_SC, ucp_Old_Persian },
{ 925, PT_SC, ucp_Old_South_Arabian },
{ 943, PT_SC, ucp_Old_Turkic },
{ 954, PT_SC, ucp_Oriya },
{ 960, PT_SC, ucp_Osmanya },
{ 968, PT_GC, ucp_P },
{ 970, PT_SC, ucp_Pahawh_Hmong },
{ 983, PT_SC, ucp_Palmyrene },
{ 993, PT_SC, ucp_Pau_Cin_Hau },
{ 1005, PT_PC, ucp_Pc },
{ 1008, PT_PC, ucp_Pd },
{ 1011, PT_PC, ucp_Pe },
{ 1014, PT_PC, ucp_Pf },
{ 1017, PT_SC, ucp_Phags_Pa },
{ 1026, PT_SC, ucp_Phoenician },
{ 1037, PT_PC, ucp_Pi },
{ 1040, PT_PC, ucp_Po },
{ 1043, PT_PC, ucp_Ps },
{ 1046, PT_SC, ucp_Psalter_Pahlavi },
{ 1062, PT_SC, ucp_Rejang },
{ 1069, PT_SC, ucp_Runic },
{ 1075, PT_GC, ucp_S },
{ 1077, PT_SC, ucp_Samaritan },
{ 1087, PT_SC, ucp_Saurashtra },
{ 1098, PT_PC, ucp_Sc },
{ 1101, PT_SC, ucp_Sharada },
{ 1109, PT_SC, ucp_Shavian },
{ 1117, PT_SC, ucp_Siddham },
{ 1125, PT_SC, ucp_SignWriting },
{ 1137, PT_SC, ucp_Sinhala },
{ 1145, PT_PC, ucp_Sk },
{ 1148, PT_PC, ucp_Sm },
{ 1151, PT_PC, ucp_So },
{ 1154, PT_SC, ucp_Sora_Sompeng },
{ 1167, PT_SC, ucp_Sundanese },
{ 1177, PT_SC, ucp_Syloti_Nagri },
{ 1190, PT_SC, ucp_Syriac },
{ 1197, PT_SC, ucp_Tagalog },
{ 1205, PT_SC, ucp_Tagbanwa },
{ 1214, PT_SC, ucp_Tai_Le },
{ 1221, PT_SC, ucp_Tai_Tham },
{ 1230, PT_SC, ucp_Tai_Viet },
{ 1239, PT_SC, ucp_Takri },
{ 1245, PT_SC, ucp_Tamil },
{ 1251, PT_SC, ucp_Telugu },
{ 1258, PT_SC, ucp_Thaana },
{ 1265, PT_SC, ucp_Thai },
{ 1270, PT_SC, ucp_Tibetan },
{ 1278, PT_SC, ucp_Tifinagh },
{ 1287, PT_SC, ucp_Tirhuta },
{ 1295, PT_SC, ucp_Ugaritic },
{ 1304, PT_SC, ucp_Vai },
{ 1308, PT_SC, ucp_Warang_Citi },
{ 1320, PT_ALNUM, 0 },
{ 1324, PT_PXSPACE, 0 },
{ 1328, PT_SPACE, 0 },
{ 1332, PT_UCNC, 0 },
{ 1336, PT_WORD, 0 },
{ 1340, PT_SC, ucp_Yi },
{ 1343, PT_GC, ucp_Z },
{ 1345, PT_PC, ucp_Zl },
{ 1348, PT_PC, ucp_Zp },
{ 1351, PT_PC, ucp_Zs }
};
const size_t PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);

4520
src/pcre2_ucd.c
View File

File diff suppressed because it is too large Load Diff

9
src/pcre2_ucp.h
View File

@ -253,7 +253,14 @@ enum {
ucp_Pau_Cin_Hau,
ucp_Siddham,
ucp_Tirhuta,
ucp_Warang_Citi
ucp_Warang_Citi,
/* New for Unicode 8.0.0: */
ucp_Ahom,
ucp_Anatolian_Hieroglyphs,
ucp_Hatran,
ucp_Multani,
ucp_Old_Hungarian,
ucp_SignWriting
};
#endif