lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2026-10-24 01:33:52 +03:00
Code Activity

Bug 21533: Update to Unicode 10.0.0

Browse Source 
* Unicode 10.0.0 Support: Character encoding, character type info, and
  transliteration tables are all updated to Unicode 10.0.0, using
  generator scripts contributed by Mike FABIAN (Red Hat).
This commit is contained in:
Mike FABIAN
2017-05-31 11:10:25 +02:00
parent f768b45020
commit 925fac7793
16 changed files with 3791 additions and 1098 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ChangeLog
View File

@@ -1,3 +1,9 @@
2017-06-22 Mike FABIAN <mfabian@redhat.com>
[BZ #21533]
* include/stdc-predef.h (__STDC_ISO_10646__): Update to
201706L for Unicode 10.0.
2017-06-21 Benjamin Cama <b.cama@kerlink.fr>
[BZ #21657]

4
NEWS
View File

@@ -7,8 +7,8 @@ using `glibc' in the "product" field.
Version 2.26
* Unicode 9.0.0 Support: Character encoding, character type info, and
transliteration tables are all updated to Unicode 9.0.0, using
* Unicode 10.0.0 Support: Character encoding, character type info, and
transliteration tables are all updated to Unicode 10.0.0, using
generator scripts contributed by Mike FABIAN (Red Hat).
* errno.h is now safe to use from C-preprocessed assembly language on all

13
include/stdc-predef.h
View File

@@ -49,12 +49,13 @@
# define __STDC_IEC_559_COMPLEX__ 1
#endif
/* wchar_t uses Unicode 9.0.0. Version 9.0 of the Unicode Standard is
synchronized with ISO/IEC 10646:2014, fourth edition, plus
Amd. 1 and Amd. 2 and 273 characters from forthcoming 10646, fifth edition.
(Amd. 2 was published 2016-05-01,
see https://www.iso.org/obp/ui/#iso:std:iso-iec:10646:ed-4:v1:amd:2:v1:en) */
#define __STDC_ISO_10646__ 201605L
/* wchar_t uses Unicode 10.0.0. Version 10.0 of the Unicode Standard is
synchronized with ISO/IEC 10646:2017, fifth edition, plus
the following additions from Amendment 1 to the fifth edition:
- 56 emoji characters
- 285 hentaigana
- 3 additional Zanabazar Square characters */
#define __STDC_ISO_10646__ 201706L
/* We do not support C11 <threads.h>. */
#define __STDC_NO_THREADS__ 1

1242
localedata/charmaps/UTF-8
View File

File diff suppressed because it is too large Load Diff

1012
localedata/locales/i18n
View File

File diff suppressed because it is too large Load Diff

1012
localedata/locales/tr_TR
View File

File diff suppressed because it is too large Load Diff

2
localedata/locales/translit_circle
View File

@@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of encircled characters.
% Generated automatically from UnicodeData.txt by gen_translit_circle.py on 2016-06-29 for Unicode 9.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_circle.py on 2017-06-01 for Unicode 10.0.0.
LC_CTYPE

2
localedata/locales/translit_cjk_compat
View File

@@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of CJK compatibility characters.
% Generated automatically from UnicodeData.txt by gen_translit_cjk_compat.py on 2016-06-29 for Unicode 9.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_cjk_compat.py on 2017-06-01 for Unicode 10.0.0.
LC_CTYPE

142
localedata/locales/translit_combining
View File

@@ -10,7 +10,7 @@ comment_char %
% Transliterations that remove all combining characters (accents,
% pronounciation marks, etc.).
% Generated automatically from UnicodeData.txt by gen_translit_combining.py on 2016-06-29 for Unicode 9.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_combining.py on 2017-06-01 for Unicode 10.0.0.
LC_CTYPE
@@ -670,6 +670,14 @@ translit_start
<U1DF4> ""
% COMBINING UP TACK ABOVE
<U1DF5> ""
% COMBINING KAVYKA ABOVE RIGHT
<U1DF6> ""
% COMBINING KAVYKA ABOVE LEFT
<U1DF7> ""
% COMBINING DOT ABOVE LEFT
<U1DF8> ""
% COMBINING WIDE INVERTED BRIDGE BELOW
<U1DF9> ""
% COMBINING DELETION MARK
<U1DFB> ""
% COMBINING DOUBLE INVERTED BREVE BELOW
@@ -828,6 +836,104 @@ translit_start
<U00011445> ""
% NEWA SIGN NUKTA
<U00011446> ""
% ZANABAZAR SQUARE VOWEL SIGN I
<U00011A01> ""
% ZANABAZAR SQUARE VOWEL SIGN UE
<U00011A02> ""
% ZANABAZAR SQUARE VOWEL SIGN U
<U00011A03> ""
% ZANABAZAR SQUARE VOWEL SIGN E
<U00011A04> ""
% ZANABAZAR SQUARE VOWEL SIGN OE
<U00011A05> ""
% ZANABAZAR SQUARE VOWEL SIGN O
<U00011A06> ""
% ZANABAZAR SQUARE VOWEL SIGN AI
<U00011A07> ""
% ZANABAZAR SQUARE VOWEL SIGN AU
<U00011A08> ""
% ZANABAZAR SQUARE VOWEL SIGN REVERSED I
<U00011A09> ""
% ZANABAZAR SQUARE VOWEL LENGTH MARK
<U00011A0A> ""
% ZANABAZAR SQUARE FINAL CONSONANT MARK
<U00011A33> ""
% ZANABAZAR SQUARE SIGN VIRAMA
<U00011A34> ""
% ZANABAZAR SQUARE SIGN CANDRABINDU
<U00011A35> ""
% ZANABAZAR SQUARE SIGN CANDRABINDU WITH ORNAMENT
<U00011A36> ""
% ZANABAZAR SQUARE SIGN CANDRA WITH ORNAMENT
<U00011A37> ""
% ZANABAZAR SQUARE SIGN ANUSVARA
<U00011A38> ""
% ZANABAZAR SQUARE SIGN VISARGA
<U00011A39> ""
% ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA
<U00011A3B> ""
% ZANABAZAR SQUARE CLUSTER-FINAL LETTER RA
<U00011A3C> ""
% ZANABAZAR SQUARE CLUSTER-FINAL LETTER LA
<U00011A3D> ""
% ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
<U00011A3E> ""
% ZANABAZAR SQUARE SUBJOINER
<U00011A47> ""
% SOYOMBO VOWEL SIGN I
<U00011A51> ""
% SOYOMBO VOWEL SIGN UE
<U00011A52> ""
% SOYOMBO VOWEL SIGN U
<U00011A53> ""
% SOYOMBO VOWEL SIGN E
<U00011A54> ""
% SOYOMBO VOWEL SIGN O
<U00011A55> ""
% SOYOMBO VOWEL SIGN OE
<U00011A56> ""
% SOYOMBO VOWEL SIGN AI
<U00011A57> ""
% SOYOMBO VOWEL SIGN AU
<U00011A58> ""
% SOYOMBO VOWEL SIGN VOCALIC R
<U00011A59> ""
% SOYOMBO VOWEL SIGN VOCALIC L
<U00011A5A> ""
% SOYOMBO VOWEL LENGTH MARK
<U00011A5B> ""
% SOYOMBO FINAL CONSONANT SIGN G
<U00011A8A> ""
% SOYOMBO FINAL CONSONANT SIGN K
<U00011A8B> ""
% SOYOMBO FINAL CONSONANT SIGN NG
<U00011A8C> ""
% SOYOMBO FINAL CONSONANT SIGN D
<U00011A8D> ""
% SOYOMBO FINAL CONSONANT SIGN N
<U00011A8E> ""
% SOYOMBO FINAL CONSONANT SIGN B
<U00011A8F> ""
% SOYOMBO FINAL CONSONANT SIGN M
<U00011A90> ""
% SOYOMBO FINAL CONSONANT SIGN R
<U00011A91> ""
% SOYOMBO FINAL CONSONANT SIGN L
<U00011A92> ""
% SOYOMBO FINAL CONSONANT SIGN SH
<U00011A93> ""
% SOYOMBO FINAL CONSONANT SIGN S
<U00011A94> ""
% SOYOMBO FINAL CONSONANT SIGN -A
<U00011A95> ""
% SOYOMBO SIGN ANUSVARA
<U00011A96> ""
% SOYOMBO SIGN VISARGA
<U00011A97> ""
% SOYOMBO GEMINATION MARK
<U00011A98> ""
% SOYOMBO SUBJOINER
<U00011A99> ""
% BHAIKSUKI VOWEL SIGN AA
<U00011C2F> ""
% BHAIKSUKI VOWEL SIGN I
@@ -932,6 +1038,40 @@ translit_start
<U00011CB5> ""
% MARCHEN SIGN CANDRABINDU
<U00011CB6> ""
% MASARAM GONDI VOWEL SIGN AA
<U00011D31> ""
% MASARAM GONDI VOWEL SIGN I
<U00011D32> ""
% MASARAM GONDI VOWEL SIGN II
<U00011D33> ""
% MASARAM GONDI VOWEL SIGN U
<U00011D34> ""
% MASARAM GONDI VOWEL SIGN UU
<U00011D35> ""
% MASARAM GONDI VOWEL SIGN VOCALIC R
<U00011D36> ""
% MASARAM GONDI VOWEL SIGN E
<U00011D3A> ""
% MASARAM GONDI VOWEL SIGN AI
<U00011D3C> ""
% MASARAM GONDI VOWEL SIGN O
<U00011D3D> ""
% MASARAM GONDI VOWEL SIGN AU
<U00011D3F> ""
% MASARAM GONDI SIGN ANUSVARA
<U00011D40> ""
% MASARAM GONDI SIGN VISARGA
<U00011D41> ""
% MASARAM GONDI SIGN NUKTA
<U00011D42> ""
% MASARAM GONDI SIGN CANDRA
<U00011D43> ""
% MASARAM GONDI SIGN HALANTA
<U00011D44> ""
% MASARAM GONDI VIRAMA
<U00011D45> ""
% MASARAM GONDI RA-KARA
<U00011D47> ""
% COMBINING GREEK MUSICAL TRISEME
<U0001D242> ""
% COMBINING GREEK MUSICAL TETRASEME

2
localedata/locales/translit_compat
View File

@@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of compatibility characters and ligatures.
% Generated automatically from UnicodeData.txt by gen_translit_compat.py on 2016-06-29 for Unicode 9.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_compat.py on 2017-06-01 for Unicode 10.0.0.
LC_CTYPE

2
localedata/locales/translit_font
View File

@@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of font equivalents.
% Generated automatically from UnicodeData.txt by gen_translit_font.py on 2016-06-29 for Unicode 9.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_font.py on 2017-06-01 for Unicode 10.0.0.
LC_CTYPE

2
localedata/locales/translit_fraction
View File

@@ -9,7 +9,7 @@ comment_char %
% otherwise be governed by that license.
% Transliterations of fractions.
% Generated automatically from UnicodeData.txt by gen_translit_fraction.py on 2016-06-29 for Unicode 9.0.0.
% Generated automatically from UnicodeData.txt by gen_translit_fraction.py on 2017-06-01 for Unicode 10.0.0.
% The replacements have been surrounded with spaces, because fractions are
% often preceded by a decimal number and followed by a unit or a math symbol.

328
localedata/unicode-gen/DerivedCoreProperties.txt
View File

@@ -1,6 +1,6 @@
# DerivedCoreProperties-9.0.0.txt
# Date: 2016-06-01, 10:34:24 GMT
# © 2016 Unicode®, Inc.
# DerivedCoreProperties-10.0.0.txt
# Date: 2017-03-19, 00:05:15 GMT
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@@ -340,6 +340,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
0828 ; Alphabetic # Lm SAMARITAN MODIFIER LETTER I
0829..082C ; Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN
0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; Alphabetic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; Alphabetic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA
@@ -379,6 +380,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
09DF..09E1 ; Alphabetic # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
09E2..09E3 ; Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
09F0..09F1 ; Alphabetic # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
09FC ; Alphabetic # Lo BENGALI LETTER VEDIC ANUSVARA
0A01..0A02 ; Alphabetic # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
0A03 ; Alphabetic # Mc GURMUKHI SIGN VISARGA
0A05..0A0A ; Alphabetic # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
@@ -416,6 +418,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
0AE0..0AE1 ; Alphabetic # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL
0AE2..0AE3 ; Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AF9 ; Alphabetic # Lo GUJARATI LETTER ZHA
0AFA..0AFC ; Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH
0B01 ; Alphabetic # Mn ORIYA SIGN CANDRABINDU
0B02..0B03 ; Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C ; Alphabetic # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
@@ -491,7 +494,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL
0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0D01 ; Alphabetic # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01 ; Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C ; Alphabetic # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; Alphabetic # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
@@ -792,12 +795,12 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
30A1..30FA ; Alphabetic # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FC..30FE ; Alphabetic # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; Alphabetic # Lo KATAKANA DIGRAPH KOTO
3105..312D ; Alphabetic # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; Alphabetic # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; Alphabetic # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; Alphabetic # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; Alphabetic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FD5 ; Alphabetic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; Alphabetic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; Alphabetic # Lm YI SYLLABLE WU
A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -955,7 +958,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
10280..1029C ; Alphabetic # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X
102A0..102D0 ; Alphabetic # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
10300..1031F ; Alphabetic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10330..10340 ; Alphabetic # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
1032D..10340 ; Alphabetic # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; Alphabetic # Nl GOTHIC LETTER NINETY
10342..10349 ; Alphabetic # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; Alphabetic # Nl GOTHIC LETTER NINE HUNDRED
@@ -1115,6 +1118,23 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
11727..1172A ; Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM
118A0..118DF ; Alphabetic # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118FF ; Alphabetic # Lo WARANG CITI OM
11A00 ; Alphabetic # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06 ; Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32 ; Alphabetic # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A35..11A38 ; Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3A ; Alphabetic # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A3B..11A3E ; Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A50 ; Alphabetic # Lo SOYOMBO LETTER A
11A51..11A56 ; Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A57..11A58 ; Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
11A59..11A5B ; Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A5C..11A83 ; Alphabetic # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; Alphabetic # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA
11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
@@ -1131,6 +1151,16 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
11CB2..11CB3 ; Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB4 ; Alphabetic # Mc MARCHEN VOWEL SIGN O
11CB5..11CB6 ; Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D00..11D06 ; Alphabetic # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; Alphabetic # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; Alphabetic # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D31..11D36 ; Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; Alphabetic # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D41 ; Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA
11D43 ; Alphabetic # Mn MASARAM GONDI SIGN CANDRA
11D46 ; Alphabetic # Lo MASARAM GONDI REPHA
11D47 ; Alphabetic # Mn MASARAM GONDI RA-KARA
12000..12399 ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -1148,10 +1178,11 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
16F50 ; Alphabetic # Lo MIAO LETTER NASALIZATION
16F51..16F7E ; Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
16F93..16F9F ; Alphabetic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; Alphabetic # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; Alphabetic # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC ; Alphabetic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; Alphabetic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001 ; Alphabetic # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; Alphabetic # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; Alphabetic # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; Alphabetic # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -1235,9 +1266,10 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
2A700..2B734 ; Alphabetic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 118240
# Total code points: 126629
# ================================================
@@ -2798,6 +2830,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
0AC7..0AC8 ; Case_Ignorable # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
0ACD ; Case_Ignorable # Mn GUJARATI SIGN VIRAMA
0AE2..0AE3 ; Case_Ignorable # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AFA..0AFF ; Case_Ignorable # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; Case_Ignorable # Mn ORIYA SIGN CANDRABINDU
0B3C ; Case_Ignorable # Mn ORIYA SIGN NUKTA
0B3F ; Case_Ignorable # Mn ORIYA VOWEL SIGN I
@@ -2820,7 +2853,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
0CC6 ; Case_Ignorable # Mn KANNADA VOWEL SIGN E
0CCC..0CCD ; Case_Ignorable # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CE2..0CE3 ; Case_Ignorable # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0D01 ; Case_Ignorable # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01 ; Case_Ignorable # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D3B..0D3C ; Case_Ignorable # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D41..0D44 ; Case_Ignorable # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
0D4D ; Case_Ignorable # Mn MALAYALAM SIGN VIRAMA
0D62..0D63 ; Case_Ignorable # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
@@ -2916,7 +2950,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
1D2C..1D6A ; Case_Ignorable # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D78 ; Case_Ignorable # Lm MODIFIER LETTER CYRILLIC EN
1D9B..1DBF ; Case_Ignorable # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1DC0..1DF5 ; Case_Ignorable # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
1DC0..1DF9 ; Case_Ignorable # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
1DFB..1DFF ; Case_Ignorable # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1FBD ; Case_Ignorable # Sk GREEK KORONIS
1FBF..1FC1 ; Case_Ignorable # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI
@@ -3078,6 +3112,15 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI
1171D..1171F ; Case_Ignorable # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11722..11725 ; Case_Ignorable # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11727..1172B ; Case_Ignorable # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
11A01..11A06 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A09..11A0A ; Case_Ignorable # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A33..11A38 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A3B..11A3E ; Case_Ignorable # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A47 ; Case_Ignorable # Mn ZANABAZAR SQUARE SUBJOINER
11A51..11A56 ; Case_Ignorable # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A59..11A5B ; Case_Ignorable # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A8A..11A96 ; Case_Ignorable # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A98..11A99 ; Case_Ignorable # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11C30..11C36 ; Case_Ignorable # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
11C38..11C3D ; Case_Ignorable # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
11C3F ; Case_Ignorable # Mn BHAIKSUKI SIGN VIRAMA
@@ -3085,12 +3128,17 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI
11CAA..11CB0 ; Case_Ignorable # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
11CB2..11CB3 ; Case_Ignorable # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB5..11CB6 ; Case_Ignorable # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D31..11D36 ; Case_Ignorable # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; Case_Ignorable # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; Case_Ignorable # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D45 ; Case_Ignorable # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
11D47 ; Case_Ignorable # Mn MASARAM GONDI RA-KARA
16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM
16F8F..16F92 ; Case_Ignorable # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
16F93..16F9F ; Case_Ignorable # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; Case_Ignorable # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
1BC9D..1BC9E ; Case_Ignorable # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK
1BCA0..1BCA3 ; Case_Ignorable # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
1D167..1D169 ; Case_Ignorable # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
@@ -3117,7 +3165,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG
E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 2240
# Total code points: 2314
# ================================================
@@ -5763,6 +5811,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER
0824 ; ID_Start # Lm SAMARITAN MODIFIER LETTER SHORT A
0828 ; ID_Start # Lm SAMARITAN MODIFIER LETTER I
0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; ID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; ID_Start # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
@@ -5782,6 +5831,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER
09DC..09DD ; ID_Start # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; ID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
09F0..09F1 ; ID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
09FC ; ID_Start # Lo BENGALI LETTER VEDIC ANUSVARA
0A05..0A0A ; ID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; ID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
0A13..0A28 ; ID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA
@@ -6039,12 +6089,12 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER
30A1..30FA ; ID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FC..30FE ; ID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; ID_Start # Lo KATAKANA DIGRAPH KOTO
3105..312D ; ID_Start # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; ID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; ID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; ID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; ID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FD5 ; ID_Start # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; ID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; ID_Start # Lm YI SYLLABLE WU
A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -6162,7 +6212,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
10280..1029C ; ID_Start # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X
102A0..102D0 ; ID_Start # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
10300..1031F ; ID_Start # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10330..10340 ; ID_Start # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
1032D..10340 ; ID_Start # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; ID_Start # Nl GOTHIC LETTER NINETY
10342..10349 ; ID_Start # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; ID_Start # Nl GOTHIC LETTER NINE HUNDRED
@@ -6249,11 +6299,21 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
11700..11719 ; ID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
118A0..118DF ; ID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118FF ; ID_Start # Lo WARANG CITI OM
11A00 ; ID_Start # Lo ZANABAZAR SQUARE LETTER A
11A0B..11A32 ; ID_Start # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A3A ; ID_Start # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A50 ; ID_Start # Lo SOYOMBO LETTER A
11A5C..11A83 ; ID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; ID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08 ; ID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; ID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
11C40 ; ID_Start # Lo BHAIKSUKI SIGN AVAGRAHA
11C72..11C8F ; ID_Start # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
11D00..11D06 ; ID_Start # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; ID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; ID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D46 ; ID_Start # Lo MASARAM GONDI REPHA
12000..12399 ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -6269,10 +6329,11 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
16F00..16F44 ; ID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION
16F93..16F9F ; ID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; ID_Start # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; ID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC ; ID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; ID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001 ; ID_Start # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; ID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; ID_Start # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; ID_Start # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -6346,9 +6407,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
2A700..2B734 ; ID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 117007
# Total code points: 125334
# ================================================
@@ -6451,6 +6513,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
0829..082D ; ID_Continue # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0840..0858 ; ID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; ID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; ID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1 ; ID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
@@ -6495,6 +6558,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
09E2..09E3 ; ID_Continue # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
09E6..09EF ; ID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
09F0..09F1 ; ID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
09FC ; ID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA
0A01..0A02 ; ID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
0A03 ; ID_Continue # Mc GURMUKHI SIGN VISARGA
0A05..0A0A ; ID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
@@ -6537,6 +6601,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
0AE2..0AE3 ; ID_Continue # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AE6..0AEF ; ID_Continue # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0AF9 ; ID_Continue # Lo GUJARATI LETTER ZHA
0AFA..0AFF ; ID_Continue # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; ID_Continue # Mn ORIYA SIGN CANDRABINDU
0B02..0B03 ; ID_Continue # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C ; ID_Continue # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
@@ -6620,11 +6685,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; ID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0D01 ; ID_Continue # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01 ; ID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; ID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C ; ID_Continue # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; ID_Continue # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A ; ID_Continue # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3B..0D3C ; ID_Continue # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3D ; ID_Continue # Lo MALAYALAM SIGN AVAGRAHA
0D3E..0D40 ; ID_Continue # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; ID_Continue # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
@@ -6888,6 +6954,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1CF2..1CF3 ; ID_Continue # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF4 ; ID_Continue # Mn VEDIC TONE CANDRA ABOVE
1CF5..1CF6 ; ID_Continue # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
1CF7 ; ID_Continue # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9 ; ID_Continue # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1D00..1D2B ; ID_Continue # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A ; ID_Continue # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
@@ -6895,7 +6962,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
1D78 ; ID_Continue # Lm MODIFIER LETTER CYRILLIC EN
1D79..1D9A ; ID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF ; ID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1DC0..1DF5 ; ID_Continue # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
1DC0..1DF9 ; ID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
1DFB..1DFF ; ID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1E00..1F15 ; ID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; ID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@@ -6986,12 +7053,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
30A1..30FA ; ID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FC..30FE ; ID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; ID_Continue # Lo KATAKANA DIGRAPH KOTO
3105..312D ; ID_Continue # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; ID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; ID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; ID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; ID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FD5 ; ID_Continue # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; ID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; ID_Continue # Lm YI SYLLABLE WU
A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -7179,7 +7246,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
102A0..102D0 ; ID_Continue # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
102E0 ; ID_Continue # Mn COPTIC EPACT THOUSANDS MARK
10300..1031F ; ID_Continue # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10330..10340 ; ID_Continue # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
1032D..10340 ; ID_Continue # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; ID_Continue # Nl GOTHIC LETTER NINETY
10342..10349 ; ID_Continue # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; ID_Continue # Nl GOTHIC LETTER NINE HUNDRED
@@ -7367,6 +7434,25 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
118A0..118DF ; ID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118E0..118E9 ; ID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118FF ; ID_Continue # Lo WARANG CITI OM
11A00 ; ID_Continue # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06 ; ID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; ID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; ID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32 ; ID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A33..11A38 ; ID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; ID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3A ; ID_Continue # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A3B..11A3E ; ID_Continue # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A47 ; ID_Continue # Mn ZANABAZAR SQUARE SUBJOINER
11A50 ; ID_Continue # Lo SOYOMBO LETTER A
11A51..11A56 ; ID_Continue # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A57..11A58 ; ID_Continue # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
11A59..11A5B ; ID_Continue # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A5C..11A83 ; ID_Continue # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; ID_Continue # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11A8A..11A96 ; ID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA
11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; ID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
@@ -7385,6 +7471,16 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
11CB2..11CB3 ; ID_Continue # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB4 ; ID_Continue # Mc MARCHEN VOWEL SIGN O
11CB5..11CB6 ; ID_Continue # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D00..11D06 ; ID_Continue # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; ID_Continue # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; ID_Continue # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D31..11D36 ; ID_Continue # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; ID_Continue # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; ID_Continue # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D45 ; ID_Continue # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
11D46 ; ID_Continue # Lo MASARAM GONDI REPHA
11D47 ; ID_Continue # Mn MASARAM GONDI RA-KARA
11D50..11D59 ; ID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
12000..12399 ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -7406,10 +7502,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
16F51..16F7E ; ID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
16F8F..16F92 ; ID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
16F93..16F9F ; ID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; ID_Continue # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; ID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC ; ID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; ID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001 ; ID_Continue # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; ID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; ID_Continue # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; ID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -7506,10 +7603,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
2A700..2B734 ; ID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 119691
# Total code points: 128108
# ================================================
@@ -7578,6 +7676,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR
0824 ; XID_Start # Lm SAMARITAN MODIFIER LETTER SHORT A
0828 ; XID_Start # Lm SAMARITAN MODIFIER LETTER I
0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; XID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; XID_Start # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA
@@ -7597,6 +7696,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR
09DC..09DD ; XID_Start # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA
09DF..09E1 ; XID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL
09F0..09F1 ; XID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
09FC ; XID_Start # Lo BENGALI LETTER VEDIC ANUSVARA
0A05..0A0A ; XID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; XID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
0A13..0A28 ; XID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA
@@ -7853,12 +7953,12 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR
30A1..30FA ; XID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FC..30FE ; XID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; XID_Start # Lo KATAKANA DIGRAPH KOTO
3105..312D ; XID_Start # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; XID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; XID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; XID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; XID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FD5 ; XID_Start # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; XID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; XID_Start # Lm YI SYLLABLE WU
A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -7981,7 +8081,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
10280..1029C ; XID_Start # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X
102A0..102D0 ; XID_Start # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
10300..1031F ; XID_Start # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10330..10340 ; XID_Start # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
1032D..10340 ; XID_Start # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; XID_Start # Nl GOTHIC LETTER NINETY
10342..10349 ; XID_Start # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; XID_Start # Nl GOTHIC LETTER NINE HUNDRED
@@ -8068,11 +8168,21 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
11700..11719 ; XID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA
118A0..118DF ; XID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118FF ; XID_Start # Lo WARANG CITI OM
11A00 ; XID_Start # Lo ZANABAZAR SQUARE LETTER A
11A0B..11A32 ; XID_Start # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A3A ; XID_Start # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A50 ; XID_Start # Lo SOYOMBO LETTER A
11A5C..11A83 ; XID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; XID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08 ; XID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; XID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
11C40 ; XID_Start # Lo BHAIKSUKI SIGN AVAGRAHA
11C72..11C8F ; XID_Start # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A
11D00..11D06 ; XID_Start # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; XID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; XID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D46 ; XID_Start # Lo MASARAM GONDI REPHA
12000..12399 ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -8088,10 +8198,11 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
16F00..16F44 ; XID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA
16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION
16F93..16F9F ; XID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; XID_Start # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; XID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC ; XID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; XID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001 ; XID_Start # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; XID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; XID_Start # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; XID_Start # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -8165,9 +8276,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
2A700..2B734 ; XID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 116984
# Total code points: 125311
# ================================================
@@ -8266,6 +8378,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
0829..082D ; XID_Continue # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
0840..0858 ; XID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; XID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; XID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1 ; XID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
@@ -8310,6 +8423,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
09E2..09E3 ; XID_Continue # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
09E6..09EF ; XID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE
09F0..09F1 ; XID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL
09FC ; XID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA
0A01..0A02 ; XID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
0A03 ; XID_Continue # Mc GURMUKHI SIGN VISARGA
0A05..0A0A ; XID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
@@ -8352,6 +8466,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
0AE2..0AE3 ; XID_Continue # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AE6..0AEF ; XID_Continue # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE
0AF9 ; XID_Continue # Lo GUJARATI LETTER ZHA
0AFA..0AFF ; XID_Continue # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; XID_Continue # Mn ORIYA SIGN CANDRABINDU
0B02..0B03 ; XID_Continue # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C ; XID_Continue # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
@@ -8435,11 +8550,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2 ; XID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0D01 ; XID_Continue # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01 ; XID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03 ; XID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C ; XID_Continue # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10 ; XID_Continue # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A ; XID_Continue # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3B..0D3C ; XID_Continue # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3D ; XID_Continue # Lo MALAYALAM SIGN AVAGRAHA
0D3E..0D40 ; XID_Continue # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44 ; XID_Continue # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
@@ -8703,6 +8819,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
1CF2..1CF3 ; XID_Continue # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF4 ; XID_Continue # Mn VEDIC TONE CANDRA ABOVE
1CF5..1CF6 ; XID_Continue # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
1CF7 ; XID_Continue # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9 ; XID_Continue # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1D00..1D2B ; XID_Continue # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A ; XID_Continue # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
@@ -8710,7 +8827,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
1D78 ; XID_Continue # Lm MODIFIER LETTER CYRILLIC EN
1D79..1D9A ; XID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF ; XID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1DC0..1DF5 ; XID_Continue # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
1DC0..1DF9 ; XID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
1DFB..1DFF ; XID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1E00..1F15 ; XID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
1F18..1F1D ; XID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
@@ -8800,12 +8917,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
30A1..30FA ; XID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO
30FC..30FE ; XID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; XID_Continue # Lo KATAKANA DIGRAPH KOTO
3105..312D ; XID_Continue # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; XID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; XID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
31A0..31BA ; XID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY
31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO
3400..4DB5 ; XID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4E00..9FD5 ; XID_Continue # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; XID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; XID_Continue # Lm YI SYLLABLE WU
A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -8999,7 +9116,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
102A0..102D0 ; XID_Continue # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3
102E0 ; XID_Continue # Mn COPTIC EPACT THOUSANDS MARK
10300..1031F ; XID_Continue # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10330..10340 ; XID_Continue # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
1032D..10340 ; XID_Continue # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; XID_Continue # Nl GOTHIC LETTER NINETY
10342..10349 ; XID_Continue # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; XID_Continue # Nl GOTHIC LETTER NINE HUNDRED
@@ -9187,6 +9304,25 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
118A0..118DF ; XID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO
118E0..118E9 ; XID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118FF ; XID_Continue # Lo WARANG CITI OM
11A00 ; XID_Continue # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06 ; XID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08 ; XID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A ; XID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32 ; XID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A33..11A38 ; XID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A39 ; XID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3A ; XID_Continue # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A3B..11A3E ; XID_Continue # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A47 ; XID_Continue # Mn ZANABAZAR SQUARE SUBJOINER
11A50 ; XID_Continue # Lo SOYOMBO LETTER A
11A51..11A56 ; XID_Continue # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A57..11A58 ; XID_Continue # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
11A59..11A5B ; XID_Continue # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A5C..11A83 ; XID_Continue # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; XID_Continue # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11A8A..11A96 ; XID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA
11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; XID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
@@ -9205,6 +9341,16 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
11CB2..11CB3 ; XID_Continue # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB4 ; XID_Continue # Mc MARCHEN VOWEL SIGN O
11CB5..11CB6 ; XID_Continue # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D00..11D06 ; XID_Continue # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; XID_Continue # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; XID_Continue # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D31..11D36 ; XID_Continue # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; XID_Continue # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; XID_Continue # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D45 ; XID_Continue # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
11D46 ; XID_Continue # Lo MASARAM GONDI REPHA
11D47 ; XID_Continue # Mn MASARAM GONDI RA-KARA
11D50..11D59 ; XID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
12000..12399 ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12480..12543 ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
@@ -9226,10 +9372,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
16F51..16F7E ; XID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
16F8F..16F92 ; XID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
16F93..16F9F ; XID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; XID_Continue # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; XID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC ; XID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; XID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001 ; XID_Continue # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; XID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; XID_Continue # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; XID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -9326,10 +9473,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
2A700..2B734 ; XID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 119672
# Total code points: 128089
# ================================================
@@ -9339,8 +9487,8 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO
# + Cf (Format characters)
# + Variation_Selector
# - White_Space
# - FFF9..FFFB (Annotation Characters)
# - 0600..0605, 06DD, 070F, 08E2, 110BD (exceptional Cf characters that should be visible)
# - FFF9..FFFB (Annotation characters)
# - Prepended_Concatenation_Mark (Exceptional format characters that should be visible)
00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN
034F ; Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER
@@ -9431,6 +9579,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese
0AC7..0AC8 ; Grapheme_Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
0ACD ; Grapheme_Extend # Mn GUJARATI SIGN VIRAMA
0AE2..0AE3 ; Grapheme_Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
0AFA..0AFF ; Grapheme_Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01 ; Grapheme_Extend # Mn ORIYA SIGN CANDRABINDU
0B3C ; Grapheme_Extend # Mn ORIYA SIGN NUKTA
0B3E ; Grapheme_Extend # Mc ORIYA VOWEL SIGN AA
@@ -9459,7 +9608,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese
0CCC..0CCD ; Grapheme_Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
0CD5..0CD6 ; Grapheme_Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
0CE2..0CE3 ; Grapheme_Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0D01 ; Grapheme_Extend # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01 ; Grapheme_Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D3B..0D3C ; Grapheme_Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3E ; Grapheme_Extend # Mc MALAYALAM VOWEL SIGN AA
0D41..0D44 ; Grapheme_Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
0D4D ; Grapheme_Extend # Mn MALAYALAM SIGN VIRAMA
@@ -9548,7 +9698,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese
1CED ; Grapheme_Extend # Mn VEDIC SIGN TIRYAK
1CF4 ; Grapheme_Extend # Mn VEDIC TONE CANDRA ABOVE
1CF8..1CF9 ; Grapheme_Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1DC0..1DF5 ; Grapheme_Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
1DC0..1DF9 ; Grapheme_Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
1DFB..1DFF ; Grapheme_Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
200C ; Grapheme_Extend # Cf ZERO WIDTH NON-JOINER
20D0..20DC ; Grapheme_Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
@@ -9658,6 +9808,15 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK.
1171D..1171F ; Grapheme_Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA
11722..11725 ; Grapheme_Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU
11727..1172B ; Grapheme_Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER
11A01..11A06 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A09..11A0A ; Grapheme_Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A33..11A38 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A3B..11A3E ; Grapheme_Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A47 ; Grapheme_Extend # Mn ZANABAZAR SQUARE SUBJOINER
11A51..11A56 ; Grapheme_Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A59..11A5B ; Grapheme_Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A8A..11A96 ; Grapheme_Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A98..11A99 ; Grapheme_Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11C30..11C36 ; Grapheme_Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L
11C38..11C3D ; Grapheme_Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA
11C3F ; Grapheme_Extend # Mn BHAIKSUKI SIGN VIRAMA
@@ -9665,6 +9824,11 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK.
11CAA..11CB0 ; Grapheme_Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA
11CB2..11CB3 ; Grapheme_Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB5..11CB6 ; Grapheme_Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D31..11D36 ; Grapheme_Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A ; Grapheme_Extend # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D ; Grapheme_Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D45 ; Grapheme_Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
11D47 ; Grapheme_Extend # Mn MASARAM GONDI RA-KARA
16AF0..16AF4 ; Grapheme_Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
16B30..16B36 ; Grapheme_Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
@@ -9692,7 +9856,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK.
E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG
E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
# Total code points: 1828
# Total code points: 1901
# ================================================
@@ -9849,6 +10013,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
0830..083E ; Grapheme_Base # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU
0840..0858 ; Grapheme_Base # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
085E ; Grapheme_Base # Po MANDAIC PUNCTUATION
0860..086A ; Grapheme_Base # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4 ; Grapheme_Base # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD ; Grapheme_Base # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
0903 ; Grapheme_Base # Mc DEVANAGARI SIGN VISARGA
@@ -9885,6 +10050,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
09F4..09F9 ; Grapheme_Base # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN
09FA ; Grapheme_Base # So BENGALI ISSHAR
09FB ; Grapheme_Base # Sc BENGALI GANDA MARK
09FC ; Grapheme_Base # Lo BENGALI LETTER VEDIC ANUSVARA
09FD ; Grapheme_Base # Po BENGALI ABBREVIATION SIGN
0A03 ; Grapheme_Base # Mc GURMUKHI SIGN VISARGA
0A05..0A0A ; Grapheme_Base # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
0A0F..0A10 ; Grapheme_Base # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI
@@ -10227,6 +10394,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
1CEE..1CF1 ; Grapheme_Base # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA
1CF2..1CF3 ; Grapheme_Base # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF5..1CF6 ; Grapheme_Base # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
1CF7 ; Grapheme_Base # Mc VEDIC SIGN ATIKRAMA
1D00..1D2B ; Grapheme_Base # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A ; Grapheme_Base # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
1D6B..1D77 ; Grapheme_Base # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G
@@ -10297,7 +10465,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
208D ; Grapheme_Base # Ps SUBSCRIPT LEFT PARENTHESIS
208E ; Grapheme_Base # Pe SUBSCRIPT RIGHT PARENTHESIS
2090..209C ; Grapheme_Base # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T
20A0..20BE ; Grapheme_Base # Sc [31] EURO-CURRENCY SIGN..LARI SIGN
20A0..20BF ; Grapheme_Base # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN
2100..2101 ; Grapheme_Base # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
2102 ; Grapheme_Base # L& DOUBLE-STRUCK CAPITAL C
2103..2106 ; Grapheme_Base # So [4] DEGREE CELSIUS..CADA UNA
@@ -10371,8 +10539,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
239B..23B3 ; Grapheme_Base # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM
23B4..23DB ; Grapheme_Base # So [40] TOP SQUARE BRACKET..FUSE
23DC..23E1 ; Grapheme_Base # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET
23E2..23FE ; Grapheme_Base # So [29] WHITE TRAPEZIUM..POWER SLEEP SYMBOL
2400..2426 ; Grapheme_Base # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
23E2..2426 ; Grapheme_Base # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A ; Grapheme_Base # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..249B ; Grapheme_Base # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
249C..24E9 ; Grapheme_Base # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z
@@ -10458,7 +10625,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
2B76..2B95 ; Grapheme_Base # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9 ; Grapheme_Base # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8 ; Grapheme_Base # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD1 ; Grapheme_Base # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
2BCA..2BD2 ; Grapheme_Base # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF ; Grapheme_Base # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2C00..2C2E ; Grapheme_Base # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E ; Grapheme_Base # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
@@ -10523,7 +10690,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
2E40 ; Grapheme_Base # Pd DOUBLE HYPHEN
2E41 ; Grapheme_Base # Po REVERSED COMMA
2E42 ; Grapheme_Base # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E44 ; Grapheme_Base # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK
2E43..2E49 ; Grapheme_Base # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E80..2E99 ; Grapheme_Base # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3 ; Grapheme_Base # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5 ; Grapheme_Base # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
@@ -10575,7 +10742,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
30FB ; Grapheme_Base # Po KATAKANA MIDDLE DOT
30FC..30FE ; Grapheme_Base # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF ; Grapheme_Base # Lo KATAKANA DIGRAPH KOTO
3105..312D ; Grapheme_Base # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E ; Grapheme_Base # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E ; Grapheme_Base # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3190..3191 ; Grapheme_Base # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK
3192..3195 ; Grapheme_Base # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
@@ -10597,7 +10764,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE
3300..33FF ; Grapheme_Base # So [256] SQUARE APAATO..SQUARE GAL
3400..4DB5 ; Grapheme_Base # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4DC0..4DFF ; Grapheme_Base # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
4E00..9FD5 ; Grapheme_Base # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
4E00..9FEA ; Grapheme_Base # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
A000..A014 ; Grapheme_Base # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015 ; Grapheme_Base # Lm YI SYLLABLE WU
A016..A48C ; Grapheme_Base # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -10871,7 +11038,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
102E1..102FB ; Grapheme_Base # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED
10300..1031F ; Grapheme_Base # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10320..10323 ; Grapheme_Base # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY
10330..10340 ; Grapheme_Base # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
1032D..10340 ; Grapheme_Base # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA
10341 ; Grapheme_Base # Nl GOTHIC LETTER NINETY
10342..10349 ; Grapheme_Base # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
1034A ; Grapheme_Base # Nl GOTHIC LETTER NINE HUNDRED
@@ -11062,6 +11229,19 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
118E0..118E9 ; Grapheme_Base # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118EA..118F2 ; Grapheme_Base # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
118FF ; Grapheme_Base # Lo WARANG CITI OM
11A00 ; Grapheme_Base # Lo ZANABAZAR SQUARE LETTER A
11A07..11A08 ; Grapheme_Base # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A0B..11A32 ; Grapheme_Base # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A39 ; Grapheme_Base # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3A ; Grapheme_Base # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A3F..11A46 ; Grapheme_Base # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK
11A50 ; Grapheme_Base # Lo SOYOMBO LETTER A
11A57..11A58 ; Grapheme_Base # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
11A5C..11A83 ; Grapheme_Base # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89 ; Grapheme_Base # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11A97 ; Grapheme_Base # Mc SOYOMBO SIGN VISARGA
11A9A..11A9C ; Grapheme_Base # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
11A9E..11AA2 ; Grapheme_Base # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
11AC0..11AF8 ; Grapheme_Base # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08 ; Grapheme_Base # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E ; Grapheme_Base # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
@@ -11076,6 +11256,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
11CA9 ; Grapheme_Base # Mc MARCHEN SUBJOINED LETTER YA
11CB1 ; Grapheme_Base # Mc MARCHEN VOWEL SIGN I
11CB4 ; Grapheme_Base # Mc MARCHEN VOWEL SIGN O
11D00..11D06 ; Grapheme_Base # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09 ; Grapheme_Base # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30 ; Grapheme_Base # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D46 ; Grapheme_Base # Lo MASARAM GONDI REPHA
11D50..11D59 ; Grapheme_Base # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
12000..12399 ; Grapheme_Base # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E ; Grapheme_Base # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12470..12474 ; Grapheme_Base # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
@@ -11102,10 +11287,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
16F50 ; Grapheme_Base # Lo MIAO LETTER NASALIZATION
16F51..16F7E ; Grapheme_Base # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
16F93..16F9F ; Grapheme_Base # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0 ; Grapheme_Base # Lm TANGUT ITERATION MARK
16FE0..16FE1 ; Grapheme_Base # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC ; Grapheme_Base # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2 ; Grapheme_Base # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001 ; Grapheme_Base # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B11E ; Grapheme_Base # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB ; Grapheme_Base # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A ; Grapheme_Base # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C ; Grapheme_Base # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88 ; Grapheme_Base # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -11225,11 +11411,12 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1F210..1F23B ; Grapheme_Base # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248 ; Grapheme_Base # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251 ; Grapheme_Base # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
1F260..1F265 ; Grapheme_Base # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
1F300..1F3FA ; Grapheme_Base # So [251] CYCLONE..AMPHORA
1F3FB..1F3FF ; Grapheme_Base # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
1F400..1F6D2 ; Grapheme_Base # So [723] RAT..SHOPPING TROLLEY
1F400..1F6D4 ; Grapheme_Base # So [725] RAT..PAGODA
1F6E0..1F6EC ; Grapheme_Base # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING
1F6F0..1F6F6 ; Grapheme_Base # So [7] SATELLITE..CANOE
1F6F0..1F6F8 ; Grapheme_Base # So [9] SATELLITE..FLYING SAUCER
1F700..1F773 ; Grapheme_Base # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D4 ; Grapheme_Base # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F800..1F80B ; Grapheme_Base # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -11237,21 +11424,21 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
1F850..1F859 ; Grapheme_Base # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
1F860..1F887 ; Grapheme_Base # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F910..1F91E ; Grapheme_Base # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED
1F920..1F927 ; Grapheme_Base # So [8] FACE WITH COWBOY HAT..SNEEZING FACE
1F930 ; Grapheme_Base # So PREGNANT WOMAN
1F933..1F93E ; Grapheme_Base # So [12] SELFIE..HANDBALL
1F940..1F94B ; Grapheme_Base # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM
1F950..1F95E ; Grapheme_Base # So [15] CROISSANT..PANCAKES
1F980..1F991 ; Grapheme_Base # So [18] CRAB..SQUID
1F900..1F90B ; Grapheme_Base # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
1F910..1F93E ; Grapheme_Base # So [47] ZIPPER-MOUTH FACE..HANDBALL
1F940..1F94C ; Grapheme_Base # So [13] WILTED FLOWER..CURLING STONE
1F950..1F96B ; Grapheme_Base # So [28] CROISSANT..CANNED FOOD
1F980..1F997 ; Grapheme_Base # So [24] CRAB..CRICKET
1F9C0 ; Grapheme_Base # So CHEESE WEDGE
1F9D0..1F9E6 ; Grapheme_Base # So [23] FACE WITH MONOCLE..SOCKS
20000..2A6D6 ; Grapheme_Base # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A700..2B734 ; Grapheme_Base # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Grapheme_Base # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Grapheme_Base # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
# Total code points: 126288
# Total code points: 134733
# ================================================
@@ -11267,6 +11454,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME
0BCD ; Grapheme_Link # Mn TAMIL SIGN VIRAMA
0C4D ; Grapheme_Link # Mn TELUGU SIGN VIRAMA
0CCD ; Grapheme_Link # Mn KANNADA SIGN VIRAMA
0D3B..0D3C ; Grapheme_Link # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D4D ; Grapheme_Link # Mn MALAYALAM SIGN VIRAMA
0DCA ; Grapheme_Link # Mn SINHALA SIGN AL-LAKUNA
0E3A ; Grapheme_Link # Mn THAI CHARACTER PHINTHU
@@ -11302,8 +11490,12 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK
1163F ; Grapheme_Link # Mn MODI SIGN VIRAMA
116B6 ; Grapheme_Link # Mc TAKRI SIGN VIRAMA
1172B ; Grapheme_Link # Mn AHOM SIGN KILLER
11A34 ; Grapheme_Link # Mn ZANABAZAR SQUARE SIGN VIRAMA
11A47 ; Grapheme_Link # Mn ZANABAZAR SQUARE SUBJOINER
11A99 ; Grapheme_Link # Mn SOYOMBO SUBJOINER
11C3F ; Grapheme_Link # Mn BHAIKSUKI SIGN VIRAMA
11D44..11D45 ; Grapheme_Link # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
# Total code points: 47
# Total code points: 54
# EOF

90
localedata/unicode-gen/EastAsianWidth.txt
View File

@@ -1,6 +1,6 @@
# EastAsianWidth-9.0.0.txt
# Date: 2016-05-27, 17:00:00 GMT [KW, LI]
# © 2016 Unicode®, Inc.
# EastAsianWidth-10.0.0.txt
# Date: 2017-03-08, 02:00:00 GMT [KW, LI]
# © 2017 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
@@ -328,6 +328,7 @@
0840..0858;N # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0859..085B;N # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
085E;N # Po MANDAIC PUNCTUATION
0860..086A;N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
08A0..08B4;N # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW
08B6..08BD;N # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON
08D4..08E1;N # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA
@@ -381,6 +382,8 @@
09F4..09F9;N # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN
09FA;N # So BENGALI ISSHAR
09FB;N # Sc BENGALI GANDA MARK
09FC;N # Lo BENGALI LETTER VEDIC ANUSVARA
09FD;N # Po BENGALI ABBREVIATION SIGN
0A01..0A02;N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
0A03;N # Mc GURMUKHI SIGN VISARGA
0A05..0A0A;N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU
@@ -425,6 +428,7 @@
0AF0;N # Po GUJARATI ABBREVIATION SIGN
0AF1;N # Sc GUJARATI RUPEE SIGN
0AF9;N # Lo GUJARATI LETTER ZHA
0AFA..0AFF;N # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B01;N # Mn ORIYA SIGN CANDRABINDU
0B02..0B03;N # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA
0B05..0B0C;N # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L
@@ -516,11 +520,12 @@
0CE2..0CE3;N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
0CE6..0CEF;N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
0CF1..0CF2;N # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
0D01;N # Mn MALAYALAM SIGN CANDRABINDU
0D00..0D01;N # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02..0D03;N # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
0D05..0D0C;N # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L
0D0E..0D10;N # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
0D12..0D3A;N # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA
0D3B..0D3C;N # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA
0D3D;N # Lo MALAYALAM SIGN AVAGRAHA
0D3E..0D40;N # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
0D41..0D44;N # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
@@ -853,6 +858,7 @@
1CF2..1CF3;N # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
1CF4;N # Mn VEDIC TONE CANDRA ABOVE
1CF5..1CF6;N # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA
1CF7;N # Mc VEDIC SIGN ATIKRAMA
1CF8..1CF9;N # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE
1D00..1D2B;N # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL
1D2C..1D6A;N # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
@@ -861,7 +867,7 @@
1D79..1D7F;N # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE
1D80..1D9A;N # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK
1D9B..1DBF;N # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
1DC0..1DF5;N # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE
1DC0..1DF9;N # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW
1DFB..1DFF;N # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
1E00..1EFF;N # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP
1F00..1F15;N # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
@@ -954,7 +960,7 @@
20A9;H # Sc WON SIGN
20AA..20AB;N # Sc [2] NEW SHEQEL SIGN..DONG SIGN
20AC;A # Sc EURO SIGN
20AD..20BE;N # Sc [18] KIP SIGN..LARI SIGN
20AD..20BF;N # Sc [19] KIP SIGN..BITCOIN SIGN
20D0..20DC;N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
20DD..20E0;N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
20E1;N # Mn COMBINING LEFT RIGHT ARROW ABOVE
@@ -1120,7 +1126,7 @@
23F0;W # So ALARM CLOCK
23F1..23F2;N # So [2] STOPWATCH..TIMER CLOCK
23F3;W # So HOURGLASS WITH FLOWING SAND
23F4..23FE;N # So [11] BLACK MEDIUM LEFT-POINTING TRIANGLE..POWER SLEEP SYMBOL
23F4..23FF;N # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL
2400..2426;N # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO
2440..244A;N # So [11] OCR HOOK..OCR DOUBLE BACKSLASH
2460..249B;A # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP
@@ -1328,7 +1334,7 @@
2B76..2B95;N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW
2B98..2BB9;N # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX
2BBD..2BC8;N # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED
2BCA..2BD1;N # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN
2BCA..2BD2;N # So [9] TOP HALF BLACK CIRCLE..GROUP MARK
2BEC..2BEF;N # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS
2C00..2C2E;N # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
2C30..2C5E;N # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE
@@ -1397,7 +1403,7 @@
2E40;N # Pd DOUBLE HYPHEN
2E41;N # Po REVERSED COMMA
2E42;N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK
2E43..2E44;N # Po [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK
2E43..2E49;N # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA
2E80..2E99;W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP
2E9B..2EF3;W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE
2F00..2FD5;W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE
@@ -1453,7 +1459,7 @@
30FB;W # Po KATAKANA MIDDLE DOT
30FC..30FE;W # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK
30FF;W # Lo KATAKANA DIGRAPH KOTO
3105..312D;W # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH
3105..312E;W # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE
3131..318E;W # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE
3190..3191;W # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK
3192..3195;W # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK
@@ -1476,8 +1482,8 @@
3400..4DB5;W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5
4DB6..4DBF;W # Cn [10] <reserved-4DB6>..<reserved-4DBF>
4DC0..4DFF;N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION
4E00..9FD5;W # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5
9FD6..9FFF;W # Cn [42] <reserved-9FD6>..<reserved-9FFF>
4E00..9FEA;W # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA
9FEB..9FFF;W # Cn [21] <reserved-9FEB>..<reserved-9FFF>
A000..A014;W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E
A015;W # Lm YI SYLLABLE WU
A016..A48C;W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR
@@ -1803,6 +1809,7 @@ FFFD;A # So REPLACEMENT CHARACTER
102E1..102FB;N # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED
10300..1031F;N # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS
10320..10323;N # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY
1032D..1032F;N # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE
10330..10340;N # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA
10341;N # Nl GOTHIC LETTER NINETY
10342..10349;N # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL
@@ -2050,6 +2057,28 @@ FFFD;A # So REPLACEMENT CHARACTER
118E0..118E9;N # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE
118EA..118F2;N # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY
118FF;N # Lo WARANG CITI OM
11A00;N # Lo ZANABAZAR SQUARE LETTER A
11A01..11A06;N # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O
11A07..11A08;N # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU
11A09..11A0A;N # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK
11A0B..11A32;N # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA
11A33..11A38;N # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA
11A39;N # Mc ZANABAZAR SQUARE SIGN VISARGA
11A3A;N # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
11A3B..11A3E;N # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA
11A3F..11A46;N # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK
11A47;N # Mn ZANABAZAR SQUARE SUBJOINER
11A50;N # Lo SOYOMBO LETTER A
11A51..11A56;N # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE
11A57..11A58;N # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU
11A59..11A5B;N # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK
11A5C..11A83;N # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA
11A86..11A89;N # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA
11A8A..11A96;N # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA
11A97;N # Mc SOYOMBO SIGN VISARGA
11A98..11A99;N # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER
11A9A..11A9C;N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
11A9E..11AA2;N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
11AC0..11AF8;N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL
11C00..11C08;N # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
11C0A..11C2E;N # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
@@ -2071,6 +2100,16 @@ FFFD;A # So REPLACEMENT CHARACTER
11CB2..11CB3;N # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E
11CB4;N # Mc MARCHEN VOWEL SIGN O
11CB5..11CB6;N # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D00..11D06;N # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E
11D08..11D09;N # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O
11D0B..11D30;N # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA
11D31..11D36;N # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R
11D3A;N # Mn MASARAM GONDI VOWEL SIGN E
11D3C..11D3D;N # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O
11D3F..11D45;N # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA
11D46;N # Lo MASARAM GONDI REPHA
11D47;N # Mn MASARAM GONDI RA-KARA
11D50..11D59;N # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
12000..12399;N # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
12400..1246E;N # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
12470..12474;N # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
@@ -2100,10 +2139,12 @@ FFFD;A # So REPLACEMENT CHARACTER
16F51..16F7E;N # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG
16F8F..16F92;N # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
16F93..16F9F;N # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8
16FE0;W # Lm TANGUT ITERATION MARK
16FE0..16FE1;W # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK
17000..187EC;W # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC
18800..18AF2;W # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755
1B000..1B001;W # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE
1B000..1B0FF;W # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2
1B100..1B11E;W # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2
1B170..1B2FB;W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
1BC00..1BC6A;N # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
1BC70..1BC7C;N # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK
1BC80..1BC88;N # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL
@@ -2255,6 +2296,7 @@ FFFD;A # So REPLACEMENT CHARACTER
1F210..1F23B;W # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D
1F240..1F248;W # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
1F250..1F251;W # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
1F260..1F265;W # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
1F300..1F320;W # So [33] CYCLONE..SHOOTING STAR
1F321..1F32C;N # So [12] THERMOMETER..WIND BLOWING FACE
1F32D..1F335;W # So [9] HOT DOG..CACTUS
@@ -2299,10 +2341,11 @@ FFFD;A # So REPLACEMENT CHARACTER
1F6CC;W # So SLEEPING ACCOMMODATION
1F6CD..1F6CF;N # So [3] SHOPPING BAGS..BED
1F6D0..1F6D2;W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY
1F6D3..1F6D4;N # So [2] STUPA..PAGODA
1F6E0..1F6EA;N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE
1F6EB..1F6EC;W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING
1F6F0..1F6F3;N # So [4] SATELLITE..PASSENGER SHIP
1F6F4..1F6F6;W # So [3] SCOOTER..CANOE
1F6F4..1F6F8;W # So [5] SCOOTER..FLYING SAUCER
1F700..1F773;N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
1F780..1F7D4;N # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR
1F800..1F80B;N # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -2310,14 +2353,13 @@ FFFD;A # So REPLACEMENT CHARACTER
1F850..1F859;N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW
1F860..1F887;N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
1F890..1F8AD;N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS
1F910..1F91E;W # So [15] ZIPPER-MOUTH FACE..HAND WITH INDEX AND MIDDLE FINGERS CROSSED
1F920..1F927;W # So [8] FACE WITH COWBOY HAT..SNEEZING FACE
1F930;W # So PREGNANT WOMAN
1F933..1F93E;W # So [12] SELFIE..HANDBALL
1F940..1F94B;W # So [12] WILTED FLOWER..MARTIAL ARTS UNIFORM
1F950..1F95E;W # So [15] CROISSANT..PANCAKES
1F980..1F991;W # So [18] CRAB..SQUID
1F900..1F90B;N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT
1F910..1F93E;W # So [47] ZIPPER-MOUTH FACE..HANDBALL
1F940..1F94C;W # So [13] WILTED FLOWER..CURLING STONE
1F950..1F96B;W # So [28] CROISSANT..CANNED FOOD
1F980..1F997;W # So [24] CRAB..CRICKET
1F9C0;W # So CHEESE WEDGE
1F9D0..1F9E6;W # So [23] FACE WITH MONOCLE..SOCKS
20000..2A6D6;W # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
2A6D7..2A6FF;W # Cn [41] <reserved-2A6D7>..<reserved-2A6FF>
2A700..2B734;W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
@@ -2325,7 +2367,9 @@ FFFD;A # So REPLACEMENT CHARACTER
2B740..2B81D;W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B81E..2B81F;W # Cn [2] <reserved-2B81E>..<reserved-2B81F>
2B820..2CEA1;W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEA2..2F7FF;W # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF>
2CEA2..2CEAF;W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF>
2CEB0..2EBE0;W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
2EBE1..2F7FF;W # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF>
2F800..2FA1D;W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
2FA1E..2FFFD;W # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD>
30000..3FFFD;W # Cn [65534] <reserved-30000>..<reserved-3FFFD>

2
localedata/unicode-gen/Makefile
View File

@@ -35,7 +35,7 @@
# files for making modifications.
UNICODE_VERSION = 9.0.0
UNICODE_VERSION = 10.0.0
PYTHON3 = python3
WGET = wget

1028
localedata/unicode-gen/UnicodeData.txt
View File

File diff suppressed because it is too large Load Diff