diff options
author | Unicode Consortium <unicode.org> | 2021-09-15 08:26:00 -0600 |
---|---|---|
committer | Karl Williamson <khw@cpan.org> | 2021-09-15 08:48:07 -0600 |
commit | 2f1eff3d4e0c24e2ac28c8bcaa8eb740b8e22c48 (patch) | |
tree | 5663d676e6faeb3a092b9ca3d1226eedf5a7f8a8 /lib | |
parent | 5c7c2de1bc6dcddd66e6617b3747594ee19229a6 (diff) | |
download | perl-2f1eff3d4e0c24e2ac28c8bcaa8eb740b8e22c48.tar.gz |
Support Unicode 14.0
Diffstat (limited to 'lib')
59 files changed, 6804 insertions, 2525 deletions
diff --git a/lib/Unicode/UCD.t b/lib/Unicode/UCD.t index c7e3ecb046..3d39121217 100644 --- a/lib/Unicode/UCD.t +++ b/lib/Unicode/UCD.t @@ -19,7 +19,7 @@ use Test::More; use Unicode::UCD qw(charinfo charprop charprops_all); -my $expected_version = '13.0.0'; +my $expected_version = '14.0.0'; my $current_version = Unicode::UCD::UnicodeVersion; my $v_unicode_version = pack "C*", split /\./, $current_version; my $unknown_script = ($v_unicode_version lt v5.0.0) @@ -786,7 +786,7 @@ SKIP: skip("Latin range count will be wrong when using older Unicode release", 2) if $current_version lt $expected_version; my $n1 = @$r1; - is($n1, 32, "number of ranges in Latin script (Unicode $expected_version)") if $::IS_ASCII; + is($n1, 38, "number of ranges in Latin script (Unicode $expected_version)") if $::IS_ASCII; shift @$r1 while @$r1; my $r2 = charscript('Latin'); is(@$r2, $n1, "modifying results should not mess up internal caches"); diff --git a/lib/unicore/ArabicShaping.txt b/lib/unicore/ArabicShaping.txt index 9a93adc12f..bfb6b47a55 100644 --- a/lib/unicore/ArabicShaping.txt +++ b/lib/unicore/ArabicShaping.txt @@ -1,6 +1,6 @@ -# ArabicShaping-13.0.0.txt -# Date: 2020-01-31, 23:55:00 GMT [KW, RP] -# © 2020 Unicode®, Inc. +# ArabicShaping-14.0.0.txt +# Date: 2021-05-21, 01:54:00 GMT [KW, RP] +# © 2021 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 # @@ -13,11 +13,12 @@ # exemplified in Tables 9-3, 9-8, 9-9, 9-10, 9-14, 9-15, 9-16, 9-19, # 9-20, 10-4, 10-5, 10-6, 10-7, and 19-5 of The Unicode Standard core # specification. This file also defines Joining_Type values for -# Mongolian, Phags-pa, Psalter Pahlavi, Sogdian, Chorasmian, and Adlam positional shaping, +# Mongolian, Phags-pa, Psalter Pahlavi, Sogdian, Old Uyghur, Chorasmian, +# and Adlam positional shaping, # and Joining_Type and Joining_Group values for Hanifi Rohingya positional shaping, # which are not listed in tables in the standard. # -# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 14.10, 16.14, 19.4, and 19.9 +# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.5, 14.4, 14.10, 14.11, 16.14, 19.4, and 19.9 # of The Unicode Standard core specification for more information. # # Each line contains four fields, separated by a semicolon. @@ -44,7 +45,7 @@ # Note that for cursive joining scripts which are typically rendered # top-to-bottom, rather than right-to-left, Joining_Type=L conventionally # refers to bottom joining, and Joining_Type=R conventionally refers -# to top joining. See Section 14.3, Phags-pa for more information on the +# to top joining. See Section 14.4, Phags-pa for more information on the # interpretation of joining types in vertical layout. # # Field 3: defines the joining group (property name: Joining_Group) @@ -79,7 +80,7 @@ # joining group values will be defined only if an explicit proposal # to define those values exactly has been approved by the UTC. This # is the convention exemplified by the N'Ko, Mandaic, Mongolian, -# Phags-pa, Psalter Pahlavi, Sogdian, Chorasmian, and Adlam scripts. +# Phags-pa, Psalter Pahlavi, Sogdian, Old Uyghur, Chorasmian, and Adlam scripts. # Only the Arabic, Manichaean, and Syriac scripts currently have # explicit joining group values defined for all characters, including # those which have only a single character in a particular Joining_Group @@ -162,7 +163,7 @@ 0674; HIGH HAMZA; U; No_Joining_Group 0675; HIGH HAMZA ALEF; R; ALEF 0676; HIGH HAMZA WAW; R; WAW -0677; HIGH HAMZA WAW WITH DAMMA ABOVE; R; WAW +0677; HIGH HAMZA WAW WITH COMMA ABOVE; R; WAW 0678; HIGH HAMZA DOTLESS YEH; D; YEH 0679; DOTLESS BEH WITH TAH ABOVE; D; BEH 067A; DOTLESS BEH WITH VERTICAL 2 DOTS ABOVE; D; BEH @@ -240,9 +241,9 @@ 06C2; HEH GOAL WITH HAMZA ABOVE; D; HEH GOAL 06C3; TEH MARBUTA GOAL; R; TEH MARBUTA GOAL 06C4; WAW WITH ATTACHED RING WITHIN; R; WAW -06C5; WAW WITH BAR; R; WAW +06C5; WAW WITH LOOP; R; WAW 06C6; WAW WITH V ABOVE; R; WAW -06C7; WAW WITH DAMMA ABOVE; R; WAW +06C7; WAW WITH COMMA ABOVE; R; WAW 06C8; WAW WITH ALEF ABOVE; R; WAW 06C9; WAW WITH INVERTED V ABOVE; R; WAW 06CA; WAW WITH 2 DOTS ABOVE; R; WAW @@ -432,6 +433,42 @@ 0869; MALAYALAM LLLA; R; MALAYALAM LLLA 086A; MALAYALAM SSA; R; MALAYALAM SSA +# Arabic Extended-B Characters + +0870; ALEF WITH ATTACHED FATHA; R; ALEF +0871; ALEF WITH ATTACHED TOP RIGHT FATHA; R; ALEF +0872; ALEF WITH RIGHT MIDDLE STROKE; R; ALEF +0873; ALEF WITH LEFT MIDDLE STROKE; R; ALEF +0874; ALEF WITH ATTACHED KASRA; R; ALEF +0875; ALEF WITH ATTACHED BOTTOM RIGHT KASRA; R; ALEF +0876; ALEF WITH ATTACHED ROUND DOT ABOVE; R; ALEF +0877; ALEF WITH ATTACHED RIGHT ROUND DOT; R; ALEF +0878; ALEF WITH ATTACHED LEFT ROUND DOT; R; ALEF +0879; ALEF WITH ATTACHED ROUND DOT BELOW; R; ALEF +087A; ALEF WITH DOT ABOVE; R; ALEF +087B; ALEF WITH ATTACHED TOP RIGHT FATHA AND DOT ABOVE; R; ALEF +087C; ALEF WITH RIGHT MIDDLE STROKE AND DOT ABOVE; R; ALEF +087D; ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND DOT ABOVE; R; ALEF +087E; ALEF WITH ATTACHED TOP RIGHT FATHA AND LEFT RING; R; ALEF +087F; ALEF WITH RIGHT MIDDLE STROKE AND LEFT RING; R; ALEF +0880; ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND LEFT RING; R; ALEF +0881; ALEF WITH ATTACHED RIGHT HAMZA; R; ALEF +0882; ALEF WITH ATTACHED LEFT HAMZA; R; ALEF +0883; TATWEEL WITH OVERSTRUCK HAMZA; C; No_Joining_Group +0884; TATWEEL WITH OVERSTRUCK WAW; C; No_Joining_Group +0885; TATWEEL WITH TWO DOTS BELOW; C; No_Joining_Group +0886; THIN YEH; D; THIN YEH +0887; ARABIC BASELINE ROUND DOT; U; No_Joining_Group +0888; ARABIC RAISED ROUND DOT; U; No_Joining_Group +0889; DOTLESS NOON WITH INVERTED V ABOVE; D; NOON +088A; HAH WITH INVERTED V BELOW; D; HAH +088B; TAH WITH DOT BELOW; D; TAH +088C; TAH WITH 3 DOTS BELOW; D; TAH +088D; KEHEH WITH VERTICAL 2 DOTS BELOW; D; GAF +088E; VERTICAL TAIL; R; VERTICAL TAIL +0890; ARABIC POUND MARK ABOVE; U; No_Joining_Group +0891; ARABIC PIASTRE MARK ABOVE; U; No_Joining_Group + # Arabic Extended-A Characters 08A0; DOTLESS BEH WITH V BELOW; D; BEH @@ -455,6 +492,7 @@ 08B2; REH WITH DOT AND INVERTED V ABOVE; R; REH 08B3; AIN WITH 3 DOTS BELOW; D; AIN 08B4; KAF WITH DOT BELOW; D; KAF +08B5; DOTLESS QAF WITH DOT BELOW; D; QAF 08B6; BEH WITH MEEM ABOVE; D; BEH 08B7; DOTLESS BEH WITH 3 DOTS BELOW AND MEEM ABOVE; D; BEH 08B8; DOTLESS BEH WITH TEH ABOVE; D; BEH @@ -473,6 +511,7 @@ 08C5; HAH WITH DOT BELOW AND 3 DOTS ABOVE; D; HAH 08C6; HAH WITH DIAMOND 4 DOTS BELOW; D; HAH 08C7; LAM WITH TAH ABOVE; D; LAM +08C8; KEHEH WITH ELONGATED HAMZA ABOVE; D; GAF 08E2; ARABIC DISPUTED END OF AYAH; U; No_Joining_Group # Mongolian Characters @@ -819,6 +858,27 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group 10F53; SOGDIAN TWENTY; D; No_Joining_Group 10F54; SOGDIAN ONE HUNDRED; R; No_Joining_Group +# Old Uyghur Characters + +10F70; OLD UYGHUR ALEPH; D; No_Joining_Group +10F71; OLD UYGHUR BETH; D; No_Joining_Group +10F72; OLD UYGHUR GIMEL-HETH; D; No_Joining_Group +10F73; OLD UYGHUR WAW; D; No_Joining_Group +10F74; OLD UYGHUR ZAYIN; R; No_Joining_Group +10F75; OLD UYGHUR FINAL HETH; R; No_Joining_Group +10F76; OLD UYGHUR YODH; D; No_Joining_Group +10F77; OLD UYGHUR KAPH; D; No_Joining_Group +10F78; OLD UYGHUR LAMEDH; D; No_Joining_Group +10F79; OLD UYGHUR MEM; D; No_Joining_Group +10F7A; OLD UYGHUR NUN; D; No_Joining_Group +10F7B; OLD UYGHUR SAMEKH; D; No_Joining_Group +10F7C; OLD UYGHUR PE; D; No_Joining_Group +10F7D; OLD UYGHUR SADHE; D; No_Joining_Group +10F7E; OLD UYGHUR RESH; D; No_Joining_Group +10F7F; OLD UYGHUR SHIN; D; No_Joining_Group +10F80; OLD UYGHUR TAW; D; No_Joining_Group +10F81; OLD UYGHUR LESH; D; No_Joining_Group + # Chorasmian Characters 10FB0; CHORASMIAN ALEPH; D; No_Joining_Group diff --git a/lib/unicore/BidiBrackets.txt b/lib/unicore/BidiBrackets.txt index a95e5ca5ca..89698f588a 100644 --- a/lib/unicore/BidiBrackets.txt +++ b/lib/unicore/BidiBrackets.txt @@ -1,11 +1,11 @@ -# BidiBrackets-13.0.0.txt -# Date: 2019-09-09, 19:31:00 GMT [AG, LI, KW] -# © 2019 Unicode®, Inc. +# BidiBrackets-14.0.0.txt +# Date: 2021-06-30, 23:59:00 GMT [AG, LI, KW] +# © 2021 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 +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Bidi_Paired_Bracket and Bidi_Paired_Bracket_Type Properties # @@ -56,7 +56,7 @@ # of each line. # # For information on bidirectional paired brackets, see UAX #9: Unicode -# Bidirectional Algorithm, at http://www.unicode.org/unicode/reports/tr9/ +# Bidirectional Algorithm, at https://www.unicode.org/reports/tr9/ # # This file was originally created by Andrew Glass and Laurentiu Iancu # for Unicode 6.3. @@ -147,6 +147,14 @@ 2E27; 2E26; c # RIGHT SIDEWAYS U BRACKET 2E28; 2E29; o # LEFT DOUBLE PARENTHESIS 2E29; 2E28; c # RIGHT DOUBLE PARENTHESIS +2E55; 2E56; o # LEFT SQUARE BRACKET WITH STROKE +2E56; 2E55; c # RIGHT SQUARE BRACKET WITH STROKE +2E57; 2E58; o # LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58; 2E57; c # RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59; 2E5A; o # TOP HALF LEFT PARENTHESIS +2E5A; 2E59; c # TOP HALF RIGHT PARENTHESIS +2E5B; 2E5C; o # BOTTOM HALF LEFT PARENTHESIS +2E5C; 2E5B; c # BOTTOM HALF RIGHT PARENTHESIS 3008; 3009; o # LEFT ANGLE BRACKET 3009; 3008; c # RIGHT ANGLE BRACKET 300A; 300B; o # LEFT DOUBLE ANGLE BRACKET diff --git a/lib/unicore/BidiMirroring.txt b/lib/unicore/BidiMirroring.txt index 34e42ae8dc..bd8e2c5d00 100644 --- a/lib/unicore/BidiMirroring.txt +++ b/lib/unicore/BidiMirroring.txt @@ -1,10 +1,10 @@ -# BidiMirroring-13.0.0.txt -# Date: 2019-09-09, 19:34:00 GMT [KW, LI, RP] -# © 2019 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# BidiMirroring-14.0.0.txt +# Date: 2021-08-08, 22:55:00 GMT [KW, RP] +# © 2021 Unicode®, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Bidi_Mirroring_Glyph Property # @@ -15,7 +15,7 @@ # value, for which there is another Unicode character that typically has a glyph # that is the mirror image of the original character's glyph. # -# The repertoire covered by the file is Unicode 13.0.0. +# The repertoire covered by the file is Unicode 14.0.0. # # The file contains a list of lines with mappings from one code point # to another one for character-based mirroring. @@ -40,7 +40,7 @@ # for character-based mirroring. # # For information on bidi mirroring, see UAX #9: Unicode Bidirectional Algorithm, -# at http://www.unicode.org/unicode/reports/tr9/ +# at https://www.unicode.org/reports/tr9/ # # This file was originally created by Markus Scherer. # Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler, @@ -96,10 +96,10 @@ 208D; 208E # SUBSCRIPT LEFT PARENTHESIS 208E; 208D # SUBSCRIPT RIGHT PARENTHESIS 2208; 220B # ELEMENT OF -2209; 220C # NOT AN ELEMENT OF +2209; 220C # [BEST FIT] NOT AN ELEMENT OF 220A; 220D # SMALL ELEMENT OF 220B; 2208 # CONTAINS AS MEMBER -220C; 2209 # DOES NOT CONTAIN AS MEMBER +220C; 2209 # [BEST FIT] DOES NOT CONTAIN AS MEMBER 220D; 220A # SMALL CONTAINS AS MEMBER 2215; 29F5 # DIVISION SLASH 221F; 2BFE # RIGHT ANGLE @@ -453,6 +453,14 @@ 2E27; 2E26 # RIGHT SIDEWAYS U BRACKET 2E28; 2E29 # LEFT DOUBLE PARENTHESIS 2E29; 2E28 # RIGHT DOUBLE PARENTHESIS +2E55; 2E56 # LEFT SQUARE BRACKET WITH STROKE +2E56; 2E55 # RIGHT SQUARE BRACKET WITH STROKE +2E57; 2E58 # LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58; 2E57 # RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59; 2E5A # TOP HALF LEFT PARENTHESIS +2E5A; 2E59 # TOP HALF RIGHT PARENTHESIS +2E5B; 2E5C # BOTTOM HALF LEFT PARENTHESIS +2E5C; 2E5B # BOTTOM HALF RIGHT PARENTHESIS 3008; 3009 # LEFT ANGLE BRACKET 3009; 3008 # RIGHT ANGLE BRACKET 300A; 300B # LEFT DOUBLE ANGLE BRACKET diff --git a/lib/unicore/Blocks.txt b/lib/unicore/Blocks.txt index 56877db10f..cc5d61988b 100644 --- a/lib/unicore/Blocks.txt +++ b/lib/unicore/Blocks.txt @@ -1,6 +1,6 @@ -# Blocks-13.0.0.txt -# Date: 2019-07-10, 19:06:00 GMT [KW] -# © 2019 Unicode®, Inc. +# Blocks-14.0.0.txt +# Date: 2021-01-22, 23:29:00 GMT [KW] +# © 2021 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -52,6 +52,7 @@ 0800..083F; Samaritan 0840..085F; Mandaic 0860..086F; Syriac Supplement +0870..089F; Arabic Extended-B 08A0..08FF; Arabic Extended-A 0900..097F; Devanagari 0980..09FF; Bengali @@ -215,7 +216,9 @@ FFF0..FFFF; Specials 104B0..104FF; Osage 10500..1052F; Elbasan 10530..1056F; Caucasian Albanian +10570..105BF; Vithkuqi 10600..1077F; Linear A +10780..107BF; Latin Extended-F 10800..1083F; Cypriot Syllabary 10840..1085F; Imperial Aramaic 10860..1087F; Palmyrene @@ -240,6 +243,7 @@ FFF0..FFFF; Specials 10E80..10EBF; Yezidi 10F00..10F2F; Old Sogdian 10F30..10F6F; Sogdian +10F70..10FAF; Old Uyghur 10FB0..10FDF; Chorasmian 10FE0..10FFF; Elymaic 11000..1107F; Brahmi @@ -259,13 +263,14 @@ FFF0..FFFF; Specials 11600..1165F; Modi 11660..1167F; Mongolian Supplement 11680..116CF; Takri -11700..1173F; Ahom +11700..1174F; Ahom 11800..1184F; Dogra 118A0..118FF; Warang Citi 11900..1195F; Dives Akuru 119A0..119FF; Nandinagari 11A00..11A4F; Zanabazar Square 11A50..11AAF; Soyombo +11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A 11AC0..11AFF; Pau Cin Hau 11C00..11C6F; Bhaiksuki 11C70..11CBF; Marchen @@ -277,11 +282,13 @@ FFF0..FFFF; Specials 12000..123FF; Cuneiform 12400..1247F; Cuneiform Numbers and Punctuation 12480..1254F; Early Dynastic Cuneiform +12F90..12FFF; Cypro-Minoan 13000..1342F; Egyptian Hieroglyphs 13430..1343F; Egyptian Hieroglyph Format Controls 14400..1467F; Anatolian Hieroglyphs 16800..16A3F; Bamum Supplement 16A40..16A6F; Mro +16A70..16ACF; Tangsa 16AD0..16AFF; Bassa Vah 16B00..16B8F; Pahawh Hmong 16E40..16E9F; Medefaidrin @@ -290,13 +297,15 @@ FFF0..FFFF; Specials 17000..187FF; Tangut 18800..18AFF; Tangut Components 18B00..18CFF; Khitan Small Script -18D00..18D8F; Tangut Supplement +18D00..18D7F; Tangut Supplement +1AFF0..1AFFF; Kana Extended-B 1B000..1B0FF; Kana Supplement 1B100..1B12F; Kana Extended-A 1B130..1B16F; Small Kana Extension 1B170..1B2FF; Nushu 1BC00..1BC9F; Duployan 1BCA0..1BCAF; Shorthand Format Controls +1CF00..1CFCF; Znamenny Musical Notation 1D000..1D0FF; Byzantine Musical Symbols 1D100..1D1FF; Musical Symbols 1D200..1D24F; Ancient Greek Musical Notation @@ -305,9 +314,12 @@ FFF0..FFFF; Specials 1D360..1D37F; Counting Rod Numerals 1D400..1D7FF; Mathematical Alphanumeric Symbols 1D800..1DAAF; Sutton SignWriting +1DF00..1DFFF; Latin Extended-G 1E000..1E02F; Glagolitic Supplement 1E100..1E14F; Nyiakeng Puachue Hmong +1E290..1E2BF; Toto 1E2C0..1E2FF; Wancho +1E7E0..1E7FF; Ethiopic Extended-B 1E800..1E8DF; Mende Kikakui 1E900..1E95F; Adlam 1EC70..1ECBF; Indic Siyaq Numbers diff --git a/lib/unicore/CJKRadicals.txt b/lib/unicore/CJKRadicals.txt index 231361591f..61a45878ef 100644 --- a/lib/unicore/CJKRadicals.txt +++ b/lib/unicore/CJKRadicals.txt @@ -1,6 +1,6 @@ -# CJKRadicals-13.0.0.txt -# Date: 2019-09-09, 19:38:00 GMT [RC, KW, LI] -# © 2019 Unicode®, Inc. +# CJKRadicals-14.0.0.txt +# Date: 2021-03-16, 21:39:00 GMT [RC, KW, LI] +# © 2021 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database diff --git a/lib/unicore/CaseFolding.txt b/lib/unicore/CaseFolding.txt index 033788b253..932ace29e6 100644 --- a/lib/unicore/CaseFolding.txt +++ b/lib/unicore/CaseFolding.txt @@ -1,6 +1,6 @@ -# CaseFolding-13.0.0.txt -# Date: 2019-09-08, 23:30:59 GMT -# © 2019 Unicode®, Inc. +# CaseFolding-14.0.0.txt +# Date: 2021-03-08, 19:35:41 GMT +# © 2021 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 # @@ -1050,6 +1050,7 @@ 2C2C; C; 2C5C; # GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D; C; 2C5D; # GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E; C; 2C5E; # GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F; C; 2C5F; # GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60; C; 2C61; # LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62; C; 026B; # LATIN CAPITAL LETTER L WITH MIDDLE TILDE 2C63; C; 1D7D; # LATIN CAPITAL LETTER P WITH STROKE @@ -1230,12 +1231,16 @@ A7B8; C; A7B9; # LATIN CAPITAL LETTER U WITH STROKE A7BA; C; A7BB; # LATIN CAPITAL LETTER GLOTTAL A A7BC; C; A7BD; # LATIN CAPITAL LETTER GLOTTAL I A7BE; C; A7BF; # LATIN CAPITAL LETTER GLOTTAL U +A7C0; C; A7C1; # LATIN CAPITAL LETTER OLD POLISH O A7C2; C; A7C3; # LATIN CAPITAL LETTER ANGLICANA W A7C4; C; A794; # LATIN CAPITAL LETTER C WITH PALATAL HOOK A7C5; C; 0282; # LATIN CAPITAL LETTER S WITH HOOK A7C6; C; 1D8E; # LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H AB70; C; 13A0; # CHEROKEE SMALL LETTER A AB71; C; 13A1; # CHEROKEE SMALL LETTER E @@ -1431,6 +1436,41 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z 104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA 104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA 104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA +10570; C; 10597; # VITHKUQI CAPITAL LETTER A +10571; C; 10598; # VITHKUQI CAPITAL LETTER BBE +10572; C; 10599; # VITHKUQI CAPITAL LETTER BE +10573; C; 1059A; # VITHKUQI CAPITAL LETTER CE +10574; C; 1059B; # VITHKUQI CAPITAL LETTER CHE +10575; C; 1059C; # VITHKUQI CAPITAL LETTER DE +10576; C; 1059D; # VITHKUQI CAPITAL LETTER DHE +10577; C; 1059E; # VITHKUQI CAPITAL LETTER EI +10578; C; 1059F; # VITHKUQI CAPITAL LETTER E +10579; C; 105A0; # VITHKUQI CAPITAL LETTER FE +1057A; C; 105A1; # VITHKUQI CAPITAL LETTER GA +1057C; C; 105A3; # VITHKUQI CAPITAL LETTER HA +1057D; C; 105A4; # VITHKUQI CAPITAL LETTER HHA +1057E; C; 105A5; # VITHKUQI CAPITAL LETTER I +1057F; C; 105A6; # VITHKUQI CAPITAL LETTER IJE +10580; C; 105A7; # VITHKUQI CAPITAL LETTER JE +10581; C; 105A8; # VITHKUQI CAPITAL LETTER KA +10582; C; 105A9; # VITHKUQI CAPITAL LETTER LA +10583; C; 105AA; # VITHKUQI CAPITAL LETTER LLA +10584; C; 105AB; # VITHKUQI CAPITAL LETTER ME +10585; C; 105AC; # VITHKUQI CAPITAL LETTER NE +10586; C; 105AD; # VITHKUQI CAPITAL LETTER NJE +10587; C; 105AE; # VITHKUQI CAPITAL LETTER O +10588; C; 105AF; # VITHKUQI CAPITAL LETTER PE +10589; C; 105B0; # VITHKUQI CAPITAL LETTER QA +1058A; C; 105B1; # VITHKUQI CAPITAL LETTER RE +1058C; C; 105B3; # VITHKUQI CAPITAL LETTER SE +1058D; C; 105B4; # VITHKUQI CAPITAL LETTER SHE +1058E; C; 105B5; # VITHKUQI CAPITAL LETTER TE +1058F; C; 105B6; # VITHKUQI CAPITAL LETTER THE +10590; C; 105B7; # VITHKUQI CAPITAL LETTER U +10591; C; 105B8; # VITHKUQI CAPITAL LETTER VE +10592; C; 105B9; # VITHKUQI CAPITAL LETTER XE +10594; C; 105BB; # VITHKUQI CAPITAL LETTER Y +10595; C; 105BC; # VITHKUQI CAPITAL LETTER ZE 10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A 10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA 10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB diff --git a/lib/unicore/CompositionExclusions.txt b/lib/unicore/CompositionExclusions.txt index 52bbb465bc..74e425e2a0 100644 --- a/lib/unicore/CompositionExclusions.txt +++ b/lib/unicore/CompositionExclusions.txt @@ -1,10 +1,10 @@ -# CompositionExclusions-13.0.0.txt -# Date: 2019-10-15, 18:27:00 GMT [KW, LI] -# © 2019 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# CompositionExclusions-14.0.0.txt +# Date: 2021-03-30, 23:59:00 GMT [KW, LI] +# © 2021 Unicode®, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # This file lists the characters for the Composition Exclusion Table # defined in UAX #15, Unicode Normalization Forms. @@ -13,7 +13,7 @@ # Unicode Character Database. # # For more information, see -# http://www.unicode.org/unicode/reports/tr15/#Primary_Exclusion_List_Table +# https://www.unicode.org/reports/tr15/#Primary_Exclusion_List_Table # # For a full derivation of composition exclusions, see the derived property # Full_Composition_Exclusion in DerivedNormalizationProps.txt diff --git a/lib/unicore/DAge.txt b/lib/unicore/DAge.txt index 0d2bd10f8d..c8ee531b8a 100644 --- a/lib/unicore/DAge.txt +++ b/lib/unicore/DAge.txt @@ -1,6 +1,6 @@ -# DerivedAge-13.0.0.txt -# Date: 2019-09-08, 23:30:59 GMT -# © 2019 Unicode®, Inc. +# DerivedAge-14.0.0.txt +# Date: 2021-07-10, 00:35:00 GMT +# © 2021 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 # @@ -40,7 +40,7 @@ # an expression such as "\p{age=3.0}" matches all of the code points # assigned in Version 3.0--that is, all the code points with a value # less than or equal to 3.0 for the Age property. -# For more information, see [http://www.unicode.org/reports/tr18/]. +# For more information, see [https://www.unicode.org/reports/tr18/]. # All code points not explicitly listed for Age # have the value Unassigned (NA). @@ -1862,4 +1862,91 @@ AB68..AB6B ; 13.0 # [4] LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE..MODI # Total code points: 5930 +# ================================================ + +# Age=V14_0 + +# Newly assigned in Unicode 14.0.0 (September, 2021) + +061D ; 14.0 # ARABIC END OF TEXT MARK +0870..088E ; 14.0 # [31] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC VERTICAL TAIL +0890..0891 ; 14.0 # [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; 14.0 # [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08B5 ; 14.0 # ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE +08C8..08D2 ; 14.0 # [11] ARABIC LETTER GRAF..ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW +0C3C ; 14.0 # TELUGU SIGN NUKTA +0C5D ; 14.0 # TELUGU LETTER NAKAARA POLLU +0CDD ; 14.0 # KANNADA LETTER NAKAARA POLLU +170D ; 14.0 # TAGALOG LETTER RA +1715 ; 14.0 # TAGALOG SIGN PAMUDPOD +171F ; 14.0 # TAGALOG LETTER ARCHAIC RA +180F ; 14.0 # MONGOLIAN FREE VARIATION SELECTOR FOUR +1AC1..1ACE ; 14.0 # [14] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING LATIN SMALL LETTER INSULAR T +1B4C ; 14.0 # BALINESE LETTER ARCHAIC JNYA +1B7D..1B7E ; 14.0 # [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG +1DFA ; 14.0 # COMBINING DOT BELOW LEFT +20C0 ; 14.0 # SOM SIGN +2C2F ; 14.0 # GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI +2C5F ; 14.0 # GLAGOLITIC SMALL LETTER CAUDATE CHRIVI +2E53..2E5D ; 14.0 # [11] MEDIEVAL EXCLAMATION MARK..OBLIQUE HYPHEN +9FFD..9FFF ; 14.0 # [3] CJK UNIFIED IDEOGRAPH-9FFD..CJK UNIFIED IDEOGRAPH-9FFF +A7C0..A7C1 ; 14.0 # [2] LATIN CAPITAL LETTER OLD POLISH O..LATIN SMALL LETTER OLD POLISH O +A7D0..A7D1 ; 14.0 # [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; 14.0 # LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; 14.0 # [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; 14.0 # [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +FBC2 ; 14.0 # ARABIC SYMBOL WASLA ABOVE +FD40..FD4F ; 14.0 # [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FDCF ; 14.0 # ARABIC LIGATURE SALAAMUHU ALAYNAA +FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGATURE AZZA WA JALL +10570..1057A ; 14.0 # [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; 14.0 # [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; 14.0 # [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; 14.0 # [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; 14.0 # [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; 14.0 # [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; 14.0 # [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; 14.0 # [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780..10785 ; 14.0 # [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; 14.0 # [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; 14.0 # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +10F70..10F89 ; 14.0 # [26] OLD UYGHUR LETTER ALEPH..OLD UYGHUR PUNCTUATION FOUR DOTS +11070..11075 ; 14.0 # [6] BRAHMI SIGN OLD TAMIL VIRAMA..BRAHMI LETTER OLD TAMIL LLA +110C2 ; 14.0 # KAITHI VOWEL SIGN VOCALIC R +116B9 ; 14.0 # TAKRI ABBREVIATION SIGN +11740..11746 ; 14.0 # [7] AHOM LETTER CA..AHOM LETTER LLA +11AB0..11ABF ; 14.0 # [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA +12F90..12FF2 ; 14.0 # [99] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM302 +16A70..16ABE ; 14.0 # [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; 14.0 # [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE +1AFF0..1AFF3 ; 14.0 # [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; 14.0 # [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; 14.0 # [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B11F..1B122 ; 14.0 # [4] HIRAGANA LETTER ARCHAIC WU..KATAKANA LETTER ARCHAIC WU +1CF00..1CF2D ; 14.0 # [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; 14.0 # [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF50..1CFC3 ; 14.0 # [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK +1D1E9..1D1EA ; 14.0 # [2] MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON +1DF00..1DF1E ; 14.0 # [31] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL +1E290..1E2AE ; 14.0 # [31] TOTO LETTER PA..TOTO SIGN RISING TONE +1E7E0..1E7E6 ; 14.0 # [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; 14.0 # [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; 14.0 # [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; 14.0 # [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE +1F6DD..1F6DF ; 14.0 # [3] PLAYGROUND SLIDE..RING BUOY +1F7F0 ; 14.0 # HEAVY EQUALS SIGN +1F979 ; 14.0 # FACE HOLDING BACK TEARS +1F9CC ; 14.0 # TROLL +1FA7B..1FA7C ; 14.0 # [2] X-RAY..CRUTCH +1FAA9..1FAAC ; 14.0 # [4] MIRROR BALL..HAMSA +1FAB7..1FABA ; 14.0 # [4] LOTUS..NEST WITH EGGS +1FAC3..1FAC5 ; 14.0 # [3] PREGNANT MAN..PERSON WITH CROWN +1FAD7..1FAD9 ; 14.0 # [3] POURING LIQUID..JAR +1FAE0..1FAE7 ; 14.0 # [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; 14.0 # [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS +2A6DE..2A6DF ; 14.0 # [2] CJK UNIFIED IDEOGRAPH-2A6DE..CJK UNIFIED IDEOGRAPH-2A6DF +2B735..2B738 ; 14.0 # [4] CJK UNIFIED IDEOGRAPH-2B735..CJK UNIFIED IDEOGRAPH-2B738 + +# Total code points: 838 + # EOF diff --git a/lib/unicore/DCoreProperties.txt b/lib/unicore/DCoreProperties.txt index bc97e2173d..afc2abd97e 100644 --- a/lib/unicore/DCoreProperties.txt +++ b/lib/unicore/DCoreProperties.txt @@ -1,6 +1,6 @@ -# DerivedCoreProperties-13.0.0.txt -# Date: 2020-01-22, 00:07:19 GMT -# © 2020 Unicode®, Inc. +# DerivedCoreProperties-14.0.0.txt +# Date: 2021-08-12, 23:12:53 GMT +# © 2021 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 # @@ -341,8 +341,10 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 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..08C7 ; Alphabetic # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Alphabetic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Alphabetic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Alphabetic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; Alphabetic # Lm ARABIC SMALL FARSI YEH 08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA 08E3..08E9 ; Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN 08F0..0902 ; Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA @@ -471,6 +473,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0C4A..0C4C ; Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C55..0C56 ; Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Alphabetic # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Alphabetic # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Alphabetic # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C80 ; Alphabetic # Lo KANNADA SIGN SPACING CANDRABINDU @@ -490,7 +493,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CCA..0CCB ; Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; Alphabetic # Lo KANNADA LETTER FA +0CDD..0CDE ; Alphabetic # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 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 @@ -614,10 +617,9 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 16A0..16EA ; Alphabetic # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; Alphabetic # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Alphabetic # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Alphabetic # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; Alphabetic # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1713 ; Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U -1720..1731 ; Alphabetic # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +171F..1731 ; Alphabetic # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1732..1733 ; Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1740..1751 ; Alphabetic # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -670,6 +672,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1A73..1A74 ; Alphabetic # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG 1AA7 ; Alphabetic # Lm TAI THAM SIGN MAI YAMOK 1ABF..1AC0 ; Alphabetic # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ACC..1ACE ; Alphabetic # Mn [3] COMBINING LATIN SMALL LETTER INSULAR G..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Alphabetic # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Alphabetic # Mc BALINESE SIGN BISAH 1B05..1B33 ; Alphabetic # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -680,7 +683,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1B3D..1B41 ; Alphabetic # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; Alphabetic # Mn BALINESE VOWEL SIGN PEPET 1B43 ; Alphabetic # Mc BALINESE VOWEL SIGN PEPET TEDUNG -1B45..1B4B ; Alphabetic # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Alphabetic # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B80..1B81 ; Alphabetic # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; Alphabetic # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; Alphabetic # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -760,9 +763,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 2183..2184 ; Alphabetic # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; Alphabetic # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND 24B6..24E9 ; Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Alphabetic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Alphabetic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Alphabetic # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Alphabetic # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Alphabetic # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Alphabetic # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; Alphabetic # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -802,8 +803,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 31A0..31BF ; Alphabetic # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; Alphabetic # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Alphabetic # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Alphabetic # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; Alphabetic # Lm YI SYLLABLE WU A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Alphabetic # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -828,8 +828,11 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; Alphabetic # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Alphabetic # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Alphabetic # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Alphabetic # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Alphabetic # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -985,9 +988,20 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 104D8..104FB ; Alphabetic # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; Alphabetic # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Alphabetic # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; Alphabetic # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Alphabetic # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Alphabetic # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Alphabetic # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Alphabetic # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Alphabetic # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Alphabetic # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Alphabetic # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; Alphabetic # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Alphabetic # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Alphabetic # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; Alphabetic # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Alphabetic # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Alphabetic # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; Alphabetic # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Alphabetic # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Alphabetic # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1028,6 +1042,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; Alphabetic # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; Alphabetic # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; Alphabetic # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; Alphabetic # Mc BRAHMI SIGN CANDRABINDU @@ -1035,11 +1050,15 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11002 ; Alphabetic # Mc BRAHMI SIGN VISARGA 11003..11037 ; Alphabetic # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11045 ; Alphabetic # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU +11071..11072 ; Alphabetic # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; Alphabetic # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; Alphabetic # Lo BRAHMI LETTER OLD TAMIL LLA 11082 ; Alphabetic # Mc KAITHI SIGN VISARGA 11083..110AF ; Alphabetic # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110C2 ; Alphabetic # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; Alphabetic # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11100..11102 ; Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11103..11126 ; Alphabetic # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -1144,6 +1163,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11722..11725 ; Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Alphabetic # Mc AHOM VOWEL SIGN E 11727..1172A ; Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11740..11746 ; Alphabetic # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Alphabetic # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; Alphabetic # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; Alphabetic # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -1185,7 +1205,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA 11A9D ; Alphabetic # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; Alphabetic # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 11C2F ; Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA @@ -1227,10 +1247,12 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 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 +12F90..12FF0 ; Alphabetic # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; Alphabetic # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; Alphabetic # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Alphabetic # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Alphabetic # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; Alphabetic # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; Alphabetic # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; Alphabetic # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; Alphabetic # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -1249,7 +1271,10 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 17000..187F7 ; Alphabetic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Alphabetic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Alphabetic # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Alphabetic # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Alphabetic # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -1288,6 +1313,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1D78A..1D7A8 ; Alphabetic # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Alphabetic # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Alphabetic # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Alphabetic # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; Alphabetic # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; Alphabetic # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -1296,7 +1324,12 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1E100..1E12C ; Alphabetic # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Alphabetic # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; Alphabetic # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; Alphabetic # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Alphabetic # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Alphabetic # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Alphabetic # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; Alphabetic # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E947 ; Alphabetic # Mn ADLAM HAMZA @@ -1337,15 +1370,15 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1F130..1F149 ; Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -20000..2A6DD ; Alphabetic # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Alphabetic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Alphabetic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Alphabetic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 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 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 132875 +# Total code points: 133396 # ================================================ @@ -1798,7 +1831,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 2170..217F ; Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Lowercase # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Lowercase # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Lowercase # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Lowercase # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Lowercase # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Lowercase # L& LATIN SMALL LETTER H WITH DESCENDER @@ -1970,9 +2003,15 @@ A7B9 ; Lowercase # L& LATIN SMALL LETTER U WITH STROKE A7BB ; Lowercase # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Lowercase # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Lowercase # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Lowercase # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Lowercase # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lowercase # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lowercase # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Lowercase # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Lowercase # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Lowercase # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Lowercase # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -1985,6 +2024,14 @@ FB13..FB17 ; Lowercase # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN S FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lowercase # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Lowercase # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Lowercase # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Lowercase # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Lowercase # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Lowercase # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10CC0..10CF2 ; Lowercase # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lowercase # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y @@ -2016,9 +2063,11 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7AA..1D7C2 ; Lowercase # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Lowercase # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Lowercase # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Lowercase # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2344 +# Total code points: 2471 # ================================================ @@ -2458,7 +2507,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 2160..216F ; Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Uppercase # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Uppercase # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Uppercase # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Uppercase # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Uppercase # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Uppercase # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -2623,13 +2672,21 @@ A7B8 ; Uppercase # L& LATIN CAPITAL LETTER U WITH STROKE A7BA ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Uppercase # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Uppercase # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Uppercase # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Uppercase # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Uppercase # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Uppercase # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Uppercase # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Uppercase # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Uppercase # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Uppercase # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Uppercase # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Uppercase # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -2669,7 +2726,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1911 +# Total code points: 1951 # ================================================ @@ -2761,9 +2818,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 2160..217F ; Cased # Nl [32] ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2183..2184 ; Cased # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 24B6..24E9 ; Cased # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Cased # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Cased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Cased # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Cased # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Cased # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Cased # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; Cased # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -2778,8 +2833,10 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7BF ; Cased # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Cased # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Cased # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Cased # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2794,6 +2851,18 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10400..1044F ; Cased # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 104B0..104D3 ; Cased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 104D8..104FB ; Cased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10570..1057A ; Cased # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Cased # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Cased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Cased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Cased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Cased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Cased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Cased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Cased # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Cased # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Cased # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Cased # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10C80..10CB2 ; Cased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Cased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Cased # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -2828,12 +2897,14 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D78A..1D7A8 ; Cased # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Cased # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Cased # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Cased # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Cased # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E900..1E943 ; Cased # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1F130..1F149 ; Cased # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4286 +# Total code points: 4453 # ================================================ @@ -2908,7 +2979,11 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0828 ; Case_Ignorable # Lm SAMARITAN MODIFIER LETTER I 0829..082D ; Case_Ignorable # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Case_Ignorable # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Case_Ignorable # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0888 ; Case_Ignorable # Sk ARABIC RAISED ROUND DOT +0890..0891 ; Case_Ignorable # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; Case_Ignorable # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08C9 ; Case_Ignorable # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; Case_Ignorable # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; Case_Ignorable # Cf ARABIC DISPUTED END OF AYAH 08E3..0902 ; Case_Ignorable # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Case_Ignorable # Mn DEVANAGARI VOWEL SIGN OE @@ -2951,6 +3026,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0BCD ; Case_Ignorable # Mn TAMIL SIGN VIRAMA 0C00 ; Case_Ignorable # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Case_Ignorable # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Case_Ignorable # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Case_Ignorable # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Case_Ignorable # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Case_Ignorable # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -3003,7 +3079,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10FC ; Case_Ignorable # Lm MODIFIER LETTER GEORGIAN NAR 135D..135F ; Case_Ignorable # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Case_Ignorable # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Case_Ignorable # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Case_Ignorable # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Case_Ignorable # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Case_Ignorable # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Case_Ignorable # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -3014,6 +3090,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 17DD ; Case_Ignorable # Mn KHMER SIGN ATTHACAN 180B..180D ; Case_Ignorable # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Case_Ignorable # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Case_Ignorable # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1843 ; Case_Ignorable # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1885..1886 ; Case_Ignorable # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Case_Ignorable # Mn MONGOLIAN LETTER ALI GALI DAGALGA @@ -3033,7 +3110,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Case_Ignorable # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Case_Ignorable # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3060,8 +3137,7 @@ 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..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 +1DC0..1DFF ; Case_Ignorable # Mn [64] COMBINING DOTTED GRAVE ACCENT..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 1FCD..1FCF ; Case_Ignorable # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -3114,6 +3190,7 @@ A720..A721 ; Case_Ignorable # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE.. A770 ; Case_Ignorable # Lm MODIFIER LETTER US A788 ; Case_Ignorable # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Case_Ignorable # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN +A7F2..A7F4 ; Case_Ignorable # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Case_Ignorable # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A802 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN HASANTA @@ -3156,7 +3233,7 @@ ABE5 ; Case_Ignorable # Mn MEETEI MAYEK VOWEL SIGN ANAP ABE8 ; Case_Ignorable # Mn MEETEI MAYEK VOWEL SIGN UNAP ABED ; Case_Ignorable # Mn MEETEI MAYEK APUN IYEK FB1E ; Case_Ignorable # Mn HEBREW POINT JUDEO-SPANISH VARIKA -FBB2..FBC1 ; Case_Ignorable # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Case_Ignorable # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FE00..FE0F ; Case_Ignorable # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE13 ; Case_Ignorable # Po PRESENTATION FORM FOR VERTICAL COLON FE20..FE2F ; Case_Ignorable # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF @@ -3175,6 +3252,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 101FD ; Case_Ignorable # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE 102E0 ; Case_Ignorable # Mn COPTIC EPACT THOUSANDS MARK 10376..1037A ; Case_Ignorable # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10780..10785 ; Case_Ignorable # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Case_Ignorable # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Case_Ignorable # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10A01..10A03 ; Case_Ignorable # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R 10A05..10A06 ; Case_Ignorable # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0F ; Case_Ignorable # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA @@ -3184,12 +3264,16 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10D24..10D27 ; Case_Ignorable # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Case_Ignorable # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Case_Ignorable # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Case_Ignorable # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Case_Ignorable # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Case_Ignorable # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Case_Ignorable # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA 110BD ; Case_Ignorable # Cf KAITHI NUMBER SIGN +110C2 ; Case_Ignorable # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; Case_Ignorable # Cf KAITHI NUMBER SIGN ABOVE 11100..11102 ; Case_Ignorable # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Case_Ignorable # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU @@ -3274,8 +3358,13 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Case_Ignorable # Lm OLD CHINESE ITERATION MARK 16FE4 ; Case_Ignorable # Mn KHITAN SMALL SCRIPT FILLER +1AFF0..1AFF3 ; Case_Ignorable # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Case_Ignorable # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Case_Ignorable # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 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 +1CF00..1CF2D ; Case_Ignorable # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Case_Ignorable # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Case_Ignorable # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D173..1D17A ; Case_Ignorable # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D17B..1D182 ; Case_Ignorable # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE @@ -3295,6 +3384,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E026..1E02A ; Case_Ignorable # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Case_Ignorable # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; Case_Ignorable # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E2AE ; Case_Ignorable # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Case_Ignorable # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA @@ -3304,7 +3394,7 @@ 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: 2413 +# Total code points: 2602 # ================================================ @@ -3738,7 +3828,7 @@ E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELEC 2160..216F ; Changes_When_Lowercased # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Changes_When_Lowercased # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Changes_When_Lowercased # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Changes_When_Lowercased # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_Lowercased # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_Lowercased # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -3903,19 +3993,27 @@ A7B8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER U WITH S A7BA ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Lowercased # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_Lowercased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_Lowercased # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Lowercased # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Lowercased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Lowercased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Lowercased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Lowercased # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1393 +# Total code points: 1433 # ================================================ @@ -4363,7 +4461,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 2170..217F ; Changes_When_Uppercased # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Changes_When_Uppercased # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Changes_When_Uppercased # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Changes_When_Uppercased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Changes_When_Uppercased # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Changes_When_Uppercased # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Changes_When_Uppercased # L& LATIN SMALL LETTER H WITH DESCENDER @@ -4528,9 +4626,13 @@ A7B9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER U WITH STR A7BB ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Changes_When_Uppercased # L& LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Uppercased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -4539,12 +4641,16 @@ FB13..FB17 ; Changes_When_Uppercased # L& [5] ARMENIAN SMALL LIGATURE MEN N FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Uppercased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Changes_When_Uppercased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Changes_When_Uppercased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Uppercased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Uppercased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Uppercased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Uppercased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Uppercased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1485 +# Total code points: 1525 # ================================================ @@ -4991,7 +5097,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 2170..217F ; Changes_When_Titlecased # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Changes_When_Titlecased # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Changes_When_Titlecased # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Changes_When_Titlecased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Changes_When_Titlecased # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Changes_When_Titlecased # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Changes_When_Titlecased # L& LATIN SMALL LETTER H WITH DESCENDER @@ -5156,9 +5262,13 @@ A7B9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER U WITH STR A7BB ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Changes_When_Titlecased # L& LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Titlecased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5167,12 +5277,16 @@ FB13..FB17 ; Changes_When_Titlecased # L& [5] ARMENIAN SMALL LIGATURE MEN N FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Titlecased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Changes_When_Titlecased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Changes_When_Titlecased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Titlecased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Titlecased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Titlecased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Titlecased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Titlecased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1412 +# Total code points: 1452 # ================================================ @@ -5616,7 +5730,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 2160..216F ; Changes_When_Casefolded # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Changes_When_Casefolded # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Changes_When_Casefolded # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Changes_When_Casefolded # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_Casefolded # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_Casefolded # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -5781,9 +5895,13 @@ A7B8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER U WITH S A7BA ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H AB70..ABBF ; Changes_When_Casefolded # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Changes_When_Casefolded # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST @@ -5791,12 +5909,16 @@ FB13..FB17 ; Changes_When_Casefolded # L& [5] ARMENIAN SMALL LIGATURE MEN N FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_Casefolded # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Casefolded # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Casefolded # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Casefolded # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1466 +# Total code points: 1506 # ================================================ @@ -5893,9 +6015,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 2160..217F ; Changes_When_Casemapped # Nl [32] ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2183..2184 ; Changes_When_Casemapped # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 24B6..24E9 ; Changes_When_Casemapped # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Changes_When_Casemapped # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Changes_When_Casemapped # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C70 ; Changes_When_Casemapped # L& [17] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN CAPITAL LETTER TURNED ALPHA +2C00..2C70 ; Changes_When_Casemapped # L& [113] GLAGOLITIC CAPITAL LETTER AZU..LATIN CAPITAL LETTER TURNED ALPHA 2C72..2C73 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER W WITH HOOK..LATIN SMALL LETTER W WITH HOOK 2C75..2C76 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER HALF H..LATIN SMALL LETTER HALF H 2C7E..2CE3 ; Changes_When_Casemapped # L& [102] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SMALL LETTER OLD NUBIAN WAU @@ -5912,8 +6032,9 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7BF ; Changes_When_Casemapped # L& [16] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Changes_When_Casemapped # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7B0..A7CA ; Changes_When_Casemapped # L& [27] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D6..A7D9 ; Changes_When_Casemapped # L& [4] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN SMALL LETTER SIGMOID S A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5924,13 +6045,21 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 10400..1044F ; Changes_When_Casemapped # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 104B0..104D3 ; Changes_When_Casemapped # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 104D8..104FB ; Changes_When_Casemapped # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10570..1057A ; Changes_When_Casemapped # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Casemapped # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Casemapped # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Casemapped # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Changes_When_Casemapped # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Casemapped # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Casemapped # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Casemapped # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10C80..10CB2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Changes_When_Casemapped # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2847 +# Total code points: 2927 # ================================================ @@ -6003,8 +6132,10 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 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..08C7 ; ID_Start # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; ID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; ID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ID_Start # Lo DEVANAGARI OM @@ -6070,6 +6201,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0C2A..0C39 ; ID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ID_Start # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -6078,7 +6210,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0CAA..0CB3 ; ID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ID_Start # Lo KANNADA SIGN AVAGRAHA -0CDE ; ID_Start # Lo KANNADA LETTER FA +0CDD..0CDE ; ID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -6153,9 +6285,8 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 16A0..16EA ; ID_Start # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ID_Start # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ID_Start # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ID_Start # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ID_Start # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; ID_Start # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; ID_Start # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; ID_Start # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; ID_Start # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; ID_Start # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; ID_Start # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -6179,7 +6310,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 1A20..1A54 ; ID_Start # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; ID_Start # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; ID_Start # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; ID_Start # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ID_Start # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; ID_Start # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; ID_Start # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; ID_Start # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -6242,9 +6373,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 2160..2182 ; ID_Start # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; ID_Start # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ID_Start # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; ID_Start # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ID_Start # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ID_Start # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ID_Start # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ID_Start # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ID_Start # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ID_Start # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -6283,8 +6412,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 31A0..31BF ; ID_Start # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; ID_Start # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID_Start # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID_Start # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; ID_Start # Lm YI SYLLABLE WU A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; ID_Start # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -6307,8 +6435,11 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ID_Start # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ID_Start # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6418,9 +6549,20 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 104D8..104FB ; ID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ID_Start # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ID_Start # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ID_Start # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ID_Start # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ID_Start # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -6456,9 +6598,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; ID_Start # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; ID_Start # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ID_Start # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; ID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; ID_Start # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; ID_Start # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; ID_Start # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; ID_Start # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; ID_Start # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -6500,6 +6645,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; ID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; ID_Start # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; ID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; ID_Start # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; ID_Start # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; ID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF..11906 ; ID_Start # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E @@ -6519,7 +6665,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; ID_Start # Lo SOYOMBO LETTER A 11A5C..11A89 ; ID_Start # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; ID_Start # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ID_Start # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 @@ -6537,10 +6683,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 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 +12F90..12FF0 ; ID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; ID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; ID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; ID_Start # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; ID_Start # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; ID_Start # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; ID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -6555,7 +6703,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17000..187F7 ; ID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; ID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; ID_Start # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; ID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; ID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -6593,10 +6744,18 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78A..1D7A8 ; ID_Start # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; ID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; ID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; ID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; ID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; ID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ID_Start # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; ID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; ID_Start # Lm ADLAM NASALIZATION MARK @@ -6633,15 +6792,15 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1EEA1..1EEA3 ; ID_Start # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; ID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; ID_Start # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; ID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; ID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; ID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 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 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 131482 +# Total code points: 131997 # ================================================ @@ -6746,9 +6905,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 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..08C7 ; ID_Continue # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; ID_Continue # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; ID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0898..089F ; ID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; ID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ID_Continue # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; ID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; ID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; ID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; ID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -6886,6 +7048,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C0E..0C10 ; ID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; ID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; ID_Continue # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; ID_Continue # Mn TELUGU SIGN NUKTA 0C3D ; ID_Continue # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; ID_Continue # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; ID_Continue # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -6893,6 +7056,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C4A..0C4D ; ID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; ID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; ID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ID_Continue # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; ID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; ID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -6914,7 +7078,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CCA..0CCB ; ID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; ID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; ID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; ID_Continue # Lo KANNADA LETTER FA +0CDD..0CDE ; ID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 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 @@ -7058,11 +7222,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16A0..16EA ; ID_Continue # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ID_Continue # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ID_Continue # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ID_Continue # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ID_Continue # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; ID_Continue # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; ID_Continue # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; ID_Continue # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; ID_Continue # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; ID_Continue # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; ID_Continue # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; ID_Continue # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; ID_Continue # Mc HANUNOO SIGN PAMUDPOD 1740..1751 ; ID_Continue # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; ID_Continue # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1760..176C ; ID_Continue # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -7081,6 +7246,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17DD ; ID_Continue # Mn KHMER SIGN ATTHACAN 17E0..17E9 ; ID_Continue # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 180B..180D ; ID_Continue # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; ID_Continue # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; ID_Continue # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; ID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -7128,7 +7294,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; ID_Continue # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; ID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -7140,7 +7306,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1B3D..1B41 ; ID_Continue # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; ID_Continue # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; ID_Continue # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; ID_Continue # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ID_Continue # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; ID_Continue # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B6B..1B73 ; ID_Continue # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1B81 ; ID_Continue # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR @@ -7194,8 +7360,7 @@ 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..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 +1DC0..1DFF ; ID_Continue # Mn [64] COMBINING DOTTED GRAVE ACCENT..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 1F20..1F45 ; ID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -7243,9 +7408,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2160..2182 ; ID_Continue # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; ID_Continue # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ID_Continue # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; ID_Continue # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ID_Continue # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ID_Continue # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ID_Continue # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ID_Continue # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ID_Continue # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ID_Continue # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -7290,8 +7453,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 31A0..31BF ; ID_Continue # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; ID_Continue # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID_Continue # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID_Continue # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; ID_Continue # Lm YI SYLLABLE WU A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; ID_Continue # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -7319,8 +7481,11 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ID_Continue # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ID_Continue # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -7499,9 +7664,20 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 104D8..104FB ; ID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ID_Continue # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ID_Continue # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ID_Continue # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ID_Continue # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ID_Continue # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -7547,6 +7723,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F46..10F50 ; ID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F70..10F81 ; ID_Continue # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; ID_Continue # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; ID_Continue # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ID_Continue # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; ID_Continue # Mc BRAHMI SIGN CANDRABINDU @@ -7555,6 +7733,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11003..11037 ; ID_Continue # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11046 ; ID_Continue # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11066..1106F ; ID_Continue # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; ID_Continue # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; ID_Continue # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; ID_Continue # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; ID_Continue # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; ID_Continue # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; ID_Continue # Mc KAITHI SIGN VISARGA 11083..110AF ; ID_Continue # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -7562,6 +7744,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 110B3..110B6 ; ID_Continue # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; ID_Continue # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; ID_Continue # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; ID_Continue # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; ID_Continue # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; ID_Continue # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11100..11102 ; ID_Continue # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -7687,6 +7870,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11726 ; ID_Continue # Mc AHOM VOWEL SIGN E 11727..1172B ; ID_Continue # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 11730..11739 ; ID_Continue # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; ID_Continue # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; ID_Continue # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; ID_Continue # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; ID_Continue # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -7737,7 +7921,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; ID_Continue # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 11C2F ; ID_Continue # Mc BHAIKSUKI VOWEL SIGN AA @@ -7783,11 +7967,14 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 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 +12F90..12FF0 ; ID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; ID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; ID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; ID_Continue # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A70..16ABE ; ID_Continue # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; ID_Continue # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; ID_Continue # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; ID_Continue # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B2F ; ID_Continue # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -7810,7 +7997,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 17000..187F7 ; ID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; ID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; ID_Continue # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; ID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; ID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -7819,6 +8009,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1BC80..1BC88 ; ID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; ID_Continue # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9D..1BC9E ; ID_Continue # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; ID_Continue # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; ID_Continue # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; ID_Continue # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; ID_Continue # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; ID_Continue # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -7863,6 +8055,9 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DA84 ; ID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; ID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; ID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; ID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; ID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -7873,9 +8068,15 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1E137..1E13D ; ID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; ID_Continue # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; ID_Continue # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ID_Continue # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; ID_Continue # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; ID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; ID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; ID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ID_Continue # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; ID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E900..1E943 ; ID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -7916,8 +8117,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1EEA5..1EEA9 ; ID_Continue # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; ID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; ID_Continue # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; ID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; ID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; ID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 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 @@ -7925,7 +8126,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 134434 +# Total code points: 135072 # ================================================ @@ -7995,8 +8196,10 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 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..08C7 ; XID_Start # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; XID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; XID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; XID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; XID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; XID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; XID_Start # Lo DEVANAGARI OM @@ -8062,6 +8265,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0C2A..0C39 ; XID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; XID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; XID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; XID_Start # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; XID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; XID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -8070,7 +8274,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0CAA..0CB3 ; XID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; XID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; XID_Start # Lo KANNADA SIGN AVAGRAHA -0CDE ; XID_Start # Lo KANNADA LETTER FA +0CDD..0CDE ; XID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; XID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; XID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; XID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -8145,9 +8349,8 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 16A0..16EA ; XID_Start # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; XID_Start # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; XID_Start # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; XID_Start # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; XID_Start # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; XID_Start # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; XID_Start # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; XID_Start # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; XID_Start # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; XID_Start # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; XID_Start # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -8171,7 +8374,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 1A20..1A54 ; XID_Start # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; XID_Start # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; XID_Start # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; XID_Start # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; XID_Start # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; XID_Start # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; XID_Start # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; XID_Start # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -8234,9 +8437,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 2160..2182 ; XID_Start # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; XID_Start # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; XID_Start # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; XID_Start # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; XID_Start # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; XID_Start # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; XID_Start # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; XID_Start # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; XID_Start # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; XID_Start # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -8274,8 +8475,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 31A0..31BF ; XID_Start # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; XID_Start # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; XID_Start # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; XID_Start # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; XID_Start # Lm YI SYLLABLE WU A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; XID_Start # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -8298,8 +8498,11 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; XID_Start # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; XID_Start # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; XID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; XID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; XID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -8414,9 +8617,20 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 104D8..104FB ; XID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; XID_Start # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; XID_Start # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; XID_Start # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; XID_Start # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; XID_Start # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; XID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; XID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; XID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; XID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; XID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; XID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; XID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; XID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -8452,9 +8666,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; XID_Start # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; XID_Start # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; XID_Start # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; XID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; XID_Start # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; XID_Start # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; XID_Start # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; XID_Start # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; XID_Start # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -8496,6 +8713,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11680..116AA ; XID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; XID_Start # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; XID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; XID_Start # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; XID_Start # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; XID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF..11906 ; XID_Start # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E @@ -8515,7 +8733,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11A50 ; XID_Start # Lo SOYOMBO LETTER A 11A5C..11A89 ; XID_Start # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; XID_Start # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; XID_Start # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 @@ -8533,10 +8751,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 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 +12F90..12FF0 ; XID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; XID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; XID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; XID_Start # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; XID_Start # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; XID_Start # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; XID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -8551,7 +8771,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 17000..187F7 ; XID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; XID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; XID_Start # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; XID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; XID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -8589,10 +8812,18 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78A..1D7A8 ; XID_Start # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; XID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; XID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; XID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; XID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; XID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; XID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; XID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; XID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; XID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; XID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; XID_Start # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; XID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; XID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; XID_Start # Lm ADLAM NASALIZATION MARK @@ -8629,15 +8860,15 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1EEA1..1EEA3 ; XID_Start # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; XID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; XID_Start # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; XID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; XID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; XID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 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 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 131459 +# Total code points: 131974 # ================================================ @@ -8738,9 +8969,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 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..08C7 ; XID_Continue # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; XID_Continue # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; XID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; XID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0898..089F ; XID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; XID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; XID_Continue # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; XID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; XID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; XID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; XID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -8878,6 +9112,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C0E..0C10 ; XID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; XID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; XID_Continue # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; XID_Continue # Mn TELUGU SIGN NUKTA 0C3D ; XID_Continue # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; XID_Continue # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; XID_Continue # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -8885,6 +9120,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C4A..0C4D ; XID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; XID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; XID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; XID_Continue # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; XID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; XID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -8906,7 +9142,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CCA..0CCB ; XID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; XID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; XID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; XID_Continue # Lo KANNADA LETTER FA +0CDD..0CDE ; XID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; XID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 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 @@ -9050,11 +9286,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16A0..16EA ; XID_Continue # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; XID_Continue # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; XID_Continue # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; XID_Continue # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; XID_Continue # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; XID_Continue # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; XID_Continue # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; XID_Continue # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; XID_Continue # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; XID_Continue # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; XID_Continue # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; XID_Continue # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; XID_Continue # Mc HANUNOO SIGN PAMUDPOD 1740..1751 ; XID_Continue # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; XID_Continue # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1760..176C ; XID_Continue # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -9073,6 +9310,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 17DD ; XID_Continue # Mn KHMER SIGN ATTHACAN 17E0..17E9 ; XID_Continue # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 180B..180D ; XID_Continue # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; XID_Continue # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; XID_Continue # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; XID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; XID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -9120,7 +9358,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; XID_Continue # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; XID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -9132,7 +9370,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1B3D..1B41 ; XID_Continue # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; XID_Continue # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; XID_Continue # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; XID_Continue # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; XID_Continue # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; XID_Continue # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B6B..1B73 ; XID_Continue # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1B81 ; XID_Continue # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR @@ -9186,8 +9424,7 @@ 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..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 +1DC0..1DFF ; XID_Continue # Mn [64] COMBINING DOTTED GRAVE ACCENT..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 1F20..1F45 ; XID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -9235,9 +9472,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 2160..2182 ; XID_Continue # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; XID_Continue # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; XID_Continue # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; XID_Continue # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; XID_Continue # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; XID_Continue # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; XID_Continue # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; XID_Continue # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; XID_Continue # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; XID_Continue # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -9281,8 +9516,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 31A0..31BF ; XID_Continue # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; XID_Continue # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; XID_Continue # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; XID_Continue # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; XID_Continue # Lm YI SYLLABLE WU A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; XID_Continue # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -9310,8 +9544,11 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; XID_Continue # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; XID_Continue # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; XID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; XID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; XID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -9496,9 +9733,20 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 104D8..104FB ; XID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; XID_Continue # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; XID_Continue # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; XID_Continue # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; XID_Continue # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; XID_Continue # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; XID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; XID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; XID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; XID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; XID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; XID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; XID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; XID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -9544,6 +9792,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F46..10F50 ; XID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F70..10F81 ; XID_Continue # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; XID_Continue # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; XID_Continue # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; XID_Continue # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; XID_Continue # Mc BRAHMI SIGN CANDRABINDU @@ -9552,6 +9802,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11003..11037 ; XID_Continue # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11046 ; XID_Continue # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11066..1106F ; XID_Continue # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; XID_Continue # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; XID_Continue # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; XID_Continue # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; XID_Continue # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; XID_Continue # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; XID_Continue # Mc KAITHI SIGN VISARGA 11083..110AF ; XID_Continue # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -9559,6 +9813,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 110B3..110B6 ; XID_Continue # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; XID_Continue # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; XID_Continue # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; XID_Continue # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; XID_Continue # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; XID_Continue # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11100..11102 ; XID_Continue # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -9684,6 +9939,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11726 ; XID_Continue # Mc AHOM VOWEL SIGN E 11727..1172B ; XID_Continue # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 11730..11739 ; XID_Continue # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; XID_Continue # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; XID_Continue # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; XID_Continue # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; XID_Continue # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -9734,7 +9990,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; XID_Continue # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; XID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 11C2F ; XID_Continue # Mc BHAIKSUKI VOWEL SIGN AA @@ -9780,11 +10036,14 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 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 +12F90..12FF0 ; XID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; XID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; XID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; XID_Continue # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A70..16ABE ; XID_Continue # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; XID_Continue # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; XID_Continue # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; XID_Continue # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B2F ; XID_Continue # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -9807,7 +10066,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 17000..187F7 ; XID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; XID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; XID_Continue # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; XID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; XID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -9816,6 +10078,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1BC80..1BC88 ; XID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; XID_Continue # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9D..1BC9E ; XID_Continue # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; XID_Continue # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; XID_Continue # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; XID_Continue # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; XID_Continue # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; XID_Continue # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -9860,6 +10124,9 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DA84 ; XID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; XID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; XID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; XID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; XID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; XID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; XID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -9870,9 +10137,15 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1E137..1E13D ; XID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; XID_Continue # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; XID_Continue # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; XID_Continue # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; XID_Continue # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; XID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; XID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; XID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; XID_Continue # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; XID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; XID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E900..1E943 ; XID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -9913,8 +10186,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1EEA5..1EEA9 ; XID_Continue # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; XID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; XID_Continue # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; XID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; XID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; XID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 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 @@ -9922,7 +10195,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 134415 +# Total code points: 135053 # ================================================ @@ -9943,6 +10216,7 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO 17B4..17B5 ; Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Default_Ignorable_Code_Point # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Default_Ignorable_Code_Point # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 200B..200F ; Default_Ignorable_Code_Point # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK 202A..202E ; Default_Ignorable_Code_Point # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Default_Ignorable_Code_Point # Cf [5] WORD JOINER..INVISIBLE PLUS @@ -9963,7 +10237,7 @@ E0080..E00FF ; Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reser E0100..E01EF ; Default_Ignorable_Code_Point # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 4173 +# Total code points: 4174 # ================================================ @@ -9997,7 +10271,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0825..0827 ; Grapheme_Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Grapheme_Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Grapheme_Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Grapheme_Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Grapheme_Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Grapheme_Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Grapheme_Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Grapheme_Extend # Mn DEVANAGARI VOWEL SIGN OE 093C ; Grapheme_Extend # Mn DEVANAGARI SIGN NUKTA @@ -10044,6 +10319,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0BD7 ; Grapheme_Extend # Mc TAMIL AU LENGTH MARK 0C00 ; Grapheme_Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Grapheme_Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Grapheme_Extend # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Grapheme_Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Grapheme_Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Grapheme_Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -10099,7 +10375,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 109D ; Grapheme_Extend # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; Grapheme_Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Grapheme_Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Grapheme_Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Grapheme_Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Grapheme_Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Grapheme_Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Grapheme_Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -10108,6 +10384,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 17C9..17D3 ; Grapheme_Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Grapheme_Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Grapheme_Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Grapheme_Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Grapheme_Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Grapheme_Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Grapheme_Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -10125,7 +10402,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 1A7F ; Grapheme_Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Grapheme_Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Grapheme_Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Grapheme_Extend # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Grapheme_Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Grapheme_Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Grapheme_Extend # Mn BALINESE SIGN REREKAN 1B35 ; Grapheme_Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -10149,8 +10426,7 @@ 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..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 +1DC0..1DFF ; Grapheme_Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..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 20DD..20E0 ; Grapheme_Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -10215,11 +10491,15 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 10D24..10D27 ; Grapheme_Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Grapheme_Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Grapheme_Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Grapheme_Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Grapheme_Extend # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Grapheme_Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Grapheme_Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Grapheme_Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Grapheme_Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Grapheme_Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Grapheme_Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Grapheme_Extend # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Grapheme_Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Grapheme_Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; Grapheme_Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -10305,6 +10585,8 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Grapheme_Extend # Mn KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; Grapheme_Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Grapheme_Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Grapheme_Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165 ; Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM 1D167..1D169 ; Grapheme_Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16E..1D172 ; Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5 @@ -10324,13 +10606,14 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1E023..1E024 ; Grapheme_Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Grapheme_Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Grapheme_Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Grapheme_Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Grapheme_Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Grapheme_Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Grapheme_Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 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: 1979 +# Total code points: 2090 # ================================================ @@ -10451,7 +10734,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 060C..060D ; Grapheme_Base # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR 060E..060F ; Grapheme_Base # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 061B ; Grapheme_Base # Po ARABIC SEMICOLON -061E..061F ; Grapheme_Base # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; Grapheme_Base # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F ; Grapheme_Base # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; Grapheme_Base # Lm ARABIC TATWEEL 0641..064A ; Grapheme_Base # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -10489,8 +10772,11 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 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..08C7 ; Grapheme_Base # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Grapheme_Base # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; Grapheme_Base # Sk ARABIC RAISED ROUND DOT +0889..088E ; Grapheme_Base # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Grapheme_Base # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; Grapheme_Base # Lm ARABIC SMALL FARSI YEH 0903 ; Grapheme_Base # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; Grapheme_Base # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093B ; Grapheme_Base # Mc DEVANAGARI VOWEL SIGN OOE @@ -10603,6 +10889,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0C3D ; Grapheme_Base # Lo TELUGU SIGN AVAGRAHA 0C41..0C44 ; Grapheme_Base # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C58..0C5A ; Grapheme_Base # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Grapheme_Base # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Grapheme_Base # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; Grapheme_Base # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C77 ; Grapheme_Base # Po TELUGU SIGN SIDDHAM @@ -10622,7 +10909,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0CC3..0CC4 ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR 0CC7..0CC8 ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI 0CCA..0CCB ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO -0CDE ; Grapheme_Base # Lo KANNADA LETTER FA +0CDD..0CDE ; Grapheme_Base # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Grapheme_Base # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE6..0CEF ; Grapheme_Base # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; Grapheme_Base # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -10768,9 +11055,10 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 16EB..16ED ; Grapheme_Base # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0 ; Grapheme_Base # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; Grapheme_Base # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Grapheme_Base # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Grapheme_Base # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; Grapheme_Base # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; Grapheme_Base # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +1715 ; Grapheme_Base # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; Grapheme_Base # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1734 ; Grapheme_Base # Mc HANUNOO SIGN PAMUDPOD 1735..1736 ; Grapheme_Base # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751 ; Grapheme_Base # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; Grapheme_Base # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -10831,11 +11119,12 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1B3B ; Grapheme_Base # Mc BALINESE VOWEL SIGN RA REPA TEDUNG 1B3D..1B41 ; Grapheme_Base # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B43..1B44 ; Grapheme_Base # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; Grapheme_Base # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Grapheme_Base # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; Grapheme_Base # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; Grapheme_Base # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; Grapheme_Base # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; Grapheme_Base # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; Grapheme_Base # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B82 ; Grapheme_Base # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; Grapheme_Base # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BA1 ; Grapheme_Base # Mc SUNDANESE CONSONANT SIGN PAMINGKAL @@ -10940,7 +11229,7 @@ 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..20BF ; Grapheme_Base # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; Grapheme_Base # Sc [33] EURO-CURRENCY SIGN..SOM 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 @@ -11099,9 +11388,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2B4D..2B73 ; Grapheme_Base # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95 ; Grapheme_Base # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF ; Grapheme_Base # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -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 -2C60..2C7B ; Grapheme_Base # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Grapheme_Base # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Grapheme_Base # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Grapheme_Base # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CE5..2CEA ; Grapheme_Base # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA @@ -11164,7 +11451,16 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2E42 ; Grapheme_Base # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; Grapheme_Base # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; Grapheme_Base # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; Grapheme_Base # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; Grapheme_Base # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; Grapheme_Base # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Grapheme_Base # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Grapheme_Base # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Grapheme_Base # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Grapheme_Base # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Grapheme_Base # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Grapheme_Base # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Grapheme_Base # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; Grapheme_Base # Pd OBLIQUE HYPHEN 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 @@ -11237,8 +11533,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 32C0..33FF ; Grapheme_Base # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL 3400..4DBF ; Grapheme_Base # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF 4DC0..4DFF ; Grapheme_Base # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FFC ; Grapheme_Base # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Grapheme_Base # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Grapheme_Base # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; Grapheme_Base # Lm YI SYLLABLE WU A016..A48C ; Grapheme_Base # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; Grapheme_Base # So [55] YI RADICAL QOT..YI RADICAL KE @@ -11271,8 +11566,11 @@ A788 ; Grapheme_Base # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; Grapheme_Base # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Grapheme_Base # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Grapheme_Base # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Grapheme_Base # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Grapheme_Base # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Grapheme_Base # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Grapheme_Base # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Grapheme_Base # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -11387,15 +11685,17 @@ FB3E ; Grapheme_Base # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; Grapheme_Base # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; Grapheme_Base # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; Grapheme_Base # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; Grapheme_Base # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Grapheme_Base # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; Grapheme_Base # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; Grapheme_Base # Pe ORNATE LEFT PARENTHESIS FD3F ; Grapheme_Base # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F ; Grapheme_Base # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Grapheme_Base # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; Grapheme_Base # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; Grapheme_Base # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Grapheme_Base # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; Grapheme_Base # Sc RIAL SIGN -FDFD ; Grapheme_Base # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; Grapheme_Base # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE10..FE16 ; Grapheme_Base # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; Grapheme_Base # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET FE18 ; Grapheme_Base # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET @@ -11533,9 +11833,20 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10500..10527 ; Grapheme_Base # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Grapheme_Base # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; Grapheme_Base # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; Grapheme_Base # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Grapheme_Base # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Grapheme_Base # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Grapheme_Base # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Grapheme_Base # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Grapheme_Base # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Grapheme_Base # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Grapheme_Base # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; Grapheme_Base # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Grapheme_Base # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Grapheme_Base # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; Grapheme_Base # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Grapheme_Base # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Grapheme_Base # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; Grapheme_Base # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Grapheme_Base # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Grapheme_Base # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -11603,6 +11914,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10F30..10F45 ; Grapheme_Base # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; Grapheme_Base # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; Grapheme_Base # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81 ; Grapheme_Base # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F86..10F89 ; Grapheme_Base # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4 ; Grapheme_Base # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; Grapheme_Base # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6 ; Grapheme_Base # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -11612,6 +11925,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11047..1104D ; Grapheme_Base # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; Grapheme_Base # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; Grapheme_Base # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11071..11072 ; Grapheme_Base # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; Grapheme_Base # Lo BRAHMI LETTER OLD TAMIL LLA 11082 ; Grapheme_Base # Mc KAITHI SIGN VISARGA 11083..110AF ; Grapheme_Base # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; Grapheme_Base # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II @@ -11713,6 +12028,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 116AE..116AF ; Grapheme_Base # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II 116B6 ; Grapheme_Base # Mc TAKRI SIGN VIRAMA 116B8 ; Grapheme_Base # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; Grapheme_Base # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; Grapheme_Base # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A ; Grapheme_Base # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 11720..11721 ; Grapheme_Base # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA @@ -11721,6 +12037,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1173A..1173B ; Grapheme_Base # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; Grapheme_Base # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; Grapheme_Base # So AHOM SYMBOL VI +11740..11746 ; Grapheme_Base # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Grapheme_Base # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; Grapheme_Base # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 11838 ; Grapheme_Base # Mc DOGRA SIGN VISARGA @@ -11762,7 +12079,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11A9A..11A9C ; Grapheme_Base # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9D ; Grapheme_Base # Lo SOYOMBO MARK PLUTA 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 +11AB0..11AF8 ; Grapheme_Base # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 11C2F ; Grapheme_Base # Mc BHAIKSUKI VOWEL SIGN AA @@ -11802,12 +12119,16 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 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 12480..12543 ; Grapheme_Base # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; Grapheme_Base # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; Grapheme_Base # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E ; Grapheme_Base # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; Grapheme_Base # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Grapheme_Base # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Grapheme_Base # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; Grapheme_Base # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F ; Grapheme_Base # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE ; Grapheme_Base # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; Grapheme_Base # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; Grapheme_Base # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF5 ; Grapheme_Base # Po BASSA VAH FULL STOP 16B00..16B2F ; Grapheme_Base # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -11834,7 +12155,10 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 17000..187F7 ; Grapheme_Base # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Grapheme_Base # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Grapheme_Base # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Grapheme_Base # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; Grapheme_Base # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Grapheme_Base # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Grapheme_Base # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; Grapheme_Base # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Grapheme_Base # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Grapheme_Base # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Grapheme_Base # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -11844,6 +12168,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1BC90..1BC99 ; Grapheme_Base # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; Grapheme_Base # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; Grapheme_Base # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1CF50..1CFC3 ; Grapheme_Base # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Grapheme_Base # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Grapheme_Base # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; Grapheme_Base # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -11852,7 +12177,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1D16D ; Grapheme_Base # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT 1D183..1D184 ; Grapheme_Base # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; Grapheme_Base # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; Grapheme_Base # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; Grapheme_Base # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; Grapheme_Base # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; Grapheme_Base # So GREEK MUSICAL LEIMMA 1D2E0..1D2F3 ; Grapheme_Base # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN @@ -11905,14 +12230,22 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1DA76..1DA83 ; Grapheme_Base # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH 1DA85..1DA86 ; Grapheme_Base # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS 1DA87..1DA8B ; Grapheme_Base # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS +1DF00..1DF09 ; Grapheme_Base # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; Grapheme_Base # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; Grapheme_Base # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; Grapheme_Base # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Grapheme_Base # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; Grapheme_Base # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; Grapheme_Base # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; Grapheme_Base # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; Grapheme_Base # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Grapheme_Base # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2F0..1E2F9 ; Grapheme_Base # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF ; Grapheme_Base # Sc WANCHO NGUN SIGN +1E7E0..1E7E6 ; Grapheme_Base # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Grapheme_Base # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Grapheme_Base # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Grapheme_Base # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Grapheme_Base # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; Grapheme_Base # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E900..1E943 ; Grapheme_Base # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -11977,40 +12310,41 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 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..1F6D7 ; Grapheme_Base # So [728] RAT..ELEVATOR -1F6E0..1F6EC ; Grapheme_Base # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DD..1F6EC ; Grapheme_Base # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6F0..1F6FC ; Grapheme_Base # So [13] SATELLITE..ROLLER SKATE 1F700..1F773 ; Grapheme_Base # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8 ; Grapheme_Base # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; Grapheme_Base # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; Grapheme_Base # So HEAVY EQUALS SIGN 1F800..1F80B ; Grapheme_Base # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; Grapheme_Base # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 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 1F8B0..1F8B1 ; Grapheme_Base # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; Grapheme_Base # So [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; Grapheme_Base # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; Grapheme_Base # So [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; Grapheme_Base # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Grapheme_Base # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74 ; Grapheme_Base # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; Grapheme_Base # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; Grapheme_Base # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; Grapheme_Base # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; Grapheme_Base # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; Grapheme_Base # So [7] FLY..FEATHER -1FAC0..1FAC2 ; Grapheme_Base # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; Grapheme_Base # So [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC ; Grapheme_Base # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; Grapheme_Base # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; Grapheme_Base # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; Grapheme_Base # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; Grapheme_Base # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; Grapheme_Base # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; Grapheme_Base # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; Grapheme_Base # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; Grapheme_Base # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; Grapheme_Base # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Grapheme_Base # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Grapheme_Base # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Grapheme_Base # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 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 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 141814 +# Total code points: 142539 # ================================================ @@ -12034,7 +12368,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 0F84 ; Grapheme_Link # Mn TIBETAN MARK HALANTA 1039..103A ; Grapheme_Link # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT 1714 ; Grapheme_Link # Mn TAGALOG SIGN VIRAMA -1734 ; Grapheme_Link # Mn HANUNOO SIGN PAMUDPOD +1715 ; Grapheme_Link # Mc TAGALOG SIGN PAMUDPOD +1734 ; Grapheme_Link # Mc HANUNOO SIGN PAMUDPOD 17D2 ; Grapheme_Link # Mn KHMER SIGN COENG 1A60 ; Grapheme_Link # Mn TAI THAM SIGN SAKOT 1B44 ; Grapheme_Link # Mc BALINESE ADEG ADEG @@ -12051,6 +12386,7 @@ AAF6 ; Grapheme_Link # Mn MEETEI MAYEK VIRAMA ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 10A3F ; Grapheme_Link # Mn KHAROSHTHI VIRAMA 11046 ; Grapheme_Link # Mn BRAHMI VIRAMA +11070 ; Grapheme_Link # Mn BRAHMI SIGN OLD TAMIL VIRAMA 1107F ; Grapheme_Link # Mn BRAHMI NUMBER JOINER 110B9 ; Grapheme_Link # Mn KAITHI SIGN VIRAMA 11133..11134 ; Grapheme_Link # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA @@ -12075,6 +12411,6 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 11D44..11D45 ; Grapheme_Link # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA 11D97 ; Grapheme_Link # Mn GUNJALA GONDI VIRAMA -# Total code points: 61 +# Total code points: 63 # EOF diff --git a/lib/unicore/DNormalizationProps.txt b/lib/unicore/DNormalizationProps.txt index 00a25f0e7e..b344567fd3 100644 --- a/lib/unicore/DNormalizationProps.txt +++ b/lib/unicore/DNormalizationProps.txt @@ -1,6 +1,6 @@ -# DerivedNormalizationProps-13.0.0.txt -# Date: 2019-09-08, 23:31:08 GMT -# © 2019 Unicode®, Inc. +# DerivedNormalizationProps-14.0.0.txt +# Date: 2021-06-04, 02:19:20 GMT +# © 2021 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 # @@ -132,6 +132,9 @@ 33DD ; FC_NFKC; 0077 0062 # So SQUARE WB 33DE ; FC_NFKC; 0076 2215 006D # So SQUARE V OVER M 33DF ; FC_NFKC; 0061 2215 006D # So SQUARE A OVER M +A7F2 ; FC_NFKC; 0063 # Lm MODIFIER LETTER CAPITAL C +A7F3 ; FC_NFKC; 0066 # Lm MODIFIER LETTER CAPITAL F +A7F4 ; FC_NFKC; 0071 # Lm MODIFIER LETTER CAPITAL Q A7F8 ; FC_NFKC; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE 1D400 ; FC_NFKC; 0061 # L& MATHEMATICAL BOLD CAPITAL A 1D401 ; FC_NFKC; 0062 # L& MATHEMATICAL BOLD CAPITAL B @@ -650,7 +653,7 @@ A7F8 ; FC_NFKC; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE 1F16C ; FC_NFKC; 006D 0072 # So RAISED MR SIGN 1F190 ; FC_NFKC; 0064 006A # So SQUARE DJ -# Total code points: 634 +# Total code points: 637 # ================================================ @@ -1469,6 +1472,7 @@ FB46..FB4E ; NFC_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 32C0..33FF ; NFKD_QC; N # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL A69C..A69D ; NFKD_QC; N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; NFKD_QC; N # Lm MODIFIER LETTER US +A7F2..A7F4 ; NFKD_QC; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; NFKD_QC; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; NFKD_QC; N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; NFKD_QC; N # Lm MODIFIER LETTER SMALL TURNED W @@ -1593,6 +1597,9 @@ FFE5..FFE6 ; NFKD_QC; N # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN FFE8 ; NFKD_QC; N # So HALFWIDTH FORMS LIGHT VERTICAL FFE9..FFEC ; NFKD_QC; N # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +10781..10785 ; NFKD_QC; N # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; NFKD_QC; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; NFKD_QC; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1109A ; NFKD_QC; N # Lo KAITHI LETTER DDDHA 1109C ; NFKD_QC; N # Lo KAITHI LETTER RHA 110AB ; NFKD_QC; N # Lo KAITHI LETTER VA @@ -1690,7 +1697,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 16908 +# Total code points: 16967 # ================================================ @@ -1883,6 +1890,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 32C0..33FF ; NFKC_QC; N # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL A69C..A69D ; NFKC_QC; N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; NFKC_QC; N # Lm MODIFIER LETTER US +A7F2..A7F4 ; NFKC_QC; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; NFKC_QC; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; NFKC_QC; N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; NFKC_QC; N # Lm MODIFIER LETTER SMALL TURNED W @@ -2006,6 +2014,9 @@ FFE5..FFE6 ; NFKC_QC; N # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN FFE8 ; NFKC_QC; N # So HALFWIDTH FORMS LIGHT VERTICAL FFE9..FFEC ; NFKC_QC; N # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +10781..10785 ; NFKC_QC; N # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; NFKC_QC; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; NFKC_QC; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1D15E..1D164 ; NFKC_QC; N # So [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; NFKC_QC; N # So [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1D400..1D454 ; NFKC_QC; N # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G @@ -2094,7 +2105,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKC_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4807 +# Total code points: 4866 # ================================================ @@ -2889,7 +2900,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON # It is constructed by applying NFKC, CaseFolding, and removal of Default_Ignorable_Code_Points. # The process of applying these transformations is repeated until a stable result is produced. # WARNING: Application to STRINGS must apply NFC after mapping each character, because characters may interact. -# For more information, see [http://www.unicode.org/reports/tr44/] +# For more information, see [https://www.unicode.org/reports/tr44/] # Omitted code points are unchanged by this mapping. # @missing: 0000..10FFFF; NFKC_CF; <code point> @@ -3523,6 +3534,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 17B4..17B5 ; NFKC_CF; # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; NFKC_CF; # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; NFKC_CF; # Cf MONGOLIAN VOWEL SEPARATOR +180F ; NFKC_CF; # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1C80 ; NFKC_CF; 0432 # L& CYRILLIC SMALL LETTER ROUNDED VE 1C81 ; NFKC_CF; 0434 # L& CYRILLIC SMALL LETTER LONG-LEGGED DE 1C82 ; NFKC_CF; 043E # L& CYRILLIC SMALL LETTER NARROW O @@ -4318,6 +4330,7 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 2C2C ; NFKC_CF; 2C5C # L& GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D ; NFKC_CF; 2C5D # L& GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E ; NFKC_CF; 2C5E # L& GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F ; NFKC_CF; 2C5F # L& GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; NFKC_CF; 2C61 # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62 ; NFKC_CF; 026B # L& LATIN CAPITAL LETTER L WITH MIDDLE TILDE 2C63 ; NFKC_CF; 1D7D # L& LATIN CAPITAL LETTER P WITH STROKE @@ -5339,12 +5352,19 @@ A7B8 ; NFKC_CF; A7B9 # L& LATIN CAPITAL LETTER U WITH S A7BA ; NFKC_CF; A7BB # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; NFKC_CF; A7BD # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; NFKC_CF; A7BF # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; NFKC_CF; A7C1 # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; NFKC_CF; A7C3 # L& LATIN CAPITAL LETTER ANGLICANA W A7C4 ; NFKC_CF; A794 # L& LATIN CAPITAL LETTER C WITH PALATAL HOOK A7C5 ; NFKC_CF; 0282 # L& LATIN CAPITAL LETTER S WITH HOOK A7C6 ; NFKC_CF; 1D8E # L& LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7 ; NFKC_CF; A7C8 # L& LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; NFKC_CF; A7CA # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; NFKC_CF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S +A7F2 ; NFKC_CF; 0063 # Lm MODIFIER LETTER CAPITAL C +A7F3 ; NFKC_CF; 0066 # Lm MODIFIER LETTER CAPITAL F +A7F4 ; NFKC_CF; 0071 # Lm MODIFIER LETTER CAPITAL Q A7F5 ; NFKC_CF; A7F6 # L& LATIN CAPITAL LETTER REVERSED HALF H A7F8 ; NFKC_CF; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE A7F9 ; NFKC_CF; 0153 # Lm MODIFIER LETTER SMALL LIGATURE OE @@ -6845,6 +6865,97 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF 104D1 ; NFKC_CF; 104F9 # L& OSAGE CAPITAL LETTER GHA 104D2 ; NFKC_CF; 104FA # L& OSAGE CAPITAL LETTER ZA 104D3 ; NFKC_CF; 104FB # L& OSAGE CAPITAL LETTER ZHA +10570 ; NFKC_CF; 10597 # L& VITHKUQI CAPITAL LETTER A +10571 ; NFKC_CF; 10598 # L& VITHKUQI CAPITAL LETTER BBE +10572 ; NFKC_CF; 10599 # L& VITHKUQI CAPITAL LETTER BE +10573 ; NFKC_CF; 1059A # L& VITHKUQI CAPITAL LETTER CE +10574 ; NFKC_CF; 1059B # L& VITHKUQI CAPITAL LETTER CHE +10575 ; NFKC_CF; 1059C # L& VITHKUQI CAPITAL LETTER DE +10576 ; NFKC_CF; 1059D # L& VITHKUQI CAPITAL LETTER DHE +10577 ; NFKC_CF; 1059E # L& VITHKUQI CAPITAL LETTER EI +10578 ; NFKC_CF; 1059F # L& VITHKUQI CAPITAL LETTER E +10579 ; NFKC_CF; 105A0 # L& VITHKUQI CAPITAL LETTER FE +1057A ; NFKC_CF; 105A1 # L& VITHKUQI CAPITAL LETTER GA +1057C ; NFKC_CF; 105A3 # L& VITHKUQI CAPITAL LETTER HA +1057D ; NFKC_CF; 105A4 # L& VITHKUQI CAPITAL LETTER HHA +1057E ; NFKC_CF; 105A5 # L& VITHKUQI CAPITAL LETTER I +1057F ; NFKC_CF; 105A6 # L& VITHKUQI CAPITAL LETTER IJE +10580 ; NFKC_CF; 105A7 # L& VITHKUQI CAPITAL LETTER JE +10581 ; NFKC_CF; 105A8 # L& VITHKUQI CAPITAL LETTER KA +10582 ; NFKC_CF; 105A9 # L& VITHKUQI CAPITAL LETTER LA +10583 ; NFKC_CF; 105AA # L& VITHKUQI CAPITAL LETTER LLA +10584 ; NFKC_CF; 105AB # L& VITHKUQI CAPITAL LETTER ME +10585 ; NFKC_CF; 105AC # L& VITHKUQI CAPITAL LETTER NE +10586 ; NFKC_CF; 105AD # L& VITHKUQI CAPITAL LETTER NJE +10587 ; NFKC_CF; 105AE # L& VITHKUQI CAPITAL LETTER O +10588 ; NFKC_CF; 105AF # L& VITHKUQI CAPITAL LETTER PE +10589 ; NFKC_CF; 105B0 # L& VITHKUQI CAPITAL LETTER QA +1058A ; NFKC_CF; 105B1 # L& VITHKUQI CAPITAL LETTER RE +1058C ; NFKC_CF; 105B3 # L& VITHKUQI CAPITAL LETTER SE +1058D ; NFKC_CF; 105B4 # L& VITHKUQI CAPITAL LETTER SHE +1058E ; NFKC_CF; 105B5 # L& VITHKUQI CAPITAL LETTER TE +1058F ; NFKC_CF; 105B6 # L& VITHKUQI CAPITAL LETTER THE +10590 ; NFKC_CF; 105B7 # L& VITHKUQI CAPITAL LETTER U +10591 ; NFKC_CF; 105B8 # L& VITHKUQI CAPITAL LETTER VE +10592 ; NFKC_CF; 105B9 # L& VITHKUQI CAPITAL LETTER XE +10594 ; NFKC_CF; 105BB # L& VITHKUQI CAPITAL LETTER Y +10595 ; NFKC_CF; 105BC # L& VITHKUQI CAPITAL LETTER ZE +10781 ; NFKC_CF; 02D0 # Lm MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON +10782 ; NFKC_CF; 02D1 # Lm MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON +10783 ; NFKC_CF; 00E6 # Lm MODIFIER LETTER SMALL AE +10784 ; NFKC_CF; 0299 # Lm MODIFIER LETTER SMALL CAPITAL B +10785 ; NFKC_CF; 0253 # Lm MODIFIER LETTER SMALL B WITH HOOK +10787 ; NFKC_CF; 02A3 # Lm MODIFIER LETTER SMALL DZ DIGRAPH +10788 ; NFKC_CF; AB66 # Lm MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK +10789 ; NFKC_CF; 02A5 # Lm MODIFIER LETTER SMALL DZ DIGRAPH WITH CURL +1078A ; NFKC_CF; 02A4 # Lm MODIFIER LETTER SMALL DEZH DIGRAPH +1078B ; NFKC_CF; 0256 # Lm MODIFIER LETTER SMALL D WITH TAIL +1078C ; NFKC_CF; 0257 # Lm MODIFIER LETTER SMALL D WITH HOOK +1078D ; NFKC_CF; 1D91 # Lm MODIFIER LETTER SMALL D WITH HOOK AND TAIL +1078E ; NFKC_CF; 0258 # Lm MODIFIER LETTER SMALL REVERSED E +1078F ; NFKC_CF; 025E # Lm MODIFIER LETTER SMALL CLOSED REVERSED OPEN E +10790 ; NFKC_CF; 02A9 # Lm MODIFIER LETTER SMALL FENG DIGRAPH +10791 ; NFKC_CF; 0264 # Lm MODIFIER LETTER SMALL RAMS HORN +10792 ; NFKC_CF; 0262 # Lm MODIFIER LETTER SMALL CAPITAL G +10793 ; NFKC_CF; 0260 # Lm MODIFIER LETTER SMALL G WITH HOOK +10794 ; NFKC_CF; 029B # Lm MODIFIER LETTER SMALL CAPITAL G WITH HOOK +10795 ; NFKC_CF; 0127 # Lm MODIFIER LETTER SMALL H WITH STROKE +10796 ; NFKC_CF; 029C # Lm MODIFIER LETTER SMALL CAPITAL H +10797 ; NFKC_CF; 0267 # Lm MODIFIER LETTER SMALL HENG WITH HOOK +10798 ; NFKC_CF; 0284 # Lm MODIFIER LETTER SMALL DOTLESS J WITH STROKE AND HOOK +10799 ; NFKC_CF; 02AA # Lm MODIFIER LETTER SMALL LS DIGRAPH +1079A ; NFKC_CF; 02AB # Lm MODIFIER LETTER SMALL LZ DIGRAPH +1079B ; NFKC_CF; 026C # Lm MODIFIER LETTER SMALL L WITH BELT +1079C ; NFKC_CF; 1DF04 # Lm MODIFIER LETTER SMALL CAPITAL L WITH BELT +1079D ; NFKC_CF; A78E # Lm MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT +1079E ; NFKC_CF; 026E # Lm MODIFIER LETTER SMALL LEZH +1079F ; NFKC_CF; 1DF05 # Lm MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK +107A0 ; NFKC_CF; 028E # Lm MODIFIER LETTER SMALL TURNED Y +107A1 ; NFKC_CF; 1DF06 # Lm MODIFIER LETTER SMALL TURNED Y WITH BELT +107A2 ; NFKC_CF; 00F8 # Lm MODIFIER LETTER SMALL O WITH STROKE +107A3 ; NFKC_CF; 0276 # Lm MODIFIER LETTER SMALL CAPITAL OE +107A4 ; NFKC_CF; 0277 # Lm MODIFIER LETTER SMALL CLOSED OMEGA +107A5 ; NFKC_CF; 0071 # Lm MODIFIER LETTER SMALL Q +107A6 ; NFKC_CF; 027A # Lm MODIFIER LETTER SMALL TURNED R WITH LONG LEG +107A7 ; NFKC_CF; 1DF08 # Lm MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK +107A8 ; NFKC_CF; 027D # Lm MODIFIER LETTER SMALL R WITH TAIL +107A9 ; NFKC_CF; 027E # Lm MODIFIER LETTER SMALL R WITH FISHHOOK +107AA ; NFKC_CF; 0280 # Lm MODIFIER LETTER SMALL CAPITAL R +107AB ; NFKC_CF; 02A8 # Lm MODIFIER LETTER SMALL TC DIGRAPH WITH CURL +107AC ; NFKC_CF; 02A6 # Lm MODIFIER LETTER SMALL TS DIGRAPH +107AD ; NFKC_CF; AB67 # Lm MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK +107AE ; NFKC_CF; 02A7 # Lm MODIFIER LETTER SMALL TESH DIGRAPH +107AF ; NFKC_CF; 0288 # Lm MODIFIER LETTER SMALL T WITH RETROFLEX HOOK +107B0 ; NFKC_CF; 2C71 # Lm MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2 ; NFKC_CF; 028F # Lm MODIFIER LETTER SMALL CAPITAL Y +107B3 ; NFKC_CF; 02A1 # Lm MODIFIER LETTER GLOTTAL STOP WITH STROKE +107B4 ; NFKC_CF; 02A2 # Lm MODIFIER LETTER REVERSED GLOTTAL STOP WITH STROKE +107B5 ; NFKC_CF; 0298 # Lm MODIFIER LETTER BILABIAL CLICK +107B6 ; NFKC_CF; 01C0 # Lm MODIFIER LETTER DENTAL CLICK +107B7 ; NFKC_CF; 01C1 # Lm MODIFIER LETTER LATERAL CLICK +107B8 ; NFKC_CF; 01C2 # Lm MODIFIER LETTER ALVEOLAR CLICK +107B9 ; NFKC_CF; 1DF0A # Lm MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +107BA ; NFKC_CF; 1DF1E # Lm MODIFIER LETTER SMALL S WITH CURL 10C80 ; NFKC_CF; 10CC0 # L& OLD HUNGARIAN CAPITAL LETTER A 10C81 ; NFKC_CF; 10CC1 # L& OLD HUNGARIAN CAPITAL LETTER AA 10C82 ; NFKC_CF; 10CC2 # L& OLD HUNGARIAN CAPITAL LETTER EB @@ -8826,7 +8937,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] <reserved-E0080>..<reserved-E E0100..E01EF ; NFKC_CF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 10329 +# Total code points: 10429 # ================================================ @@ -9164,6 +9275,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved- 17B4..17B5 ; Changes_When_NFKC_Casefolded # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Changes_When_NFKC_Casefolded # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Changes_When_NFKC_Casefolded # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Changes_When_NFKC_Casefolded # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1C80..1C88 ; Changes_When_NFKC_Casefolded # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1C90..1CBA ; Changes_When_NFKC_Casefolded # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN 1CBD..1CBF ; Changes_When_NFKC_Casefolded # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN @@ -9399,7 +9511,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved- 2A0C ; Changes_When_NFKC_Casefolded # Sm QUADRUPLE INTEGRAL OPERATOR 2A74..2A76 ; Changes_When_NFKC_Casefolded # Sm [3] DOUBLE COLON EQUAL..THREE CONSECUTIVE EQUALS SIGNS 2ADC ; Changes_When_NFKC_Casefolded # Sm FORKING -2C00..2C2E ; Changes_When_NFKC_Casefolded # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_NFKC_Casefolded # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_NFKC_Casefolded # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -9590,9 +9702,14 @@ A7B8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER U W A7BA ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S +A7F2..A7F4 ; Changes_When_NFKC_Casefolded # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Changes_When_NFKC_Casefolded # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK @@ -9723,6 +9840,13 @@ FFED..FFEE ; Changes_When_NFKC_Casefolded # So [2] HALFWIDTH BLACK SQUARE.. FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserved-FFF8> 10400..10427 ; Changes_When_NFKC_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_NFKC_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_NFKC_Casefolded # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_NFKC_Casefolded # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_NFKC_Casefolded # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_NFKC_Casefolded # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10781..10785 ; Changes_When_NFKC_Casefolded # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Changes_When_NFKC_Casefolded # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Changes_When_NFKC_Casefolded # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10C80..10CB2 ; Changes_When_NFKC_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_NFKC_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_NFKC_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -9824,6 +9948,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser E0100..E01EF ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 10329 +# Total code points: 10429 # EOF diff --git a/lib/unicore/EastAsianWidth.txt b/lib/unicore/EastAsianWidth.txt index b43aec9273..e04f705178 100644 --- a/lib/unicore/EastAsianWidth.txt +++ b/lib/unicore/EastAsianWidth.txt @@ -1,11 +1,11 @@ -# EastAsianWidth-13.0.0.txt -# Date: 2029-01-21, 18:14:00 GMT [KW, LI] -# © 2020 Unicode®, Inc. +# EastAsianWidth-14.0.0.txt +# Date: 2021-07-06, 09:58:53 GMT [KW, LI] +# © 2021 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 +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # East_Asian_Width Property # @@ -37,7 +37,7 @@ # with ranges of code points, the code point count in square brackets. # # For more information, see UAX #11: East Asian Width, -# at http://www.unicode.org/reports/tr11/ +# at https://www.unicode.org/reports/tr11/ # # @missing: 0000..10FFFF; N 0000..001F;N # Cc [32] <control-0000>..<control-001F> @@ -273,7 +273,7 @@ 0610..061A;N # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061B;N # Po ARABIC SEMICOLON 061C;N # Cf ARABIC LETTER MARK -061E..061F;N # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F;N # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F;N # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640;N # Lm ARABIC TATWEEL 0641..064A;N # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -331,9 +331,14 @@ 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..08C7;N # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1;N # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887;N # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888;N # Sk ARABIC RAISED ROUND DOT +0889..088E;N # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891;N # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F;N # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8;N # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9;N # Lm ARABIC SMALL FARSI YEH +08CA..08E1;N # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2;N # Cf ARABIC DISPUTED END OF AYAH 08E3..08FF;N # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA 0900..0902;N # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA @@ -490,6 +495,7 @@ 0C0E..0C10;N # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28;N # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39;N # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C;N # Mn TELUGU SIGN NUKTA 0C3D;N # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40;N # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44;N # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -497,6 +503,7 @@ 0C4A..0C4D;N # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56;N # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A;N # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D;N # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61;N # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63;N # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F;N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -522,7 +529,7 @@ 0CCA..0CCB;N # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD;N # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6;N # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE;N # Lo KANNADA LETTER FA +0CDD..0CDE;N # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1;N # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 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 @@ -709,11 +716,13 @@ 16EB..16ED;N # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0;N # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8;N # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C;N # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711;N # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711;N # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714;N # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1715;N # Mc TAGALOG SIGN PAMUDPOD +171F;N # Lo TAGALOG LETTER ARCHAIC RA 1720..1731;N # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734;N # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733;N # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734;N # Mc HANUNOO SIGN PAMUDPOD 1735..1736;N # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751;N # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753;N # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -741,6 +750,7 @@ 1807..180A;N # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D;N # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E;N # Cf MONGOLIAN VOWEL SEPARATOR +180F;N # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819;N # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842;N # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843;N # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -796,7 +806,7 @@ 1AA8..1AAD;N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD;N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE;N # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0;N # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE;N # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03;N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04;N # Mc BALINESE SIGN BISAH 1B05..1B33;N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -808,12 +818,13 @@ 1B3D..1B41;N # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42;N # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44;N # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B;N # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C;N # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59;N # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60;N # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A;N # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73;N # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C;N # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E;N # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B80..1B81;N # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82;N # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0;N # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -872,8 +883,7 @@ 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..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 +1DC0..1DFF;N # Mn [64] COMBINING DOTTED GRAVE ACCENT..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 1F18..1F1D;N # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -965,7 +975,7 @@ 20A9;H # Sc WON SIGN 20AA..20AB;N # Sc [2] NEW SHEQEL SIGN..DONG SIGN 20AC;A # Sc EURO SIGN -20AD..20BF;N # Sc [19] KIP SIGN..BITCOIN SIGN +20AD..20C0;N # Sc [20] KIP SIGN..SOM 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 @@ -1338,8 +1348,7 @@ 2B5A..2B73;N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95;N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF;N # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -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 +2C00..2C5F;N # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60..2C7B;N # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D;N # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2C7F;N # Lu [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL @@ -1407,7 +1416,16 @@ 2E42;N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F;N # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51;N # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52;N # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54;N # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55;N # Ps LEFT SQUARE BRACKET WITH STROKE +2E56;N # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57;N # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58;N # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59;N # Ps TOP HALF LEFT PARENTHESIS +2E5A;N # Pe TOP HALF RIGHT PARENTHESIS +2E5B;N # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C;N # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D;N # Pd OBLIQUE HYPHEN 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 @@ -1485,8 +1503,7 @@ 3300..33FF;W # So [256] SQUARE APAATO..SQUARE GAL 3400..4DBF;W # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF 4DC0..4DFF;N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FFC;W # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -9FFD..9FFF;W # Cn [3] <reserved-9FFD>..<reserved-9FFF> +4E00..9FFF;W # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-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 @@ -1525,8 +1542,11 @@ A788;N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A;N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E;N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F;N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF;N # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA;N # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA;N # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1;N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3;N # Ll LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9;N # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4;N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6;N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7;N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9;N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1682,15 +1702,17 @@ FB40..FB41;N # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEK FB43..FB44;N # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FB4F;N # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1;N # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1;N # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2;N # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D;N # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E;N # Pe ORNATE LEFT PARENTHESIS FD3F;N # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F;N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F;N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7;N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF;N # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB;N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC;N # Sc RIAL SIGN -FDFD;N # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF;N # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F;A # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE10..FE16;W # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17;W # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET @@ -1839,9 +1861,20 @@ FFFD;A # So REPLACEMENT CHARACTER 10500..10527;N # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563;N # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F;N # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A;N # Lu [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A;N # Lu [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592;N # Lu [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595;N # Lu [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1;N # Ll [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1;N # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9;N # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC;N # Ll [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736;N # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755;N # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767;N # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785;N # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0;N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA;N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805;N # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808;N # Lo CYPRIOT SYLLABLE JO 1080A..10835;N # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1920,6 +1953,9 @@ FFFD;A # So REPLACEMENT CHARACTER 10F46..10F50;N # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F51..10F54;N # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59;N # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81;N # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85;N # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +10F86..10F89;N # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4;N # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB;N # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6;N # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -1931,6 +1967,10 @@ FFFD;A # So REPLACEMENT CHARACTER 11047..1104D;N # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065;N # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F;N # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070;N # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072;N # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074;N # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075;N # Lo BRAHMI LETTER OLD TAMIL LLA 1107F;N # Mn BRAHMI NUMBER JOINER 11080..11081;N # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11082;N # Mc KAITHI SIGN VISARGA @@ -1942,6 +1982,7 @@ FFFD;A # So REPLACEMENT CHARACTER 110BB..110BC;N # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD;N # Cf KAITHI NUMBER SIGN 110BE..110C1;N # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110C2;N # Mn KAITHI VOWEL SIGN VOCALIC R 110CD;N # Cf KAITHI NUMBER SIGN ABOVE 110D0..110E8;N # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9;N # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -2076,6 +2117,7 @@ FFFD;A # So REPLACEMENT CHARACTER 116B6;N # Mc TAKRI SIGN VIRAMA 116B7;N # Mn TAKRI SIGN NUKTA 116B8;N # Lo TAKRI LETTER ARCHAIC KHA +116B9;N # Po TAKRI ABBREVIATION SIGN 116C0..116C9;N # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A;N # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F;N # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA @@ -2087,6 +2129,7 @@ FFFD;A # So REPLACEMENT CHARACTER 1173A..1173B;N # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E;N # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F;N # So AHOM SYMBOL VI +11740..11746;N # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B;N # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E;N # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837;N # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -2145,6 +2188,7 @@ FFFD;A # So REPLACEMENT CHARACTER 11A9A..11A9C;N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9D;N # Lo SOYOMBO MARK PLUTA 11A9E..11AA2;N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 +11AB0..11ABF;N # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 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 @@ -2201,6 +2245,8 @@ FFFD;A # So REPLACEMENT CHARACTER 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 12480..12543;N # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0;N # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2;N # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E;N # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 13430..13438;N # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT 14400..14646;N # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 @@ -2208,6 +2254,8 @@ FFFD;A # So REPLACEMENT CHARACTER 16A40..16A5E;N # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69;N # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F;N # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE;N # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9;N # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED;N # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4;N # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16AF5;N # Po BASSA VAH FULL STOP @@ -2240,8 +2288,11 @@ FFFD;A # So REPLACEMENT CHARACTER 18800..18AFF;W # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18B00..18CD5;W # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08;W # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 +1AFF0..1AFF3;W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB;W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE;W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 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 +1B100..1B122;W # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU 1B150..1B152;W # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167;W # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB;W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -2253,6 +2304,9 @@ FFFD;A # So REPLACEMENT CHARACTER 1BC9D..1BC9E;N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F;N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3;N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D;N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46;N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF50..1CFC3;N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5;N # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126;N # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164;N # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -2266,7 +2320,7 @@ FFFD;A # So REPLACEMENT CHARACTER 1D185..1D18B;N # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D18C..1D1A9;N # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH 1D1AA..1D1AD;N # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO -1D1AE..1D1E8;N # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA;N # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241;N # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D242..1D244;N # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME 1D245;N # So GREEK MUSICAL LEIMMA @@ -2326,6 +2380,9 @@ FFFD;A # So REPLACEMENT CHARACTER 1DA87..1DA8B;N # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1DA9B..1DA9F;N # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF;N # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09;N # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A;N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E;N # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006;N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018;N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021;N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -2337,10 +2394,16 @@ FFFD;A # So REPLACEMENT CHARACTER 1E140..1E149;N # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E;N # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F;N # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD;N # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE;N # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB;N # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF;N # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9;N # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF;N # Sc WANCHO NGUN SIGN +1E7E0..1E7E6;N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB;N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE;N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE;N # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4;N # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF;N # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6;N # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS @@ -2465,6 +2528,7 @@ FFFD;A # So REPLACEMENT CHARACTER 1F6D0..1F6D2;W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY 1F6D3..1F6D4;N # So [2] STUPA..PAGODA 1F6D5..1F6D7;W # So [3] HINDU TEMPLE..ELEVATOR +1F6DD..1F6DF;W # So [3] PLAYGROUND SLIDE..RING BUOY 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 @@ -2472,6 +2536,7 @@ FFFD;A # So REPLACEMENT CHARACTER 1F700..1F773;N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8;N # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB;W # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0;W # So HEAVY EQUALS SIGN 1F800..1F80B;N # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847;N # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859;N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW @@ -2483,25 +2548,25 @@ FFFD;A # So REPLACEMENT CHARACTER 1F93B;N # So MODERN PENTATHLON 1F93C..1F945;W # So [10] WRESTLERS..GOAL NET 1F946;N # So RIFLE -1F947..1F978;W # So [50] FIRST PLACE MEDAL..DISGUISED FACE -1F97A..1F9CB;W # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1F9FF;W # So [51] STANDING PERSON..NAZAR AMULET +1F947..1F9FF;W # So [185] FIRST PLACE MEDAL..NAZAR AMULET 1FA00..1FA53;N # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D;N # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74;W # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A;W # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C;W # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86;W # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8;W # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6;W # So [7] FLY..FEATHER -1FAC0..1FAC2;W # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6;W # So [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC;W # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA;W # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5;W # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9;W # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7;W # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6;W # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92;N # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA;N # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9;N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD;W # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF;W # Cn [34] <reserved-2A6DE>..<reserved-2A6FF> -2A700..2B734;W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F;W # Cn [11] <reserved-2B735>..<reserved-2B73F> +20000..2A6DF;W # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF;W # Cn [32] <reserved-2A6E0>..<reserved-2A6FF> +2A700..2B738;W # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F;W # Cn [7] <reserved-2B739>..<reserved-2B73F> 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 diff --git a/lib/unicore/EmojiSources.txt b/lib/unicore/EmojiSources.txt index b2a526160c..391a7e0750 100644 --- a/lib/unicore/EmojiSources.txt +++ b/lib/unicore/EmojiSources.txt @@ -1,6 +1,6 @@ -# EmojiSources-13.0.0.txt -# Date: 2019-09-09, 19:40:00 GMT [MS, KW] -# © 2019 Unicode®, Inc. +# EmojiSources-14.0.0.txt +# Date: 2021-03-16, 21:39:00 GMT [MS, KW] +# © 2021 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database diff --git a/lib/unicore/EquivalentUnifiedIdeograph.txt b/lib/unicore/EquivalentUnifiedIdeograph.txt index 98dc294b19..340ec3a71e 100644 --- a/lib/unicore/EquivalentUnifiedIdeograph.txt +++ b/lib/unicore/EquivalentUnifiedIdeograph.txt @@ -1,6 +1,6 @@ -# EquivalentUnifiedIdeograph-13.0.0.txt -# Date: 2019-09-09, 19:41:00 GMT [KL, KW] -# © 2019 Unicode®, Inc. +# EquivalentUnifiedIdeograph-14.0.0.txt +# Date: 2021-03-16, 21:41:00 GMT [KL, KW] +# © 2021 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 # diff --git a/lib/unicore/HangulSyllableType.txt b/lib/unicore/HangulSyllableType.txt index 90aa56964e..8e7ca091f6 100644 --- a/lib/unicore/HangulSyllableType.txt +++ b/lib/unicore/HangulSyllableType.txt @@ -1,6 +1,6 @@ -# HangulSyllableType-13.0.0.txt -# Date: 2019-09-08, 23:31:10 GMT -# © 2019 Unicode®, Inc. +# HangulSyllableType-14.0.0.txt +# Date: 2021-03-08, 19:35:46 GMT +# © 2021 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 # diff --git a/lib/unicore/IdStatus.txt b/lib/unicore/IdStatus.txt index e699176ca9..29043bc846 100644 --- a/lib/unicore/IdStatus.txt +++ b/lib/unicore/IdStatus.txt @@ -1,11 +1,11 @@ # IdentifierStatus.txt -# Date: 2020-02-07, 22:02:47 GMT -# © 2020 Unicode®, Inc. +# Date: 2021-08-12, 01:13:34 GMT +# © 2021 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Security Mechanisms for UTS #39 -# Version: 13.0.0 +# Version: 14.0.0 # # For documentation and usage, see http://www.unicode.org/reports/tr39 # @@ -140,12 +140,16 @@ 076E..077F ; Allowed # 5.1 [18] ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE 0780..07B0 ; Allowed # 3.0 [49] THAANA LETTER HAA..THAANA SUKUN 07B1 ; Allowed # 3.2 THAANA LETTER NAA +0870..0887 ; Allowed # 14.0 [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Allowed # 14.0 [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL 08A0 ; Allowed # 6.1 ARABIC LETTER BEH WITH SMALL V BELOW 08A1 ; Allowed # 7.0 ARABIC LETTER BEH WITH HAMZA ABOVE 08A2..08AC ; Allowed # 6.1 [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH 08B2 ; Allowed # 7.0 ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B5 ; Allowed # 14.0 ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE 08B6..08BD ; Allowed # 9.0 [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08BE..08C7 ; Allowed # 13.0 [10] ARABIC LETTER PEH WITH SMALL V..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +08C8..08C9 ; Allowed # 14.0 [2] ARABIC LETTER GRAF..ARABIC SMALL FARSI YEH 0901..0903 ; Allowed # 1.1 [3] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN VISARGA 0904 ; Allowed # 4.0 DEVANAGARI LETTER SHORT A 0905..0939 ; Allowed # 1.1 [53] DEVANAGARI LETTER A..DEVANAGARI LETTER HA @@ -254,11 +258,13 @@ 0C12..0C28 ; Allowed # 1.1 [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C33 ; Allowed # 1.1 [10] TELUGU LETTER PA..TELUGU LETTER LLA 0C35..0C39 ; Allowed # 1.1 [5] TELUGU LETTER VA..TELUGU LETTER HA +0C3C ; Allowed # 14.0 TELUGU SIGN NUKTA 0C3D ; Allowed # 5.1 TELUGU SIGN AVAGRAHA 0C3E..0C44 ; Allowed # 1.1 [7] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN VOCALIC RR 0C46..0C48 ; Allowed # 1.1 [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Allowed # 1.1 [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; Allowed # 1.1 [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C5D ; Allowed # 14.0 TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Allowed # 1.1 [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; Allowed # 1.1 [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C80 ; Allowed # 9.0 KANNADA SIGN SPACING CANDRABINDU @@ -273,6 +279,7 @@ 0CC6..0CC8 ; Allowed # 1.1 [3] KANNADA VOWEL SIGN E..KANNADA VOWEL SIGN AI 0CCA..0CCD ; Allowed # 1.1 [4] KANNADA VOWEL SIGN O..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Allowed # 1.1 [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CDD ; Allowed # 14.0 KANNADA LETTER NAKAARA POLLU 0CE0..0CE1 ; Allowed # 1.1 [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Allowed # 5.0 [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; Allowed # 1.1 [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -434,7 +441,8 @@ 1780..17A2 ; Allowed # 3.0 [35] KHMER LETTER KA..KHMER LETTER QA 17A5..17A7 ; Allowed # 3.0 [3] KHMER INDEPENDENT VOWEL QI..KHMER INDEPENDENT VOWEL QU 17A9..17B3 ; Allowed # 3.0 [11] KHMER INDEPENDENT VOWEL QUU..KHMER INDEPENDENT VOWEL QAU -17B6..17CA ; Allowed # 3.0 [21] KHMER VOWEL SIGN AA..KHMER SIGN TRIISAP +17B6..17CD ; Allowed # 3.0 [24] KHMER VOWEL SIGN AA..KHMER SIGN TOANDAKHIAT +17D0 ; Allowed # 3.0 KHMER SIGN SAMYOK SANNYA 17D2 ; Allowed # 3.0 KHMER SIGN COENG 17D7 ; Allowed # 3.0 KHMER SIGN LEK TOO 17DC ; Allowed # 3.0 KHMER SIGN AVAKRAHASANYA @@ -514,6 +522,7 @@ 9FD6..9FEA ; Allowed # 10.0 [21] CJK UNIFIED IDEOGRAPH-9FD6..CJK UNIFIED IDEOGRAPH-9FEA 9FEB..9FEF ; Allowed # 11.0 [5] CJK UNIFIED IDEOGRAPH-9FEB..CJK UNIFIED IDEOGRAPH-9FEF 9FF0..9FFC ; Allowed # 13.0 [13] CJK UNIFIED IDEOGRAPH-9FF0..CJK UNIFIED IDEOGRAPH-9FFC +9FFD..9FFF ; Allowed # 14.0 [3] CJK UNIFIED IDEOGRAPH-9FFD..CJK UNIFIED IDEOGRAPH-9FFF A67F ; Allowed # 5.1 CYRILLIC PAYEROK A717..A71A ; Allowed # 5.0 [4] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOWER RIGHT CORNER ANGLE A71B..A71F ; Allowed # 5.1 [5] MODIFIER LETTER RAISED UP ARROW..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK @@ -523,8 +532,12 @@ A792..A793 ; Allowed # 6.1 [2] LATIN CAPITAL LETTER C WITH BAR..LATIN S A7AA ; Allowed # 6.1 LATIN CAPITAL LETTER H WITH HOOK A7AE ; Allowed # 9.0 LATIN CAPITAL LETTER SMALL CAPITAL I A7B8..A7B9 ; Allowed # 11.0 [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE +A7C0..A7C1 ; Allowed # 14.0 [2] LATIN CAPITAL LETTER OLD POLISH O..LATIN SMALL LETTER OLD POLISH O A7C2..A7C6 ; Allowed # 12.0 [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7..A7CA ; Allowed # 13.0 [4] LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Allowed # 14.0 [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Allowed # 14.0 LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Allowed # 14.0 [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S A9E7..A9FE ; Allowed # 7.0 [24] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING BHA AA60..AA76 ; Allowed # 5.2 [23] MYANMAR LETTER KHAMTI GA..MYANMAR LOGOGRAM KHAMTI HM AA7A..AA7B ; Allowed # 5.2 [2] MYANMAR LETTER AITON RA..MYANMAR SIGN PAO KAREN TONE @@ -548,14 +561,22 @@ FA27..FA29 ; Allowed # 1.1 [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK CO 1133B ; Allowed # 11.0 COMBINING BINDU BELOW 1133C ; Allowed # 7.0 GRANTHA SIGN NUKTA 16FF0..16FF1 ; Allowed # 13.0 [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY +1B11F..1B122 ; Allowed # 14.0 [4] HIRAGANA LETTER ARCHAIC WU..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Allowed # 12.0 [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Allowed # 12.0 [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N +1DF00..1DF1E ; Allowed # 14.0 [31] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL +1E7E0..1E7E6 ; Allowed # 14.0 [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Allowed # 14.0 [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Allowed # 14.0 [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Allowed # 14.0 [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 20000..2A6D6 ; Allowed # 3.1 [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6DD ; Allowed # 13.0 [7] CJK UNIFIED IDEOGRAPH-2A6D7..CJK UNIFIED IDEOGRAPH-2A6DD +2A6DE..2A6DF ; Allowed # 14.0 [2] CJK UNIFIED IDEOGRAPH-2A6DE..CJK UNIFIED IDEOGRAPH-2A6DF 2A700..2B734 ; Allowed # 5.2 [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +2B735..2B738 ; Allowed # 14.0 [4] CJK UNIFIED IDEOGRAPH-2B735..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Allowed # 6.0 [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Allowed # 8.0 [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Allowed # 10.0 [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 30000..3134A ; Allowed # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 107835 +# Total code points: 107957 diff --git a/lib/unicore/IdType.txt b/lib/unicore/IdType.txt index f71717465a..dc2f735451 100644 --- a/lib/unicore/IdType.txt +++ b/lib/unicore/IdType.txt @@ -1,11 +1,11 @@ # IdentifierType.txt -# Date: 2020-02-07, 22:02:47 GMT -# © 2020 Unicode®, Inc. +# Date: 2021-08-12, 01:13:33 GMT +# © 2021 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Security Mechanisms for UTS #39 -# Version: 13.0.0 +# Version: 14.0.0 # # For documentation and usage, see http://www.unicode.org/reports/tr39 # @@ -137,12 +137,16 @@ 076E..077F ; Recommended # 5.1 [18] ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE 0780..07B0 ; Recommended # 3.0 [49] THAANA LETTER HAA..THAANA SUKUN 07B1 ; Recommended # 3.2 THAANA LETTER NAA +0870..0887 ; Recommended # 14.0 [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Recommended # 14.0 [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL 08A0 ; Recommended # 6.1 ARABIC LETTER BEH WITH SMALL V BELOW 08A1 ; Recommended # 7.0 ARABIC LETTER BEH WITH HAMZA ABOVE 08A2..08AC ; Recommended # 6.1 [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH 08B2 ; Recommended # 7.0 ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B5 ; Recommended # 14.0 ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE 08B6..08BD ; Recommended # 9.0 [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08BE..08C7 ; Recommended # 13.0 [10] ARABIC LETTER PEH WITH SMALL V..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +08C8..08C9 ; Recommended # 14.0 [2] ARABIC LETTER GRAF..ARABIC SMALL FARSI YEH 0901..0903 ; Recommended # 1.1 [3] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN VISARGA 0904 ; Recommended # 4.0 DEVANAGARI LETTER SHORT A 0905..0939 ; Recommended # 1.1 [53] DEVANAGARI LETTER A..DEVANAGARI LETTER HA @@ -251,11 +255,13 @@ 0C12..0C28 ; Recommended # 1.1 [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C33 ; Recommended # 1.1 [10] TELUGU LETTER PA..TELUGU LETTER LLA 0C35..0C39 ; Recommended # 1.1 [5] TELUGU LETTER VA..TELUGU LETTER HA +0C3C ; Recommended # 14.0 TELUGU SIGN NUKTA 0C3D ; Recommended # 5.1 TELUGU SIGN AVAGRAHA 0C3E..0C44 ; Recommended # 1.1 [7] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN VOCALIC RR 0C46..0C48 ; Recommended # 1.1 [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Recommended # 1.1 [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; Recommended # 1.1 [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C5D ; Recommended # 14.0 TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Recommended # 1.1 [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; Recommended # 1.1 [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C80 ; Recommended # 9.0 KANNADA SIGN SPACING CANDRABINDU @@ -270,6 +276,7 @@ 0CC6..0CC8 ; Recommended # 1.1 [3] KANNADA VOWEL SIGN E..KANNADA VOWEL SIGN AI 0CCA..0CCD ; Recommended # 1.1 [4] KANNADA VOWEL SIGN O..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Recommended # 1.1 [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CDD ; Recommended # 14.0 KANNADA LETTER NAKAARA POLLU 0CE0..0CE1 ; Recommended # 1.1 [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Recommended # 5.0 [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; Recommended # 1.1 [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -430,7 +437,8 @@ 1780..17A2 ; Recommended # 3.0 [35] KHMER LETTER KA..KHMER LETTER QA 17A5..17A7 ; Recommended # 3.0 [3] KHMER INDEPENDENT VOWEL QI..KHMER INDEPENDENT VOWEL QU 17A9..17B3 ; Recommended # 3.0 [11] KHMER INDEPENDENT VOWEL QUU..KHMER INDEPENDENT VOWEL QAU -17B6..17CA ; Recommended # 3.0 [21] KHMER VOWEL SIGN AA..KHMER SIGN TRIISAP +17B6..17CD ; Recommended # 3.0 [24] KHMER VOWEL SIGN AA..KHMER SIGN TOANDAKHIAT +17D0 ; Recommended # 3.0 KHMER SIGN SAMYOK SANNYA 17D2 ; Recommended # 3.0 KHMER SIGN COENG 17D7 ; Recommended # 3.0 KHMER SIGN LEK TOO 17DC ; Recommended # 3.0 KHMER SIGN AVAKRAHASANYA @@ -506,6 +514,7 @@ 9FD6..9FEA ; Recommended # 10.0 [21] CJK UNIFIED IDEOGRAPH-9FD6..CJK UNIFIED IDEOGRAPH-9FEA 9FEB..9FEF ; Recommended # 11.0 [5] CJK UNIFIED IDEOGRAPH-9FEB..CJK UNIFIED IDEOGRAPH-9FEF 9FF0..9FFC ; Recommended # 13.0 [13] CJK UNIFIED IDEOGRAPH-9FF0..CJK UNIFIED IDEOGRAPH-9FFC +9FFD..9FFF ; Recommended # 14.0 [3] CJK UNIFIED IDEOGRAPH-9FFD..CJK UNIFIED IDEOGRAPH-9FFF A67F ; Recommended # 5.1 CYRILLIC PAYEROK A717..A71A ; Recommended # 5.0 [4] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOWER RIGHT CORNER ANGLE A71B..A71F ; Recommended # 5.1 [5] MODIFIER LETTER RAISED UP ARROW..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK @@ -515,8 +524,12 @@ A792..A793 ; Recommended # 6.1 [2] LATIN CAPITAL LETTER A7AA ; Recommended # 6.1 LATIN CAPITAL LETTER H WITH HOOK A7AE ; Recommended # 9.0 LATIN CAPITAL LETTER SMALL CAPITAL I A7B8..A7B9 ; Recommended # 11.0 [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE +A7C0..A7C1 ; Recommended # 14.0 [2] LATIN CAPITAL LETTER OLD POLISH O..LATIN SMALL LETTER OLD POLISH O A7C2..A7C6 ; Recommended # 12.0 [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7..A7CA ; Recommended # 13.0 [4] LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Recommended # 14.0 [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Recommended # 14.0 LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Recommended # 14.0 [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S A9E7..A9FE ; Recommended # 7.0 [24] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING BHA AA60..AA76 ; Recommended # 5.2 [23] MYANMAR LETTER KHAMTI GA..MYANMAR LOGOGRAM KHAMTI HM AA7A..AA7B ; Recommended # 5.2 [2] MYANMAR LETTER AITON RA..MYANMAR SIGN PAO KAREN TONE @@ -540,17 +553,25 @@ FA27..FA29 ; Recommended # 1.1 [3] CJK COMPATIBILITY ID 1133B ; Recommended # 11.0 COMBINING BINDU BELOW 1133C ; Recommended # 7.0 GRANTHA SIGN NUKTA 16FF0..16FF1 ; Recommended # 13.0 [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY +1B11F..1B122 ; Recommended # 14.0 [4] HIRAGANA LETTER ARCHAIC WU..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Recommended # 12.0 [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Recommended # 12.0 [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N +1DF00..1DF1E ; Recommended # 14.0 [31] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL +1E7E0..1E7E6 ; Recommended # 14.0 [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Recommended # 14.0 [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Recommended # 14.0 [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Recommended # 14.0 [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 20000..2A6D6 ; Recommended # 3.1 [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6DD ; Recommended # 13.0 [7] CJK UNIFIED IDEOGRAPH-2A6D7..CJK UNIFIED IDEOGRAPH-2A6DD +2A6DE..2A6DF ; Recommended # 14.0 [2] CJK UNIFIED IDEOGRAPH-2A6DE..CJK UNIFIED IDEOGRAPH-2A6DF 2A700..2B734 ; Recommended # 5.2 [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +2B735..2B738 ; Recommended # 14.0 [4] CJK UNIFIED IDEOGRAPH-2B735..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Recommended # 6.0 [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Recommended # 8.0 [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Recommended # 10.0 [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 30000..3134A ; Recommended # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 107816 +# Total code points: 107938 # Identifier_Type: Inclusion @@ -607,8 +628,8 @@ FA27..FA29 ; Recommended # 1.1 [3] CJK COMPATIBILITY ID 1A90..1A99 ; Limited_Use # 5.2 [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; Limited_Use # 5.2 TAI THAM SIGN MAI YAMOK 1B00..1B4B ; Limited_Use # 5.0 [76] BALINESE SIGN ULU RICEM..BALINESE LETTER ASYURA SASAK +1B4C ; Limited_Use # 14.0 BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; Limited_Use # 5.0 [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE -1B6B..1B73 ; Limited_Use # 5.0 [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1BAA ; Limited_Use # 5.1 [43] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PAMAAEH 1BAB..1BAD ; Limited_Use # 6.1 [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA 1BAE..1BB9 ; Limited_Use # 5.1 [12] SUNDANESE LETTER KHA..SUNDANESE DIGIT NINE @@ -657,6 +678,7 @@ ABF0..ABF9 ; Limited_Use # 5.2 [10] MEETEI MAYEK DIGIT Z 1145E ; Limited_Use # 11.0 NEWA SANDHI MARK 1145F ; Limited_Use # 12.0 NEWA LETTER VEDIC ANUSVARA 11460..11461 ; Limited_Use # 13.0 [2] NEWA SIGN JIHVAMULIYA..NEWA SIGN UPADHMANIYA +11AB0..11ABF ; Limited_Use # 14.0 [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11D60..11D65 ; Limited_Use # 11.0 [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU 11D67..11D68 ; Limited_Use # 11.0 [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI 11D6A..11D8E ; Limited_Use # 11.0 [37] GUNJALA GONDI LETTER OO..GUNJALA GONDI VOWEL SIGN UU @@ -680,13 +702,15 @@ ABF0..ABF9 ; Limited_Use # 5.2 [10] MEETEI MAYEK DIGIT Z 1E94B ; Limited_Use # 12.0 ADLAM NASALIZATION MARK 1E950..1E959 ; Limited_Use # 9.0 [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 5025 +# Total code points: 5033 # Identifier_Type: Limited_Use Technical 0740..074A ; Limited_Use Technical # 3.0 [11] SYRIAC FEMININE DOT..SYRIAC BARREKH +1B6B..1B73 ; Limited_Use Technical # 5.0 [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1DFA ; Limited_Use Technical # 14.0 COMBINING DOT BELOW LEFT -# Total code points: 11 +# Total code points: 21 # Identifier_Type: Limited_Use Exclusion @@ -719,6 +743,7 @@ A62A..A62B ; Limited_Use Obsolete # 5.1 [2] VAI SYLLABLE NDOLE M 1AA8..1AAD ; Limited_Use Not_XID # 5.2 [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1B5A..1B6A ; Limited_Use Not_XID # 5.0 [17] BALINESE PANTI..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; Limited_Use Not_XID # 5.0 [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; Limited_Use Not_XID # 14.0 [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1BFC..1BFF ; Limited_Use Not_XID # 6.0 [4] BATAK SYMBOL BINDU NA METEK..BATAK SYMBOL BINDU PANGOLAT 1C3B..1C3F ; Limited_Use Not_XID # 5.1 [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; Limited_Use Not_XID # 5.1 [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD @@ -754,7 +779,7 @@ ABEB ; Limited_Use Not_XID # 5.2 MEETEI MAYEK CHEIKHE 1E2FF ; Limited_Use Not_XID # 12.0 WANCHO NGUN SIGN 1E95E..1E95F ; Limited_Use Not_XID # 9.0 [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 202 +# Total code points: 204 # Identifier_Type: Uncommon_Use @@ -798,7 +823,9 @@ ABEB ; Limited_Use Not_XID # 5.2 MEETEI MAYEK CHEIKHE 06DF..06E4 ; Uncommon_Use # 1.1 [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA 06E7..06E8 ; Uncommon_Use # 1.1 [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON 06EA..06ED ; Uncommon_Use # 1.1 [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +0898..089F ; Uncommon_Use # 14.0 [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA 08B3..08B4 ; Uncommon_Use # 8.0 [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08CA..08D2 ; Uncommon_Use # 14.0 [9] ARABIC SMALL HIGH FARSI YEH..ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW 08D3 ; Uncommon_Use # 11.0 ARABIC SMALL LOW WAW 08D4..08E1 ; Uncommon_Use # 9.0 [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3 ; Uncommon_Use # 8.0 ARABIC TURNED DAMMA BELOW @@ -816,6 +843,7 @@ ABEB ; Limited_Use Not_XID # 5.2 MEETEI MAYEK CHEIKHE 0D44 ; Uncommon_Use # 5.1 MALAYALAM VOWEL SIGN VOCALIC RR 0D62..0D63 ; Uncommon_Use # 5.1 [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL 0F39 ; Uncommon_Use # 2.0 TIBETAN MARK TSA -PHRU +1AC1..1ACE ; Uncommon_Use # 14.0 [14] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING LATIN SMALL LETTER INSULAR T 2054 ; Uncommon_Use # 4.0 INVERTED UNDERTIE 2C68..2C6C ; Uncommon_Use # 5.0 [5] LATIN SMALL LETTER H WITH DESCENDER..LATIN SMALL LETTER Z WITH DESCENDER A66F ; Uncommon_Use # 5.1 COMBINING CYRILLIC VZMET @@ -824,8 +852,12 @@ A78B..A78C ; Uncommon_Use # 5.1 [2] LATIN CAPITAL LETTER A78F ; Uncommon_Use # 8.0 LATIN LETTER SINOLOGICAL DOT A7B2..A7B7 ; Uncommon_Use # 8.0 [6] LATIN CAPITAL LETTER J WITH CROSSED-TAIL..LATIN SMALL LETTER OMEGA AB60..AB63 ; Uncommon_Use # 8.0 [4] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER UO +10780 ; Uncommon_Use # 14.0 MODIFIER LETTER SMALL CAPITAL AA +1AFF0..1AFF3 ; Uncommon_Use # 14.0 [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Uncommon_Use # 14.0 [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Uncommon_Use # 14.0 [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 -# Total code points: 263 +# Total code points: 308 # Identifier_Type: Uncommon_Use Technical @@ -931,7 +963,7 @@ A8FC ; Uncommon_Use Obsolete Not_XID # 8.0 DEVANAGARI SIGN SIDD 0953..0954 ; Technical # 1.1 [2] DEVANAGARI GRAVE ACCENT..DEVANAGARI ACUTE ACCENT 0D81 ; Technical # 13.0 SINHALA SIGN CANDRABINDU 0F18..0F19 ; Technical # 2.0 [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS -17CB..17D0 ; Technical # 3.0 [6] KHMER SIGN BANTOC..KHMER SIGN SAMYOK SANNYA +17CE..17CF ; Technical # 3.0 [2] KHMER SIGN KAKABAT..KHMER SIGN AHSDA 1ABF..1AC0 ; Technical # 13.0 [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW 1D00..1D2B ; Technical # 4.0 [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2F ; Technical # 4.0 MODIFIER LETTER CAPITAL BARRED B @@ -967,7 +999,6 @@ A8FC ; Uncommon_Use Obsolete Not_XID # 8.0 DEVANAGARI SIGN SIDD 3021..302D ; Technical # 1.1 [13] HANGZHOU NUMERAL ONE..IDEOGRAPHIC ENTERING TONE MARK 3031..3035 ; Technical # 1.1 [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF 303B..303C ; Technical # 3.2 [2] VERTICAL IDEOGRAPHIC ITERATION MARK..MASU MARK -31F0..31FF ; Technical # 3.2 [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO A78E ; Technical # 6.0 LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A7AF ; Technical # 11.0 LATIN LETTER SMALL CAPITAL Q A7BA..A7BF ; Technical # 12.0 [6] LATIN CAPITAL LETTER GLOTTAL A..LATIN SMALL LETTER GLOTTAL U @@ -977,13 +1008,15 @@ FE20..FE23 ; Technical # 1.1 [4] COMBINING LIGATURE L FE24..FE26 ; Technical # 5.1 [3] COMBINING MACRON LEFT HALF..COMBINING CONJOINING MACRON FE27..FE2D ; Technical # 7.0 [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CONJOINING MACRON BELOW FE73 ; Technical # 3.2 ARABIC TAIL FRAGMENT +1CF00..1CF2D ; Technical # 14.0 [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Technical # 14.0 [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D169 ; Technical # 3.1 [5] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; Technical # 3.1 [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 1D17B..1D182 ; Technical # 3.1 [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Technical # 3.1 [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Technical # 3.1 [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO -# Total code points: 451 +# Total code points: 500 # Identifier_Type: Technical Exclusion @@ -1035,9 +1068,14 @@ A722..A72F ; Technical Obsolete # 5.1 [14] LATIN CAPITAL LETTER 4DC0..4DFF ; Technical Not_XID # 4.0 [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION A708..A716 ; Technical Not_XID # 4.1 [15] MODIFIER LETTER EXTRA-HIGH DOTTED TONE BAR..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR FBB2..FBC1 ; Technical Not_XID # 6.0 [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBC2 ; Technical Not_XID # 14.0 ARABIC SYMBOL WASLA ABOVE FD3E..FD3F ; Technical Not_XID # 1.1 [2] ORNATE LEFT PARENTHESIS..ORNATE RIGHT PARENTHESIS +FD40..FD4F ; Technical Not_XID # 14.0 [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FDCF ; Technical Not_XID # 14.0 ARABIC LIGATURE SALAAMUHU ALAYNAA FDFD ; Technical Not_XID # 4.0 ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFE..FDFF ; Technical Not_XID # 14.0 [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGATURE AZZA WA JALL FE45..FE46 ; Technical Not_XID # 3.2 [2] SESAME DOT..WHITE SESAME DOT +1CF50..1CFC3 ; Technical Not_XID # 14.0 [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Technical Not_XID # 3.1 [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Technical Not_XID # 3.1 [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129 ; Technical Not_XID # 5.1 MUSICAL SYMBOL MULTIPLE MEASURE REST @@ -1047,9 +1085,10 @@ FE45..FE46 ; Technical Not_XID # 3.2 [2] SESAME DOT..WHITE SE 1D18C..1D1A9 ; Technical Not_XID # 3.1 [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH 1D1AE..1D1BA ; Technical Not_XID # 3.1 [13] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL SEMIBREVIS BLACK 1D1C1..1D1DD ; Technical Not_XID # 3.1 [29] MUSICAL SYMBOL LONGA PERFECTA REST..MUSICAL SYMBOL PES SUBPUNCTIS +1D1E9..1D1EA ; Technical Not_XID # 14.0 [2] MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON 1D300..1D356 ; Technical Not_XID # 4.0 [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING -# Total code points: 887 +# Total code points: 1025 # Identifier_Type: Exclusion @@ -1060,7 +1099,10 @@ FE45..FE46 ; Technical Not_XID # 3.2 [2] SESAME DOT..WHITE SE 16EE..16F0 ; Exclusion # 3.0 [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; Exclusion # 7.0 [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC 1700..170C ; Exclusion # 3.2 [13] TAGALOG LETTER A..TAGALOG LETTER YA +170D ; Exclusion # 14.0 TAGALOG LETTER RA 170E..1714 ; Exclusion # 3.2 [7] TAGALOG LETTER LA..TAGALOG SIGN VIRAMA +1715 ; Exclusion # 14.0 TAGALOG SIGN PAMUDPOD +171F ; Exclusion # 14.0 TAGALOG LETTER ARCHAIC RA 1720..1734 ; Exclusion # 3.2 [21] HANUNOO LETTER A..HANUNOO SIGN PAMUDPOD 1740..1753 ; Exclusion # 3.2 [20] BUHID LETTER A..BUHID VOWEL SIGN U 1760..176C ; Exclusion # 3.2 [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -1074,7 +1116,9 @@ FE45..FE46 ; Technical Not_XID # 3.2 [2] SESAME DOT..WHITE SE 1A00..1A1B ; Exclusion # 4.1 [28] BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE 1CFA ; Exclusion # 12.0 VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA 2C00..2C2E ; Exclusion # 4.1 [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F ; Exclusion # 14.0 GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C30..2C5E ; Exclusion # 4.1 [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C5F ; Exclusion # 14.0 GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C80..2CE4 ; Exclusion # 4.1 [101] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL KAI 2CEB..2CEF ; Exclusion # 5.2 [5] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC COMBINING NI ABOVE 2CF2..2CF3 ; Exclusion # 6.1 [2] COPTIC CAPITAL LETTER BOHAIRIC KHEI..COPTIC SMALL LETTER BOHAIRIC KHEI @@ -1105,6 +1149,14 @@ A930..A953 ; Exclusion # 5.1 [36] REJANG LETTER KA..RE 104A0..104A9 ; Exclusion # 4.0 [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10500..10527 ; Exclusion # 7.0 [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Exclusion # 7.0 [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; Exclusion # 14.0 [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Exclusion # 14.0 [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Exclusion # 14.0 [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Exclusion # 14.0 [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Exclusion # 14.0 [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Exclusion # 14.0 [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Exclusion # 14.0 [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Exclusion # 14.0 [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; Exclusion # 7.0 [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Exclusion # 7.0 [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Exclusion # 7.0 [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -1148,12 +1200,15 @@ A930..A953 ; Exclusion # 5.1 [36] REJANG LETTER KA..RE 10F00..10F1C ; Exclusion # 11.0 [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Exclusion # 11.0 OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F50 ; Exclusion # 11.0 [33] SOGDIAN LETTER ALEPH..SOGDIAN COMBINING STROKE BELOW +10F70..10F85 ; Exclusion # 14.0 [22] OLD UYGHUR LETTER ALEPH..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; Exclusion # 13.0 [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; Exclusion # 12.0 [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000..11046 ; Exclusion # 6.0 [71] BRAHMI SIGN CANDRABINDU..BRAHMI VIRAMA 11066..1106F ; Exclusion # 6.0 [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070..11075 ; Exclusion # 14.0 [6] BRAHMI SIGN OLD TAMIL VIRAMA..BRAHMI LETTER OLD TAMIL LLA 1107F ; Exclusion # 7.0 BRAHMI NUMBER JOINER 11080..110BA ; Exclusion # 5.2 [59] KAITHI SIGN CANDRABINDU..KAITHI SIGN NUKTA +110C2 ; Exclusion # 14.0 KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; Exclusion # 6.1 [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; Exclusion # 6.1 [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11150..11173 ; Exclusion # 7.0 [36] MAHAJANI LETTER A..MAHAJANI SIGN NUKTA @@ -1206,6 +1261,7 @@ A930..A953 ; Exclusion # 5.1 [36] REJANG LETTER KA..RE 1171A ; Exclusion # 11.0 AHOM LETTER ALTERNATE BA 1171D..1172B ; Exclusion # 8.0 [15] AHOM CONSONANT SIGN MEDIAL LA..AHOM SIGN KILLER 11730..11739 ; Exclusion # 8.0 [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; Exclusion # 14.0 [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1183A ; Exclusion # 11.0 [59] DOGRA LETTER A..DOGRA SIGN NUKTA 118A0..118E9 ; Exclusion # 7.0 [74] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI DIGIT NINE 118FF ; Exclusion # 7.0 WARANG CITI OM @@ -1249,8 +1305,11 @@ A930..A953 ; Exclusion # 5.1 [36] REJANG LETTER KA..RE 12400..12462 ; Exclusion # 5.0 [99] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN OLD ASSYRIAN ONE QUARTER 12463..1246E ; Exclusion # 7.0 [12] CUNEIFORM NUMERIC SIGN ONE QUARTER GUR..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; Exclusion # 8.0 [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; Exclusion # 14.0 [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; Exclusion # 5.2 [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; Exclusion # 8.0 [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 +16A70..16ABE ; Exclusion # 14.0 [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; Exclusion # 14.0 [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; Exclusion # 7.0 [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; Exclusion # 7.0 [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B36 ; Exclusion # 7.0 [55] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG MARK CIM TAUM @@ -1285,10 +1344,11 @@ A930..A953 ; Exclusion # 5.1 [36] REJANG LETTER KA..RE 1E01B..1E021 ; Exclusion # 9.0 [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Exclusion # 9.0 [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Exclusion # 9.0 [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E290..1E2AE ; Exclusion # 14.0 [31] TOTO LETTER PA..TOTO SIGN RISING TONE 1E800..1E8C4 ; Exclusion # 7.0 [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; Exclusion # 7.0 [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 15602 +# Total code points: 15930 # Identifier_Type: Exclusion Not_XID @@ -1336,6 +1396,7 @@ A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 10EAD ; Exclusion Not_XID # 13.0 YEZIDI HYPHENATION MARK 10F1D..10F26 ; Exclusion Not_XID # 11.0 [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F51..10F59 ; Exclusion Not_XID # 11.0 [9] SOGDIAN NUMBER ONE..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; Exclusion Not_XID # 14.0 [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FC5..10FCB ; Exclusion Not_XID # 13.0 [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 11047..1104D ; Exclusion Not_XID # 6.0 [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; Exclusion Not_XID # 6.0 [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND @@ -1355,6 +1416,7 @@ A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 115CA..115D7 ; Exclusion Not_XID # 8.0 [14] SIDDHAM SECTION MARK WITH TRIDENT AND U-SHAPED ORNAMENTS..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11643 ; Exclusion Not_XID # 7.0 [3] MODI DANDA..MODI ABBREVIATION SIGN 11660..1166C ; Exclusion Not_XID # 9.0 [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +116B9 ; Exclusion Not_XID # 14.0 TAKRI ABBREVIATION SIGN 1173A..1173F ; Exclusion Not_XID # 8.0 [6] AHOM NUMBER TEN..AHOM SYMBOL VI 1183B ; Exclusion Not_XID # 11.0 DOGRA ABBREVIATION SIGN 118EA..118F2 ; Exclusion Not_XID # 7.0 [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY @@ -1369,6 +1431,7 @@ A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 11EF7..11EF8 ; Exclusion Not_XID # 11.0 [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION 12470..12473 ; Exclusion Not_XID # 5.0 [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON 12474 ; Exclusion Not_XID # 7.0 CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON +12FF1..12FF2 ; Exclusion Not_XID # 14.0 [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13430..13438 ; Exclusion Not_XID # 12.0 [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT 16A6E..16A6F ; Exclusion Not_XID # 7.0 [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; Exclusion Not_XID # 7.0 BASSA VAH FULL STOP @@ -1385,7 +1448,7 @@ A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 1DA85..1DA8B ; Exclusion Not_XID # 8.0 [7] SIGNWRITING LOCATION TORSO..SIGNWRITING PARENTHESIS 1E8C7..1E8CF ; Exclusion Not_XID # 7.0 [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE -# Total code points: 1098 +# Total code points: 1105 # Identifier_Type: Obsolete @@ -1461,6 +1524,7 @@ A95F ; Exclusion Not_XID # 5.1 REJANG SECTION MARK 2D00..2D25 ; Obsolete # 4.1 [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE 2DE0..2DFF ; Obsolete # 5.1 [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS 312E ; Obsolete # 10.0 BOPOMOFO LETTER O WITH DOT ABOVE +31F0..31FF ; Obsolete # 3.2 [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO A640..A65F ; Obsolete # 5.1 [32] CYRILLIC CAPITAL LETTER ZEMLYA..CYRILLIC SMALL LETTER YN A660..A661 ; Obsolete # 6.0 [2] CYRILLIC CAPITAL LETTER REVERSED TSE..CYRILLIC SMALL LETTER REVERSED TSE A662..A66E ; Obsolete # 5.1 [13] CYRILLIC CAPITAL LETTER SOFT DE..CYRILLIC LETTER MULTIOCULAR O @@ -1494,7 +1558,7 @@ D7CB..D7FB ; Obsolete # 5.2 [49] HANGUL JONGSEONG NIE 1B000..1B001 ; Obsolete # 6.0 [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE 1B002..1B11E ; Obsolete # 10.0 [285] HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2 -# Total code points: 1325 +# Total code points: 1341 # Identifier_Type: Obsolete Not_XID @@ -1569,6 +1633,7 @@ A8F8..A8FA ; Obsolete Not_XID # 5.2 [3] DEVANAGARI SIGN PUSH 060C ; Not_XID # 1.1 ARABIC COMMA 060D..060F ; Not_XID # 4.0 [3] ARABIC DATE SEPARATOR..ARABIC SIGN MISRA 061B ; Not_XID # 1.1 ARABIC SEMICOLON +061D ; Not_XID # 14.0 ARABIC END OF TEXT MARK 061E ; Not_XID # 4.1 ARABIC TRIPLE DOT PUNCTUATION MARK 061F ; Not_XID # 1.1 ARABIC QUESTION MARK 066A..066D ; Not_XID # 1.1 [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR @@ -1576,6 +1641,8 @@ A8F8..A8FA ; Obsolete Not_XID # 5.2 [3] DEVANAGARI SIGN PUSH 06DD ; Not_XID # 1.1 ARABIC END OF AYAH 06DE ; Not_XID # 1.1 ARABIC START OF RUB EL HIZB 06E9 ; Not_XID # 1.1 ARABIC PLACE OF SAJDAH +0888 ; Not_XID # 14.0 ARABIC RAISED ROUND DOT +0890..0891 ; Not_XID # 14.0 [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Not_XID # 9.0 ARABIC DISPUTED END OF AYAH 0964..0965 ; Not_XID # 1.1 [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA 0970 ; Not_XID # 1.1 DEVANAGARI ABBREVIATION SIGN @@ -1656,6 +1723,7 @@ A8F8..A8FA ; Obsolete Not_XID # 5.2 [3] DEVANAGARI SIGN PUSH 20BB..20BD ; Not_XID # 7.0 [3] NORDIC MARK SIGN..RUBLE SIGN 20BE ; Not_XID # 8.0 LARI SIGN 20BF ; Not_XID # 10.0 BITCOIN SIGN +20C0 ; Not_XID # 14.0 SOM SIGN 2104 ; Not_XID # 1.1 CENTRE LINE SYMBOL 2108 ; Not_XID # 1.1 SCRUPLE 2114 ; Not_XID # 1.1 L B BAR SYMBOL @@ -1799,6 +1867,7 @@ A8F8..A8FA ; Obsolete Not_XID # 5.2 [3] DEVANAGARI SIGN PUSH 2E4A..2E4E ; Not_XID # 11.0 [5] DOTTED SOLIDUS..PUNCTUS ELEVATUS MARK 2E4F ; Not_XID # 12.0 CORNISH VERSE DIVIDER 2E50..2E52 ; Not_XID # 13.0 [3] CROSS PATTY WITH RIGHT CROSSBAR..TIRONIAN SIGN CAPITAL ET +2E53..2E5D ; Not_XID # 14.0 [11] MEDIEVAL EXCLAMATION MARK..OBLIQUE HYPHEN 2E80..2E99 ; Not_XID # 3.0 [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2E9E ; Not_XID # 3.0 [4] CJK RADICAL CHOKE..CJK RADICAL DEATH 2EA0..2EF2 ; Not_XID # 3.0 [83] CJK RADICAL CIVILIAN..CJK RADICAL J-SIMPLIFIED TURTLE @@ -1947,6 +2016,7 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 1F6D3..1F6D4 ; Not_XID # 10.0 [2] STUPA..PAGODA 1F6D5 ; Not_XID # 12.0 HINDU TEMPLE 1F6D6..1F6D7 ; Not_XID # 13.0 [2] HUT..ELEVATOR +1F6DD..1F6DF ; Not_XID # 14.0 [3] PLAYGROUND SLIDE..RING BUOY 1F6E0..1F6EC ; Not_XID # 7.0 [13] HAMMER AND WRENCH..AIRPLANE ARRIVING 1F6F0..1F6F3 ; Not_XID # 7.0 [4] SATELLITE..PASSENGER SHIP 1F6F4..1F6F6 ; Not_XID # 9.0 [3] SCOOTER..CANOE @@ -1958,6 +2028,7 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 1F780..1F7D4 ; Not_XID # 7.0 [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F7D5..1F7D8 ; Not_XID # 11.0 [4] CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; Not_XID # 12.0 [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; Not_XID # 14.0 HEAVY EQUALS SIGN 1F800..1F80B ; Not_XID # 7.0 [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; Not_XID # 7.0 [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; Not_XID # 7.0 [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW @@ -1986,6 +2057,7 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 1F972 ; Not_XID # 13.0 SMILING FACE WITH TEAR 1F973..1F976 ; Not_XID # 11.0 [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE 1F977..1F978 ; Not_XID # 13.0 [2] NINJA..DISGUISED FACE +1F979 ; Not_XID # 14.0 FACE HOLDING BACK TEARS 1F97A ; Not_XID # 11.0 FACE WITH PLEADING EYES 1F97B ; Not_XID # 12.0 SARI 1F97C..1F97F ; Not_XID # 11.0 [4] LAB COAT..FLAT SHOE @@ -2003,6 +2075,7 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 1F9C1..1F9C2 ; Not_XID # 11.0 [2] CUPCAKE..SALT SHAKER 1F9C3..1F9CA ; Not_XID # 12.0 [8] BEVERAGE BOX..ICE CUBE 1F9CB ; Not_XID # 13.0 BUBBLE TEA +1F9CC ; Not_XID # 14.0 TROLL 1F9CD..1F9CF ; Not_XID # 12.0 [3] STANDING PERSON..DEAF PERSON 1F9D0..1F9E6 ; Not_XID # 10.0 [23] FACE WITH MONOCLE..SOCKS 1F9E7..1F9FF ; Not_XID # 11.0 [25] RED GIFT ENVELOPE..NAZAR AMULET @@ -2011,17 +2084,24 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 1FA70..1FA73 ; Not_XID # 12.0 [4] BALLET SHOES..SHORTS 1FA74 ; Not_XID # 13.0 THONG SANDAL 1FA78..1FA7A ; Not_XID # 12.0 [3] DROP OF BLOOD..STETHOSCOPE +1FA7B..1FA7C ; Not_XID # 14.0 [2] X-RAY..CRUTCH 1FA80..1FA82 ; Not_XID # 12.0 [3] YO-YO..PARACHUTE 1FA83..1FA86 ; Not_XID # 13.0 [4] BOOMERANG..NESTING DOLLS 1FA90..1FA95 ; Not_XID # 12.0 [6] RINGED PLANET..BANJO 1FA96..1FAA8 ; Not_XID # 13.0 [19] MILITARY HELMET..ROCK +1FAA9..1FAAC ; Not_XID # 14.0 [4] MIRROR BALL..HAMSA 1FAB0..1FAB6 ; Not_XID # 13.0 [7] FLY..FEATHER +1FAB7..1FABA ; Not_XID # 14.0 [4] LOTUS..NEST WITH EGGS 1FAC0..1FAC2 ; Not_XID # 13.0 [3] ANATOMICAL HEART..PEOPLE HUGGING +1FAC3..1FAC5 ; Not_XID # 14.0 [3] PREGNANT MAN..PERSON WITH CROWN 1FAD0..1FAD6 ; Not_XID # 13.0 [7] BLUEBERRIES..TEAPOT +1FAD7..1FAD9 ; Not_XID # 14.0 [3] POURING LIQUID..JAR +1FAE0..1FAE7 ; Not_XID # 14.0 [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; Not_XID # 14.0 [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; Not_XID # 13.0 [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; Not_XID # 13.0 [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 5587 +# Total code points: 5640 # Identifier_Type: Not_NFKC @@ -2193,6 +2273,7 @@ FFFD ; Not_XID # 1.1 REPLACEMENT CHARACTE 33FF ; Not_NFKC # 4.0 SQUARE GAL A69C..A69D ; Not_NFKC # 7.0 [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; Not_NFKC # 5.1 MODIFIER LETTER US +A7F2..A7F4 ; Not_NFKC # 14.0 [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Not_NFKC # 6.1 [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Not_NFKC # 7.0 [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; Not_NFKC # 13.0 MODIFIER LETTER SMALL TURNED W @@ -2241,6 +2322,9 @@ FFD2..FFD7 ; Not_NFKC # 1.1 [6] HALFWIDTH HANGUL LET FFDA..FFDC ; Not_NFKC # 1.1 [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I FFE0..FFE6 ; Not_NFKC # 1.1 [7] FULLWIDTH CENT SIGN..FULLWIDTH WON SIGN FFE8..FFEE ; Not_NFKC # 1.1 [7] HALFWIDTH FORMS LIGHT VERTICAL..HALFWIDTH WHITE CIRCLE +10781..10785 ; Not_NFKC # 14.0 [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Not_NFKC # 14.0 [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Not_NFKC # 14.0 [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1D15E..1D164 ; Not_NFKC # 3.1 [7] MUSICAL SYMBOL HALF NOTE..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D1BB..1D1C0 ; Not_NFKC # 3.1 [6] MUSICAL SYMBOL MINIMA..MUSICAL SYMBOL FUSA BLACK 1D400..1D454 ; Not_NFKC # 3.1 [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G @@ -2329,7 +2413,7 @@ FFE8..FFEE ; Not_NFKC # 1.1 [7] HALFWIDTH FORMS LIGH 1FBF0..1FBF9 ; Not_NFKC # 13.0 [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; Not_NFKC # 3.1 [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4800 +# Total code points: 4859 # Identifier_Type: Default_Ignorable @@ -2340,6 +2424,7 @@ FFE8..FFEE ; Not_NFKC # 1.1 [7] HALFWIDTH FORMS LIGH 17B4..17B5 ; Default_Ignorable # 3.0 [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Default_Ignorable # 3.0 [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Default_Ignorable # 3.0 MONGOLIAN VOWEL SEPARATOR +180F ; Default_Ignorable # 14.0 MONGOLIAN FREE VARIATION SELECTOR FOUR 200B ; Default_Ignorable # 1.1 ZERO WIDTH SPACE 200E..200F ; Default_Ignorable # 1.1 [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; Default_Ignorable # 1.1 [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE @@ -2355,7 +2440,7 @@ FFA0 ; Default_Ignorable # 1.1 HALFWIDTH HANGUL FIL E0020..E007F ; Default_Ignorable # 3.1 [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Default_Ignorable # 4.0 [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 395 +# Total code points: 396 # Identifier_Type: Deprecated diff --git a/lib/unicore/Index.txt b/lib/unicore/Index.txt index 498519f58b..451255cd83 100644 --- a/lib/unicore/Index.txt +++ b/lib/unicore/Index.txt @@ -1036,6 +1036,7 @@ combining counterclockwise ring overlay 20DA Combining Diacritical Marks 0300 Combining Diacritical Marks Extended 1AB0 Combining Diacritical Marks for Symbols 20D0 +Combining Diacritical Marks Supplement 1DC0 COMBINING DIAERESIS 0308 COMBINING DIAERESIS BELOW 0324 COMBINING DOT ABOVE 0307 @@ -1937,6 +1938,7 @@ Equality and Inequality Signs 22D5 EQUALS COLON 2255 EQUALS SIGN 003D EQUALS SIGN BELOW, COMBINING 0347 +EQUALS SIGN, HEAVY 1F7F0 EQUALS, CIRCLED 229C EQUALS, COLON 2254 equals, nearly 2252 @@ -2032,6 +2034,7 @@ FACE, WHITE FROWNING 2639 FACE, WHITE SMILING 263A Faces 1F600 Faces 1F920 +Faces 1FAE0 Facial Parts Symbols 1F440 FACSIMILE SIGN 213B factorial 0021 @@ -2429,6 +2432,7 @@ han-daku-on, japanese 309C Hand Symbols 1F446 Hand Symbols 1F58E Hand Symbols 1F918 +Hand Symbols 1FAF0 Hand Symbols, Pointing 261A Hand, Index Finger Pointing 1F446 HAND, RAISED 270B @@ -2478,6 +2482,7 @@ HEADPHONE 1F3A7 HEADSTONE GRAVEYARD SYMBOL 26FC HEART BULLET, REVERSED ROTATED FLORAL 2619 Heart Dingbats 2763 +HEART HANDS 1FAF6 Heart Ornaments 2763 Heart Symbols 1F493 HEART, BLACK 1F5A4 @@ -2567,6 +2572,7 @@ HYPHEN, DOUBLE 2E40 HYPHEN, KATAKANA-HIRAGANA DOUBLE 30A0 HYPHEN, MONGOLIAN TODO SOFT 1806 HYPHEN, NON-BREAKING 2011 +HYPHEN, OBLIQUE 2E5D hyphen, papyrological 035C HYPHEN, SOFT 00AD HYPHEN-MINUS 002D diff --git a/lib/unicore/IndicPositionalCategory.txt b/lib/unicore/IndicPositionalCategory.txt index ee74dbe0fa..69109ac51f 100644 --- a/lib/unicore/IndicPositionalCategory.txt +++ b/lib/unicore/IndicPositionalCategory.txt @@ -1,6 +1,6 @@ -# IndicPositionalCategory-13.0.0.txt -# Date: 2019-07-23, 00:01:00 GMT [KW, RP] -# © 2019 Unicode®, Inc. +# IndicPositionalCategory-14.0.0.txt +# Date: 2021-05-22, 01:01:00 GMT [KW, RP] +# © 2021 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 # @@ -25,8 +25,8 @@ # # In addition to combining marks associated with Indic scripts, the # Indic_Positional_Category has non-trivial values for special signs -# associated with Indic_Syllabic_Category=Consonant_Prefixed or -# Indic_Syllabic_Category=Consonant_Preceding_Repha. Those signs +# associated with Indic_Syllabic_Category=Consonant_Prefixed +# or Indic_Syllabic_Category=Consonant_Preceding_Repha. Those signs # have General_Category=Lo, rather than being combining marks. # They occur in initial position in syllabic structure. However, when # rendered, they appear as marks positioned with respect to another @@ -184,6 +184,8 @@ 1087..108C ; Right # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3 108F ; Right # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5 109A..109C ; Right # Mc [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A +1715 ; Right # Mc TAGALOG SIGN PAMUDPOD +1734 ; Right # Mc HANUNOO SIGN PAMUDPOD 17B6 ; Right # Mc KHMER VOWEL SIGN AA 17C7..17C8 ; Right # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU 1923..1924 ; Right # Mc [2] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AI @@ -512,6 +514,8 @@ ABE5 ; Top # Mn MEETEI MAYEK VOWEL SIGN ANAP 11001 ; Top # Mn BRAHMI SIGN ANUSVARA 11038..1103B ; Top # Mn [4] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN II 11042..11046 ; Top # Mn [5] BRAHMI VOWEL SIGN E..BRAHMI VIRAMA +11070 ; Top # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Top # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 11080..11081 ; Top # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 110B5..110B6 ; Top # Mn [2] KAITHI VOWEL SIGN E..KAITHI VOWEL SIGN AI 11100..11102 ; Top # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -602,6 +606,7 @@ ABE5 ; Top # Mn MEETEI MAYEK VOWEL SIGN ANAP 0B41..0B44 ; Bottom # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Bottom # Mn ORIYA SIGN VIRAMA 0B62..0B63 ; Bottom # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0C3C ; Bottom # Mn TELUGU SIGN NUKTA 0C56 ; Bottom # Mn TELUGU AI LENGTH MARK 0C62..0C63 ; Bottom # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0CBC ; Bottom # Mn KANNADA SIGN NUKTA @@ -630,7 +635,7 @@ ABE5 ; Top # Mn MEETEI MAYEK VOWEL SIGN ANAP 1082 ; Bottom # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA 108D ; Bottom # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE 1713..1714 ; Bottom # Mn [2] TAGALOG VOWEL SIGN U..TAGALOG SIGN VIRAMA -1733..1734 ; Bottom # Mn [2] HANUNOO VOWEL SIGN U..HANUNOO SIGN PAMUDPOD +1733 ; Bottom # Mn HANUNOO VOWEL SIGN U 1753 ; Bottom # Mn BUHID VOWEL SIGN U 1773 ; Bottom # Mn TAGBANWA VOWEL SIGN U 17BB..17BD ; Bottom # Mn [3] KHMER VOWEL SIGN U..KHMER VOWEL SIGN UA @@ -675,6 +680,7 @@ ABED ; Bottom # Mn MEETEI MAYEK APUN IYEK 1103C..11041 ; Bottom # Mn [6] BRAHMI VOWEL SIGN U..BRAHMI VOWEL SIGN VOCALIC LL 110B3..110B4 ; Bottom # Mn [2] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN UU 110B9..110BA ; Bottom # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Bottom # Mn KAITHI VOWEL SIGN VOCALIC R 1112A..1112B ; Bottom # Mn [2] CHAKMA VOWEL SIGN U..CHAKMA VOWEL SIGN UU 11131..11132 ; Bottom # Mn [2] CHAKMA O MARK..CHAKMA AU MARK 11173 ; Bottom # Mn MAHAJANI SIGN NUKTA diff --git a/lib/unicore/IndicSyllabicCategory.txt b/lib/unicore/IndicSyllabicCategory.txt index 8297578d18..23b86372ae 100644 --- a/lib/unicore/IndicSyllabicCategory.txt +++ b/lib/unicore/IndicSyllabicCategory.txt @@ -1,6 +1,6 @@ -# IndicSyllabicCategory-13.0.0.txt -# Date: 2019-07-22, 19:55:00 GMT [KW, RP] -# © 2019 Unicode®, Inc. +# IndicSyllabicCategory-14.0.0.txt +# Date: 2021-05-22, 01:01:00 GMT [KW, RP] +# © 2021 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 # @@ -225,6 +225,7 @@ AAF5 ; Visarga # Mc MEETEI MAYEK VOWEL SIGN VISARGA 0ABC ; Nukta # Mn GUJARATI SIGN NUKTA 0AFD..0AFF ; Nukta # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Nukta # Mn ORIYA SIGN NUKTA +0C3C ; Nukta # Mn TELUGU SIGN NUKTA 0CBC ; Nukta # Mn KANNADA SIGN NUKTA 0F39 ; Nukta # Mn TIBETAN MARK TSA -PHRU 1B34 ; Nukta # Mn BALINESE SIGN REREKAN @@ -303,7 +304,8 @@ A9C0 ; Virama # Mc JAVANESE PANGKON 0F84 ; Pure_Killer # Mn TIBETAN MARK HALANTA 103A ; Pure_Killer # Mn MYANMAR SIGN ASAT 1714 ; Pure_Killer # Mn TAGALOG SIGN VIRAMA -1734 ; Pure_Killer # Mn HANUNOO SIGN PAMUDPOD +1715 ; Pure_Killer # Mc TAGALOG SIGN PAMUDPOD +1734 ; Pure_Killer # Mc HANUNOO SIGN PAMUDPOD 17D1 ; Pure_Killer # Mn KHMER SIGN VIRIAM 1A7A ; Pure_Killer # Mn TAI THAM SIGN RA HAAM 1BAA ; Pure_Killer # Mc SUNDANESE SIGN PAMAAEH @@ -311,6 +313,7 @@ A9C0 ; Virama # Mc JAVANESE PANGKON A82C ; Pure_Killer # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA A953 ; Pure_Killer # Mc REJANG VIRAMA ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK +11070 ; Pure_Killer # Mn BRAHMI SIGN OLD TAMIL VIRAMA 11134 ; Pure_Killer # Mn CHAKMA MAAYYAA 112EA ; Pure_Killer # Mn KHUDAWADI SIGN VIRAMA 1172B ; Pure_Killer # Mn AHOM SIGN KILLER @@ -408,6 +411,7 @@ AAE0..AAE1 ; Vowel_Independent # Lo [2] MEETEI MAYEK LETTER E..MEETEI MAYEK ABCE..ABCF ; Vowel_Independent # Lo [2] MEETEI MAYEK LETTER UN..MEETEI MAYEK LETTER I ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA 11005..11012 ; Vowel_Independent # Lo [14] BRAHMI LETTER A..BRAHMI LETTER AU +11071..11072 ; Vowel_Independent # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O 11083..1108C ; Vowel_Independent # Lo [10] KAITHI LETTER A..KAITHI LETTER AU 11103..11106 ; Vowel_Independent # Lo [4] CHAKMA LETTER AA..CHAKMA LETTER E 11183..11190 ; Vowel_Independent # Lo [14] SHARADA LETTER A..SHARADA LETTER AU @@ -617,9 +621,11 @@ ABE9..ABEA ; Vowel_Dependent # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET 10A05..10A06 ; Vowel_Dependent # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0D ; Vowel_Dependent # Mn [2] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN DOUBLE RING BELOW 11038..11045 ; Vowel_Dependent # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU +11073..11074 ; Vowel_Dependent # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 110B0..110B2 ; Vowel_Dependent # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Vowel_Dependent # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Vowel_Dependent # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110C2 ; Vowel_Dependent # Mn KAITHI VOWEL SIGN VOCALIC R 11127..1112B ; Vowel_Dependent # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Vowel_Dependent # Mc CHAKMA VOWEL SIGN E 1112D..11132 ; Vowel_Dependent # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK @@ -813,8 +819,8 @@ AA74..AA76 ; Consonant_Placeholder # Lo [3] MYANMAR LOGOGRAM KHAMTI OAY..MY 106E..1070 ; Consonant # Lo [3] MYANMAR LETTER EASTERN PWO KAREN NNA..MYANMAR LETTER EASTERN PWO KAREN GHWA 1075..1081 ; Consonant # Lo [13] MYANMAR LETTER SHAN KA..MYANMAR LETTER SHAN HA 108E ; Consonant # Lo MYANMAR LETTER RUMAI PALAUNG FA -1703..170C ; Consonant # Lo [10] TAGALOG LETTER KA..TAGALOG LETTER YA -170E..1711 ; Consonant # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1703..1711 ; Consonant # Lo [15] TAGALOG LETTER KA..TAGALOG LETTER HA +171F ; Consonant # Lo TAGALOG LETTER ARCHAIC RA 1723..1731 ; Consonant # Lo [15] HANUNOO LETTER KA..HANUNOO LETTER HA 1743..1751 ; Consonant # Lo [15] BUHID LETTER KA..BUHID LETTER HA 1763..176C ; Consonant # Lo [10] TAGBANWA LETTER KA..TAGBANWA LETTER YA @@ -827,7 +833,7 @@ AA74..AA76 ; Consonant_Placeholder # Lo [3] MYANMAR LOGOGRAM KHAMTI OAY..MY 1A20..1A4C ; Consonant # Lo [45] TAI THAM LETTER HIGH KA..TAI THAM LETTER LOW HA 1A53..1A54 ; Consonant # Lo [2] TAI THAM LETTER LAE..TAI THAM LETTER GREAT SA 1B13..1B33 ; Consonant # Lo [33] BALINESE LETTER KA..BALINESE LETTER HA -1B45..1B4B ; Consonant # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Consonant # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B8A..1BA0 ; Consonant # Lo [23] SUNDANESE LETTER KA..SUNDANESE LETTER HA 1BAE..1BAF ; Consonant # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBB..1BBD ; Consonant # Lo [3] SUNDANESE LETTER REU..SUNDANESE LETTER BHA @@ -863,6 +869,7 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 10A15..10A17 ; Consonant # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA 10A19..10A35 ; Consonant # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 11013..11037 ; Consonant # Lo [37] BRAHMI LETTER KA..BRAHMI LETTER OLD TAMIL NNNA +11075 ; Consonant # Lo BRAHMI LETTER OLD TAMIL LLA 1108D..110AF ; Consonant # Lo [35] KAITHI LETTER KA..KAITHI LETTER HA 11107..11126 ; Consonant # Lo [32] CHAKMA LETTER KAA..CHAKMA LETTER HAA 11144 ; Consonant # Lo CHAKMA LETTER LHAA @@ -888,6 +895,7 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 1168A..116AA ; Consonant # Lo [33] TAKRI LETTER KA..TAKRI LETTER RRA 116B8 ; Consonant # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; Consonant # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; Consonant # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 1180A..1182B ; Consonant # Lo [34] DOGRA LETTER KA..DOGRA LETTER RRA 1190C..11913 ; Consonant # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA 11915..11916 ; Consonant # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA @@ -910,6 +918,8 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # [Not derivable] 09CE ; Consonant_Dead # Lo BENGALI LETTER KHANDA TA +0C5D ; Consonant_Dead # Lo TELUGU LETTER NAKAARA POLLU +0CDD ; Consonant_Dead # Lo KANNADA LETTER NAKAARA POLLU 0D54..0D56 ; Consonant_Dead # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D7A..0D7F ; Consonant_Dead # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 1CF2..1CF3 ; Consonant_Dead # Lo [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA @@ -975,9 +985,6 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # [Not derivable] 17CC ; Consonant_Succeeding_Repha # Mn KHMER SIGN ROBAT -1B03 ; Consonant_Succeeding_Repha # Mn BALINESE SIGN SURANG -1B81 ; Consonant_Succeeding_Repha # Mn SUNDANESE SIGN PANGLAYAR -A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR # ================================================ @@ -1043,11 +1050,14 @@ AA35..AA36 ; Consonant_Medial # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONA 1939 ; Consonant_Final # Mn LIMBU SIGN MUKPHRENG 19C1..19C7 ; Consonant_Final # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B 1A58..1A59 ; Consonant_Final # Mn [2] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN FINAL NGA +1B03 ; Consonant_Final # Mn BALINESE SIGN SURANG +1B81 ; Consonant_Final # Mn SUNDANESE SIGN PANGLAYAR 1BBE..1BBF ; Consonant_Final # Lo [2] SUNDANESE LETTER FINAL K..SUNDANESE LETTER FINAL M 1BF0..1BF1 ; Consonant_Final # Mn [2] BATAK CONSONANT SIGN NG..BATAK CONSONANT SIGN H 1C2D..1C33 ; Consonant_Final # Mn [7] LEPCHA CONSONANT SIGN K..LEPCHA CONSONANT SIGN T A94F..A951 ; Consonant_Final # Mn [3] REJANG CONSONANT SIGN NG..REJANG CONSONANT SIGN R A952 ; Consonant_Final # Mc REJANG CONSONANT SIGN H +A982 ; Consonant_Final # Mn JAVANESE SIGN LAYAR AA40..AA42 ; Consonant_Final # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG AA43 ; Consonant_Final # Mn CHAM CONSONANT SIGN FINAL NG AA44..AA4B ; Consonant_Final # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS diff --git a/lib/unicore/Jamo.txt b/lib/unicore/Jamo.txt index 7e171e1cda..298d9df988 100644 --- a/lib/unicore/Jamo.txt +++ b/lib/unicore/Jamo.txt @@ -1,6 +1,6 @@ -# Jamo-13.0.0.txt -# Date: 2019-09-09, 19:46:00 GMT [KW, LI] -# © 2019 Unicode®, Inc. +# Jamo-14.0.0.txt +# Date: 2021-03-16, 21:43:00 GMT [KW, LI] +# © 2021 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -8,7 +8,7 @@ # # This file defines the Jamo_Short_Name property. # -# See Section 3.12 of The Unicode Standard, Version 13.0 +# See Section 3.12 of The Unicode Standard, Version 14.0 # for more information. # # Each line contains two fields, separated by a semicolon. diff --git a/lib/unicore/LineBreak.txt b/lib/unicore/LineBreak.txt index 22abddcd90..aa5985b8f0 100644 --- a/lib/unicore/LineBreak.txt +++ b/lib/unicore/LineBreak.txt @@ -1,11 +1,11 @@ -# LineBreak-13.0.0.txt -# Date: 2020-02-17, 07:43:02 GMT [KW, LI] -# © 2020 Unicode®, Inc. +# LineBreak-14.0.0.txt +# Date: 2021-07-06, 09:58:55 GMT [KW, LI] +# © 2021 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 +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Line_Break Property # @@ -49,7 +49,7 @@ # with ranges of code points, the code point count in square brackets. # # For more information, see UAX #14: Unicode Line Breaking Algorithm, -# at http://www.unicode.org/reports/tr14/ +# at https://www.unicode.org/reports/tr14/ # # @missing: 0000..10FFFF; XX 0000..0008;CM # Cc [9] <control-0000>..<control-0008> @@ -215,7 +215,7 @@ 0610..061A;CM # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061B;EX # Po ARABIC SEMICOLON 061C;CM # Cf ARABIC LETTER MARK -061E..061F;EX # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F;EX # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F;AL # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640;AL # Lm ARABIC TATWEEL 0641..064A;AL # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -277,9 +277,14 @@ 0859..085B;CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E;AL # Po MANDAIC PUNCTUATION 0860..086A;AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4;AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7;AL # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1;CM # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887;AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888;AL # Sk ARABIC RAISED ROUND DOT +0889..088E;AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891;AL # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F;CM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8;AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9;AL # Lm ARABIC SMALL FARSI YEH +08CA..08E1;CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2;AL # Cf ARABIC DISPUTED END OF AYAH 08E3..08FF;CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA 0900..0902;CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA @@ -437,6 +442,7 @@ 0C0E..0C10;AL # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28;AL # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39;AL # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C;CM # Mn TELUGU SIGN NUKTA 0C3D;AL # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40;CM # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44;CM # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -444,6 +450,7 @@ 0C4A..0C4D;CM # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56;CM # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A;AL # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D;AL # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61;AL # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63;CM # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F;NU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -469,7 +476,7 @@ 0CCA..0CCB;CM # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD;CM # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6;CM # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE;AL # Lo KANNADA LETTER FA +0CDD..0CDE;AL # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1;AL # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3;CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF;NU # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -672,11 +679,13 @@ 16EB..16ED;BA # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0;AL # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8;AL # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C;AL # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711;AL # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711;AL # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714;CM # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1715;CM # Mc TAGALOG SIGN PAMUDPOD +171F;AL # Lo TAGALOG LETTER ARCHAIC RA 1720..1731;AL # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734;CM # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733;CM # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734;CM # Mc HANUNOO SIGN PAMUDPOD 1735..1736;BA # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751;AL # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753;CM # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -711,6 +720,7 @@ 180A;AL # Po MONGOLIAN NIRUGU 180B..180D;CM # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E;GL # Cf MONGOLIAN VOWEL SEPARATOR +180F;CM # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819;NU # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842;AL # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843;AL # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -766,7 +776,7 @@ 1AA8..1AAD;SA # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD;CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE;CM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0;CM # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE;CM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03;CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04;CM # Mc BALINESE SIGN BISAH 1B05..1B33;AL # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -778,7 +788,7 @@ 1B3D..1B41;CM # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42;CM # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44;CM # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B;AL # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C;AL # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59;NU # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B5B;BA # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5C;AL # Po BALINESE WINDU @@ -786,6 +796,7 @@ 1B61..1B6A;AL # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73;CM # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C;AL # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E;BA # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B80..1B81;CM # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82;CM # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0;AL # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -844,8 +855,7 @@ 1D79..1D7F;AL # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE 1D80..1D9A;AL # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF;AL # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9;CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF;CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF;CM # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1EFF;AL # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP 1F00..1F15;AL # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D;AL # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -953,7 +963,8 @@ 20BC..20BD;PR # Sc [2] MANAT SIGN..RUBLE SIGN 20BE;PO # Sc LARI SIGN 20BF;PR # Sc BITCOIN SIGN -20C0..20CF;PR # Cn [16] <reserved-20C0>..<reserved-20CF> +20C0;PO # Sc SOM SIGN +20C1..20CF;PR # Cn [15] <reserved-20C1>..<reserved-20CF> 20D0..20DC;CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0;CM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1;CM # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1307,8 +1318,7 @@ 2B5A..2B73;AL # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95;AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF;AL # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -2C00..2C2E;AL # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E;AL # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C00..2C5F;AL # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60..2C7B;AL # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D;AL # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2C7F;AL # Lu [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL @@ -1390,6 +1400,16 @@ 2E4E..2E4F;BA # Po [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER 2E50..2E51;AL # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR 2E52;AL # Po TIRONIAN SIGN CAPITAL ET +2E53..2E54;EX # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK +2E55;OP # Ps LEFT SQUARE BRACKET WITH STROKE +2E56;CL # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57;OP # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58;CL # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59;OP # Ps TOP HALF LEFT PARENTHESIS +2E5A;CL # Pe TOP HALF RIGHT PARENTHESIS +2E5B;OP # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C;CL # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D;BA # Pd OBLIQUE HYPHEN 2E80..2E99;ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3;ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5;ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1510,8 +1530,7 @@ 3300..33FF;ID # So [256] SQUARE APAATO..SQUARE GAL 3400..4DBF;ID # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF 4DC0..4DFF;AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FFC;ID # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -9FFD..9FFF;ID # Cn [3] <reserved-9FFD>..<reserved-9FFF> +4E00..9FFF;ID # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF A000..A014;ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015;NS # Lm YI SYLLABLE WU A016..A48C;ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1553,8 +1572,11 @@ A788;AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A;AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E;AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F;AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF;AL # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA;AL # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA;AL # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1;AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3;AL # Ll LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9;AL # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4;AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6;AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7;AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9;AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -2511,15 +2533,17 @@ FB40..FB41;HL # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAME FB43..FB44;HL # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FB4F;HL # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1;AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1;AL # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2;AL # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D;AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E;CL # Pe ORNATE LEFT PARENTHESIS FD3F;OP # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F;AL # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F;AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7;AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF;AL # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB;AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC;PO # Sc RIAL SIGN -FDFD;AL # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF;AL # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F;CM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE10;IS # Po PRESENTATION FORM FOR VERTICAL COMMA FE11..FE12;CL # Po [2] PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP @@ -2682,9 +2706,20 @@ FFFD;AI # So REPLACEMENT CHARACTER 10500..10527;AL # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563;AL # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F;AL # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A;AL # Lu [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A;AL # Lu [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592;AL # Lu [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595;AL # Lu [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1;AL # Ll [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1;AL # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9;AL # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC;AL # Ll [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736;AL # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755;AL # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767;AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785;AL # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0;AL # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA;AL # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805;AL # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808;AL # Lo CYPRIOT SYLLABLE JO 1080A..10835;AL # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -2765,6 +2800,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 10F46..10F50;CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F51..10F54;AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59;AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81;AL # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85;CM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +10F86..10F89;AL # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4;AL # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB;AL # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6;AL # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -2777,6 +2815,10 @@ FFFD;AI # So REPLACEMENT CHARACTER 11049..1104D;AL # Po [5] BRAHMI PUNCTUATION DOT..BRAHMI PUNCTUATION LOTUS 11052..11065;AL # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F;NU # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070;CM # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072;AL # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074;CM # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075;AL # Lo BRAHMI LETTER OLD TAMIL LLA 1107F;CM # Mn BRAHMI NUMBER JOINER 11080..11081;CM # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11082;CM # Mc KAITHI SIGN VISARGA @@ -2788,6 +2830,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 110BB..110BC;AL # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD;AL # Cf KAITHI NUMBER SIGN 110BE..110C1;BA # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110C2;CM # Mn KAITHI VOWEL SIGN VOCALIC R 110CD;AL # Cf KAITHI NUMBER SIGN ABOVE 110D0..110E8;AL # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9;NU # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -2934,6 +2977,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 116B6;CM # Mc TAKRI SIGN VIRAMA 116B7;CM # Mn TAKRI SIGN NUKTA 116B8;AL # Lo TAKRI LETTER ARCHAIC KHA +116B9;AL # Po TAKRI ABBREVIATION SIGN 116C0..116C9;NU # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A;SA # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F;SA # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA @@ -2945,6 +2989,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 1173A..1173B;SA # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E;BA # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F;SA # So AHOM SYMBOL VI +11740..11746;SA # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B;AL # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E;CM # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837;CM # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -3008,6 +3053,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 11A9D;AL # Lo SOYOMBO MARK PLUTA 11A9E..11AA0;BB # Po [3] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO HEAD MARK WITH MOON AND SUN 11AA1..11AA2;BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 +11AB0..11ABF;AL # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11AC0..11AF8;AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08;AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E;AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -3065,6 +3111,8 @@ FFFD;AI # So REPLACEMENT CHARACTER 12400..1246E;AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474;BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 12480..12543;AL # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0;AL # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2;AL # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..13257;AL # Lo [600] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH O006 13258..1325A;OP # Lo [3] EGYPTIAN HIEROGLYPH O006A..EGYPTIAN HIEROGLYPH O006C 1325B..1325D;CL # Lo [3] EGYPTIAN HIEROGLYPH O006D..EGYPTIAN HIEROGLYPH O006F @@ -3090,6 +3138,8 @@ FFFD;AI # So REPLACEMENT CHARACTER 16A40..16A5E;AL # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69;NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F;BA # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE;AL # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9;NU # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED;AL # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4;CM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16AF5;BA # Po BASSA VAH FULL STOP @@ -3124,8 +3174,11 @@ FFFD;AI # So REPLACEMENT CHARACTER 18800..18AFF;ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18B00..18CD5;AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08;ID # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 +1AFF0..1AFF3;AL # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB;AL # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE;AL # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000..1B0FF;ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 -1B100..1B11E;ID # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 +1B100..1B122;ID # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU 1B150..1B152;CJ # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167;CJ # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB;ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -3137,6 +3190,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 1BC9D..1BC9E;CM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F;BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3;CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D;CM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46;CM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF50..1CFC3;AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5;AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126;AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164;AL # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -3150,7 +3206,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 1D185..1D18B;CM # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D18C..1D1A9;AL # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH 1D1AA..1D1AD;CM # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO -1D1AE..1D1E8;AL # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA;AL # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241;AL # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D242..1D244;CM # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME 1D245;AL # So GREEK MUSICAL LEIMMA @@ -3211,6 +3267,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 1DA8B;AL # Po SIGNWRITING PARENTHESIS 1DA9B..1DA9F;CM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF;CM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09;AL # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A;AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E;AL # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006;CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018;CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021;CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -3222,10 +3281,16 @@ FFFD;AI # So REPLACEMENT CHARACTER 1E140..1E149;NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E;AL # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F;AL # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD;AL # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE;CM # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB;AL # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF;CM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9;NU # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF;PR # Sc WANCHO NGUN SIGN +1E7E0..1E7E6;AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB;AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE;AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE;AL # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4;AL # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF;AL # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6;CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS @@ -3389,8 +3454,8 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F6C1..1F6CB;ID # So [11] BATHTUB..COUCH AND LAMP 1F6CC;EB # So SLEEPING ACCOMMODATION 1F6CD..1F6D7;ID # So [11] SHOPPING BAGS..ELEVATOR -1F6D8..1F6DF;ID # Cn [8] <reserved-1F6D8>..<reserved-1F6DF> -1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6D8..1F6DC;ID # Cn [5] <reserved-1F6D8>..<reserved-1F6DC> +1F6DD..1F6EC;ID # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6ED..1F6EF;ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> 1F6F0..1F6FC;ID # So [13] SATELLITE..ROLLER SKATE 1F6FD..1F6FF;ID # Cn [3] <reserved-1F6FD>..<reserved-1F6FF> @@ -3400,7 +3465,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F7D5..1F7D8;ID # So [4] CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7D9..1F7DF;ID # Cn [7] <reserved-1F7D9>..<reserved-1F7DF> 1F7E0..1F7EB;ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE -1F7EC..1F7FF;ID # Cn [20] <reserved-1F7EC>..<reserved-1F7FF> +1F7EC..1F7EF;ID # Cn [4] <reserved-1F7EC>..<reserved-1F7EF> +1F7F0;ID # So HEAVY EQUALS SIGN +1F7F1..1F7FF;ID # Cn [15] <reserved-1F7F1>..<reserved-1F7FF> 1F800..1F80B;AL # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F80C..1F80F;ID # Cn [4] <reserved-1F80C>..<reserved-1F80F> 1F810..1F847;AL # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW @@ -3427,16 +3494,13 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F93C..1F93E;EB # So [3] WRESTLERS..HANDBALL 1F93F..1F976;ID # So [56] DIVING MASK..FREEZING FACE 1F977;EB # So NINJA -1F978;ID # So DISGUISED FACE -1F979;ID # Cn <reserved-1F979> -1F97A..1F9B4;ID # So [59] FACE WITH PLEADING EYES..BONE +1F978..1F9B4;ID # So [61] DISGUISED FACE..BONE 1F9B5..1F9B6;EB # So [2] LEG..FOOT 1F9B7;ID # So TOOTH 1F9B8..1F9B9;EB # So [2] SUPERHERO..SUPERVILLAIN 1F9BA;ID # So SAFETY VEST 1F9BB;EB # So EAR WITH HEARING AID -1F9BC..1F9CB;ID # So [16] MOTORIZED WHEELCHAIR..BUBBLE TEA -1F9CC;ID # Cn <reserved-1F9CC> +1F9BC..1F9CC;ID # So [17] MOTORIZED WHEELCHAIR..TROLL 1F9CD..1F9CF;EB # So [3] STANDING PERSON..DEAF PERSON 1F9D0;ID # So FACE WITH MONOCLE 1F9D1..1F9DD;EB # So [13] ADULT..ELF @@ -3447,26 +3511,31 @@ FFFD;AI # So REPLACEMENT CHARACTER 1FA6E..1FA6F;ID # Cn [2] <reserved-1FA6E>..<reserved-1FA6F> 1FA70..1FA74;ID # So [5] BALLET SHOES..THONG SANDAL 1FA75..1FA77;ID # Cn [3] <reserved-1FA75>..<reserved-1FA77> -1FA78..1FA7A;ID # So [3] DROP OF BLOOD..STETHOSCOPE -1FA7B..1FA7F;ID # Cn [5] <reserved-1FA7B>..<reserved-1FA7F> +1FA78..1FA7C;ID # So [5] DROP OF BLOOD..CRUTCH +1FA7D..1FA7F;ID # Cn [3] <reserved-1FA7D>..<reserved-1FA7F> 1FA80..1FA86;ID # So [7] YO-YO..NESTING DOLLS 1FA87..1FA8F;ID # Cn [9] <reserved-1FA87>..<reserved-1FA8F> -1FA90..1FAA8;ID # So [25] RINGED PLANET..ROCK -1FAA9..1FAAF;ID # Cn [7] <reserved-1FAA9>..<reserved-1FAAF> -1FAB0..1FAB6;ID # So [7] FLY..FEATHER -1FAB7..1FABF;ID # Cn [9] <reserved-1FAB7>..<reserved-1FABF> +1FA90..1FAAC;ID # So [29] RINGED PLANET..HAMSA +1FAAD..1FAAF;ID # Cn [3] <reserved-1FAAD>..<reserved-1FAAF> +1FAB0..1FABA;ID # So [11] FLY..NEST WITH EGGS +1FABB..1FABF;ID # Cn [5] <reserved-1FABB>..<reserved-1FABF> 1FAC0..1FAC2;ID # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAC3..1FACF;ID # Cn [13] <reserved-1FAC3>..<reserved-1FACF> -1FAD0..1FAD6;ID # So [7] BLUEBERRIES..TEAPOT -1FAD7..1FAFF;ID # Cn [41] <reserved-1FAD7>..<reserved-1FAFF> +1FAC3..1FAC5;EB # So [3] PREGNANT MAN..PERSON WITH CROWN +1FAC6..1FACF;ID # Cn [10] <reserved-1FAC6>..<reserved-1FACF> +1FAD0..1FAD9;ID # So [10] BLUEBERRIES..JAR +1FADA..1FADF;ID # Cn [6] <reserved-1FADA>..<reserved-1FADF> +1FAE0..1FAE7;ID # So [8] MELTING FACE..BUBBLES +1FAE8..1FAEF;ID # Cn [8] <reserved-1FAE8>..<reserved-1FAEF> +1FAF0..1FAF6;EB # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS +1FAF7..1FAFF;ID # Cn [9] <reserved-1FAF7>..<reserved-1FAFF> 1FB00..1FB92;AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA;AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9;NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 1FC00..1FFFD;ID # Cn [1022] <reserved-1FC00>..<reserved-1FFFD> -20000..2A6DD;ID # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF;ID # Cn [34] <reserved-2A6DE>..<reserved-2A6FF> -2A700..2B734;ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F;ID # Cn [11] <reserved-2B735>..<reserved-2B73F> +20000..2A6DF;ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF;ID # Cn [32] <reserved-2A6E0>..<reserved-2A6FF> +2A700..2B738;ID # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F;ID # Cn [7] <reserved-2B739>..<reserved-2B73F> 2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F;ID # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 diff --git a/lib/unicore/NameAliases.txt b/lib/unicore/NameAliases.txt index 0e62632db5..8519284d89 100644 --- a/lib/unicore/NameAliases.txt +++ b/lib/unicore/NameAliases.txt @@ -1,6 +1,6 @@ -# NameAliases-13.0.0.txt -# Date: 2019-09-09, 19:47:00 GMT [KW, LI] -# © 2019 Unicode®, Inc. +# NameAliases-14.0.0.txt +# Date: 2020-10-21, 22:28:00 GMT [KW, LI] +# © 2020 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -270,6 +270,7 @@ 180C;FVS2;abbreviation 180D;FVS3;abbreviation 180E;MVS;abbreviation +180F;FVS4;abbreviation 200B;ZWSP;abbreviation 200C;ZWNJ;abbreviation 200D;ZWJ;abbreviation @@ -293,6 +294,7 @@ 2B7A;LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE;correction 2B7C;RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE;correction A015;YI SYLLABLE ITERATION MARK;correction +AA6E;MYANMAR LETTER KHAMTI LLA;correction FE00;VS1;abbreviation FE01;VS2;abbreviation FE02;VS3;abbreviation diff --git a/lib/unicore/NamedSequences.txt b/lib/unicore/NamedSequences.txt index b3c64f18c2..fa05c6a7d8 100644 --- a/lib/unicore/NamedSequences.txt +++ b/lib/unicore/NamedSequences.txt @@ -1,10 +1,10 @@ -# NamedSequences-13.0.0.txt -# Date: 2020-01-22, 19:12:00 GMT [KW, LI] -# © 2020 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# NamedSequences-14.0.0.txt +# Date: 2021-08-03, 23:04:00 GMT [KW] +# © 2021 Unicode®, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Unicode Named Character Sequences # @@ -28,7 +28,7 @@ # <1000, 1001, 1002> # # For more information, see UAX #34: Unicode Named Character -# Sequences, at http://www.unicode.org/unicode/reports/tr34/ +# Sequences, at https://www.unicode.org/reports/tr34/ # # Note: The order of entries in this file is not significant. # However, entries are generally in script order corresponding @@ -168,6 +168,35 @@ ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH E;0626 06D0 ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH AE;0626 06D5 ARABIC SEQUENCE NOON WITH KEHEH;0646 06A9 +# Entries that correspond to Indic characters with nuktas +# that are also listed in CompositionExclusions.txt. +# These characters decompose for normalized text, even +# in NFC. Having named sequences for these helps in +# certain specifications, including Label Generation Rules (LGR) +# for Internationalized Domain Names (IDN). +# +# Provisional 2020-01-16, Approved 2021-07-27 + +DEVANAGARI SEQUENCE FOR LETTER QA; 0915 093C +DEVANAGARI SEQUENCE FOR LETTER KHHA; 0916 093C +DEVANAGARI SEQUENCE FOR LETTER GHHA; 0917 093C +DEVANAGARI SEQUENCE FOR LETTER ZA; 091C 093C +DEVANAGARI SEQUENCE FOR LETTER DDDHA; 0921 093C +DEVANAGARI SEQUENCE FOR LETTER RHA; 0922 093C +DEVANAGARI SEQUENCE FOR LETTER FA; 092B 093C +DEVANAGARI SEQUENCE FOR LETTER YYA; 092F 093C +BENGALI SEQUENCE FOR LETTER RRA; 09A1 09BC +BENGALI SEQUENCE FOR LETTER RHA; 09A2 09BC +BENGALI SEQUENCE FOR LETTER YYA; 09AF 09BC +GURMUKHI SEQUENCE FOR LETTER LLA; 0A32 0A3C +GURMUKHI SEQUENCE FOR LETTER SHA; 0A38 0A3C +GURMUKHI SEQUENCE FOR LETTER KHHA; 0A16 0A3C +GURMUKHI SEQUENCE FOR LETTER GHHA; 0A17 0A3C +GURMUKHI SEQUENCE FOR LETTER ZA; 0A1C 0A3C +GURMUKHI SEQUENCE FOR LETTER FA; 0A2B 0A3C +ORIYA SEQUENCE FOR LETTER RRA; 0B21 0B3C +ORIYA SEQUENCE FOR LETTER RHA; 0B22 0B3C + # Entry for a Bangla entity. # Provisional 2009-08-10, Approved 2010-05-14 # @@ -180,7 +209,7 @@ BENGALI LETTER KHINYA;0995 09CD 09B7 # # A visual display of the Tamil named character sequences is available # in the documentation for the Unicode Standard. See Section 12.6, Tamil in -# http://www.unicode.org/versions/latest/ +# https://www.unicode.org/versions/latest/ TAMIL CONSONANT K; 0B95 0BCD TAMIL CONSONANT NG; 0B99 0BCD diff --git a/lib/unicore/NamedSqProv.txt b/lib/unicore/NamedSqProv.txt index a4e4fdc2e4..6c74798e65 100644 --- a/lib/unicore/NamedSqProv.txt +++ b/lib/unicore/NamedSqProv.txt @@ -1,10 +1,10 @@ -# NamedSequencesProv-13.0.0.txt -# Date: 2020-01-22, 19:32:00 GMT [KW, LI] -# © 2020 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# NamedSequencesProv-14.0.0.txt +# Date: 2021-08-03, 23:04:00 GMT [KW] +# © 2021 Unicode®, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Provisional Unicode Named Character Sequences # @@ -29,7 +29,7 @@ # <1000, 1001, 1002> # # For more information, see UAX #34: Unicode Named Character -# Sequences, at http://www.unicode.org/unicode/reports/tr34/ +# Sequences, at https://www.unicode.org/reports/tr34/ # # Note: The order of entries in this file is not significant. # However, entries are generally in script order corresponding @@ -40,34 +40,7 @@ # Provisional entries for NamedSequences.txt. -# Entries that correspond to Indic characters with nuktas -# that are also listed in CompositionExclusions.txt. -# These characters decompose for normalized text, even -# in NFC. Having named sequences for these helps in -# certain specifications, including Label Generation Rules (LGR) -# for Internationalized Domain Names (IDN). -# -# Provisional 2020-01-16 - -DEVANAGARI SEQUENCE FOR LETTER QA; 0915 093C -DEVANAGARI SEQUENCE FOR LETTER KHHA; 0916 093C -DEVANAGARI SEQUENCE FOR LETTER GHHA; 0917 093C -DEVANAGARI SEQUENCE FOR LETTER ZA; 091C 093C -DEVANAGARI SEQUENCE FOR LETTER DDDHA; 0921 093C -DEVANAGARI SEQUENCE FOR LETTER RHA; 0922 093C -DEVANAGARI SEQUENCE FOR LETTER FA; 092B 093C -DEVANAGARI SEQUENCE FOR LETTER YYA; 092F 093C -BENGALI SEQUENCE FOR LETTER RRA; 09A1 09BC -BENGALI SEQUENCE FOR LETTER RHA; 09A2 09BC -BENGALI SEQUENCE FOR LETTER YYA; 09AF 09BC -GURMUKHI SEQUENCE FOR LETTER LLA; 0A32 0A3C -GURMUKHI SEQUENCE FOR LETTER SHA; 0A38 0A3C -GURMUKHI SEQUENCE FOR LETTER KHHA; 0A16 0A3C -GURMUKHI SEQUENCE FOR LETTER GHHA; 0A17 0A3C -GURMUKHI SEQUENCE FOR LETTER ZA; 0A1C 0A3C -GURMUKHI SEQUENCE FOR LETTER FA; 0A2B 0A3C -ORIYA SEQUENCE FOR LETTER RRA; 0B21 0B3C -ORIYA SEQUENCE FOR LETTER RHA; 0B22 0B3C +# No provisional entries are currently defined. # ================================================ diff --git a/lib/unicore/NamesList.txt b/lib/unicore/NamesList.txt index 6b856885b8..a5618d9e13 100644 --- a/lib/unicore/NamesList.txt +++ b/lib/unicore/NamesList.txt @@ -1,28 +1,15 @@ ; charset=UTF-8 -@@@ The Unicode Standard 13.0.0 -@@@+ U13M200203.lst - Unicode 13.0.0 names list, eighth delta. - Repertoire synched with UnicodeData-13.0.0d6.txt - Eighth delta of annotation fixes. - Added xrefs for 27C7, 27D1, 2227, 2228. Adjusted subhead for 27C7. - Updated aliases for 26A5, 26A4, 26A2, 263F. - Updated subheads and annotations for 1DF8 through 1DFB. - Updated title of UTR #54 in notice at 1800. - Added xref to 202F for 0020. - Added annotations about abbreviations for 2066 through 2069 for consistency. - Separated aliases for 0009 and 000A onto separate lines. - Removed superfluous xrefs for 2011. - Adjusted subheads for 2028 and 202A. - Added notices for the sets of composition exclusions in four Indic scripts. - Added xrefs for 029C, 1D34, 1D78, A7F8 and a notice at A7F8. +@@@ The Unicode Standard 14.0.0 +@@@+ U14M210804.lst + Unicode 14.0.0 final names list. This file is semi-automatically derived from UnicodeData.txt and a set of manually created annotations using a script to select or suppress information from the data file. The rules used for this process are aimed at readability for the human reader, at the expense of some details; therefore, this file should not be parsed for machine-readable information. -@+ © 2020 Unicode®, Inc. - For terms of use, see http://www.unicode.org/terms_of_use.html +@+ © 2021 Unicode®, Inc. + For terms of use, see https://www.unicode.org/terms_of_use.html @@ 0000 C0 Controls and Basic Latin (Basic Latin) 007F @@+ @ C0 controls @@ -112,6 +99,9 @@ x (zero width space - 200B) x (narrow no-break space - 202F) x (word joiner - 2060) + x (symbol for space - 2420) + x (blank symbol - 2422) + x (open box - 2423) x (ideographic space - 3000) x (zero width no-break space - FEFF) 0021 EXCLAMATION MARK @@ -121,27 +111,42 @@ x (latin letter retroflex click - 01C3) x (double exclamation mark - 203C) x (interrobang - 203D) + x (warning sign - 26A0) + x (heavy exclamation mark symbol - 2757) x (heavy exclamation mark ornament - 2762) + x (medieval exclamation mark - 2E53) + x (modifier letter raised exclamation mark - A71D) 0022 QUOTATION MARK + = double quote * neutral (vertical), used as opening or closing quotation mark * preferred characters in English for paired quotation marks are 201C & 201D * 05F4 is preferred for gershayim when writing Hebrew x (modifier letter double prime - 02BA) + x (double acute accent - 02DD) + x (modifier letter double apostrophe - 02EE) x (combining double acute accent - 030B) x (combining double vertical line above - 030E) x (hebrew punctuation gershayim - 05F4) + x (left double quotation mark - 201C) + x (right double quotation mark - 201D) x (double prime - 2033) x (ditto mark - 3003) 0023 NUMBER SIGN - = pound sign, hash, crosshatch, octothorpe + = pound sign (weight) + = hashtag, hash + = crosshatch, octothorpe + * for denoting musical sharp 266F is preferred x (l b bar symbol - 2114) + x (numero sign - 2116) x (viewdata square - 2317) x (music sharp sign - 266F) + x (equals sign and slanted parallel - 29E3) 0024 DOLLAR SIGN = milréis, escudo * used for many peso currencies in Latin America and elsewhere * glyph may have one or two vertical bars * other currency symbol characters start at 20A0 + x (cent sign - 00A2) x (currency sign - 00A4) x (peso sign - 20B1) x (heavy dollar sign - 1F4B2) @@ -151,11 +156,14 @@ x (per ten thousand sign - 2031) x (commercial minus sign - 2052) 0026 AMPERSAND + = and + * originally derived from a ligature of 'e' and 't' x (tironian sign et - 204A) x (turned ampersand - 214B) x (heavy ampersand ornament - 1F674) 0027 APOSTROPHE = apostrophe-quote (1.0) + = single quote = APL quote * neutral (vertical) glyph with mixed usage * 2019 is preferred for apostrophe @@ -165,7 +173,10 @@ x (modifier letter apostrophe - 02BC) x (modifier letter vertical line - 02C8) x (combining acute accent - 0301) + x (combining vertical line above - 030D) x (hebrew punctuation geresh - 05F3) + x (left single quotation mark - 2018) + x (right single quotation mark - 2019) x (prime - 2032) x (latin small letter saltillo - A78C) 0028 LEFT PARENTHESIS @@ -174,43 +185,65 @@ = closing parenthesis (1.0) * see discussion on semantics of paired bracketing characters 002A ASTERISK - = star (on phone keypads) + = star + * can have five or six spokes x (arabic five pointed star - 066D) + x (asterism - 2042) x (low asterisk - 204E) + x (two asterisks aligned vertically - 2051) + x (combining asterisk above - 20F0) x (asterisk operator - 2217) x (sextile - 26B9) x (heavy asterisk - 2731) + x (slavonic asterisk - A673) + x (medium six spoked asterisk - 1F7B6) +@ ASCII math operator 002B PLUS SIGN + x (modifier letter plus sign - 02D6) + x (minus sign - 2212) x (heavy plus sign - 2795) + x (hebrew letter alternative plus sign - FB29) + x (light greek cross - 1F7A2) +@ ASCII punctuation 002C COMMA = decimal separator x (arabic comma - 060C) + x (arabic decimal separator - 066B) x (single low-9 quotation mark - 201A) x (reversed comma - 2E41) x (medieval comma - 2E4C) x (ideographic comma - 3001) 002D HYPHEN-MINUS - = hyphen or minus sign - * used for either hyphen or minus sign + = hyphen, dash + = minus sign + * used generically for hyphen, minus sign or en dash, all of which have dedicated alternatives + x (soft hyphen - 00AD) + x (modifier letter minus sign - 02D7) x (hyphen - 2010) x (non-breaking hyphen - 2011) x (figure dash - 2012) x (en dash - 2013) + x (hyphenation point - 2027) x (hyphen bullet - 2043) x (minus sign - 2212) x (roman uncia sign - 10191) 002E FULL STOP = period, dot, decimal point + * the use as decimal point is locale dependent * may be rendered as a raised decimal point in old style numbers x (arabic full stop - 06D4) + x (one dot leader - 2024) + x (horizontal ellipsis - 2026) + x (raised dot - 2E33) x (stenographic full stop - 2E3C) x (ideographic full stop - 3002) 002F SOLIDUS - = slash, virgule - x (latin letter dental click - 01C0) + = slash,forward slash, virgule x (combining long solidus overlay - 0338) x (fraction slash - 2044) x (division slash - 2215) + x (mathematical rising diagonal - 27CB) + x (big solidus - 29F8) x (dotted solidus - 2E4A) @ ASCII digits 0030 DIGIT ZERO @@ -224,41 +257,65 @@ 0037 DIGIT SEVEN 0038 DIGIT EIGHT 0039 DIGIT NINE -@ ASCII punctuation and symbols +@ ASCII punctuation 003A COLON * also used to denote division or scale; for that mathematical use 2236 is preferred + * in Finnish and Swedish, also used as intra-word punctation (abbreviation mark) + x (modifier letter triangular colon - 02D0) + x (modifier letter raised colon - 02F8) x (armenian full stop - 0589) x (hebrew punctuation sof pasuq - 05C3) + x (ethiopic wordspace - 1361) + x (ethiopic colon - 1365) + x (two dot punctuation - 205A) + x (tricolon - 205D) x (ratio - 2236) x (modifier letter colon - A789) + x (presentation form for vertical two dot leader - FE30) 003B SEMICOLON * this, and not 037E, is the preferred character for 'Greek question mark' x (greek question mark - 037E) x (arabic semicolon - 061B) x (reversed semicolon - 204F) + x (turned semicolon - 2E35) +@ ASCII mathematical operators +@+ Other mathematical operators start at 2200. 003C LESS-THAN SIGN + * paired with 003E for ASCII-based angle bracket markup conventions + x (modifier letter left arrowhead - 02C2) x (single left-pointing angle quotation mark - 2039) x (left-pointing angle bracket - 2329) x (mathematical left angle bracket - 27E8) x (left angle bracket - 3008) 003D EQUALS SIGN * other related characters: 2241-2263 + x (canadian syllabics hyphen - 1400) + x (almost equal to - 2248) x (not equal to - 2260) x (identical to - 2261) + x (double hyphen - 2E40) + x (katakana-hiragana double hyphen - 30A0) x (modifier letter short equals sign - A78A) x (roman sextans sign - 10190) + x (heavy equals sign - 1F7F0) 003E GREATER-THAN SIGN + x (modifier letter right arrowhead - 02C3) x (single right-pointing angle quotation mark - 203A) x (right-pointing angle bracket - 232A) x (mathematical right angle bracket - 27E9) x (right angle bracket - 3009) +@ ASCII punctuation 003F QUESTION MARK x (inverted question mark - 00BF) x (greek question mark - 037E) x (arabic question mark - 061F) x (interrobang - 203D) - x (question exclamation mark - 2048) - x (exclamation question mark - 2049) + x (double question mark - 2047) + x (black question mark ornament - 2753) + x (uncertainty sign - 2BD1) + x (reversed question mark - 2E2E) + x (medieval question mark - 2E54) + x (replacement character - FFFD) 0040 COMMERCIAL AT = at sign @ Uppercase Latin alphabet @@ -267,12 +324,16 @@ x (script capital b - 212C) 0043 LATIN CAPITAL LETTER C x (double-struck capital c - 2102) + x (degree celsius - 2103) x (black-letter capital c - 212D) + x (roman numeral one hundred - 216D) 0044 LATIN CAPITAL LETTER D + x (roman numeral five hundred - 216E) 0045 LATIN CAPITAL LETTER E x (euler constant - 2107) x (script capital e - 2130) 0046 LATIN CAPITAL LETTER F + x (degree fahrenheit - 2109) x (script capital f - 2131) x (turned capital f - 2132) 0047 LATIN CAPITAL LETTER G @@ -283,8 +344,6 @@ 0049 LATIN CAPITAL LETTER I * Turkish and Azerbaijani use 0131 for lowercase x (latin capital letter i with dot above - 0130) - x (cyrillic capital letter byelorussian-ukrainian i - 0406) - x (cyrillic letter palochka - 04C0) x (script capital i - 2110) x (black-letter capital i - 2111) x (roman numeral one - 2160) @@ -295,13 +354,16 @@ x (script capital l - 2112) 004D LATIN CAPITAL LETTER M x (script capital m - 2133) + x (roman numeral one thousand - 216F) 004E LATIN CAPITAL LETTER N x (double-struck capital n - 2115) 004F LATIN CAPITAL LETTER O 0050 LATIN CAPITAL LETTER P + x (script capital p - 2118) x (double-struck capital p - 2119) 0051 LATIN CAPITAL LETTER Q x (double-struck capital q - 211A) + x (rotated capital q - 213A) 0052 LATIN CAPITAL LETTER R x (script capital r - 211B) x (black-letter capital r - 211C) @@ -313,6 +375,7 @@ x (roman numeral five - 2164) 0057 LATIN CAPITAL LETTER W 0058 LATIN CAPITAL LETTER X + x (roman numeral ten - 2169) 0059 LATIN CAPITAL LETTER Y 005A LATIN CAPITAL LETTER Z x (double-struck capital z - 2124) @@ -325,10 +388,13 @@ = backslash x (combining reverse solidus overlay - 20E5) x (set minus - 2216) + x (mathematical falling diagonal - 27CD) + x (big reverse solidus - 29F9) 005D RIGHT SQUARE BRACKET = closing square bracket (1.0) 005E CIRCUMFLEX ACCENT * this is a spacing character + * used in ASCII-based representation of exponentiation x (modifier letter up arrowhead - 02C4) x (modifier letter circumflex accent - 02C6) x (combining circumflex accent - 0302) @@ -337,10 +403,12 @@ 005F LOW LINE = spacing underscore (1.0) * this is a spacing character + * joins with adjacent instances of itself x (modifier letter low macron - 02CD) x (combining macron below - 0331) x (combining low line - 0332) x (double low line - 2017) + x (combining conjoining macron below - FE2D) 0060 GRAVE ACCENT * this is a spacing character x (modifier letter grave accent - 02CB) @@ -354,6 +422,7 @@ 0065 LATIN SMALL LETTER E x (estimated symbol - 212E) x (script small e - 212F) + x (latin small letter blackletter e - AB32) 0066 LATIN SMALL LETTER F 0067 LATIN SMALL LETTER G x (latin small letter script g - 0261) @@ -364,6 +433,7 @@ 0069 LATIN SMALL LETTER I * Turkish and Azerbaijani use 0130 for uppercase x (latin small letter dotless i - 0131) + x (superscript latin small letter i - 2071) x (mathematical italic small dotless i - 1D6A4) 006A LATIN SMALL LETTER J x (latin small letter dotless j - 0237) @@ -377,15 +447,18 @@ x (superscript latin small letter n - 207F) 006F LATIN SMALL LETTER O x (script small o - 2134) + x (latin small letter blackletter o - AB3D) 0070 LATIN SMALL LETTER P 0071 LATIN SMALL LETTER Q 0072 LATIN SMALL LETTER R 0073 LATIN SMALL LETTER S + x (latin small letter long s - 017F) 0074 LATIN SMALL LETTER T 0075 LATIN SMALL LETTER U 0076 LATIN SMALL LETTER V 0077 LATIN SMALL LETTER W 0078 LATIN SMALL LETTER X + x (multiplication sign - 00D7) 0079 LATIN SMALL LETTER Y 007A LATIN SMALL LETTER Z x (latin small letter z with stroke - 01B6) @@ -394,10 +467,14 @@ = opening curly bracket (1.0) = left brace 007C VERTICAL LINE - = vertical bar + = vertical bar, pipe * used in pairs to indicate absolute value + * also used as an unpaired separator or as a fence + x (broken bar - 00A6) x (latin letter dental click - 01C0) x (hebrew punctuation paseq - 05C0) + x (devanagari danda - 0964) + x (combining long vertical line overlay - 20D2) x (divides - 2223) x (light vertical bar - 2758) 007D RIGHT CURLY BRACKET @@ -407,8 +484,12 @@ * this is a spacing character x (small tilde - 02DC) x (combining tilde - 0303) + x (combining tilde overlay - 0334) x (swung dash - 2053) x (tilde operator - 223C) + x (tilde with ring above - 2E1B) + x (vertical tilde - 2E2F) + x (wave dash - 301C) x (fullwidth tilde - FF5E) @ Control character 007F <control> @@ -488,30 +569,42 @@ x (figure space - 2007) x (narrow no-break space - 202F) x (word joiner - 2060) + x (shouldered open box - 237D) x (zero width no-break space - FEFF) # <noBreak> 0020 00A1 INVERTED EXCLAMATION MARK * Spanish, Asturian, Galician + * used in extended IPA to represent sublaminal lower alveolar percussive x (exclamation mark - 0021) + x (modifier letter raised inverted exclamation mark - A71E) 00A2 CENT SIGN + x (latin small letter c with stroke - 023C) + x (mill sign - 20A5) + x (cedi sign - 20B5) + x (musical symbol cut time - 1D135) 00A3 POUND SIGN - = pound sterling, Irish punt, Italian lira, Turkish lira, etc. + = pound sterling, Irish punt, lira, etc. + * glyph may have one or two crossbars, in distinction from 20A4 x (lira sign - 20A4) x (turkish lira sign - 20BA) x (roman semuncia sign - 10192) 00A4 CURRENCY SIGN - * other currency symbol characters: 20A0-20BF + * generic or unknown currency + * other currency symbol characters start at 20A0 x (dollar sign - 0024) 00A5 YEN SIGN - = yuan sign + = yuan sign (renminbi) * glyph may have one or two crossbars, but the official symbol in Japan and China has two + * in native context, specific ideographs may be used for units of these currencies x 5143 x 5186 00A6 BROKEN BAR = broken vertical bar (1.0) = parted rule (in typography) + x (vertical line - 007C) 00A7 SECTION SIGN - * paragraph sign in some European usage + * used in referencing numbered sections or paragraphs + x (top half section sign - 2E39) 00A8 DIAERESIS * this is a spacing character x (combining diaeresis - 0308) @@ -523,6 +616,7 @@ x (mask work symbol - 1F1AD) 00AA FEMININE ORDINAL INDICATOR * Spanish + x (modifier letter small a - 1D43) # <super> 0061 00AB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK = left guillemet @@ -533,26 +627,37 @@ 00AC NOT SIGN = angled dash (in typography) x (reversed not sign - 2310) + x (turned not sign - 2319) 00AD SOFT HYPHEN = discretionary hyphen * commonly abbreviated as SHY + * an invisible format character indicating a possible hyphenation location 00AE REGISTERED SIGN = registered trade mark sign (1.0) + x (trade mark sign - 2122) x (circled latin capital letter r - 24C7) + x (raised md sign - 1F16B) + x (raised mr sign - 1F16C) 00AF MACRON = overline, APL overbar * this is a spacing character + * unlike 203E, adjacent instances of this character do not join x (modifier letter macron - 02C9) x (combining macron - 0304) x (combining overline - 0305) + x (overline - 203E) + x (combining conjoining macron - FE26) # 0020 0304 00B0 DEGREE SIGN * this is a spacing character x (ring above - 02DA) x (combining ring above - 030A) x (superscript zero - 2070) + x (degree celsius - 2103) + x (degree fahrenheit - 2109) x (ring operator - 2218) 00B1 PLUS-MINUS SIGN + = biquintile (astrological aspect: 144°) x (minus-or-plus sign - 2213) 00B2 SUPERSCRIPT TWO = squared @@ -568,6 +673,8 @@ x (modifier letter prime - 02B9) x (modifier letter acute accent - 02CA) x (combining acute accent - 0301) + x (greek tonos - 0384) + x (greek oxia - 1FFD) x (prime - 2032) # 0020 0301 00B5 MICRO SIGN @@ -583,6 +690,8 @@ = Georgian comma = Greek middle dot (ano teleia) * also used as a raised decimal point or to denote multiplication; for multiplication 22C5 is preferred + x (full stop - 002E) + x (dot above - 02D9) x (greek ano teleia - 0387) x (runic single punctuation - 16EB) x (bullet - 2022) @@ -602,9 +711,12 @@ 00B9 SUPERSCRIPT ONE x (superscript two - 00B2) x (superscript three - 00B3) + x (superscript zero - 2070) # <super> 0031 00BA MASCULINE ORDINAL INDICATOR * Spanish + x (modifier letter small o - 1D52) + x (numero sign - 2116) # <super> 006F 00BB RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK = right guillemet @@ -663,6 +775,7 @@ * lowercase is 00F0 x (latin capital letter d with stroke - 0110) x (latin capital letter african d - 0189) + x (latin capital letter d with short stroke overlay - A7C7) 00D1 LATIN CAPITAL LETTER N WITH TILDE : 004E 0303 00D2 LATIN CAPITAL LETTER O WITH GRAVE @@ -678,9 +791,14 @@ @ Mathematical operator 00D7 MULTIPLICATION SIGN = z notation Cartesian product + x (latin small letter x - 0078) + x (saltire - 2613) x (multiplication x - 2715) + x (heavy ballot x - 2718) x (cross mark - 274C) x (vector or cross product - 2A2F) + x (cancellation x - 1F5D9) + x (light saltire - 1F7A9) @ Letters 00D8 LATIN CAPITAL LETTER O WITH STROKE = o slash @@ -700,9 +818,12 @@ = Eszett * German * not used in Swiss High German - * uppercase is "SS" or 1E9E + * uppercase is "SS" (standard case mapping), alternatively 1E9E * typographically the glyph for this character can be based on a ligature of 017F with either 0073 or with an old-style glyph for 007A (the latter similar in appearance to 0292). Both forms exist interchangeably today. + x (latin small letter long s - 017F) + x (latin small letter ezh - 0292) x (greek small letter beta - 03B2) + x (latin capital letter sharp s - 1E9E) 00E0 LATIN SMALL LETTER A WITH GRAVE : 0061 0300 00E1 LATIN SMALL LETTER A WITH ACUTE @@ -745,6 +866,7 @@ 00F0 LATIN SMALL LETTER ETH * Icelandic, Faroese, Old English, IPA * uppercase is 00D0 + x (latin small letter d with stroke - 0111) x (greek small letter delta - 03B4) x (partial differential - 2202) 00F1 LATIN SMALL LETTER N WITH TILDE @@ -763,7 +885,7 @@ @ Mathematical operator 00F7 DIVISION SIGN = obelus - * occasionally used as an alternate, more visually distinct version of 2212 or 2011 in some contexts + * occasionally used as an alternate, more visually distinct shape for a hyphen in some contexts * historically used as a punctuation mark to denote questionable passages in manuscripts x (syriac harklean obelus - 070B) x (commercial minus sign - 2052) @@ -772,6 +894,8 @@ x (divides - 2223) x (ratio - 2236) x (heavy division sign - 2797) + x (long division - 27CC) + x (dotted obelos - 2E13) @ Letters 00F8 LATIN SMALL LETTER O WITH STROKE = o slash @@ -1543,7 +1667,7 @@ : 00D8 0301 01FF LATIN SMALL LETTER O WITH STROKE AND ACUTE : 00F8 0301 -@ Additions for Slovenian and Croatian +@ Additions for Slovenian 0200 LATIN CAPITAL LETTER A WITH DOUBLE GRAVE : 0041 030F 0201 LATIN SMALL LETTER A WITH DOUBLE GRAVE @@ -2090,7 +2214,7 @@ # <super> 0079 @ Miscellaneous phonetic modifiers 02B9 MODIFIER LETTER PRIME - * primary stress, emphasis + * stress, emphasis * transliteration of mjagkij znak (Cyrillic soft sign: palatalization) * transliteration of Hebrew geresh x (apostrophe - 0027) @@ -2431,6 +2555,7 @@ 031F COMBINING PLUS SIGN BELOW * IPA: advanced or fronted articulation x (modifier letter plus sign - 02D6) + x (combining plus sign above - 1AC8) 0320 COMBINING MINUS SIGN BELOW * IPA: retracted or backed articulation * glyph may have small end-serifs @@ -2477,6 +2602,7 @@ 032B COMBINING INVERTED DOUBLE ARCH BELOW * IPA: labialization x (modifier letter small w - 02B7) + x (combining inverted double arch above - 1AC7) 032C COMBINING CARON BELOW * IPA: voiced 032D COMBINING CIRCUMFLEX ACCENT BELOW @@ -2961,6 +3087,7 @@ 0416 CYRILLIC CAPITAL LETTER ZHE 0417 CYRILLIC CAPITAL LETTER ZE 0418 CYRILLIC CAPITAL LETTER I +@+ This letter is also used to represent electrolarynx phonation in the Voice Quality Symbols for extended IPA. 0419 CYRILLIC CAPITAL LETTER SHORT I : 0418 0306 041A CYRILLIC CAPITAL LETTER KA @@ -3365,6 +3492,7 @@ 04FF CYRILLIC SMALL LETTER HA WITH STROKE @@ 0500 Cyrillic Supplement 052F @ Komi letters +@+ These letters are for the obsolete Molodtsov alphabet, used in the 1920s. 0500 CYRILLIC CAPITAL LETTER KOMI DE 0501 CYRILLIC SMALL LETTER KOMI DE 0502 CYRILLIC CAPITAL LETTER KOMI DJE @@ -3427,9 +3555,10 @@ 0528 CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK 0529 CYRILLIC SMALL LETTER EN WITH LEFT HOOK @ Komi letters +@+ These are obsolete letters attested in a 19th century grammar of Komi. 052A CYRILLIC CAPITAL LETTER DZZHE 052B CYRILLIC SMALL LETTER DZZHE - * also used for Ossetian + * also used for Ossetian until 1924 052C CYRILLIC CAPITAL LETTER DCHE 052D CYRILLIC SMALL LETTER DCHE @ Khanty letters @@ -3741,15 +3870,18 @@ * represents sallallahu alayhe wasallam "may God's peace and blessings be upon him" 0611 ARABIC SIGN ALAYHE ASSALLAM * represents alayhe assalam "upon him be peace" + x (arabic ligature alayhi as-salaam - FD47) 0612 ARABIC SIGN RAHMATULLAH ALAYHE * represents rahmatullah alayhe "may God have mercy upon him" + x (arabic ligature rahimahu allaah - FD40) 0613 ARABIC SIGN RADI ALLAHOU ANHU * represents radi allahu 'anhu "may God be pleased with him" + x (arabic ligature radi allaahu anh - FD41) 0614 ARABIC SIGN TAKHALLUS * sign placed over the name or nom-de-plume of a poet, or in some writings used to mark all proper names @ Quranic annotation sign 0615 ARABIC SMALL HIGH TAH - * marks a recommended pause position in some Korans published in Iran and Pakistan + * marks a recommended pause position in some Qurans published in Iran and Pakistan * should not be confused with the small TAH sign used as a diacritic for some letters such as 0679 @ Extended Arabic mark 0616 ARABIC SMALL HIGH LIGATURE ALEF WITH LAM WITH YEH @@ -3773,6 +3905,7 @@ * commonly abbreviated ALM x (right-to-left mark - 200F) @ Punctuation +061D ARABIC END OF TEXT MARK 061E ARABIC TRIPLE DOT PUNCTUATION MARK 061F ARABIC QUESTION MARK * also used with Thaana and Syriac in modern text @@ -3793,6 +3926,7 @@ 0625 ARABIC LETTER ALEF WITH HAMZA BELOW : 0627 0655 0626 ARABIC LETTER YEH WITH HAMZA ABOVE + * in Kyrgyz the hamza is consistently positioned to the top right in isolate and final forms : 064A 0654 0627 ARABIC LETTER ALEF 0628 ARABIC LETTER BEH @@ -3833,6 +3967,7 @@ 0643 ARABIC LETTER KAF 0644 ARABIC LETTER LAM 0645 ARABIC LETTER MEEM + * Sindhi uses a shape with a short tail 0646 ARABIC LETTER NOON 0647 ARABIC LETTER HEH 0648 ARABIC LETTER WAW @@ -3855,11 +3990,15 @@ 0651 ARABIC SHADDA 0652 ARABIC SUKUN * marks absence of a vowel after the base consonant - * used in some Korans to mark a long vowel as ignored + * used in some Qurans to mark a long vowel as ignored * can have a variety of shapes, including a circular one and a shape that looks like '06E1' x (arabic small high dotless head of khah - 06E1) @ Combining maddah and hamza 0653 ARABIC MADDAH ABOVE + * used for madd jaa'iz in South Asian and Indonesian orthographies + x (arabic madda waajib - 089C) + x (arabic doubled madda - 089E) + x (arabic half madda over madda - 089F) 0654 ARABIC HAMZA ABOVE * restricted to hamza and ezafe semantics * is not used as a diacritic to form new letters @@ -3925,22 +4064,21 @@ * Kashmiri * this character is deprecated and its use is strongly discouraged * use the sequence 0627 065F instead -@ Extended Arabic letters +@ High hamza 0674 ARABIC LETTER HIGH HAMZA - * Kazakh + * Kazakh, Jawi * forms digraphs +@ Digraphic letters for Kazakh +@+ Use of these characters is discouraged. They were encoded for Kazakh digraphs, but their decompositions do not reflect the preferred order of representation. 0675 ARABIC LETTER HIGH HAMZA ALEF - * Kazakh # 0627 0674 0676 ARABIC LETTER HIGH HAMZA WAW - * Kazakh # 0648 0674 0677 ARABIC LETTER U WITH HAMZA ABOVE - * Kazakh # 06C7 0674 0678 ARABIC LETTER HIGH HAMZA YEH - * Kazakh # 064A 0674 +@ Extended Arabic letters 0679 ARABIC LETTER TTEH * Urdu 067A ARABIC LETTER TTEHEH @@ -4039,7 +4177,7 @@ 06A6 ARABIC LETTER PEHEH * Sindhi 06A7 ARABIC LETTER QAF WITH DOT ABOVE - * Maghrib Arabic, Uighur + * Maghrib Arabic, Uyghur 06A8 ARABIC LETTER QAF WITH THREE DOTS ABOVE * Tunisian Arabic 06A9 ARABIC LETTER KEHEH @@ -4054,9 +4192,10 @@ * use for the Jawi gaf is not recommended, although it may be found in some existing text data; recommended character for Jawi gaf is 0762 x (arabic letter keheh with dot above - 0762) 06AD ARABIC LETTER NG - * Uighur, Kazakh, Moroccan Arabic, early Jawi, early Persian, ... + * Uyghur, Kazakh, Moroccan Arabic, early Jawi, early Persian, ... 06AE ARABIC LETTER KAF WITH THREE DOTS BELOW * Berber, early Persian + * Pegon alternative for 068A 06AF ARABIC LETTER GAF * Persian, Urdu, ... 06B0 ARABIC LETTER GAF WITH RING @@ -4088,7 +4227,7 @@ * Jawi 06BE ARABIC LETTER HEH DOACHASHMEE * forms aspirate digraphs in Urdu and other languages of South Asia - * represents the glottal fricative /h/ in Uighur + * represents the glottal fricative /h/ in Uyghur 06BF ARABIC LETTER TCHEH WITH DOT ABOVE 06C0 ARABIC LETTER HEH WITH YEH ABOVE = arabic letter hamzah on ha (1.0) @@ -4106,19 +4245,20 @@ 06C4 ARABIC LETTER WAW WITH RING * Kashmiri 06C5 ARABIC LETTER KIRGHIZ OE - * Kirghiz + * Kyrgyz + * a glyph variant occurs which replaces the looped tail with a horizontal bar through the tail 06C6 ARABIC LETTER OE - * Uighur, Kurdish, Kazakh, Azerbaijani, Bosnian + * Uyghur, Kurdish, Kazakh, Azerbaijani, Bosnian 06C7 ARABIC LETTER U - * Kirghiz, Azerbaijani + * Azerbaijani, Kazakh, Kyrgyz, Uyghur 06C8 ARABIC LETTER YU - * Uighur + * Uyghur 06C9 ARABIC LETTER KIRGHIZ YU - * Kazakh, Kirghiz, Bosnian + * Kazakh, Kyrgyz, Bosnian 06CA ARABIC LETTER WAW WITH TWO DOTS ABOVE * Kurdish 06CB ARABIC LETTER VE - * Uighur, Kazakh + * Uyghur, Kazakh 06CC ARABIC LETTER FARSI YEH * Arabic, Persian, Urdu, Kashmiri, ... * initial and medial forms of this letter have dots @@ -4130,7 +4270,7 @@ * Kurdish 06CF ARABIC LETTER WAW WITH DOT ABOVE 06D0 ARABIC LETTER E - * Pashto, Uighur + * Pashto, Uyghur * used as the letter bbeh in Sindhi 06D1 ARABIC LETTER YEH WITH THREE DOTS BELOW * Mende languages, Hausa @@ -4145,7 +4285,7 @@ * Urdu @ Extended Arabic letter 06D5 ARABIC LETTER AE - * Uighur, Kazakh, Kirghiz + * Uyghur, Kazakh, Kyrgyz @ Quranic annotation signs 06D6 ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA 06D7 ARABIC SMALL HIGH LIGATURE QAF WITH LAM WITH ALEF MAKSURA @@ -4159,10 +4299,11 @@ 06DF ARABIC SMALL HIGH ROUNDED ZERO * smaller than the typical circular shape used for 0652 06E0 ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO + * the term "rectangular zero" is a translation of the Arabic name of this sign 06E1 ARABIC SMALL HIGH DOTLESS HEAD OF KHAH = Arabic jazm * presentation form of 0652, using font technology to select the variant is preferred - * used in some Korans to mark absence of a vowel + * used in some Qurans to mark absence of a vowel x (arabic sukun - 0652) 06E2 ARABIC SMALL HIGH MEEM ISOLATED FORM 06E3 ARABIC SMALL LOW SEEN @@ -4308,6 +4449,7 @@ @ Syriac marks 0740 SYRIAC FEMININE DOT * feminine marker used with the Taw feminine suffix + x (combining dot above left - 1DF8) 0741 SYRIAC QUSHSHAYA * indicates a plosive pronunciation 0742 SYRIAC RUKKAKHA @@ -4701,6 +4843,63 @@ x (malayalam letter llla - 0D34) 086A SYRIAC LETTER MALAYALAM SSA x (malayalam letter ssa - 0D37) +@@ 0870 Arabic Extended-B 089F +@ Additions for Quranic orthographies +0870 ARABIC LETTER ALEF WITH ATTACHED FATHA +0871 ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA +0872 ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE +0873 ARABIC LETTER ALEF WITH LEFT MIDDLE STROKE +0874 ARABIC LETTER ALEF WITH ATTACHED KASRA +0875 ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA +0876 ARABIC LETTER ALEF WITH ATTACHED ROUND DOT ABOVE +0877 ARABIC LETTER ALEF WITH ATTACHED RIGHT ROUND DOT +0878 ARABIC LETTER ALEF WITH ATTACHED LEFT ROUND DOT +0879 ARABIC LETTER ALEF WITH ATTACHED ROUND DOT BELOW +087A ARABIC LETTER ALEF WITH DOT ABOVE +087B ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA AND DOT ABOVE +087C ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE AND DOT ABOVE +087D ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND DOT ABOVE +087E ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA AND LEFT RING +087F ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE AND LEFT RING +0880 ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND LEFT RING +0881 ARABIC LETTER ALEF WITH ATTACHED RIGHT HAMZA +0882 ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +0883 ARABIC TATWEEL WITH OVERSTRUCK HAMZA +0884 ARABIC TATWEEL WITH OVERSTRUCK WAW +0885 ARABIC TATWEEL WITH TWO DOTS BELOW +0886 ARABIC LETTER THIN YEH + * no final or isolated forms are attested +0887 ARABIC BASELINE ROUND DOT +0888 ARABIC RAISED ROUND DOT +@ Additions for Bosnian orthographies +0889 ARABIC LETTER NOON WITH INVERTED SMALL V +088A ARABIC LETTER HAH WITH INVERTED SMALL V BELOW +@ Additions for Pegon orthographies +088B ARABIC LETTER TAH WITH DOT BELOW + * Pegon, Malagasy +088C ARABIC LETTER TAH WITH THREE DOTS BELOW + * Pegon alternative for 088B +088D ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW + * Sundanese Pegon +@ Abbreviation mark +088E ARABIC VERTICAL TAIL + * mark used to indicate abbreviations in early movable type texts from Iran + * only attested in final form +@ Supertending currency symbols +0890 ARABIC POUND MARK ABOVE + * Egyptian pound +0891 ARABIC PIASTRE MARK ABOVE + * Egyptian piastre +@ Additions for Quranic orthographies +0898 ARABIC SMALL HIGH WORD AL-JUZ +0899 ARABIC SMALL LOW WORD ISHMAAM +089A ARABIC SMALL LOW WORD IMAALA +089B ARABIC SMALL LOW WORD TASHEEL +089C ARABIC MADDA WAAJIB + x (arabic maddah above - 0653) +089D ARABIC SUPERSCRIPT ALEF MOKHASSAS +089E ARABIC DOUBLED MADDA +089F ARABIC HALF MADDA OVER MADDA @@ 08A0 Arabic Extended-A 08FF @ Arabic letters for African languages 08A0 ARABIC LETTER BEH WITH SMALL V BELOW @@ -4746,6 +4945,8 @@ @ Arabic letters for Arwi 08B3 ARABIC LETTER AIN WITH THREE DOTS BELOW 08B4 ARABIC LETTER KAF WITH DOT BELOW +@ Early Arabic letter +08B5 ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE @ Arabic letters for Bravanese 08B6 ARABIC LETTER BEH WITH SMALL MEEM ABOVE 08B7 ARABIC LETTER PEH WITH SMALL MEEM ABOVE @@ -4782,6 +4983,20 @@ 08C6 ARABIC LETTER JEEM WITH THREE DOTS BELOW @ Arabic letter for Punjabi 08C7 ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +@ Arabic letter for Balti +08C8 ARABIC LETTER GRAF +@ Additions for Quranic orthographies +08C9 ARABIC SMALL FARSI YEH +08CA ARABIC SMALL HIGH FARSI YEH +08CB ARABIC SMALL HIGH YEH BARREE WITH TWO DOTS BELOW +08CC ARABIC SMALL HIGH WORD SAH + = sign of waqf +08CD ARABIC SMALL HIGH ZAH +08CE ARABIC LARGE ROUND DOT ABOVE +08CF ARABIC LARGE ROUND DOT BELOW +08D0 ARABIC SUKUN BELOW +08D1 ARABIC LARGE CIRCLE BELOW +08D2 ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW @ Quranic annotation signs 08D3 ARABIC SMALL LOW WAW 08D4 ARABIC SMALL HIGH WORD AR-RUB @@ -4834,8 +5049,8 @@ 08F9 ARABIC LEFT ARROWHEAD BELOW 08FA ARABIC RIGHT ARROWHEAD BELOW 08FB ARABIC DOUBLE RIGHT ARROWHEAD ABOVE -08FC ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT * also used in Quranic text in African and other orthographies to represent dammatan +08FC ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT 08FD ARABIC RIGHT ARROWHEAD ABOVE WITH DOT @ Extended vowel signs 08FE ARABIC DAMMA WITH DOT @@ -5792,6 +6007,10 @@ 0C37 TELUGU LETTER SSA 0C38 TELUGU LETTER SA 0C39 TELUGU LETTER HA +@ Sign +0C3C TELUGU SIGN NUKTA + * used for Tamil transliteration and Perso-Arabic phonemes + * can also appear as a large dot, should be placed sufficiently below the baseline of a consonant to avoid confusion/collision with the aspiration marker @ Addition for Sanskrit 0C3D TELUGU SIGN AVAGRAHA @ Dependent vowel signs @@ -5820,6 +6039,11 @@ 0C59 TELUGU LETTER DZA 0C5A TELUGU LETTER RRRA * letter for an alveolar consonant whose exact phonetic value is not known +@ Consonant +0C5D TELUGU LETTER NAKAARA POLLU + * vowelless form of na + x (kannada letter nakaara pollu - 0CDD) + x (malayalam letter chillu n - 0D7B) @ Additional vowels for Sanskrit 0C60 TELUGU LETTER VOCALIC RR 0C61 TELUGU LETTER VOCALIC LL @@ -5949,6 +6173,10 @@ 0CD5 KANNADA LENGTH MARK 0CD6 KANNADA AI LENGTH MARK @ Additional consonants +0CDD KANNADA LETTER NAKAARA POLLU + * vowelless form of na + x (telugu letter nakaara pollu - 0C5D) + x (malayalam letter chillu n - 0D7B) 0CDE KANNADA LETTER FA % KANNADA LETTER LLLA * obsolete historic letter @@ -7759,9 +7987,12 @@ 1247 ETHIOPIC SYLLABLE QOA 1248 ETHIOPIC SYLLABLE QWA 124A ETHIOPIC SYLLABLE QWI + x (ethiopic syllable gurage qwi - 1E7F0) 124B ETHIOPIC SYLLABLE QWAA 124C ETHIOPIC SYLLABLE QWEE + x (ethiopic syllable gurage qwee - 1E7F1) 124D ETHIOPIC SYLLABLE QWE + x (ethiopic syllable gurage qwe - 1E7F2) 1250 ETHIOPIC SYLLABLE QHA 1251 ETHIOPIC SYLLABLE QHU 1252 ETHIOPIC SYLLABLE QHI @@ -7853,9 +8084,12 @@ 12AF ETHIOPIC SYLLABLE KOA 12B0 ETHIOPIC SYLLABLE KWA 12B2 ETHIOPIC SYLLABLE KWI + x (ethiopic syllable gurage kwi - 1E7F5) 12B3 ETHIOPIC SYLLABLE KWAA 12B4 ETHIOPIC SYLLABLE KWEE + x (ethiopic syllable gurage kwee - 1E7F6) 12B5 ETHIOPIC SYLLABLE KWE + x (ethiopic syllable gurage kwe - 1E7F7) 12B8 ETHIOPIC SYLLABLE KXA 12B9 ETHIOPIC SYLLABLE KXU 12BA ETHIOPIC SYLLABLE KXI @@ -7864,10 +8098,14 @@ 12BD ETHIOPIC SYLLABLE KXE 12BE ETHIOPIC SYLLABLE KXO 12C0 ETHIOPIC SYLLABLE KXWA + x (ethiopic syllable gurage hhwa - 1E7E8) 12C2 ETHIOPIC SYLLABLE KXWI + x (ethiopic syllable hhwi - 1E7E9) 12C3 ETHIOPIC SYLLABLE KXWAA 12C4 ETHIOPIC SYLLABLE KXWEE + x (ethiopic syllable hhwee - 1E7EA) 12C5 ETHIOPIC SYLLABLE KXWE + x (ethiopic syllable hhwe - 1E7EB) 12C8 ETHIOPIC SYLLABLE WA 12C9 ETHIOPIC SYLLABLE WU 12CA ETHIOPIC SYLLABLE WI @@ -7941,9 +8179,12 @@ 130F ETHIOPIC SYLLABLE GOA 1310 ETHIOPIC SYLLABLE GWA 1312 ETHIOPIC SYLLABLE GWI + x (ethiopic syllable gurage gwi - 1E7F8) 1313 ETHIOPIC SYLLABLE GWAA 1314 ETHIOPIC SYLLABLE GWEE + x (ethiopic syllable gurage gwee - 1E7F9) 1315 ETHIOPIC SYLLABLE GWE + x (ethiopic syllable gurage gwe - 1E7FA) 1318 ETHIOPIC SYLLABLE GGA 1319 ETHIOPIC SYLLABLE GGU 131A ETHIOPIC SYLLABLE GGI @@ -8050,22 +8291,30 @@ 137B ETHIOPIC NUMBER HUNDRED 137C ETHIOPIC NUMBER TEN THOUSAND @@ 1380 Ethiopic Supplement 139F -@ Syllables for Sebatbeit +@ Syllables for Gurage 1380 ETHIOPIC SYLLABLE SEBATBEIT MWA 1381 ETHIOPIC SYLLABLE MWI + x (ethiopic syllable gurage mwi - 1E7ED) 1382 ETHIOPIC SYLLABLE MWEE + x (ethiopic syllable gurage mwee - 1E7EE) 1383 ETHIOPIC SYLLABLE MWE 1384 ETHIOPIC SYLLABLE SEBATBEIT BWA 1385 ETHIOPIC SYLLABLE BWI + x (ethiopic syllable gurage bwi - 1E7F3) 1386 ETHIOPIC SYLLABLE BWEE + x (ethiopic syllable gurage bwee - 1E7F4) 1387 ETHIOPIC SYLLABLE BWE 1388 ETHIOPIC SYLLABLE SEBATBEIT FWA 1389 ETHIOPIC SYLLABLE FWI + x (ethiopic syllable gurage fwi - 1E7FB) 138A ETHIOPIC SYLLABLE FWEE + x (ethiopic syllable gurage fwee - 1E7FC) 138B ETHIOPIC SYLLABLE FWE 138C ETHIOPIC SYLLABLE SEBATBEIT PWA 138D ETHIOPIC SYLLABLE PWI + x (ethiopic syllable gurage pwi - 1E7FD) 138E ETHIOPIC SYLLABLE PWEE + x (ethiopic syllable gurage pwee - 1E7FE) 138F ETHIOPIC SYLLABLE PWE @ Tonal marks @+ Intended for use with a multiline scored layout @@ -8745,6 +8994,7 @@ 15C2 CANADIAN SYLLABICS SAYISI HO * Sayisi (HU) 15C3 CANADIAN SYLLABICS SAYISI HA +@ Syllables for Carrier 15C4 CANADIAN SYLLABICS CARRIER GHU 15C5 CANADIAN SYLLABICS CARRIER GHO 15C6 CANADIAN SYLLABICS CARRIER GHE @@ -9101,6 +9351,8 @@ 170A TAGALOG LETTER BA 170B TAGALOG LETTER MA 170C TAGALOG LETTER YA +170D TAGALOG LETTER RA + * modern adaptation, not found in Old Tagalog 170E TAGALOG LETTER LA 170F TAGALOG LETTER WA 1710 TAGALOG LETTER SA @@ -9108,8 +9360,14 @@ @ Dependent vowel signs 1712 TAGALOG VOWEL SIGN I 1713 TAGALOG VOWEL SIGN U -@ Virama +@ Viramas 1714 TAGALOG SIGN VIRAMA +1715 TAGALOG SIGN PAMUDPOD + x (hanunoo sign pamudpod - 1734) +@ Archaic letter +171F TAGALOG LETTER ARCHAIC RA + = Zambales ra + * modern adaptation, not found in Old Tagalog @@ 1720 Hanunoo 173F @ Independent vowels 1720 HANUNOO LETTER A @@ -9136,6 +9394,7 @@ 1733 HANUNOO VOWEL SIGN U @ Virama 1734 HANUNOO SIGN PAMUDPOD + x (tagalog sign pamudpod - 1715) @ Generic punctuation for Philippine scripts 1735 PHILIPPINE SINGLE PUNCTUATION x (devanagari danda - 0964) @@ -9424,6 +9683,8 @@ * abbreviated FVS3 180E MONGOLIAN VOWEL SEPARATOR * abbreviated MVS +180F MONGOLIAN FREE VARIATION SELECTOR FOUR + * abbreviated FVS4 @ Digits 1810 MONGOLIAN DIGIT ZERO 1811 MONGOLIAN DIGIT ONE @@ -10150,7 +10411,8 @@ * used in combinations with other punctuation marks at ends of sections 1AAD TAI THAM SIGN CAANG @@ 1AB0 Combining Diacritical Marks Extended 1AFF -@ Used for German dialectology +@+ This block contains many specialized combining marks, often derived from European dialectology transcriptional conventions. +@ Used in German dialectology 1AB0 COMBINING DOUBLED CIRCUMFLEX ACCENT 1AB1 COMBINING DIAERESIS-RING 1AB2 COMBINING INFINITY @@ -10164,6 +10426,8 @@ 1AB8 COMBINING DOUBLE OPEN MARK BELOW 1AB9 COMBINING LIGHT CENTRALIZATION STROKE BELOW 1ABA COMBINING STRONG CENTRALIZATION STROKE BELOW +@ Marks surrounding other diacritics or letters +@+ These marks are often intended to indicate partial or uncertain applicability of another diacritic. 1ABB COMBINING PARENTHESES ABOVE * intended to surround a diacritic above 1ABC COMBINING DOUBLE PARENTHESES ABOVE @@ -10172,11 +10436,39 @@ 1ABE COMBINING PARENTHESES OVERLAY * intended to surround a base letter * exact placement is font dependent -@ Used for Scots dialectology +@ Used in Scots dialectology 1ABF COMBINING LATIN SMALL LETTER W BELOW * indicates voiced labialization + x (modifier letter small w - 02B7) 1AC0 COMBINING LATIN SMALL LETTER TURNED W BELOW * indicates voiceless labialization +@ Marks next to or surrounding other diacritics +@+ The left or right parentheses marks are used in extended IPA in combination with voicing or devoicing diacritics to indicate initial or final partial applicability. +1AC1 COMBINING LEFT PARENTHESIS ABOVE LEFT +1AC2 COMBINING RIGHT PARENTHESIS ABOVE RIGHT +1AC3 COMBINING LEFT PARENTHESIS BELOW LEFT +1AC4 COMBINING RIGHT PARENTHESIS BELOW RIGHT +1AC5 COMBINING SQUARE BRACKETS ABOVE + * intended to surround a diacritic above + * used to indicate cancellation of an accent in Japanese transliteration +@ Phonetic sign +1AC6 COMBINING NUMBER SIGN ABOVE + = superscript octothorp + * used extensively in J.P. Harrington's transcriptional notation +@ Used in extended IPA +1AC7 COMBINING INVERTED DOUBLE ARCH ABOVE + x (combining inverted double arch below - 032B) + x (combining latin small letter w - 1DF1) +1AC8 COMBINING PLUS SIGN ABOVE + x (combining plus sign below - 031F) +1AC9 COMBINING DOUBLE PLUS SIGN ABOVE +1ACA COMBINING DOUBLE PLUS SIGN BELOW +@ Used in Middle English Ormulum +1ACB COMBINING TRIPLE ACUTE ACCENT + x (combining double acute accent - 030B) +1ACC COMBINING LATIN SMALL LETTER INSULAR G +1ACD COMBINING LATIN SMALL LETTER INSULAR R +1ACE COMBINING LATIN SMALL LETTER INSULAR T @@ 1B00 Balinese 1B7F @ Various signs 1B00 BALINESE SIGN ULU RICEM @@ -10186,7 +10478,9 @@ 1B02 BALINESE SIGN CECEK = anusvara 1B03 BALINESE SIGN SURANG - = repha + = final r + * also used for repha in transliteration of Kawi + x (javanese sign layar - A982) 1B04 BALINESE SIGN BISAH = visarga @ Independent vowels @@ -10323,6 +10617,9 @@ 1B49 BALINESE LETTER VE SASAK 1B4A BALINESE LETTER ZAL SASAK 1B4B BALINESE LETTER ASYURA SASAK +1B4C BALINESE LETTER ARCHAIC JNYA + * used in older texts in place of the ja + nya conjunct + x (javanese letter nya murda - A998) @ Digits 1B50 BALINESE DIGIT ZERO 1B51 BALINESE DIGIT ONE @@ -10382,12 +10679,17 @@ 1B7A BALINESE MUSICAL SYMBOL LEFT-HAND CLOSED PLAK 1B7B BALINESE MUSICAL SYMBOL LEFT-HAND CLOSED PLUK 1B7C BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +@ Punctuation +1B7D BALINESE PANTI LANTANG + = end of text +1B7E BALINESE PAMADA LANTANG + = end of text @@ 1B80 Sundanese 1BBF @ Various signs 1B80 SUNDANESE SIGN PANYECEK = anusvara 1B81 SUNDANESE SIGN PANGLAYAR - = repha + = final r 1B82 SUNDANESE SIGN PANGWISAD = visarga @ Vowels @@ -10982,9 +11284,11 @@ 1D33 MODIFIER LETTER CAPITAL G # <super> 0047 1D34 MODIFIER LETTER CAPITAL H + # <super> 0048 +@+ A typographical distinction between a capital form and a small capital form is not distinctive for this character in IPA usage. + * voiceless epiglottalized release (extended IPA) x (latin letter small capital h - 029C) x (modifier letter cyrillic en - 1D78) - # <super> 0048 1D35 MODIFIER LETTER CAPITAL I # <super> 0049 1D36 MODIFIER LETTER CAPITAL J @@ -11117,6 +11421,7 @@ * Georgian transcription x (georgian letter turned gan - 10F9) 1D78 MODIFIER LETTER CYRILLIC EN + * sometimes substituted for 1D34 in extended IPA x (modifier letter capital h - 1D34) # <super> 043D @ Other phonetic symbols @@ -11127,6 +11432,7 @@ x (latin small letter yogh - 021D) x (latin small letter script g - 0261) x (latin small letter gamma - 0263) + x (latin small letter closed insular g - A7D1) 1D7A LATIN SMALL LETTER TH WITH STRIKETHROUGH * American dictionary usage x (greek small letter theta - 03B8) @@ -11345,6 +11651,8 @@ 1DEF COMBINING LATIN SMALL LETTER ESH 1DF0 COMBINING LATIN SMALL LETTER U WITH LIGHT CENTRALIZATION STROKE 1DF1 COMBINING LATIN SMALL LETTER W + x (combining latin small letter w below - 1ABF) + x (combining inverted double arch above - 1AC7) 1DF2 COMBINING LATIN SMALL LETTER A WITH DIAERESIS 1DF3 COMBINING LATIN SMALL LETTER O WITH DIAERESIS 1DF4 COMBINING LATIN SMALL LETTER U WITH DIAERESIS @@ -11359,9 +11667,12 @@ * used in Syriac as a disambiguation dot * used in Typicon Cyrillic, where the dot may have a square appearance x (combining dot above right - 0358) + x (syriac feminine dot - 0740) 1DF9 COMBINING WIDE INVERTED BRIDGE BELOW * used as a Typicon mark x (combining inverted bridge below - 033A) +1DFA COMBINING DOT BELOW LEFT + * used in Syriac as a disambiguation dot 1DFB COMBINING DELETION MARK * used for "mhusaa" in Newa scribal tradition @ Double diacritic mark for UPA @@ -12633,7 +12944,7 @@ = Japanese kome = Urdu paragraph separator x (tibetan ku ru kha bzhi mig can - 0FBF) - x (cjk unified ideograph-200AD - 200AD) + x 200AD @ Double punctuation for vertical text 203C DOUBLE EXCLAMATION MARK x (exclamation mark - 0021) @@ -12667,6 +12978,7 @@ @ Brackets 2045 LEFT SQUARE BRACKET WITH QUILL x (left vertical bar with quill - 2E20) + x (left square bracket with stroke - 2E55) 2046 RIGHT SQUARE BRACKET WITH QUILL @ Double punctuation for vertical text 2047 DOUBLE QUESTION MARK @@ -12895,10 +13207,10 @@ x (thai currency symbol baht - 0E3F) x (khmer currency symbol riel - 17DB) x (script capital m - 2133) - x (cjk unified ideograph-5143 - 5143) - x (cjk unified ideograph-5186 - 5186) - x (cjk unified ideograph-5706 - 5706) - x (cjk unified ideograph-5713 - 5713) + x 5143 + x 5186 + x 5706 + x 5713 x (rial sign - FDFC) x (wancho ngun sign - 1E2FF) 20A0 EURO-CURRENCY SIGN @@ -12991,6 +13303,8 @@ * Georgia 20BF BITCOIN SIGN * a cryptocurrency +20C0 SOM SIGN + * Kyrgyzstan @@ 20D0 Combining Diacritical Marks for Symbols 20FF @ Combining diacritical marks for symbols 20D0 COMBINING LEFT HARPOON ABOVE @@ -13093,6 +13407,8 @@ # <font> 0067 latin small letter g 210B SCRIPT CAPITAL H = Hamiltonian operator + ~ 210B FE00 chancery style + ~ 210B FE01 roundhand style # <font> 0048 latin capital letter h 210C BLACK-LETTER CAPITAL H = Hilbert space @@ -13108,12 +13424,16 @@ x (cyrillic small letter tshe - 045B) # <font> 0127 latin small letter h with stroke 2110 SCRIPT CAPITAL I + ~ 2110 FE00 chancery style + ~ 2110 FE01 roundhand style # <font> 0049 latin capital letter i 2111 BLACK-LETTER CAPITAL I = imaginary part # <font> 0049 latin capital letter i 2112 SCRIPT CAPITAL L = Laplace transform + ~ 2112 FE00 chancery style + ~ 2112 FE01 roundhand style # <font> 004C latin capital letter l 2113 SCRIPT SMALL L = mathematical symbol 'ell' @@ -13148,6 +13468,8 @@ # <font> 0051 latin capital letter q 211B SCRIPT CAPITAL R = Riemann Integral + ~ 211B FE00 chancery style + ~ 211B FE01 roundhand style # <font> 0052 latin capital letter r 211C BLACK-LETTER CAPITAL R = real part @@ -13202,6 +13524,8 @@ : 00C5 latin capital letter a with ring above 212C SCRIPT CAPITAL B = Bernoulli function + ~ 212C FE00 chancery style + ~ 212C FE01 roundhand style # <font> 0042 latin capital letter b 212D BLACK-LETTER CAPITAL C # <font> 0043 latin capital letter c @@ -13214,9 +13538,13 @@ # <font> 0065 latin small letter e 2130 SCRIPT CAPITAL E = emf (electromotive force) + ~ 2130 FE00 chancery style + ~ 2130 FE01 roundhand style # <font> 0045 latin capital letter e 2131 SCRIPT CAPITAL F = Fourier transform + ~ 2131 FE00 chancery style + ~ 2131 FE01 roundhand style # <font> 0046 latin capital letter f 2132 TURNED CAPITAL F = Claudian digamma inversum @@ -13228,6 +13556,8 @@ = German Mark currency symbol, before WWII * when used for the Mark symbol, the range of glyph variation is restricted x (nordic mark sign - 20BB) + ~ 2133 FE00 chancery style + ~ 2133 FE01 roundhand style # <font> 004D latin capital letter m 2134 SCRIPT SMALL O = order, of inferior order to @@ -13311,6 +13641,7 @@ x (greek small letter digamma - 03DD) @ Biblical editorial symbol 214F SYMBOL FOR SAMARITAN SOURCE +@~ Standardized Variation Sequences @@ 2150 Number Forms 218F @ Fractions @+ Other fraction number forms are found in the Latin-1 Supplement block. @@ -13890,7 +14221,9 @@ : 2261 0338 2263 STRICTLY EQUIVALENT TO 2264 LESS-THAN OR EQUAL TO + x (less-than sign - 003C) 2265 GREATER-THAN OR EQUAL TO + x (greater-than sign - 003E) 2266 LESS-THAN OVER EQUAL TO 2267 GREATER-THAN OVER EQUAL TO 2268 LESS-THAN BUT NOT EQUAL TO @@ -14110,6 +14443,9 @@ x (black star - 2605) x (white medium star - 2B50) 22C7 DIVISION TIMES + x (multiplication sign - 00D7) + x (division sign - 00F7) + x (multiplication x - 2715) @ Relation 22C8 BOWTIE x (ocr bow tie - 2445) @@ -18275,6 +18611,8 @@ 2C2C GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI +@+ This is used as an alternative to Glagolitic letter chrivi, combined with 0303 combining tilde or with 0483 combining Cyrillic titlo as an et cetera sign. @ Small letters 2C30 GLAGOLITIC SMALL LETTER AZU 2C31 GLAGOLITIC SMALL LETTER BUKY @@ -18324,6 +18662,7 @@ 2C5C GLAGOLITIC SMALL LETTER SHTAPIC 2C5D GLAGOLITIC SMALL LETTER TROKUTASTI A 2C5E GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C5F GLAGOLITIC SMALL LETTER CAUDATE CHRIVI @@ 2C60 Latin Extended-C 2C7F @ Orthographic Latin additions 2C60 LATIN CAPITAL LETTER L WITH DOUBLE BAR @@ -18338,7 +18677,7 @@ * uppercase is 023A 2C66 LATIN SMALL LETTER T WITH DIAGONAL STROKE * uppercase is 023E -@ Additions for Uighur +@ Additions for Uyghur 2C67 LATIN CAPITAL LETTER H WITH DESCENDER 2C68 LATIN SMALL LETTER H WITH DESCENDER 2C69 LATIN CAPITAL LETTER K WITH DESCENDER @@ -18705,7 +19044,7 @@ 2DBC ETHIOPIC SYLLABLE CCHEE 2DBD ETHIOPIC SYLLABLE CCHE 2DBE ETHIOPIC SYLLABLE CCHO -@ Syllables for Sebatbeit +@ Syllables for Gurage 2DC0 ETHIOPIC SYLLABLE QYA 2DC1 ETHIOPIC SYLLABLE QYU 2DC2 ETHIOPIC SYLLABLE QYI @@ -18721,12 +19060,19 @@ 2DCD ETHIOPIC SYLLABLE KYE 2DCE ETHIOPIC SYLLABLE KYO 2DD0 ETHIOPIC SYLLABLE XYA + x (ethiopic syllable hhya - 1E7E0) 2DD1 ETHIOPIC SYLLABLE XYU + x (ethiopic syllable hhyu - 1E7E1) 2DD2 ETHIOPIC SYLLABLE XYI + x (ethiopic syllable hhyi - 1E7E2) 2DD3 ETHIOPIC SYLLABLE XYAA + x (ethiopic syllable hhyaa - 1E7E3) 2DD4 ETHIOPIC SYLLABLE XYEE + x (ethiopic syllable hhyee - 1E7E4) 2DD5 ETHIOPIC SYLLABLE XYE + x (ethiopic syllable hhye - 1E7E5) 2DD6 ETHIOPIC SYLLABLE XYO + x (ethiopic syllable hhyo - 1E7E6) 2DD8 ETHIOPIC SYLLABLE GYA 2DD9 ETHIOPIC SYLLABLE GYU 2DDA ETHIOPIC SYLLABLE GYI @@ -18821,6 +19167,7 @@ x (equals sign - 003D) x (hyphen - 2010) x (double hyphen - 2E40) + x (oblique hyphen - 2E5D) @ General punctuation 2E18 INVERTED INTERROBANG = gnaborretni @@ -18978,13 +19325,37 @@ x (paragraphos - 2E0F) x (capitulum - 2E3F) 2E4E PUNCTUS ELEVATUS MARK - * indicates a major medial pause where the sense is complete but the meaning is not +@+ This mark indicates a major intermediate pause where the sensus is complete but the sentence is not; this is similar in some regards to the modern use of a semicolon. 2E4F CORNISH VERSE DIVIDER 2E50 CROSS PATTY WITH RIGHT CROSSBAR x (maltese cross - 2720) + x (latin capital letter half h - 2C75) 2E51 CROSS PATTY WITH LEFT CROSSBAR + x (latin capital letter reversed half h - A7F5) 2E52 TIRONIAN SIGN CAPITAL ET x (tironian sign et - 204A) +2E53 MEDIEVAL EXCLAMATION MARK +2E54 MEDIEVAL QUESTION MARK +@ Brackets +@+ These brackets indicate ellipsis in certain conventions for Japanese transliteration. +2E55 LEFT SQUARE BRACKET WITH STROKE + * optional ellipsis + x (left square bracket with quill - 2045) +2E56 RIGHT SQUARE BRACKET WITH STROKE +2E57 LEFT SQUARE BRACKET WITH DOUBLE STROKE + * obligatory ellipsis +2E58 RIGHT SQUARE BRACKET WITH DOUBLE STROKE +@ Parentheses top and bottom halves +@+ These are used in pairs in extended IPA to indicate dubious phonemes or questionable presence of a sound. +2E59 TOP HALF LEFT PARENTHESIS +2E5A TOP HALF RIGHT PARENTHESIS +2E5B BOTTOM HALF LEFT PARENTHESIS +2E5C BOTTOM HALF RIGHT PARENTHESIS +@ Oblique hyphen +@+ The oblique hyphen is historic punctuation seen in some medieval and Renaissance manuscripts. In some modern lexicography an oblique hyphen is used distinctly to indicate hyphenation which is retained when a word is not broken at a line boundary. +2E5D OBLIQUE HYPHEN + x (hyphen - 2010) + x (double oblique hyphen - 2E17) @@ 2E80 CJK Radicals Supplement 2EFF @+ For the characters in this block whose representative glyph takes up only a portion of the em-box, the placement relative to the em-box is either centered or respects prototypical usage. The placement of the representative glyph is for informational purposes only, and should not be considered a recommendation for implementations. @ CJK radicals supplement @@ -19090,6 +19461,7 @@ x 4E2C 2EA7 CJK RADICAL COW x 725B + x 20092 2EA8 CJK RADICAL DOG * form used on left side x 72AD @@ -19790,6 +20162,7 @@ * substitute for ideograph not in font * editorial convention to represent ideographic lacuna x (white square - 25A1) + x (heavy equals sign - 1F7F0) @ CJK brackets 3014 LEFT TORTOISE SHELL BRACKET 3015 RIGHT TORTOISE SHELL BRACKET @@ -21844,7 +22217,7 @@ 4DFD HEXAGRAM FOR SMALL PREPONDERANCE 4DFE HEXAGRAM FOR AFTER COMPLETION 4DFF HEXAGRAM FOR BEFORE COMPLETION -@@ 4E00 CJK Unified Ideographs 9FFC +@@ 4E00 CJK Unified Ideographs 9FFF @@ A000 Yi Syllables A48F @@+ @ Syllables @@ -23791,6 +24164,7 @@ A72F LATIN SMALL LETTER CUATRILLO WITH COMMA A730 LATIN LETTER SMALL CAPITAL F A731 LATIN LETTER SMALL CAPITAL S A732 LATIN CAPITAL LETTER AA + x (modifier letter small capital aa - 10780) A733 LATIN SMALL LETTER AA A734 LATIN CAPITAL LETTER AO A735 LATIN SMALL LETTER AO @@ -23976,6 +24350,7 @@ A7AE LATIN CAPITAL LETTER SMALL CAPITAL I @ Letter for Japanese phonemic transcription A7AF LATIN LETTER SMALL CAPITAL Q * used to represent gemination + x (modifier letter capital q - A7F4) @ Letters for Americanist orthographies A7B0 LATIN CAPITAL LETTER TURNED K * lowercase is 029E @@ -23996,7 +24371,7 @@ A7B5 LATIN SMALL LETTER BETA A7B6 LATIN CAPITAL LETTER OMEGA A7B7 LATIN SMALL LETTER OMEGA x (greek small letter omega - 03C9) -@ Letters for Mazahua (Mexico) +@ Letters for Mazahua (México) A7B8 LATIN CAPITAL LETTER U WITH STROKE A7B9 LATIN SMALL LETTER U WITH STROKE @ Letters for Ugaritic and Egyptological transliteration @@ -24010,7 +24385,11 @@ A7BD LATIN SMALL LETTER GLOTTAL I x (latin small letter egyptological ain - A725) A7BE LATIN CAPITAL LETTER GLOTTAL U A7BF LATIN SMALL LETTER GLOTTAL U -@ Additional letters +@ Additional medieval letters +A7C0 LATIN CAPITAL LETTER OLD POLISH O +A7C1 LATIN SMALL LETTER OLD POLISH O + * used in Old Polish as a nasal vowel + x (latin small letter o with stroke - 00F8) A7C2 LATIN CAPITAL LETTER ANGLICANA W A7C3 LATIN SMALL LETTER ANGLICANA W * used in medieval English and Cornish @@ -24028,6 +24407,31 @@ A7C8 LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY * indicates a dental affricate A7C9 LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CA LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +@ Letters used in the Middle English Ormulum +A7D0 LATIN CAPITAL LETTER CLOSED INSULAR G +A7D1 LATIN SMALL LETTER CLOSED INSULAR G + x (latin small letter insular g - 1D79) +A7D3 LATIN SMALL LETTER DOUBLE THORN + x (latin small letter thorn - 00FE) +A7D5 LATIN SMALL LETTER DOUBLE WYNN + x (latin letter wynn - 01BF) +@ Letters used in medieval palaeography +A7D6 LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D7 LATIN SMALL LETTER MIDDLE SCOTS S + * used in Middle Scots for s, ss, ser, sir, is, sis, etc. + x (latin small letter sharp s - 00DF) +A7D8 LATIN CAPITAL LETTER SIGMOID S +A7D9 LATIN SMALL LETTER SIGMOID S + * used in Middle Cornish, Middle English, and Middle Scots +@ Modifier letters for Chatino (México) +A7F2 MODIFIER LETTER CAPITAL C + # <super> 0043 +A7F3 MODIFIER LETTER CAPITAL F + # <super> 0046 +@ Modifier letter for Japanese phonemic transcription +A7F4 MODIFIER LETTER CAPITAL Q + x (latin letter small capital q - A7AF) + # <super> 0051 @ Ancient Gaulish and Celtic epigraphic letters A7F5 LATIN CAPITAL LETTER REVERSED HALF H = H dimidié @@ -24039,7 +24443,7 @@ A7F7 LATIN EPIGRAPHIC LETTER SIDEWAYS I @ Additions for Extended IPA A7F8 MODIFIER LETTER CAPITAL H WITH STROKE # <super> 0126 -@+ A typographical distinction between a capital form and a small capital form is not distinctive for this IPA usage. +@+ A typographical distinction between a capital form and a small capital form is not distinctive for this character in IPA usage. * faucalized x (latin letter small capital h - 029C) A7F9 MODIFIER LETTER SMALL LIGATURE OE @@ -24129,7 +24533,7 @@ A838 NORTH INDIC RUPEE MARK A839 NORTH INDIC QUANTITY MARK * a unit mark for various weights and measures @@ A840 Phags-pa A87F -@+ Phags-pa letters are used for Mongolian, Chinese, Uighur, Tibetan, and Sanskrit unless annotated with a more restricted list of languages. +@+ Phags-pa letters are used for Mongolian, Chinese, Uyghur, Tibetan, and Sanskrit unless annotated with a more restricted list of languages. @ Consonants A840 PHAGS-PA LETTER KA * Mongolian, Chinese, Tibetan, Sanskrit @@ -24145,10 +24549,10 @@ A844 PHAGS-PA LETTER CA * Chinese, Tibetan x (tibetan letter ca - 0F45) A845 PHAGS-PA LETTER CHA - * Mongolian, Chinese, Uighur, Tibetan + * Mongolian, Chinese, Uyghur, Tibetan x (tibetan letter cha - 0F46) A846 PHAGS-PA LETTER JA - * Mongolian, Chinese, Uighur, Tibetan + * Mongolian, Chinese, Uyghur, Tibetan x (tibetan letter ja - 0F47) A847 PHAGS-PA LETTER NYA * Chinese, Tibetan, Sanskrit @@ -24195,7 +24599,7 @@ A856 PHAGS-PA LETTER SMALL A A857 PHAGS-PA LETTER YA x (tibetan letter ya - 0F61) A858 PHAGS-PA LETTER RA - * Mongolian, Uighur, Tibetan, Sanskrit + * Mongolian, Uyghur, Tibetan, Sanskrit x (tibetan letter ra - 0F62) A859 PHAGS-PA LETTER LA x (tibetan letter la - 0F63) @@ -24223,18 +24627,18 @@ A861 PHAGS-PA LETTER O x (tibetan vowel sign o - 0F7C) @ Consonants A862 PHAGS-PA LETTER QA - * Mongolian, Uighur + * Mongolian, Uyghur A863 PHAGS-PA LETTER XA * Mongolian, Chinese A864 PHAGS-PA LETTER FA - * Chinese, Uighur + * Chinese, Uyghur x (phags-pa letter ha - A85C) A865 PHAGS-PA LETTER GGA * language usage unknown * created by reversal of A862 @ Vowel A866 PHAGS-PA LETTER EE - * Mongolian, Chinese, Uighur + * Mongolian, Chinese, Uyghur @ Subjoined consonants A867 PHAGS-PA SUBJOINED LETTER WA * Chinese, Tibetan, Sanskrit @@ -24620,7 +25024,9 @@ A980 JAVANESE SIGN PANYANGGA A981 JAVANESE SIGN CECAK = anusvara A982 JAVANESE SIGN LAYAR - = repha + = final r + * also used for repha in transliteration of Kawi + x (balinese sign surang - 1B03) A983 JAVANESE SIGN WIGNYAN = visarga @ Letters @@ -24656,6 +25062,7 @@ A996 JAVANESE LETTER CA MURDA A997 JAVANESE LETTER JA A998 JAVANESE LETTER NYA MURDA = jnya + x (balinese letter archaic jnya - 1B4C) A999 JAVANESE LETTER JA MAHAPRANA = jha A99A JAVANESE LETTER NYA @@ -24915,6 +25322,7 @@ AA6C MYANMAR LETTER KHAMTI SA ~ AA6C FE00 dotted form AA6D MYANMAR LETTER KHAMTI HA AA6E MYANMAR LETTER KHAMTI HHA + % MYANMAR LETTER KHAMTI LLA AA6F MYANMAR LETTER KHAMTI FA ~ AA6F FE00 dotted form AA70 MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION @@ -25586,7 +25994,7 @@ F92B CJK COMPATIBILITY IDEOGRAPH-F92B : 72FC F92C CJK COMPATIBILITY IDEOGRAPH-F92C * a mapping change removed the original K0 source - x (cjk unified ideograph-90DE - 90DE) + x 90DE x (cjk compatibility ideograph-FA2E - FA2E) : 90CE F92D CJK COMPATIBILITY IDEOGRAPH-F92D @@ -25869,7 +26277,7 @@ F9B7 CJK COMPATIBILITY IDEOGRAPH-F9B7 : 91B4 F9B8 CJK COMPATIBILITY IDEOGRAPH-F9B8 * a mapping change removed the original K0 source - x (cjk unified ideograph-96B7 - 96B7) + x 96B7 x (cjk compatibility ideograph-FA2F - FA2F) : 96B8 F9B9 CJK COMPATIBILITY IDEOGRAPH-F9B9 @@ -26805,6 +27213,8 @@ FBC0 ARABIC SYMBOL SMALL TAH ABOVE * Urdu FBC1 ARABIC SYMBOL SMALL TAH BELOW * Urdu +FBC2 ARABIC SYMBOL WASLA ABOVE + x (arabic letter alef wasla - 0671) @ Glyphs for contextual forms of letters for Central Asian languages FBD3 ARABIC LETTER NG ISOLATED FORM # <isolated> 06AD @@ -27538,6 +27948,29 @@ FD3D ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM @+ These parentheses also do not have compatibility decompositions and should not be considered presentation forms. FD3E ORNATE LEFT PARENTHESIS FD3F ORNATE RIGHT PARENTHESIS +@ Honorific word ligatures +FD40 ARABIC LIGATURE RAHIMAHU ALLAAH + x (arabic sign rahmatullah alayhe - 0612) +FD41 ARABIC LIGATURE RADI ALLAAHU ANH + x (arabic sign radi allahou anhu - 0613) +FD42 ARABIC LIGATURE RADI ALLAAHU ANHAA +FD43 ARABIC LIGATURE RADI ALLAAHU ANHUM +FD44 ARABIC LIGATURE RADI ALLAAHU ANHUMAA +FD45 ARABIC LIGATURE RADI ALLAAHU ANHUNNA +FD46 ARABIC LIGATURE SALLALLAAHU ALAYHI WA-AALIH + x (arabic ligature sallallahou alayhe wasallam - FDFA) +FD47 ARABIC LIGATURE ALAYHI AS-SALAAM + x (arabic sign alayhe assallam - 0611) +FD48 ARABIC LIGATURE ALAYHIM AS-SALAAM +FD49 ARABIC LIGATURE ALAYHIMAA AS-SALAAM +FD4A ARABIC LIGATURE ALAYHI AS-SALAATU WAS-SALAAM +FD4B ARABIC LIGATURE QUDDISA SIRRAH +FD4C ARABIC LIGATURE SALLALLAHU ALAYHI WAAALIHEE WA-SALLAM + x (arabic ligature sallallahou alayhe wasallam - FDFA) + x (arabic ligature sallallaahu alayhi wa-aalih - FD46) +FD4D ARABIC LIGATURE ALAYHAA AS-SALAAM +FD4E ARABIC LIGATURE TABAARAKA WA-TAAALAA +FD4F ARABIC LIGATURE RAHIMAHUM ALLAAH @ Ligatures (three elements) FD50 ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM # <initial> 062A 062C 0645 @@ -27775,6 +28208,10 @@ FDC6 ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM # <final> 0633 062E 064A FDC7 ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM # <final> 0646 062C 064A +@ Honorific word ligature +FDCF ARABIC LIGATURE SALAAMUHU ALAYNAA + * his blessing on us + * used in Christian texts @ Noncharacters @+ These codes are intended for process-internal uses. FDD0 <not a character> @@ -27839,9 +28276,11 @@ FDFB ARABIC LIGATURE JALLAJALALOUHOU @ Currency symbol FDFC RIAL SIGN # <isolated> 0631 06CC 0627 0644 -@ Symbol -@+ The bismillah is treated as an atomic symbol, rather than as a word ligature. It has no decomposition. +@ Honorific word ligatures +@+ These word ligatures have no decompositions. FDFD ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFE ARABIC LIGATURE SUBHAANAHU WA TAAALAA +FDFF ARABIC LIGATURE AZZA WA JALL @@ FE00 Variation Selectors FE0F @ Variation selectors @+ These are combining characters; in conjunction with the preceding character they indicate a predetermined choice of variant glyph. @@ -30036,6 +30475,83 @@ FFFF <not a character> 10563 CAUCASIAN ALBANIAN LETTER KIW @ Punctuation 1056F CAUCASIAN ALBANIAN CITATION MARK +@@ 10570 Vithkuqi 105BF +@ Capital letters +10570 VITHKUQI CAPITAL LETTER A +10571 VITHKUQI CAPITAL LETTER BBE +10572 VITHKUQI CAPITAL LETTER BE +10573 VITHKUQI CAPITAL LETTER CE +10574 VITHKUQI CAPITAL LETTER CHE +10575 VITHKUQI CAPITAL LETTER DE +10576 VITHKUQI CAPITAL LETTER DHE +10577 VITHKUQI CAPITAL LETTER EI +10578 VITHKUQI CAPITAL LETTER E +10579 VITHKUQI CAPITAL LETTER FE +1057A VITHKUQI CAPITAL LETTER GA +1057C VITHKUQI CAPITAL LETTER HA +1057D VITHKUQI CAPITAL LETTER HHA + * used in 19th-century orthography +1057E VITHKUQI CAPITAL LETTER I +1057F VITHKUQI CAPITAL LETTER IJE + * used in 19th-century orthography +10580 VITHKUQI CAPITAL LETTER JE +10581 VITHKUQI CAPITAL LETTER KA +10582 VITHKUQI CAPITAL LETTER LA +10583 VITHKUQI CAPITAL LETTER LLA +10584 VITHKUQI CAPITAL LETTER ME +10585 VITHKUQI CAPITAL LETTER NE +10586 VITHKUQI CAPITAL LETTER NJE +10587 VITHKUQI CAPITAL LETTER O +10588 VITHKUQI CAPITAL LETTER PE +10589 VITHKUQI CAPITAL LETTER QA +1058A VITHKUQI CAPITAL LETTER RE +1058C VITHKUQI CAPITAL LETTER SE +1058D VITHKUQI CAPITAL LETTER SHE +1058E VITHKUQI CAPITAL LETTER TE +1058F VITHKUQI CAPITAL LETTER THE +10590 VITHKUQI CAPITAL LETTER U +10591 VITHKUQI CAPITAL LETTER VE +10592 VITHKUQI CAPITAL LETTER XE +10594 VITHKUQI CAPITAL LETTER Y +10595 VITHKUQI CAPITAL LETTER ZE +@ Small letters +10597 VITHKUQI SMALL LETTER A +10598 VITHKUQI SMALL LETTER BBE +10599 VITHKUQI SMALL LETTER BE +1059A VITHKUQI SMALL LETTER CE +1059B VITHKUQI SMALL LETTER CHE +1059C VITHKUQI SMALL LETTER DE +1059D VITHKUQI SMALL LETTER DHE +1059E VITHKUQI SMALL LETTER EI +1059F VITHKUQI SMALL LETTER E +105A0 VITHKUQI SMALL LETTER FE +105A1 VITHKUQI SMALL LETTER GA +105A3 VITHKUQI SMALL LETTER HA +105A4 VITHKUQI SMALL LETTER HHA + * used in 19th-century orthography +105A5 VITHKUQI SMALL LETTER I +105A6 VITHKUQI SMALL LETTER IJE + * used in 19th-century orthography +105A7 VITHKUQI SMALL LETTER JE +105A8 VITHKUQI SMALL LETTER KA +105A9 VITHKUQI SMALL LETTER LA +105AA VITHKUQI SMALL LETTER LLA +105AB VITHKUQI SMALL LETTER ME +105AC VITHKUQI SMALL LETTER NE +105AD VITHKUQI SMALL LETTER NJE +105AE VITHKUQI SMALL LETTER O +105AF VITHKUQI SMALL LETTER PE +105B0 VITHKUQI SMALL LETTER QA +105B1 VITHKUQI SMALL LETTER RE +105B3 VITHKUQI SMALL LETTER SE +105B4 VITHKUQI SMALL LETTER SHE +105B5 VITHKUQI SMALL LETTER TE +105B6 VITHKUQI SMALL LETTER THE +105B7 VITHKUQI SMALL LETTER U +105B8 VITHKUQI SMALL LETTER VE +105B9 VITHKUQI SMALL LETTER XE +105BB VITHKUQI SMALL LETTER Y +105BC VITHKUQI SMALL LETTER ZE @@ 10600 Linear A 1077F @ Simple signs 10600 LINEAR A SIGN AB001 @@ -30587,6 +31103,124 @@ FFFF <not a character> * 10668 a316, 10601 ab002 10767 LINEAR A SIGN A807 * 10668 a316, 10742 a703 d +@@ 10780 Latin Extended-F 107BF +@ Modifier letter for VoQS +10780 MODIFIER LETTER SMALL CAPITAL AA + * actually a small capital in VoQS (voice quality symbol) usage, with no semantic distinction from a full capital + x (latin capital letter aa - A732) +@ Modifier letters for IPA +10781 MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON + # <super> 02D0 +10782 MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON + # <super> 02D1 +10783 MODIFIER LETTER SMALL AE + # <super> 00E6 +10784 MODIFIER LETTER SMALL CAPITAL B + # <super> 0299 +10785 MODIFIER LETTER SMALL B WITH HOOK + # <super> 0253 +10787 MODIFIER LETTER SMALL DZ DIGRAPH + # <super> 02A3 +10788 MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK + # <super> AB66 +10789 MODIFIER LETTER SMALL DZ DIGRAPH WITH CURL + # <super> 02A5 +1078A MODIFIER LETTER SMALL DEZH DIGRAPH + # <super> 02A4 +1078B MODIFIER LETTER SMALL D WITH TAIL + # <super> 0256 +1078C MODIFIER LETTER SMALL D WITH HOOK + # <super> 0257 +1078D MODIFIER LETTER SMALL D WITH HOOK AND TAIL + # <super> 1D91 +1078E MODIFIER LETTER SMALL REVERSED E + # <super> 0258 +1078F MODIFIER LETTER SMALL CLOSED REVERSED OPEN E + # <super> 025E +10790 MODIFIER LETTER SMALL FENG DIGRAPH + # <super> 02A9 +10791 MODIFIER LETTER SMALL RAMS HORN + # <super> 0264 +10792 MODIFIER LETTER SMALL CAPITAL G + # <super> 0262 +10793 MODIFIER LETTER SMALL G WITH HOOK + # <super> 0260 +10794 MODIFIER LETTER SMALL CAPITAL G WITH HOOK + # <super> 029B +10795 MODIFIER LETTER SMALL H WITH STROKE + # <super> 0127 +10796 MODIFIER LETTER SMALL CAPITAL H + # <super> 029C +10797 MODIFIER LETTER SMALL HENG WITH HOOK + # <super> 0267 +10798 MODIFIER LETTER SMALL DOTLESS J WITH STROKE AND HOOK + # <super> 0284 +10799 MODIFIER LETTER SMALL LS DIGRAPH + # <super> 02AA +1079A MODIFIER LETTER SMALL LZ DIGRAPH + # <super> 02AB +1079B MODIFIER LETTER SMALL L WITH BELT + # <super> 026C +1079C MODIFIER LETTER SMALL CAPITAL L WITH BELT + # <super> 1DF04 +1079D MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT + # <super> A78E +1079E MODIFIER LETTER SMALL LEZH + # <super> 026E +1079F MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK + # <super> 1DF05 +107A0 MODIFIER LETTER SMALL TURNED Y + # <super> 028E +107A1 MODIFIER LETTER SMALL TURNED Y WITH BELT + # <super> 1DF06 +107A2 MODIFIER LETTER SMALL O WITH STROKE + # <super> 00F8 +107A3 MODIFIER LETTER SMALL CAPITAL OE + # <super> 0276 +107A4 MODIFIER LETTER SMALL CLOSED OMEGA + # <super> 0277 +107A5 MODIFIER LETTER SMALL Q + # <super> 0071 +107A6 MODIFIER LETTER SMALL TURNED R WITH LONG LEG + # <super> 027A +107A7 MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK + # <super> 1DF08 +107A8 MODIFIER LETTER SMALL R WITH TAIL + # <super> 027D +107A9 MODIFIER LETTER SMALL R WITH FISHHOOK + # <super> 027E +107AA MODIFIER LETTER SMALL CAPITAL R + # <super> 0280 +107AB MODIFIER LETTER SMALL TC DIGRAPH WITH CURL + # <super> 02A8 +107AC MODIFIER LETTER SMALL TS DIGRAPH + # <super> 02A6 +107AD MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK + # <super> AB67 +107AE MODIFIER LETTER SMALL TESH DIGRAPH + # <super> 02A7 +107AF MODIFIER LETTER SMALL T WITH RETROFLEX HOOK + # <super> 0288 +107B0 MODIFIER LETTER SMALL V WITH RIGHT HOOK + # <super> 2C71 +107B2 MODIFIER LETTER SMALL CAPITAL Y + # <super> 028F +107B3 MODIFIER LETTER GLOTTAL STOP WITH STROKE + # <super> 02A1 +107B4 MODIFIER LETTER REVERSED GLOTTAL STOP WITH STROKE + # <super> 02A2 +107B5 MODIFIER LETTER BILABIAL CLICK + # <super> 0298 +107B6 MODIFIER LETTER DENTAL CLICK + # <super> 01C0 +107B7 MODIFIER LETTER LATERAL CLICK + # <super> 01C1 +107B8 MODIFIER LETTER ALVEOLAR CLICK + # <super> 01C2 +107B9 MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK + # <super> 1DF0A +107BA MODIFIER LETTER SMALL S WITH CURL + # <super> 1DF1E @@ 10800 Cypriot Syllabary 1083F @ Syllables 10800 CYPRIOT SYLLABLE A @@ -32120,6 +32754,37 @@ FFFF <not a character> 10F57 SOGDIAN PUNCTUATION CIRCLE WITH DOT 10F58 SOGDIAN PUNCTUATION TWO CIRCLES WITH DOTS 10F59 SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +@@ 10F70 Old Uyghur 10FAF +@ Letters +10F70 OLD UYGHUR LETTER ALEPH +10F71 OLD UYGHUR LETTER BETH +10F72 OLD UYGHUR LETTER GIMEL-HETH +10F73 OLD UYGHUR LETTER WAW +10F74 OLD UYGHUR LETTER ZAYIN +10F75 OLD UYGHUR LETTER FINAL HETH +10F76 OLD UYGHUR LETTER YODH +10F77 OLD UYGHUR LETTER KAPH +10F78 OLD UYGHUR LETTER LAMEDH +10F79 OLD UYGHUR LETTER MEM +10F7A OLD UYGHUR LETTER NUN +10F7B OLD UYGHUR LETTER SAMEKH +10F7C OLD UYGHUR LETTER PE +10F7D OLD UYGHUR LETTER SADHE +10F7E OLD UYGHUR LETTER RESH +10F7F OLD UYGHUR LETTER SHIN +10F80 OLD UYGHUR LETTER TAW +10F81 OLD UYGHUR LETTER LESH + = hooked resh +@ Combining signs +10F82 OLD UYGHUR COMBINING DOT ABOVE +10F83 OLD UYGHUR COMBINING DOT BELOW +10F84 OLD UYGHUR COMBINING TWO DOTS ABOVE +10F85 OLD UYGHUR COMBINING TWO DOTS BELOW +@ Punctuation +10F86 OLD UYGHUR PUNCTUATION BAR +10F87 OLD UYGHUR PUNCTUATION TWO BARS +10F88 OLD UYGHUR PUNCTUATION TWO DOTS +10F89 OLD UYGHUR PUNCTUATION FOUR DOTS @@ 10FB0 Chorasmian 10FDF @+ This script is also known as 'Khwarezmian', from its classical Persian name xvārazm. @ Letters @@ -32296,6 +32961,17 @@ FFFF <not a character> 1106D BRAHMI DIGIT SEVEN 1106E BRAHMI DIGIT EIGHT 1106F BRAHMI DIGIT NINE +@ Virama +@+ The Old Tamil virama and the other Old Tamil characters below are extensions used in Brahmi when writing Old Tamil. +11070 BRAHMI SIGN OLD TAMIL VIRAMA +@ Independent vowels +11071 BRAHMI LETTER OLD TAMIL SHORT E +11072 BRAHMI LETTER OLD TAMIL SHORT O +@ Dependent vowel signs +11073 BRAHMI VOWEL SIGN OLD TAMIL SHORT E +11074 BRAHMI VOWEL SIGN OLD TAMIL SHORT O +@ Consonant +11075 BRAHMI LETTER OLD TAMIL LLA @ Number joiner 1107F BRAHMI NUMBER JOINER * a virama used to form ligatures between Brahmi numbers signifying multiplication @@ -32382,6 +33058,8 @@ FFFF <not a character> x (khojki double section mark - 1123C) 110C0 KAITHI DANDA 110C1 KAITHI DOUBLE DANDA +@ Vowel sign +110C2 KAITHI VOWEL SIGN VOCALIC R @ Sign 110CD KAITHI NUMBER SIGN ABOVE * used to indicate a number in an itemized list @@ -33544,6 +34222,10 @@ FFFF <not a character> @ Consonant 116B8 TAKRI LETTER ARCHAIC KHA * used in earlier writings to denote kha +@ Punctuation +116B9 TAKRI ABBREVIATION SIGN + x (gurmukhi abbreviation sign - 0A76) + x (sharada abbreviation sign - 111C7) @ Digits 116C0 TAKRI DIGIT ZERO 116C1 TAKRI DIGIT ONE @@ -33555,7 +34237,7 @@ FFFF <not a character> 116C7 TAKRI DIGIT SEVEN 116C8 TAKRI DIGIT EIGHT 116C9 TAKRI DIGIT NINE -@@ 11700 Ahom 1173F +@@ 11700 Ahom 1174F @ Consonants 11700 AHOM LETTER KA 11701 AHOM LETTER KHA @@ -33620,6 +34302,14 @@ FFFF <not a character> 1173D AHOM SIGN SECTION 1173E AHOM SIGN RULAI 1173F AHOM SYMBOL VI +@ Additional consonants +11740 AHOM LETTER CA +11741 AHOM LETTER TTA +11742 AHOM LETTER TTHA +11743 AHOM LETTER DDA +11744 AHOM LETTER DDHA +11745 AHOM LETTER NNA +11746 AHOM LETTER LLA @@ 11800 Dogra 1184F @ Independent vowels 11800 DOGRA LETTER A @@ -34181,6 +34871,29 @@ FFFF <not a character> 11AA1 SOYOMBO TERMINAL MARK-1 11AA2 SOYOMBO TERMINAL MARK-2 = cintamani, candamani +@@ 11AB0 Unified Canadian Aboriginal Syllabics Extended-A 11ABF +@ Syllables for Nattilik +11AB0 CANADIAN SYLLABICS NATTILIK HI +11AB1 CANADIAN SYLLABICS NATTILIK HII +11AB2 CANADIAN SYLLABICS NATTILIK HO + * Nattilik (HU) +11AB3 CANADIAN SYLLABICS NATTILIK HOO + * Nattilik (HUU) +11AB4 CANADIAN SYLLABICS NATTILIK HA +11AB5 CANADIAN SYLLABICS NATTILIK HAA +11AB6 CANADIAN SYLLABICS NATTILIK SHRI +11AB7 CANADIAN SYLLABICS NATTILIK SHRII +11AB8 CANADIAN SYLLABICS NATTILIK SHRO + * Nattilik (SHRU) +11AB9 CANADIAN SYLLABICS NATTILIK SHROO + * Nattilik (SHRUU) +11ABA CANADIAN SYLLABICS NATTILIK SHRA +11ABB CANADIAN SYLLABICS NATTILIK SHRAA +@ Historic syllables for Cree and Ojibway +11ABC CANADIAN SYLLABICS SPE +11ABD CANADIAN SYLLABICS SPI +11ABE CANADIAN SYLLABICS SPO +11ABF CANADIAN SYLLABICS SPA @@ 11AC0 Pau Cin Hau 11AFF @ Consonants 11AC0 PAU CIN HAU LETTER PA @@ -36005,6 +36718,108 @@ FFFF <not a character> 12541 CUNEIFORM SIGN ZA7 12542 CUNEIFORM SIGN ZU OVER ZU PLUS SAR 12543 CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +@@ 12F90 Cypro-Minoan 12FFF +@ Signs +12F90 CYPRO-MINOAN SIGN CM001 +12F91 CYPRO-MINOAN SIGN CM002 +12F92 CYPRO-MINOAN SIGN CM004 +12F93 CYPRO-MINOAN SIGN CM005 +12F94 CYPRO-MINOAN SIGN CM006 +12F95 CYPRO-MINOAN SIGN CM007 +12F96 CYPRO-MINOAN SIGN CM008 +12F97 CYPRO-MINOAN SIGN CM009 +12F98 CYPRO-MINOAN SIGN CM010 +12F99 CYPRO-MINOAN SIGN CM011 +12F9A CYPRO-MINOAN SIGN CM012 +12F9B CYPRO-MINOAN SIGN CM012B +12F9C CYPRO-MINOAN SIGN CM013 +12F9D CYPRO-MINOAN SIGN CM015 +12F9E CYPRO-MINOAN SIGN CM017 +12F9F CYPRO-MINOAN SIGN CM019 +12FA0 CYPRO-MINOAN SIGN CM021 +12FA1 CYPRO-MINOAN SIGN CM023 +12FA2 CYPRO-MINOAN SIGN CM024 +12FA3 CYPRO-MINOAN SIGN CM025 +12FA4 CYPRO-MINOAN SIGN CM026 +12FA5 CYPRO-MINOAN SIGN CM027 +12FA6 CYPRO-MINOAN SIGN CM028 +12FA7 CYPRO-MINOAN SIGN CM029 +12FA8 CYPRO-MINOAN SIGN CM030 +12FA9 CYPRO-MINOAN SIGN CM033 +12FAA CYPRO-MINOAN SIGN CM034 +12FAB CYPRO-MINOAN SIGN CM035 +12FAC CYPRO-MINOAN SIGN CM036 +12FAD CYPRO-MINOAN SIGN CM037 +12FAE CYPRO-MINOAN SIGN CM038 +12FAF CYPRO-MINOAN SIGN CM039 +12FB0 CYPRO-MINOAN SIGN CM040 +12FB1 CYPRO-MINOAN SIGN CM041 +12FB2 CYPRO-MINOAN SIGN CM044 +12FB3 CYPRO-MINOAN SIGN CM046 +12FB4 CYPRO-MINOAN SIGN CM047 +12FB5 CYPRO-MINOAN SIGN CM049 +12FB6 CYPRO-MINOAN SIGN CM050 +12FB7 CYPRO-MINOAN SIGN CM051 +12FB8 CYPRO-MINOAN SIGN CM052 +12FB9 CYPRO-MINOAN SIGN CM053 +12FBA CYPRO-MINOAN SIGN CM054 +12FBB CYPRO-MINOAN SIGN CM055 +12FBC CYPRO-MINOAN SIGN CM056 +12FBD CYPRO-MINOAN SIGN CM058 +12FBE CYPRO-MINOAN SIGN CM059 +12FBF CYPRO-MINOAN SIGN CM060 +12FC0 CYPRO-MINOAN SIGN CM061 +12FC1 CYPRO-MINOAN SIGN CM062 +12FC2 CYPRO-MINOAN SIGN CM063 +12FC3 CYPRO-MINOAN SIGN CM064 +12FC4 CYPRO-MINOAN SIGN CM066 +12FC5 CYPRO-MINOAN SIGN CM067 +12FC6 CYPRO-MINOAN SIGN CM068 +12FC7 CYPRO-MINOAN SIGN CM069 +12FC8 CYPRO-MINOAN SIGN CM070 +12FC9 CYPRO-MINOAN SIGN CM071 +12FCA CYPRO-MINOAN SIGN CM072 +12FCB CYPRO-MINOAN SIGN CM073 +12FCC CYPRO-MINOAN SIGN CM074 +12FCD CYPRO-MINOAN SIGN CM075 +12FCE CYPRO-MINOAN SIGN CM075B +12FCF CYPRO-MINOAN SIGN CM076 +12FD0 CYPRO-MINOAN SIGN CM078 +12FD1 CYPRO-MINOAN SIGN CM079 +12FD2 CYPRO-MINOAN SIGN CM080 +12FD3 CYPRO-MINOAN SIGN CM081 +12FD4 CYPRO-MINOAN SIGN CM082 +12FD5 CYPRO-MINOAN SIGN CM083 +12FD6 CYPRO-MINOAN SIGN CM084 +12FD7 CYPRO-MINOAN SIGN CM085 +12FD8 CYPRO-MINOAN SIGN CM086 +12FD9 CYPRO-MINOAN SIGN CM087 +12FDA CYPRO-MINOAN SIGN CM088 +12FDB CYPRO-MINOAN SIGN CM089 +12FDC CYPRO-MINOAN SIGN CM090 +12FDD CYPRO-MINOAN SIGN CM091 +12FDE CYPRO-MINOAN SIGN CM092 +12FDF CYPRO-MINOAN SIGN CM094 +12FE0 CYPRO-MINOAN SIGN CM095 +12FE1 CYPRO-MINOAN SIGN CM096 +12FE2 CYPRO-MINOAN SIGN CM097 +12FE3 CYPRO-MINOAN SIGN CM098 +12FE4 CYPRO-MINOAN SIGN CM099 +12FE5 CYPRO-MINOAN SIGN CM100 +12FE6 CYPRO-MINOAN SIGN CM101 +12FE7 CYPRO-MINOAN SIGN CM102 +12FE8 CYPRO-MINOAN SIGN CM103 +12FE9 CYPRO-MINOAN SIGN CM104 +12FEA CYPRO-MINOAN SIGN CM105 +12FEB CYPRO-MINOAN SIGN CM107 +12FEC CYPRO-MINOAN SIGN CM108 +12FED CYPRO-MINOAN SIGN CM109 +12FEE CYPRO-MINOAN SIGN CM110 +12FEF CYPRO-MINOAN SIGN CM112 +12FF0 CYPRO-MINOAN SIGN CM114 +@ Punctuation +12FF1 CYPRO-MINOAN SIGN CM301 +12FF2 CYPRO-MINOAN SIGN CM302 @@ 13000 Egyptian Hieroglyphs 1342F @+ The characters in this block are taken primarily from Alan Gardiner's works on Middle Egyptian. @ A. Man and his occupations @@ -36104,7 +36919,9 @@ FFFF <not a character> 1305B EGYPTIAN HIEROGLYPH C002 1305C EGYPTIAN HIEROGLYPH C002A 1305D EGYPTIAN HIEROGLYPH C002B + * mirrored version of 1305C 1305E EGYPTIAN HIEROGLYPH C002C + * mirrored version of 1305B 1305F EGYPTIAN HIEROGLYPH C003 13060 EGYPTIAN HIEROGLYPH C004 13061 EGYPTIAN HIEROGLYPH C005 @@ -36118,8 +36935,10 @@ FFFF <not a character> * 1,000,000 13069 EGYPTIAN HIEROGLYPH C012 1306A EGYPTIAN HIEROGLYPH C013 + * mirrored version of 13069 1306B EGYPTIAN HIEROGLYPH C014 1306C EGYPTIAN HIEROGLYPH C015 + * mirrored version of 1306B 1306D EGYPTIAN HIEROGLYPH C016 1306E EGYPTIAN HIEROGLYPH C017 1306F EGYPTIAN HIEROGLYPH C018 @@ -36144,6 +36963,8 @@ FFFF <not a character> 13081 EGYPTIAN HIEROGLYPH D011 * 1/2 13082 EGYPTIAN HIEROGLYPH D012 + * pupil of the eye + * not to be confused with 131F3 or 133F8 * 1/4 13083 EGYPTIAN HIEROGLYPH D013 * 1/8 @@ -36158,6 +36979,8 @@ FFFF <not a character> 13089 EGYPTIAN HIEROGLYPH D019 1308A EGYPTIAN HIEROGLYPH D020 1308B EGYPTIAN HIEROGLYPH D021 + * mouth + * not to be confused with 133AB * transliterated as r 1308C EGYPTIAN HIEROGLYPH D022 1308D EGYPTIAN HIEROGLYPH D023 @@ -36197,6 +37020,8 @@ FFFF <not a character> 130AB EGYPTIAN HIEROGLYPH D048A 130AC EGYPTIAN HIEROGLYPH D049 130AD EGYPTIAN HIEROGLYPH D050 + * classifier 'accurate, finger' + * not to be confused with 130B7 * 10,000 130AE EGYPTIAN HIEROGLYPH D050A * 20,000 @@ -36217,12 +37042,16 @@ FFFF <not a character> 130B6 EGYPTIAN HIEROGLYPH D050I * 50,000 130B7 EGYPTIAN HIEROGLYPH D051 + * classifier 'measure, nail, scratching, taking' + * not to be confused with 130AD 130B8 EGYPTIAN HIEROGLYPH D052 130B9 EGYPTIAN HIEROGLYPH D052A 130BA EGYPTIAN HIEROGLYPH D053 130BB EGYPTIAN HIEROGLYPH D054 + * (forward) motion 130BC EGYPTIAN HIEROGLYPH D054A 130BD EGYPTIAN HIEROGLYPH D055 + * backward motion 130BE EGYPTIAN HIEROGLYPH D056 130BF EGYPTIAN HIEROGLYPH D057 130C0 EGYPTIAN HIEROGLYPH D058 @@ -36237,6 +37066,7 @@ FFFF <not a character> 130C8 EGYPTIAN HIEROGLYPH D066 130C9 EGYPTIAN HIEROGLYPH D067 * 1 heqat measure + * not to be confused with 13212 130CA EGYPTIAN HIEROGLYPH D067A * 2 heqat measures 130CB EGYPTIAN HIEROGLYPH D067B @@ -36255,7 +37085,10 @@ FFFF <not a character> * 9 heqat measures @ E. Mammals 130D2 EGYPTIAN HIEROGLYPH E001 + * bull, classifier 'cattle' + * not to be confused with 130FD 130D3 EGYPTIAN HIEROGLYPH E002 + * aggressive bull 130D4 EGYPTIAN HIEROGLYPH E003 130D5 EGYPTIAN HIEROGLYPH E004 130D6 EGYPTIAN HIEROGLYPH E005 @@ -36295,9 +37128,12 @@ FFFF <not a character> 130F8 EGYPTIAN HIEROGLYPH E033 130F9 EGYPTIAN HIEROGLYPH E034 130FA EGYPTIAN HIEROGLYPH E034A + * stylistic variant, use of 130F9 is preferred 130FB EGYPTIAN HIEROGLYPH E036 130FC EGYPTIAN HIEROGLYPH E037 130FD EGYPTIAN HIEROGLYPH E038 + * cow + * not to be confused with 130D2 @ F. Parts of mammals 130FE EGYPTIAN HIEROGLYPH F001 130FF EGYPTIAN HIEROGLYPH F001A @@ -36314,6 +37150,7 @@ FFFF <not a character> 1310A EGYPTIAN HIEROGLYPH F012 1310B EGYPTIAN HIEROGLYPH F013 1310C EGYPTIAN HIEROGLYPH F013A + * stylistic variant, use of 1310B is preferred 1310D EGYPTIAN HIEROGLYPH F014 1310E EGYPTIAN HIEROGLYPH F015 1310F EGYPTIAN HIEROGLYPH F016 @@ -36323,9 +37160,11 @@ FFFF <not a character> 13113 EGYPTIAN HIEROGLYPH F020 13114 EGYPTIAN HIEROGLYPH F021 13115 EGYPTIAN HIEROGLYPH F021A + * from hieratic 13116 EGYPTIAN HIEROGLYPH F022 13117 EGYPTIAN HIEROGLYPH F023 13118 EGYPTIAN HIEROGLYPH F024 + * mirrored version of 13117 13119 EGYPTIAN HIEROGLYPH F025 1311A EGYPTIAN HIEROGLYPH F026 1311B EGYPTIAN HIEROGLYPH F027 @@ -36334,6 +37173,7 @@ FFFF <not a character> 1311E EGYPTIAN HIEROGLYPH F030 1311F EGYPTIAN HIEROGLYPH F031 13120 EGYPTIAN HIEROGLYPH F031A + * cursive variant of 1311F 13121 EGYPTIAN HIEROGLYPH F032 * transliterated as 1E96 13122 EGYPTIAN HIEROGLYPH F033 @@ -36354,25 +37194,35 @@ FFFF <not a character> 13131 EGYPTIAN HIEROGLYPH F045A 13132 EGYPTIAN HIEROGLYPH F046 13133 EGYPTIAN HIEROGLYPH F046A + * rotated version of 13132 13134 EGYPTIAN HIEROGLYPH F047 + * mirrored version of 13132 13135 EGYPTIAN HIEROGLYPH F047A + * mirrored version of 13133 13136 EGYPTIAN HIEROGLYPH F048 13137 EGYPTIAN HIEROGLYPH F049 + * mirrored version of 13136 13138 EGYPTIAN HIEROGLYPH F050 13139 EGYPTIAN HIEROGLYPH F051 1313A EGYPTIAN HIEROGLYPH F051A 1313B EGYPTIAN HIEROGLYPH F051B + * variant of 1313A 1313C EGYPTIAN HIEROGLYPH F051C + * rotated version of 13139 1313D EGYPTIAN HIEROGLYPH F052 1313E EGYPTIAN HIEROGLYPH F053 @ G. Birds 1313F EGYPTIAN HIEROGLYPH G001 + * Egyptian vulture, Egyptological alef + * not to be confused with 13142 * transliterated as A723 x (hebrew letter alef - 05D0) x (arabic letter alef with hamza above - 0623) 13140 EGYPTIAN HIEROGLYPH G002 13141 EGYPTIAN HIEROGLYPH G003 13142 EGYPTIAN HIEROGLYPH G004 + * phonogram 'tw' + * not to be confused with 1313F 13143 EGYPTIAN HIEROGLYPH G005 13144 EGYPTIAN HIEROGLYPH G006 13145 EGYPTIAN HIEROGLYPH G006A @@ -36413,10 +37263,14 @@ FFFF <not a character> 13167 EGYPTIAN HIEROGLYPH G035 13168 EGYPTIAN HIEROGLYPH G036 13169 EGYPTIAN HIEROGLYPH G036A + * stylistic variant, use of 13168 is preferred 1316A EGYPTIAN HIEROGLYPH G037 1316B EGYPTIAN HIEROGLYPH G037A + * stylistic variant, use of 1316A is preferred 1316C EGYPTIAN HIEROGLYPH G038 + * goose 1316D EGYPTIAN HIEROGLYPH G039 + * duck 1316E EGYPTIAN HIEROGLYPH G040 1316F EGYPTIAN HIEROGLYPH G041 13170 EGYPTIAN HIEROGLYPH G042 @@ -36443,6 +37297,7 @@ FFFF <not a character> 13183 EGYPTIAN HIEROGLYPH H005 13184 EGYPTIAN HIEROGLYPH H006 13185 EGYPTIAN HIEROGLYPH H006A + * from hieratic 13186 EGYPTIAN HIEROGLYPH H007 13187 EGYPTIAN HIEROGLYPH H008 @ I. Amphibious animals, reptiles, etc. @@ -36477,7 +37332,7 @@ FFFF <not a character> 131A0 EGYPTIAN HIEROGLYPH K006 131A1 EGYPTIAN HIEROGLYPH K007 131A2 EGYPTIAN HIEROGLYPH K008 -@ L. Invertabrata and lesser animals +@ L. Invertebrata and lesser animals 131A3 EGYPTIAN HIEROGLYPH L001 131A4 EGYPTIAN HIEROGLYPH L002 131A5 EGYPTIAN HIEROGLYPH L002A @@ -36486,6 +37341,7 @@ FFFF <not a character> 131A8 EGYPTIAN HIEROGLYPH L005 131A9 EGYPTIAN HIEROGLYPH L006 131AA EGYPTIAN HIEROGLYPH L006A + * mirrored version of 131A9 131AB EGYPTIAN HIEROGLYPH L007 131AC EGYPTIAN HIEROGLYPH L008 @ M. Trees and plants @@ -36529,18 +37385,21 @@ FFFF <not a character> 131C9 EGYPTIAN HIEROGLYPH M016 131CA EGYPTIAN HIEROGLYPH M016A 131CB EGYPTIAN HIEROGLYPH M017 - * yod + * egyptological yod + * transliterated as A7BD x (hebrew letter yod - 05D9) x (arabic letter yeh - 064A) 131CC EGYPTIAN HIEROGLYPH M017A - * transliterated as y + * phonogram 'y' x (egyptian hieroglyph z004 - 133ED) 131CD EGYPTIAN HIEROGLYPH M018 131CE EGYPTIAN HIEROGLYPH M019 131CF EGYPTIAN HIEROGLYPH M020 131D0 EGYPTIAN HIEROGLYPH M021 131D1 EGYPTIAN HIEROGLYPH M022 + * classifier 'bud, lotus bud' 131D2 EGYPTIAN HIEROGLYPH M022A + *phonogram 'nn' 131D3 EGYPTIAN HIEROGLYPH M023 131D4 EGYPTIAN HIEROGLYPH M024 131D5 EGYPTIAN HIEROGLYPH M024A @@ -36556,30 +37415,42 @@ FFFF <not a character> 131DF EGYPTIAN HIEROGLYPH M032 131E0 EGYPTIAN HIEROGLYPH M033 131E1 EGYPTIAN HIEROGLYPH M033A + * variant of 131E0 131E2 EGYPTIAN HIEROGLYPH M033B + * variant of 131E0 131E3 EGYPTIAN HIEROGLYPH M034 131E4 EGYPTIAN HIEROGLYPH M035 131E5 EGYPTIAN HIEROGLYPH M036 131E6 EGYPTIAN HIEROGLYPH M037 + * older variant of 131E5 131E7 EGYPTIAN HIEROGLYPH M038 131E8 EGYPTIAN HIEROGLYPH M039 131E9 EGYPTIAN HIEROGLYPH M040 + * phonogram 'js' + * not to be confused with 132A7 or 1342A 131EA EGYPTIAN HIEROGLYPH M040A 131EB EGYPTIAN HIEROGLYPH M041 131EC EGYPTIAN HIEROGLYPH M042 131ED EGYPTIAN HIEROGLYPH M043 131EE EGYPTIAN HIEROGLYPH M044 + * thorn + * not to be confused with 133DA @ N. Sky, earth, water 131EF EGYPTIAN HIEROGLYPH N001 131F0 EGYPTIAN HIEROGLYPH N002 131F1 EGYPTIAN HIEROGLYPH N003 + * older variant of 131F0 131F2 EGYPTIAN HIEROGLYPH N004 131F3 EGYPTIAN HIEROGLYPH N005 + * sun + * not to be confused with 13082 or 133F8 131F4 EGYPTIAN HIEROGLYPH N006 131F5 EGYPTIAN HIEROGLYPH N007 131F6 EGYPTIAN HIEROGLYPH N008 131F7 EGYPTIAN HIEROGLYPH N009 + * variant of 131F8 131F8 EGYPTIAN HIEROGLYPH N010 + * variant of 131F7 131F9 EGYPTIAN HIEROGLYPH N011 131FA EGYPTIAN HIEROGLYPH N012 131FB EGYPTIAN HIEROGLYPH N013 @@ -36587,10 +37458,15 @@ FFFF <not a character> 131FD EGYPTIAN HIEROGLYPH N015 131FE EGYPTIAN HIEROGLYPH N016 131FF EGYPTIAN HIEROGLYPH N017 + * land + * variant of 131FE 13200 EGYPTIAN HIEROGLYPH N018 + * island + * not to be confused with 132F0, 133D4, or 133F3 13201 EGYPTIAN HIEROGLYPH N018A 13202 EGYPTIAN HIEROGLYPH N018B 13203 EGYPTIAN HIEROGLYPH N019 + * logogram 'akhti' 13204 EGYPTIAN HIEROGLYPH N020 13205 EGYPTIAN HIEROGLYPH N021 13206 EGYPTIAN HIEROGLYPH N022 @@ -36598,10 +37474,13 @@ FFFF <not a character> 13208 EGYPTIAN HIEROGLYPH N024 13209 EGYPTIAN HIEROGLYPH N025 1320A EGYPTIAN HIEROGLYPH N025A + * stylistic variant, use of 13209 is preferred 1320B EGYPTIAN HIEROGLYPH N026 1320C EGYPTIAN HIEROGLYPH N027 1320D EGYPTIAN HIEROGLYPH N028 1320E EGYPTIAN HIEROGLYPH N029 + * hill + * not to be confused with 133D8 * transliterated as q or as 1E33 x (hebrew letter qof - 05E7) x (arabic letter qaf - 0642) @@ -36609,21 +37488,33 @@ FFFF <not a character> 13210 EGYPTIAN HIEROGLYPH N031 13211 EGYPTIAN HIEROGLYPH N032 13212 EGYPTIAN HIEROGLYPH N033 + * classifier 'granule, grain' + * not to be confused with 130C9 13213 EGYPTIAN HIEROGLYPH N033A + * classifier 'granules, grains' + * not to be confused with 133E7 13214 EGYPTIAN HIEROGLYPH N034 13215 EGYPTIAN HIEROGLYPH N034A + * stylistic variant, use of 13214 is preferred 13216 EGYPTIAN HIEROGLYPH N035 * transliterated as n 13217 EGYPTIAN HIEROGLYPH N035A + * classifier 'liquid' 13218 EGYPTIAN HIEROGLYPH N036 13219 EGYPTIAN HIEROGLYPH N037 + * lake * transliterated as 0161 + * not to be confused with 1328C 1321A EGYPTIAN HIEROGLYPH N037A + * variant of 13219 1321B EGYPTIAN HIEROGLYPH N038 + * variant of 13219 1321C EGYPTIAN HIEROGLYPH N039 + * variant of 13219 1321D EGYPTIAN HIEROGLYPH N040 1321E EGYPTIAN HIEROGLYPH N041 1321F EGYPTIAN HIEROGLYPH N042 + * variant of 1321E @ NL. Nomes of Lower Egypt 13220 EGYPTIAN HIEROGLYPH NL001 13221 EGYPTIAN HIEROGLYPH NL002 @@ -36685,6 +37576,7 @@ FFFF <not a character> x (arabic letter heh - 0647) 13255 EGYPTIAN HIEROGLYPH O005 13256 EGYPTIAN HIEROGLYPH O005A + * mirrored version of 13255 13257 EGYPTIAN HIEROGLYPH O006 13258 EGYPTIAN HIEROGLYPH O006A * beginning of hwt or serekh enclosure @@ -36730,11 +37622,15 @@ FFFF <not a character> 1327A EGYPTIAN HIEROGLYPH O028 1327B EGYPTIAN HIEROGLYPH O029 1327C EGYPTIAN HIEROGLYPH O029A + * rotated variant of 1327B 1327D EGYPTIAN HIEROGLYPH O030 + * supporting pole + * not to be confused with 13361 1327E EGYPTIAN HIEROGLYPH O030A 1327F EGYPTIAN HIEROGLYPH O031 13280 EGYPTIAN HIEROGLYPH O032 13281 EGYPTIAN HIEROGLYPH O033 + * classifier 'serekh' 13282 EGYPTIAN HIEROGLYPH O033A * end of serekh enclosure x (egyptian hieroglyph o006a - 13258) @@ -36754,10 +37650,13 @@ FFFF <not a character> 1328A EGYPTIAN HIEROGLYPH O037 1328B EGYPTIAN HIEROGLYPH O038 1328C EGYPTIAN HIEROGLYPH O039 + * stone, brick + * not to be confused with 13219 1328D EGYPTIAN HIEROGLYPH O040 1328E EGYPTIAN HIEROGLYPH O041 1328F EGYPTIAN HIEROGLYPH O042 13290 EGYPTIAN HIEROGLYPH O043 + * older variant of 1328F 13291 EGYPTIAN HIEROGLYPH O044 13292 EGYPTIAN HIEROGLYPH O045 13293 EGYPTIAN HIEROGLYPH O046 @@ -36767,13 +37666,18 @@ FFFF <not a character> 13297 EGYPTIAN HIEROGLYPH O050 13298 EGYPTIAN HIEROGLYPH O050A 13299 EGYPTIAN HIEROGLYPH O050B + * mirrored version of 13298 1329A EGYPTIAN HIEROGLYPH O051 @ P. Ships and parts of ships 1329B EGYPTIAN HIEROGLYPH P001 + * classifier 'ship, travel' 1329C EGYPTIAN HIEROGLYPH P001A + * classifier 'upset, overturn' 1329D EGYPTIAN HIEROGLYPH P002 1329E EGYPTIAN HIEROGLYPH P003 + * sacred ship 1329F EGYPTIAN HIEROGLYPH P003A + * mirrored variant of 1329E 132A0 EGYPTIAN HIEROGLYPH P004 132A1 EGYPTIAN HIEROGLYPH P005 132A2 EGYPTIAN HIEROGLYPH P006 @@ -36782,6 +37686,8 @@ FFFF <not a character> 132A5 EGYPTIAN HIEROGLYPH P009 132A6 EGYPTIAN HIEROGLYPH P010 132A7 EGYPTIAN HIEROGLYPH P011 + * mooring post + * not to be confused with 131E9 or 1342A @ Q. Domestic and funerary furniture 132A8 EGYPTIAN HIEROGLYPH Q001 132A9 EGYPTIAN HIEROGLYPH Q002 @@ -36859,6 +37765,8 @@ FFFF <not a character> 132EE EGYPTIAN HIEROGLYPH S025 132EF EGYPTIAN HIEROGLYPH S026 132F0 EGYPTIAN HIEROGLYPH S026A + * loin-cloth + * not to be confused with 13200, 133D4, or 133F3 132F1 EGYPTIAN HIEROGLYPH S026B 132F2 EGYPTIAN HIEROGLYPH S027 132F3 EGYPTIAN HIEROGLYPH S028 @@ -36872,12 +37780,16 @@ FFFF <not a character> 132F9 EGYPTIAN HIEROGLYPH S034 132FA EGYPTIAN HIEROGLYPH S035 132FB EGYPTIAN HIEROGLYPH S035A + * variant of 132FA 132FC EGYPTIAN HIEROGLYPH S036 + * older variant of 132FA 132FD EGYPTIAN HIEROGLYPH S037 132FE EGYPTIAN HIEROGLYPH S038 132FF EGYPTIAN HIEROGLYPH S039 13300 EGYPTIAN HIEROGLYPH S040 + * phonogram 'wꜣs' 13301 EGYPTIAN HIEROGLYPH S041 + * phonogram 'ḏꜣm' 13302 EGYPTIAN HIEROGLYPH S042 13303 EGYPTIAN HIEROGLYPH S043 13304 EGYPTIAN HIEROGLYPH S044 @@ -36886,7 +37798,9 @@ FFFF <not a character> @ T. Warfare, hunting, butchery 13307 EGYPTIAN HIEROGLYPH T001 13308 EGYPTIAN HIEROGLYPH T002 + * classifier 'striking, hitting' 13309 EGYPTIAN HIEROGLYPH T003 + * classifier 'mace' 1330A EGYPTIAN HIEROGLYPH T003A 1330B EGYPTIAN HIEROGLYPH T004 1330C EGYPTIAN HIEROGLYPH T005 @@ -36894,9 +37808,11 @@ FFFF <not a character> 1330E EGYPTIAN HIEROGLYPH T007 1330F EGYPTIAN HIEROGLYPH T007A 13310 EGYPTIAN HIEROGLYPH T008 + * older variant of 13311 13311 EGYPTIAN HIEROGLYPH T008A 13312 EGYPTIAN HIEROGLYPH T009 13313 EGYPTIAN HIEROGLYPH T009A + * older variant of 13312 13314 EGYPTIAN HIEROGLYPH T010 13315 EGYPTIAN HIEROGLYPH T011 13316 EGYPTIAN HIEROGLYPH T011A @@ -36904,41 +37820,55 @@ FFFF <not a character> 13318 EGYPTIAN HIEROGLYPH T013 13319 EGYPTIAN HIEROGLYPH T014 1331A EGYPTIAN HIEROGLYPH T015 + * older variant of 13319 1331B EGYPTIAN HIEROGLYPH T016 1331C EGYPTIAN HIEROGLYPH T016A 1331D EGYPTIAN HIEROGLYPH T017 1331E EGYPTIAN HIEROGLYPH T018 1331F EGYPTIAN HIEROGLYPH T019 13320 EGYPTIAN HIEROGLYPH T020 + * older variant of 1331F 13321 EGYPTIAN HIEROGLYPH T021 13322 EGYPTIAN HIEROGLYPH T022 13323 EGYPTIAN HIEROGLYPH T023 + * more recent variant of 13322 13324 EGYPTIAN HIEROGLYPH T024 13325 EGYPTIAN HIEROGLYPH T025 13326 EGYPTIAN HIEROGLYPH T026 13327 EGYPTIAN HIEROGLYPH T027 + * older variant of 13326 13328 EGYPTIAN HIEROGLYPH T028 13329 EGYPTIAN HIEROGLYPH T029 1332A EGYPTIAN HIEROGLYPH T030 + * classifier 'knife, cutting' 1332B EGYPTIAN HIEROGLYPH T031 + * phonogram 'sšm' 1332C EGYPTIAN HIEROGLYPH T032 1332D EGYPTIAN HIEROGLYPH T032A 1332E EGYPTIAN HIEROGLYPH T033 + * older variant of 13326 1332F EGYPTIAN HIEROGLYPH T033A 13330 EGYPTIAN HIEROGLYPH T034 13331 EGYPTIAN HIEROGLYPH T035 + * variant of 13330 13332 EGYPTIAN HIEROGLYPH T036 @ U. Agriculture, crafts, and professions 13333 EGYPTIAN HIEROGLYPH U001 13334 EGYPTIAN HIEROGLYPH U002 + * stylistic variant of 13333 13335 EGYPTIAN HIEROGLYPH U003 13336 EGYPTIAN HIEROGLYPH U004 13337 EGYPTIAN HIEROGLYPH U005 + * stylistic variant of 13336 13338 EGYPTIAN HIEROGLYPH U006 13339 EGYPTIAN HIEROGLYPH U006A + * stylistic variant of 13338 1333A EGYPTIAN HIEROGLYPH U006B + * mirrored version of 13339 1333B EGYPTIAN HIEROGLYPH U007 + * variant of 13338 1333C EGYPTIAN HIEROGLYPH U008 + * variant of 1333B 1333D EGYPTIAN HIEROGLYPH U009 1333E EGYPTIAN HIEROGLYPH U010 1333F EGYPTIAN HIEROGLYPH U011 @@ -36949,18 +37879,24 @@ FFFF <not a character> 13344 EGYPTIAN HIEROGLYPH U016 13345 EGYPTIAN HIEROGLYPH U017 13346 EGYPTIAN HIEROGLYPH U018 + * variant of 13345 13347 EGYPTIAN HIEROGLYPH U019 13348 EGYPTIAN HIEROGLYPH U020 + * older variant of 13347 13349 EGYPTIAN HIEROGLYPH U021 1334A EGYPTIAN HIEROGLYPH U022 1334B EGYPTIAN HIEROGLYPH U023 1334C EGYPTIAN HIEROGLYPH U023A + * stylistic variant of 1334B 1334D EGYPTIAN HIEROGLYPH U024 1334E EGYPTIAN HIEROGLYPH U025 + * older variant of 1334D 1334F EGYPTIAN HIEROGLYPH U026 13350 EGYPTIAN HIEROGLYPH U027 + * older variant of 1334F 13351 EGYPTIAN HIEROGLYPH U028 13352 EGYPTIAN HIEROGLYPH U029 + * older variant of 13351 13353 EGYPTIAN HIEROGLYPH U029A 13354 EGYPTIAN HIEROGLYPH U030 13355 EGYPTIAN HIEROGLYPH U031 @@ -36974,11 +37910,16 @@ FFFF <not a character> 1335D EGYPTIAN HIEROGLYPH U038 1335E EGYPTIAN HIEROGLYPH U039 1335F EGYPTIAN HIEROGLYPH U040 + * cursive variant of 1335E 13360 EGYPTIAN HIEROGLYPH U041 13361 EGYPTIAN HIEROGLYPH U042 + * pitchfork + * not to be confused with 1327D @ V. Rope, fiber, baskets, bags, etc. 13362 EGYPTIAN HIEROGLYPH V001 * 100 + * classifier 'cord, rope' + * not to be confused with 133F2 13363 EGYPTIAN HIEROGLYPH V001A * 200 13364 EGYPTIAN HIEROGLYPH V001B @@ -37003,13 +37944,17 @@ FFFF <not a character> 1336F EGYPTIAN HIEROGLYPH V004 13370 EGYPTIAN HIEROGLYPH V005 13371 EGYPTIAN HIEROGLYPH V006 + * phonogram 'šs' 13372 EGYPTIAN HIEROGLYPH V007 + * phonogram 'šn' 13373 EGYPTIAN HIEROGLYPH V007A 13374 EGYPTIAN HIEROGLYPH V007B 13375 EGYPTIAN HIEROGLYPH V008 13376 EGYPTIAN HIEROGLYPH V009 13377 EGYPTIAN HIEROGLYPH V010 + * logogram 'name' 13378 EGYPTIAN HIEROGLYPH V011 + * classifier 'restrain, split' 13379 EGYPTIAN HIEROGLYPH V011A * beginning of cartouche 1337A EGYPTIAN HIEROGLYPH V011B @@ -37022,15 +37967,19 @@ FFFF <not a character> 1337F EGYPTIAN HIEROGLYPH V013 * transliterated as 1E6F 13380 EGYPTIAN HIEROGLYPH V014 + * variant of 1337F 13381 EGYPTIAN HIEROGLYPH V015 13382 EGYPTIAN HIEROGLYPH V016 13383 EGYPTIAN HIEROGLYPH V017 13384 EGYPTIAN HIEROGLYPH V018 + * older variant of 13383 13385 EGYPTIAN HIEROGLYPH V019 13386 EGYPTIAN HIEROGLYPH V020 * 10 + * not to be confused with 133AD 13387 EGYPTIAN HIEROGLYPH V020A * 20 + * not to be confused with 133AE 13388 EGYPTIAN HIEROGLYPH V020B * 30 13389 EGYPTIAN HIEROGLYPH V020C @@ -37047,20 +37996,27 @@ FFFF <not a character> * 90 1338F EGYPTIAN HIEROGLYPH V020I * 20 + * variant of 13387 13390 EGYPTIAN HIEROGLYPH V020J * 30 + * variant of 13388 13391 EGYPTIAN HIEROGLYPH V020K * 40 + * variant of 13389 13392 EGYPTIAN HIEROGLYPH V020L * 50 + * variant of 1338A 13393 EGYPTIAN HIEROGLYPH V021 13394 EGYPTIAN HIEROGLYPH V022 13395 EGYPTIAN HIEROGLYPH V023 + * older variant of 13394 13396 EGYPTIAN HIEROGLYPH V023A 13397 EGYPTIAN HIEROGLYPH V024 13398 EGYPTIAN HIEROGLYPH V025 + * more recent variant of 13397 13399 EGYPTIAN HIEROGLYPH V026 1339A EGYPTIAN HIEROGLYPH V027 + * older variant of 13399 1339B EGYPTIAN HIEROGLYPH V028 * transliterated as 1E25 x (arabic letter hah - 062D) @@ -37069,30 +38025,38 @@ FFFF <not a character> 1339E EGYPTIAN HIEROGLYPH V029A 1339F EGYPTIAN HIEROGLYPH V030 133A0 EGYPTIAN HIEROGLYPH V030A + * stylistic variant, use of 1339F is preferred 133A1 EGYPTIAN HIEROGLYPH V031 * transliterated as k x (hebrew letter kaf - 05DB) x (arabic letter kaf - 0643) 133A2 EGYPTIAN HIEROGLYPH V031A + * from hieratic 133A3 EGYPTIAN HIEROGLYPH V032 133A4 EGYPTIAN HIEROGLYPH V033 133A5 EGYPTIAN HIEROGLYPH V033A 133A6 EGYPTIAN HIEROGLYPH V034 + * more recent variant of 133A4 133A7 EGYPTIAN HIEROGLYPH V035 133A8 EGYPTIAN HIEROGLYPH V036 133A9 EGYPTIAN HIEROGLYPH V037 133AA EGYPTIAN HIEROGLYPH V037A 133AB EGYPTIAN HIEROGLYPH V038 + * bandage + * not to be confused with 1308B 133AC EGYPTIAN HIEROGLYPH V039 133AD EGYPTIAN HIEROGLYPH V040 * 10 in dates + * not to be confused with 13386 133AE EGYPTIAN HIEROGLYPH V040A * 20 in dates + * not to be confused with 13387 @ W. Vessels of stone and earthenware 133AF EGYPTIAN HIEROGLYPH W001 133B0 EGYPTIAN HIEROGLYPH W002 133B1 EGYPTIAN HIEROGLYPH W003 133B2 EGYPTIAN HIEROGLYPH W003A + * stylistic variant, use of 133B1 is preferred 133B3 EGYPTIAN HIEROGLYPH W004 133B4 EGYPTIAN HIEROGLYPH W005 133B5 EGYPTIAN HIEROGLYPH W006 @@ -37100,11 +38064,13 @@ FFFF <not a character> 133B7 EGYPTIAN HIEROGLYPH W008 133B8 EGYPTIAN HIEROGLYPH W009 133B9 EGYPTIAN HIEROGLYPH W009A + * mirrored version of 133B8 133BA EGYPTIAN HIEROGLYPH W010 133BB EGYPTIAN HIEROGLYPH W010A 133BC EGYPTIAN HIEROGLYPH W011 * transliterated as g 133BD EGYPTIAN HIEROGLYPH W012 + * older variant of 133BC 133BE EGYPTIAN HIEROGLYPH W013 133BF EGYPTIAN HIEROGLYPH W014 133C0 EGYPTIAN HIEROGLYPH W014A @@ -37112,81 +38078,122 @@ FFFF <not a character> 133C2 EGYPTIAN HIEROGLYPH W016 133C3 EGYPTIAN HIEROGLYPH W017 133C4 EGYPTIAN HIEROGLYPH W017A + * cursive variant of 133C3 133C5 EGYPTIAN HIEROGLYPH W018 + * older variant of 133C3 133C6 EGYPTIAN HIEROGLYPH W018A + * cursive variant of 133C5 133C7 EGYPTIAN HIEROGLYPH W019 133C8 EGYPTIAN HIEROGLYPH W020 133C9 EGYPTIAN HIEROGLYPH W021 133CA EGYPTIAN HIEROGLYPH W022 133CB EGYPTIAN HIEROGLYPH W023 133CC EGYPTIAN HIEROGLYPH W024 + * phonogramm 'nw' 133CD EGYPTIAN HIEROGLYPH W024A + * monogramm 'nw(n)' or 'nww' 133CE EGYPTIAN HIEROGLYPH W025 @ X. Loaves and cakes 133CF EGYPTIAN HIEROGLYPH X001 * transliterated as t 133D0 EGYPTIAN HIEROGLYPH X002 133D1 EGYPTIAN HIEROGLYPH X003 + * variant of 133D0 133D2 EGYPTIAN HIEROGLYPH X004 133D3 EGYPTIAN HIEROGLYPH X004A + * variant of 133D2 133D4 EGYPTIAN HIEROGLYPH X004B + * cake + * variant of 133D2 + * not to be confused with 13200, 132F0, or 133F3 133D5 EGYPTIAN HIEROGLYPH X005 + * hieratic + * variant of 133D4 133D6 EGYPTIAN HIEROGLYPH X006 133D7 EGYPTIAN HIEROGLYPH X006A 133D8 EGYPTIAN HIEROGLYPH X007 + * classifier 'food' + * not to be confused with 1320E 133D9 EGYPTIAN HIEROGLYPH X008 133DA EGYPTIAN HIEROGLYPH X008A + * bread + * variant of 133D9 + * not to be confused with 131EE @ Y. Writings, games, music 133DB EGYPTIAN HIEROGLYPH Y001 133DC EGYPTIAN HIEROGLYPH Y001A + * rotated variant of 133DB 133DD EGYPTIAN HIEROGLYPH Y002 + * older variant of 133DB 133DE EGYPTIAN HIEROGLYPH Y003 133DF EGYPTIAN HIEROGLYPH Y004 + * mirrored version of 133DE 133E0 EGYPTIAN HIEROGLYPH Y005 133E1 EGYPTIAN HIEROGLYPH Y006 133E2 EGYPTIAN HIEROGLYPH Y007 133E3 EGYPTIAN HIEROGLYPH Y008 @ Z. Strokes, signs derived from Hieratic, geometrical figures 133E4 EGYPTIAN HIEROGLYPH Z001 - x (egyptian hieroglyph z015 - 133FA) + * semogram index + * classifier 'single' + * not to be confuse with 133FA 133E5 EGYPTIAN HIEROGLYPH Z002 - * plurality - x (egyptian hieroglyph z015b - 133FC) + * classifier 'plural' + * not to be confused with 133FC 133E6 EGYPTIAN HIEROGLYPH Z002A + * stylistic variant of 133E5 133E7 EGYPTIAN HIEROGLYPH Z002B + * classifier 'plural' + * not to be confused with 13213 133E8 EGYPTIAN HIEROGLYPH Z002C + * variant of 133E6 133E9 EGYPTIAN HIEROGLYPH Z002D + * variant of 133E8 133EA EGYPTIAN HIEROGLYPH Z003 + * variant of 133E5 133EB EGYPTIAN HIEROGLYPH Z003A + * variant of 133EA 133EC EGYPTIAN HIEROGLYPH Z003B - * 3 + * variant of 133E7 133ED EGYPTIAN HIEROGLYPH Z004 - * duality + * classifier 'dual' * transliterated as y x (egyptian hieroglyph m017a - 131CC) 133EE EGYPTIAN HIEROGLYPH Z004A - * duality - x (egyptian hieroglyph z015a - 133FB) + * variant of 133ED + * classifier 'dual' + * transliterated as y + * not to be confused with 133FB 133EF EGYPTIAN HIEROGLYPH Z005 133F0 EGYPTIAN HIEROGLYPH Z005A + * variant of 133EF 133F1 EGYPTIAN HIEROGLYPH Z006 133F2 EGYPTIAN HIEROGLYPH Z007 + * phonogram 'w' + * not to be confused with 13362 133F3 EGYPTIAN HIEROGLYPH Z008 + * oval + * not to be confused with 13200, 132F0, or 133D4 133F4 EGYPTIAN HIEROGLYPH Z009 133F5 EGYPTIAN HIEROGLYPH Z010 + * older variant of 133F4 133F6 EGYPTIAN HIEROGLYPH Z011 133F7 EGYPTIAN HIEROGLYPH Z012 + * hieratic 133F8 EGYPTIAN HIEROGLYPH Z013 + * circle, unmarked round sign + * not to be confused with 13082 or 131F3 133F9 EGYPTIAN HIEROGLYPH Z014 + * hieratic 133FA EGYPTIAN HIEROGLYPH Z015 * 1 - x (egyptian hieroglyph z001 - 133E4) + * not to be confused with 133E4 133FB EGYPTIAN HIEROGLYPH Z015A * 2 - x (egyptian hieroglyph z004a - 133EE) + * not to be confused with 133EE 133FC EGYPTIAN HIEROGLYPH Z015B * 3 - x (egyptian hieroglyph z002 - 133E5) + * not to be confused with 133E5 x (egyptian hieroglyph z003 - 133EA) 133FD EGYPTIAN HIEROGLYPH Z015C * 4 @@ -37231,31 +38238,41 @@ FFFF <not a character> 13412 EGYPTIAN HIEROGLYPH AA006 13413 EGYPTIAN HIEROGLYPH AA007 13414 EGYPTIAN HIEROGLYPH AA007A + * mirrored version of 13413 13415 EGYPTIAN HIEROGLYPH AA007B 13416 EGYPTIAN HIEROGLYPH AA008 13417 EGYPTIAN HIEROGLYPH AA009 13418 EGYPTIAN HIEROGLYPH AA010 13419 EGYPTIAN HIEROGLYPH AA011 1341A EGYPTIAN HIEROGLYPH AA012 + * older variant of 13419 1341B EGYPTIAN HIEROGLYPH AA013 1341C EGYPTIAN HIEROGLYPH AA014 + * older variant of 1341B 1341D EGYPTIAN HIEROGLYPH AA015 1341E EGYPTIAN HIEROGLYPH AA016 + * variant of 1341D 1341F EGYPTIAN HIEROGLYPH AA017 13420 EGYPTIAN HIEROGLYPH AA018 + * more recent variant of 1341F 13421 EGYPTIAN HIEROGLYPH AA019 13422 EGYPTIAN HIEROGLYPH AA020 13423 EGYPTIAN HIEROGLYPH AA021 13424 EGYPTIAN HIEROGLYPH AA022 13425 EGYPTIAN HIEROGLYPH AA023 13426 EGYPTIAN HIEROGLYPH AA024 + * older variant of 13425 13427 EGYPTIAN HIEROGLYPH AA025 13428 EGYPTIAN HIEROGLYPH AA026 13429 EGYPTIAN HIEROGLYPH AA027 1342A EGYPTIAN HIEROGLYPH AA028 + * phonogram 'qd' + * not to be confused with 131E9 and 132A7 1342B EGYPTIAN HIEROGLYPH AA029 + * older variant of 1342A 1342C EGYPTIAN HIEROGLYPH AA030 1342D EGYPTIAN HIEROGLYPH AA031 + * older variant of 1342C 1342E EGYPTIAN HIEROGLYPH AA032 @@ 13430 Egyptian Hieroglyph Format Controls 1343F @+ These format controls are used to render Egyptian hieroglyphic quadrats. @@ -38955,6 +39972,99 @@ FFFF <not a character> @ Punctuation 16A6E MRO DANDA 16A6F MRO DOUBLE DANDA +@@ 16A70 Tangsa 16ACF +@ Vowels +16A70 TANGSA LETTER OZ +16A71 TANGSA LETTER OC +16A72 TANGSA LETTER OQ +16A73 TANGSA LETTER OX +16A74 TANGSA LETTER AZ +16A75 TANGSA LETTER AC +16A76 TANGSA LETTER AQ +16A77 TANGSA LETTER AX +16A78 TANGSA LETTER VZ +16A79 TANGSA LETTER VC +16A7A TANGSA LETTER VQ +16A7B TANGSA LETTER VX +16A7C TANGSA LETTER EZ +16A7D TANGSA LETTER EC +16A7E TANGSA LETTER EQ +16A7F TANGSA LETTER EX +16A80 TANGSA LETTER IZ +16A81 TANGSA LETTER IC +16A82 TANGSA LETTER IQ +16A83 TANGSA LETTER IX +16A84 TANGSA LETTER UZ +16A85 TANGSA LETTER UC +16A86 TANGSA LETTER UQ +16A87 TANGSA LETTER UX +16A88 TANGSA LETTER AWZ +16A89 TANGSA LETTER AWC +16A8A TANGSA LETTER AWQ +16A8B TANGSA LETTER AWX +16A8C TANGSA LETTER UIZ +16A8D TANGSA LETTER UIC +16A8E TANGSA LETTER UIQ +16A8F TANGSA LETTER UIX +16A90 TANGSA LETTER FINAL NG +16A91 TANGSA LETTER LONG UEX +16A92 TANGSA LETTER SHORT UEZ +16A93 TANGSA LETTER SHORT AWX +16A94 TANGSA LETTER UEC +16A95 TANGSA LETTER UEZ +16A96 TANGSA LETTER UEQ +16A97 TANGSA LETTER UEX +16A98 TANGSA LETTER UIUZ +16A99 TANGSA LETTER UIUC +16A9A TANGSA LETTER UIUQ +16A9B TANGSA LETTER UIUX +16A9C TANGSA LETTER MZ +16A9D TANGSA LETTER MC +16A9E TANGSA LETTER MQ +16A9F TANGSA LETTER MX +@ Consonants +16AA0 TANGSA LETTER KA +16AA1 TANGSA LETTER KHA +16AA2 TANGSA LETTER GA +16AA3 TANGSA LETTER NGA +16AA4 TANGSA LETTER SA +16AA5 TANGSA LETTER YA +16AA6 TANGSA LETTER WA +16AA7 TANGSA LETTER PA +16AA8 TANGSA LETTER NYA +16AA9 TANGSA LETTER PHA +16AAA TANGSA LETTER BA +16AAB TANGSA LETTER MA +16AAC TANGSA LETTER NA +16AAD TANGSA LETTER HA +16AAE TANGSA LETTER LA +16AAF TANGSA LETTER HTA +16AB0 TANGSA LETTER TA +16AB1 TANGSA LETTER DA +16AB2 TANGSA LETTER RA +16AB3 TANGSA LETTER NHA +16AB4 TANGSA LETTER SHA +16AB5 TANGSA LETTER CA +16AB6 TANGSA LETTER TSA +16AB7 TANGSA LETTER GHA +16AB8 TANGSA LETTER HTTA +16AB9 TANGSA LETTER THA +16ABA TANGSA LETTER XA +16ABB TANGSA LETTER FA +16ABC TANGSA LETTER DHA +16ABD TANGSA LETTER CHA +16ABE TANGSA LETTER ZA +@ Digits +16AC0 TANGSA DIGIT ZERO +16AC1 TANGSA DIGIT ONE +16AC2 TANGSA DIGIT TWO +16AC3 TANGSA DIGIT THREE +16AC4 TANGSA DIGIT FOUR +16AC5 TANGSA DIGIT FIVE +16AC6 TANGSA DIGIT SIX +16AC7 TANGSA DIGIT SEVEN +16AC8 TANGSA DIGIT EIGHT +16AC9 TANGSA DIGIT NINE @@ 16AD0 Bassa Vah 16AFF @ Consonant letters 16AD0 BASSA VAH LETTER ENNI @@ -40862,6 +41972,23 @@ FFFF <not a character> 18CD4 KHITAN SMALL SCRIPT CHARACTER-18CD4 18CD5 KHITAN SMALL SCRIPT CHARACTER-18CD5 @@ 18D00 Tangut Supplement 18D08 +@@ 1AFF0 Kana Extended-B 1AFFF +@+ This block contains tone marks occasionally used in furigana extensions to annotate Minnan Chinese. +@ Tone marks +1AFF0 KATAKANA LETTER MINNAN TONE-2 +1AFF1 KATAKANA LETTER MINNAN TONE-3 +1AFF2 KATAKANA LETTER MINNAN TONE-4 +1AFF3 KATAKANA LETTER MINNAN TONE-5 +1AFF5 KATAKANA LETTER MINNAN TONE-7 +1AFF6 KATAKANA LETTER MINNAN TONE-8 +@ Nasalized tone marks +1AFF7 KATAKANA LETTER MINNAN NASALIZED TONE-1 +1AFF8 KATAKANA LETTER MINNAN NASALIZED TONE-2 +1AFF9 KATAKANA LETTER MINNAN NASALIZED TONE-3 +1AFFA KATAKANA LETTER MINNAN NASALIZED TONE-4 +1AFFB KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD KATAKANA LETTER MINNAN NASALIZED TONE-7 +1AFFE KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ 1B000 Kana Supplement 1B0FF @ Historic Katakana 1B000 KATAKANA LETTER ARCHAIC E @@ -41442,6 +42569,13 @@ FFFF <not a character> * derived from 65E0 1B11E HENTAIGANA LETTER N-MU-MO-2 * derived from 65E0 +@ Historic Hiragana +1B11F HIRAGANA LETTER ARCHAIC WU + * derived from 6C59 +@ Historic Katakana +1B120 KATAKANA LETTER ARCHAIC YI +1B121 KATAKANA LETTER ARCHAIC YE +1B122 KATAKANA LETTER ARCHAIC WU @@ 1B130 Small Kana Extension 1B16F @ Historic small hiragana letters 1B150 HIRAGANA LETTER SMALL WI @@ -42357,6 +43491,210 @@ FFFF <not a character> = Sloan contracted ending oo/o + ZWSP 1BCA3 SHORTHAND FORMAT UP STEP = Sloan contracted ending uh/au/aui + ZWSP +@@ 1CF00 Znamenny Musical Notation 1CFCF +@ Combining red marks +1CF00 ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT +1CF01 ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT +1CF02 ZNAMENNY COMBINING MARK TSATA ON LEFT +1CF03 ZNAMENNY COMBINING MARK GORAZDO NIZKO ON LEFT +1CF04 ZNAMENNY COMBINING MARK NIZKO ON LEFT +1CF05 ZNAMENNY COMBINING MARK SREDNE ON LEFT +1CF06 ZNAMENNY COMBINING MARK MALO POVYSHE ON LEFT +1CF07 ZNAMENNY COMBINING MARK POVYSHE ON LEFT +1CF08 ZNAMENNY COMBINING MARK VYSOKO ON LEFT +1CF09 ZNAMENNY COMBINING MARK MALO POVYSHE S KHOKHLOM ON LEFT +1CF0A ZNAMENNY COMBINING MARK POVYSHE S KHOKHLOM ON LEFT +1CF0B ZNAMENNY COMBINING MARK VYSOKO S KHOKHLOM ON LEFT +1CF0C ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON RIGHT +1CF0D ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON RIGHT +1CF0E ZNAMENNY COMBINING MARK TSATA ON RIGHT +1CF0F ZNAMENNY COMBINING MARK GORAZDO NIZKO ON RIGHT +1CF10 ZNAMENNY COMBINING MARK NIZKO ON RIGHT +1CF11 ZNAMENNY COMBINING MARK SREDNE ON RIGHT +1CF12 ZNAMENNY COMBINING MARK MALO POVYSHE ON RIGHT +1CF13 ZNAMENNY COMBINING MARK POVYSHE ON RIGHT +1CF14 ZNAMENNY COMBINING MARK VYSOKO ON RIGHT +1CF15 ZNAMENNY COMBINING MARK MALO POVYSHE S KHOKHLOM ON RIGHT +1CF16 ZNAMENNY COMBINING MARK POVYSHE S KHOKHLOM ON RIGHT +1CF17 ZNAMENNY COMBINING MARK VYSOKO S KHOKHLOM ON RIGHT +1CF18 ZNAMENNY COMBINING MARK TSATA S KRYZHEM +1CF19 ZNAMENNY COMBINING MARK MALO POVYSHE S KRYZHEM +1CF1A ZNAMENNY COMBINING MARK STRANNO MALO POVYSHE +1CF1B ZNAMENNY COMBINING MARK POVYSHE S KRYZHEM +1CF1C ZNAMENNY COMBINING MARK POVYSHE STRANNO +1CF1D ZNAMENNY COMBINING MARK VYSOKO S KRYZHEM +1CF1E ZNAMENNY COMBINING MARK MALO POVYSHE STRANNO +1CF1F ZNAMENNY COMBINING MARK GORAZDO VYSOKO +1CF20 ZNAMENNY COMBINING MARK ZELO +1CF21 ZNAMENNY COMBINING MARK ON +1CF22 ZNAMENNY COMBINING MARK RAVNO +1CF23 ZNAMENNY COMBINING MARK TIKHAYA +1CF24 ZNAMENNY COMBINING MARK BORZAYA +1CF25 ZNAMENNY COMBINING MARK UDARKA +1CF26 ZNAMENNY COMBINING MARK PODVERTKA +1CF27 ZNAMENNY COMBINING MARK LOMKA +1CF28 ZNAMENNY COMBINING MARK KUPNAYA +1CF29 ZNAMENNY COMBINING MARK KACHKA +1CF2A ZNAMENNY COMBINING MARK ZEVOK +1CF2B ZNAMENNY COMBINING MARK SKOBA +1CF2C ZNAMENNY COMBINING MARK RAZSEKA +1CF2D ZNAMENNY COMBINING MARK KRYZH ON LEFT +@ Combining black marks +1CF30 ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO +1CF31 ZNAMENNY COMBINING TONAL RANGE MARK SVETLO +1CF32 ZNAMENNY COMBINING TONAL RANGE MARK TRESVETLO +1CF33 ZNAMENNY COMBINING MARK ZADERZHKA + = ottyazhka +1CF34 ZNAMENNY COMBINING MARK DEMESTVENNY ZADERZHKA +1CF35 ZNAMENNY COMBINING MARK OTSECHKA +1CF36 ZNAMENNY COMBINING MARK PODCHASHIE +1CF37 ZNAMENNY COMBINING MARK PODCHASHIE WITH VERTICAL STROKE +1CF38 ZNAMENNY COMBINING MARK CHASHKA +1CF39 ZNAMENNY COMBINING MARK CHASHKA POLNAYA +1CF3A ZNAMENNY COMBINING MARK OBLACHKO +1CF3B ZNAMENNY COMBINING MARK SOROCHYA NOZHKA + = sokolik +1CF3C ZNAMENNY COMBINING MARK TOCHKA +1CF3D ZNAMENNY COMBINING MARK DVOETOCHIE +1CF3E ZNAMENNY COMBINING ATTACHING VERTICAL OMET +1CF3F ZNAMENNY COMBINING MARK CURVED OMET +1CF40 ZNAMENNY COMBINING MARK KRYZH +1CF41 ZNAMENNY COMBINING LOWER TONAL RANGE INDICATOR +@ Modifying marks for priznaki +1CF42 ZNAMENNY PRIZNAK MODIFIER LEVEL-2 +1CF43 ZNAMENNY PRIZNAK MODIFIER LEVEL-3 +1CF44 ZNAMENNY PRIZNAK MODIFIER DIRECTION FLIP +1CF45 ZNAMENNY PRIZNAK MODIFIER KRYZH +1CF46 ZNAMENNY PRIZNAK MODIFIER ROG +@ Znamenny neumes +1CF50 ZNAMENNY NEUME KRYUK +1CF51 ZNAMENNY NEUME KRYUK TIKHY +1CF52 ZNAMENNY NEUME PARAKLIT +1CF53 ZNAMENNY NEUME DVA V CHELNU +1CF54 ZNAMENNY NEUME KLYUCH + = kryuk klyuchevoy +1CF55 ZNAMENNY NEUME ZANOZHEK +1CF56 ZNAMENNY NEUME STOPITSA +1CF57 ZNAMENNY NEUME STOPITSA S OCHKOM +1CF58 ZNAMENNY NEUME PEREVODKA +1CF59 ZNAMENNY NEUME PEREVODKA NEPOSTOYANNAYA +1CF5A ZNAMENNY NEUME STOPITSA WITH SOROCHYA NOZHKA + * not a decomposable character +1CF5B ZNAMENNY NEUME CHELYUSTKA +1CF5C ZNAMENNY NEUME PALKA +1CF5D ZNAMENNY NEUME ZAPYATAYA +1CF5E ZNAMENNY NEUME GOLUBCHIK BORZY +1CF5F ZNAMENNY NEUME GOLUBCHIK TIKHY +1CF60 ZNAMENNY NEUME GOLUBCHIK MRACHNY +1CF61 ZNAMENNY NEUME GOLUBCHIK SVETLY +1CF62 ZNAMENNY NEUME GOLUBCHIK TRESVETLY + = golubchik nepostoyanny +1CF63 ZNAMENNY NEUME VRAKHIYA PROSTAYA +1CF64 ZNAMENNY NEUME VRAKHIYA MRACHNAYA +1CF65 ZNAMENNY NEUME VRAKHIYA SVETLAYA +1CF66 ZNAMENNY NEUME VRAKHIYA TRESVETLAYA + = vrakhia nepostoyannaya +1CF67 ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA PROSTAYA +1CF68 ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA MRACHNAYA +1CF69 ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA SVETLAYA +1CF6A ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA TRESVETLAYA + = vrakhia klyuchevaya nepostoyannaya +1CF6B ZNAMENNY NEUME DOUBLE ZAPYATAYA +1CF6C ZNAMENNY NEUME REVERSED CHELYUSTKA +1CF6D ZNAMENNY NEUME DERBITSA +1CF6E ZNAMENNY NEUME KHAMILO +1CF6F ZNAMENNY NEUME CHASHKA +1CF70 ZNAMENNY NEUME PODCHASHIE +1CF71 ZNAMENNY NEUME SKAMEYTSA MRACHNAYA +1CF72 ZNAMENNY NEUME SKAMEYTSA SVETLAYA +1CF73 ZNAMENNY NEUME SKAMEYTSA TRESVETLAYA +1CF74 ZNAMENNY NEUME SKAMEYTSA TIKHAYA +1CF75 ZNAMENNY NEUME DEMESTVENNY KLYUCH + = skameytsa klyuchevaya +1CF76 ZNAMENNY NEUME SKAMEYTSA KLYUCHEVAYA SVETLAYA +1CF77 ZNAMENNY NEUME SKAMEYTSA KLYUCHENEPOSTOYANNAYA +1CF78 ZNAMENNY NEUME SKAMEYTSA KLYUCHEVAYA TIKHAYA +1CF79 ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA PROSTAYA +1CF7A ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA SVETLAYA +1CF7B ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA NEPOSTOYANNAYA +1CF7C ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA KLYUCHEVAYA +1CF7D ZNAMENNY NEUME SLOZHITIE +1CF7E ZNAMENNY NEUME SLOZHITIE S ZAPYATOY +1CF7F ZNAMENNY NEUME SLOZHITIE ZAKRYTOE +1CF80 ZNAMENNY NEUME SLOZHITIE S KRYZHEM +1CF81 ZNAMENNY NEUME KRYZH +1CF82 ZNAMENNY NEUME ROG +1CF83 ZNAMENNY NEUME FITA +1CF84 ZNAMENNY NEUME KOBYLA +1CF85 ZNAMENNY NEUME ZMEYTSA + = litso +1CF86 ZNAMENNY NEUME STATYA +1CF87 ZNAMENNY NEUME STATYA S ZAPYATOY +1CF88 ZNAMENNY NEUME STATYA S KRYZHEM +1CF89 ZNAMENNY NEUME STATYA S ZAPYATOY I KRYZHEM +1CF8A ZNAMENNY NEUME STATYA S KRYZHEM I ZAPYATOY +1CF8B ZNAMENNY NEUME STATYA ZAKRYTAYA +1CF8C ZNAMENNY NEUME STATYA ZAKRYTAYA S ZAPYATOY +1CF8D ZNAMENNY NEUME STATYA S ROGOM +1CF8E ZNAMENNY NEUME STATYA S DVUMYA ZAPYATYMI +1CF8F ZNAMENNY NEUME STATYA S ZAPYATOY I PODCHASHIEM +1CF90 ZNAMENNY NEUME POLKULIZMY + * not a decomposable character +1CF91 ZNAMENNY NEUME STATYA NEPOSTOYANNAYA +1CF92 ZNAMENNY NEUME STRELA PROSTAYA +1CF93 ZNAMENNY NEUME STRELA MRACHNOTIKHAYA +1CF94 ZNAMENNY NEUME STRELA KRYZHEVAYA + = strela polukryzhevaya +1CF95 ZNAMENNY NEUME STRELA POLUPOVODNAYA +1CF96 ZNAMENNY NEUME STRELA POVODNAYA +1CF97 ZNAMENNY NEUME STRELA NEPOSTOYANNAYA +1CF98 ZNAMENNY NEUME STRELA KLYUCHEPOVODNAYA +1CF99 ZNAMENNY NEUME STRELA KLYUCHENEPOSTOYANNAYA +1CF9A ZNAMENNY NEUME STRELA TIKHAYA PUTNAYA +1CF9B ZNAMENNY NEUME STRELA DVOECHELNAYA +1CF9C ZNAMENNY NEUME STRELA DVOECHELNOKRYZHEVAYA +1CF9D ZNAMENNY NEUME STRELA DVOECHELNOPOVODNAYA +1CF9E ZNAMENNY NEUME STRELA DVOECHELNAYA KLYUCHEVAYA +1CF9F ZNAMENNY NEUME STRELA DVOECHELNOPOVODNAYA KLYUCHEVAYA +1CFA0 ZNAMENNY NEUME STRELA GROMNAYA WITH SINGLE ZAPYATAYA +1CFA1 ZNAMENNY NEUME STRELA GROMOPOVODNAYA WITH SINGLE ZAPYATAYA +1CFA2 ZNAMENNY NEUME STRELA GROMNAYA +1CFA3 ZNAMENNY NEUME STRELA GROMOPOVODNAYA +1CFA4 ZNAMENNY NEUME STRELA GROMOPOVODNAYA WITH DOUBLE ZAPYATAYA +1CFA5 ZNAMENNY NEUME STRELA GROMOKRYZHEVAYA +1CFA6 ZNAMENNY NEUME STRELA GROMOKRYZHEVAYA POVODNAYA + = strela gromomrachnaya s kryzhem +1CFA7 ZNAMENNY NEUME MECHIK +1CFA8 ZNAMENNY NEUME MECHIK POVODNY +1CFA9 ZNAMENNY NEUME MECHIK KLYUCHEVOY +1CFAA ZNAMENNY NEUME MECHIK KLYUCHEPOVODNY +1CFAB ZNAMENNY NEUME MECHIK KLYUCHENEPOSTOYANNY +1CFAC ZNAMENNY NEUME STRELA TRYASOGLASNAYA +1CFAD ZNAMENNY NEUME STRELA TRYASOPOVODNAYA +1CFAE ZNAMENNY NEUME STRELA TRYASOSTRELNAYA +1CFAF ZNAMENNY NEUME OSOKA +1CFB0 ZNAMENNY NEUME OSOKA SVETLAYA +1CFB1 ZNAMENNY NEUME OSOKA TRESVETLAYA + = osoka nepostoyannaya +1CFB2 ZNAMENNY NEUME OSOKA KRYUKOVAYA SVETLAYA +1CFB3 ZNAMENNY NEUME OSOKA KLYUCHEVAYA SVETLAYA +1CFB4 ZNAMENNY NEUME OSOKA KLYUCHEVAYA NEPOSTOYANNAYA +1CFB5 ZNAMENNY NEUME STRELA KRYUKOVAYA +1CFB6 ZNAMENNY NEUME STRELA KRYUKOVAYA POVODNAYA +1CFB7 ZNAMENNY NEUME STRELA KRYUKOVAYA GROMNAYA WITH SINGLE ZAPYATAYA +1CFB8 ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA WITH SINGLE ZAPYATAYA +1CFB9 ZNAMENNY NEUME STRELA KRYUKOVAYA GROMNAYA +1CFBA ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA +1CFBB ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA WITH DOUBLE ZAPYATAYA +1CFBC ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOKRYZHEVAYA +1CFBD ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOKRYZHEVAYA POVODNAYA + = strela kryukovaya gromomrachnaya s kryzhem +1CFBE ZNAMENNY NEUME STRELA KRYUKOVAYA TRYASKA +1CFBF ZNAMENNY NEUME KUFISMA +1CFC0 ZNAMENNY NEUME OBLAKO +1CFC1 ZNAMENNY NEUME DUDA +1CFC2 ZNAMENNY NEUME NEMKA +1CFC3 ZNAMENNY NEUME PAUK @@ 1D000 Byzantine Musical Symbols 1D0FF @@+ @ Prosodies (Prosodics) @@ -42956,6 +44294,11 @@ FFFF <not a character> 1D1E7 MUSICAL SYMBOL KIEVAN EIGHTH NOTE STEM UP @ Accidental 1D1E8 MUSICAL SYMBOL KIEVAN FLAT SIGN +@ Iranian notation +@+ The following range is specific to Iranian classical music. +@ Accidentals for quarter tones +1D1E9 MUSICAL SYMBOL SORI +1D1EA MUSICAL SYMBOL KORON @@ 1D200 Ancient Greek Musical Notation 1D24F @ Ancient Greek vocalic notation @+ In a few instances vocalic and instrumental symbols have been unified with each other. In other instances they have been unified with regular Greek letters. @@ -43601,57 +44944,93 @@ FFFF <not a character> @ Script symbols @+ Script symbols already encoded in the Letterlike Symbols block are omitted here to avoid duplicate encoding. Fonts that use a less elaborate style are also acceptable for many uses, as long as they can be distinguished from serifed and italic styles. 1D49C MATHEMATICAL SCRIPT CAPITAL A + ~ 1D49C FE00 chancery style + ~ 1D49C FE01 roundhand style # <font> 0041 latin capital letter a 1D49D <reserved> x (script capital b - 212C) 1D49E MATHEMATICAL SCRIPT CAPITAL C + ~ 1D49E FE00 chancery style + ~ 1D49E FE01 roundhand style # <font> 0043 latin capital letter c 1D49F MATHEMATICAL SCRIPT CAPITAL D + ~ 1D49F FE00 chancery style + ~ 1D49F FE01 roundhand style # <font> 0044 latin capital letter d 1D4A0 <reserved> x (script capital e - 2130) 1D4A1 <reserved> x (script capital f - 2131) 1D4A2 MATHEMATICAL SCRIPT CAPITAL G + ~ 1D4A2 FE00 chancery style + ~ 1D4A2 FE01 roundhand style # <font> 0047 latin capital letter g 1D4A3 <reserved> x (script capital h - 210B) 1D4A4 <reserved> x (script capital i - 2110) 1D4A5 MATHEMATICAL SCRIPT CAPITAL J + ~ 1D4A5 FE00 chancery style + ~ 1D4A5 FE01 roundhand style # <font> 004A latin capital letter j 1D4A6 MATHEMATICAL SCRIPT CAPITAL K + ~ 1D4A6 FE00 chancery style + ~ 1D4A6 FE01 roundhand style # <font> 004B latin capital letter k 1D4A7 <reserved> x (script capital l - 2112) 1D4A8 <reserved> x (script capital m - 2133) 1D4A9 MATHEMATICAL SCRIPT CAPITAL N + ~ 1D4A9 FE00 chancery style + ~ 1D4A9 FE01 roundhand style # <font> 004E latin capital letter n 1D4AA MATHEMATICAL SCRIPT CAPITAL O + ~ 1D4AA FE00 chancery style + ~ 1D4AA FE01 roundhand style # <font> 004F latin capital letter o 1D4AB MATHEMATICAL SCRIPT CAPITAL P = power set + ~ 1D4AB FE00 chancery style + ~ 1D4AB FE01 roundhand style # <font> 0050 latin capital letter p 1D4AC MATHEMATICAL SCRIPT CAPITAL Q + ~ 1D4AC FE00 chancery style + ~ 1D4AC FE01 roundhand style # <font> 0051 latin capital letter q 1D4AD <reserved> x (script capital r - 211B) 1D4AE MATHEMATICAL SCRIPT CAPITAL S + ~ 1D4AE FE00 chancery style + ~ 1D4AE FE01 roundhand style # <font> 0053 latin capital letter s 1D4AF MATHEMATICAL SCRIPT CAPITAL T + ~ 1D4AF FE00 chancery style + ~ 1D4AF FE01 roundhand style # <font> 0054 latin capital letter t 1D4B0 MATHEMATICAL SCRIPT CAPITAL U + ~ 1D4B0 FE00 chancery style + ~ 1D4B0 FE01 roundhand style # <font> 0055 latin capital letter u 1D4B1 MATHEMATICAL SCRIPT CAPITAL V + ~ 1D4B1 FE00 chancery style + ~ 1D4B1 FE01 roundhand style # <font> 0056 latin capital letter v 1D4B2 MATHEMATICAL SCRIPT CAPITAL W + ~ 1D4B2 FE00 chancery style + ~ 1D4B2 FE01 roundhand style # <font> 0057 latin capital letter w 1D4B3 MATHEMATICAL SCRIPT CAPITAL X + ~ 1D4B3 FE00 chancery style + ~ 1D4B3 FE01 roundhand style # <font> 0058 latin capital letter x 1D4B4 MATHEMATICAL SCRIPT CAPITAL Y + ~ 1D4B4 FE00 chancery style + ~ 1D4B4 FE01 roundhand style # <font> 0059 latin capital letter y 1D4B5 MATHEMATICAL SCRIPT CAPITAL Z + ~ 1D4B5 FE00 chancery style + ~ 1D4B5 FE01 roundhand style # <font> 005A latin capital letter z 1D4B6 MATHEMATICAL SCRIPT SMALL A # <font> 0061 latin small letter a @@ -45368,6 +46747,7 @@ FFFF <not a character> # <font> 0038 digit eight 1D7FF MATHEMATICAL MONOSPACE DIGIT NINE # <font> 0039 digit nine +@~ Standardized Variation Sequences @@ 1D800 Sutton SignWriting 1DAAF @ Hand shapes with index finger 1D800 SIGNWRITING HAND-FIST INDEX @@ -46063,6 +47443,45 @@ FFFF <not a character> 1DAAD SIGNWRITING ROTATION MODIFIER-14 1DAAE SIGNWRITING ROTATION MODIFIER-15 1DAAF SIGNWRITING ROTATION MODIFIER-16 +@@ 1DF00 Latin Extended-G 1DFFF +@ Extended IPA for disordered speech +1DF00 LATIN SMALL LETTER FENG DIGRAPH WITH TRILL +1DF01 LATIN SMALL LETTER REVERSED SCRIPT G +1DF02 LATIN LETTER SMALL CAPITAL TURNED G +1DF03 LATIN SMALL LETTER REVERSED K +1DF04 LATIN LETTER SMALL CAPITAL L WITH BELT +1DF05 LATIN SMALL LETTER LEZH WITH RETROFLEX HOOK +1DF06 LATIN SMALL LETTER TURNED Y WITH BELT +1DF07 LATIN SMALL LETTER REVERSED ENG +@ IPA extensions +1DF08 LATIN SMALL LETTER TURNED R WITH LONG LEG AND RETROFLEX HOOK +1DF09 LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +@ Clicks +1DF0B LATIN SMALL LETTER ESH WITH DOUBLE BAR +1DF0C LATIN SMALL LETTER ESH WITH DOUBLE BAR AND CURL +1DF0D LATIN SMALL LETTER TURNED T WITH CURL +1DF0E LATIN LETTER INVERTED GLOTTAL STOP WITH CURL +1DF0F LATIN LETTER STRETCHED C WITH CURL +1DF10 LATIN LETTER SMALL CAPITAL TURNED K +@ Lateral +1DF11 LATIN SMALL LETTER L WITH FISHHOOK +@ Letters with palatal hooks +1DF12 LATIN SMALL LETTER DEZH DIGRAPH WITH PALATAL HOOK +1DF13 LATIN SMALL LETTER L WITH BELT AND PALATAL HOOK +1DF14 LATIN SMALL LETTER ENG WITH PALATAL HOOK +1DF15 LATIN SMALL LETTER TURNED R WITH PALATAL HOOK +1DF16 LATIN SMALL LETTER R WITH FISHHOOK AND PALATAL HOOK +1DF17 LATIN SMALL LETTER TESH DIGRAPH WITH PALATAL HOOK +1DF18 LATIN SMALL LETTER EZH WITH PALATAL HOOK +@ Letters with retroflex hooks +1DF19 LATIN SMALL LETTER DEZH DIGRAPH WITH RETROFLEX HOOK +1DF1A LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK +1DF1B LATIN SMALL LETTER O WITH RETROFLEX HOOK +1DF1C LATIN SMALL LETTER TESH DIGRAPH WITH RETROFLEX HOOK +1DF1D LATIN SMALL LETTER C WITH RETROFLEX HOOK +@ IPA extension +1DF1E LATIN SMALL LETTER S WITH CURL @@ 1E000 Glagolitic Supplement 1E02F @ Combining letters 1E000 COMBINING GLAGOLITIC LETTER AZU @@ -46220,6 +47639,41 @@ FFFF <not a character> 1E14F NYIAKENG PUACHUE HMONG CIRCLED CA * used to indicate ownership x (nyiakeng puachue hmong letter ca - 1E108) +@@ 1E290 Toto 1E2BF +@ Basic consonants +1E290 TOTO LETTER PA +1E291 TOTO LETTER BA +1E292 TOTO LETTER TA +1E293 TOTO LETTER DA +1E294 TOTO LETTER KA +1E295 TOTO LETTER GA +1E296 TOTO LETTER MA +1E297 TOTO LETTER NA +1E298 TOTO LETTER NGA +1E299 TOTO LETTER SA +1E29A TOTO LETTER CHA +1E29B TOTO LETTER YA +1E29C TOTO LETTER WA +1E29D TOTO LETTER JA +1E29E TOTO LETTER HA +1E29F TOTO LETTER RA +1E2A0 TOTO LETTER LA +@ Basic vowels +1E2A1 TOTO LETTER I +1E2A2 TOTO LETTER BREATHY I +1E2A3 TOTO LETTER IU +1E2A4 TOTO LETTER BREATHY IU +1E2A5 TOTO LETTER U +1E2A6 TOTO LETTER E +1E2A7 TOTO LETTER BREATHY E +1E2A8 TOTO LETTER EO +1E2A9 TOTO LETTER BREATHY EO +1E2AA TOTO LETTER O +1E2AB TOTO LETTER AE +1E2AC TOTO LETTER BREATHY AE +1E2AD TOTO LETTER A +@ Sign +1E2AE TOTO SIGN RISING TONE @@ 1E2C0 Wancho 1E2FF @ Letters 1E2C0 WANCHO LETTER AA @@ -46286,6 +47740,64 @@ FFFF <not a character> 1E2FF WANCHO NGUN SIGN = rupee x (indian rupee sign - 20B9) +@@ 1E7E0 Ethiopic Extended-B 1E7FF +@ Syllables for Gurage +1E7E0 ETHIOPIC SYLLABLE HHYA + x (ethiopic syllable xya - 2DD0) +1E7E1 ETHIOPIC SYLLABLE HHYU + x (ethiopic syllable xyu - 2DD1) +1E7E2 ETHIOPIC SYLLABLE HHYI + x (ethiopic syllable xyi - 2DD2) +1E7E3 ETHIOPIC SYLLABLE HHYAA + x (ethiopic syllable xyaa - 2DD3) +1E7E4 ETHIOPIC SYLLABLE HHYEE + x (ethiopic syllable xyee - 2DD4) +1E7E5 ETHIOPIC SYLLABLE HHYE + x (ethiopic syllable xye - 2DD5) +1E7E6 ETHIOPIC SYLLABLE HHYO + x (ethiopic syllable xyo - 2DD6) +1E7E8 ETHIOPIC SYLLABLE GURAGE HHWA + x (ethiopic syllable kxwa - 12C0) +1E7E9 ETHIOPIC SYLLABLE HHWI + x (ethiopic syllable kxwi - 12C2) +1E7EA ETHIOPIC SYLLABLE HHWEE + x (ethiopic syllable kxwee - 12C4) +1E7EB ETHIOPIC SYLLABLE HHWE + x (ethiopic syllable kxwe - 12C5) +1E7ED ETHIOPIC SYLLABLE GURAGE MWI + x (ethiopic syllable mwi - 1381) +1E7EE ETHIOPIC SYLLABLE GURAGE MWEE + x (ethiopic syllable mwee - 1382) +1E7F0 ETHIOPIC SYLLABLE GURAGE QWI + x (ethiopic syllable qwi - 124A) +1E7F1 ETHIOPIC SYLLABLE GURAGE QWEE + x (ethiopic syllable qwee - 124C) +1E7F2 ETHIOPIC SYLLABLE GURAGE QWE + x (ethiopic syllable qwe - 124D) +1E7F3 ETHIOPIC SYLLABLE GURAGE BWI + x (ethiopic syllable bwi - 1385) +1E7F4 ETHIOPIC SYLLABLE GURAGE BWEE + x (ethiopic syllable bwee - 1386) +1E7F5 ETHIOPIC SYLLABLE GURAGE KWI + x (ethiopic syllable kwi - 12B2) +1E7F6 ETHIOPIC SYLLABLE GURAGE KWEE + x (ethiopic syllable kwee - 12B4) +1E7F7 ETHIOPIC SYLLABLE GURAGE KWE + x (ethiopic syllable kwe - 12B5) +1E7F8 ETHIOPIC SYLLABLE GURAGE GWI + x (ethiopic syllable gwi - 1312) +1E7F9 ETHIOPIC SYLLABLE GURAGE GWEE + x (ethiopic syllable gwee - 1314) +1E7FA ETHIOPIC SYLLABLE GURAGE GWE + x (ethiopic syllable gwe - 1315) +1E7FB ETHIOPIC SYLLABLE GURAGE FWI + x (ethiopic syllable fwi - 1389) +1E7FC ETHIOPIC SYLLABLE GURAGE FWEE + x (ethiopic syllable fwee - 138A) +1E7FD ETHIOPIC SYLLABLE GURAGE PWI + x (ethiopic syllable pwi - 138D) +1E7FE ETHIOPIC SYLLABLE GURAGE PWEE + x (ethiopic syllable pwee - 138E) @@ 1E800 Mende Kikakui 1E8DF @+ Annotations refer to the syllabaries of Amara Mansaray and David Dalby. @ Syllables in k- @@ -48684,9 +50196,11 @@ FFFF <not a character> 1F448 WHITE LEFT POINTING BACKHAND INDEX x (white left pointing index - 261C) x (black left pointing backhand index - 1F59C) + x (leftwards hand - 1FAF2) 1F449 WHITE RIGHT POINTING BACKHAND INDEX x (white right pointing index - 261E) x (black right pointing backhand index - 1F59D) + x (rightwards hand - 1FAF1) 1F44A FISTED HAND SIGN = punch x (raised fist - 270A) @@ -48758,6 +50272,7 @@ FFFF <not a character> @ Fairy tale symbols 1F478 PRINCESS x (prince - 1F934) + x (person with crown - 1FAC5) 1F479 JAPANESE OGRE 1F47A JAPANESE GOBLIN 1F47B GHOST @@ -48839,6 +50354,7 @@ FFFF <not a character> 1F4A7 DROPLET * represents a drop of sweat or drop of water x (black droplet - 1F322) + x (drop of blood - 1FA78) 1F4A8 DASH SYMBOL = running dash, briffits 1F4A9 PILE OF POO @@ -49018,6 +50534,7 @@ FFFF <not a character> 1F50A SPEAKER WITH THREE SOUND WAVES = sound 1F50B BATTERY + x (low battery - 1FAAB) 1F50C ELECTRIC PLUG 1F50D LEFT-POINTING MAGNIFYING GLASS = search @@ -49435,6 +50952,7 @@ FFFF <not a character> = rated for sex = kiss x (kiss mark - 1F48B) + x (biting lip - 1FAE6) 1F5E3 SPEAKING HEAD IN SILHOUETTE = rated for strong language @ Sound symbols @@ -49823,6 +51341,9 @@ FFFF <not a character> 1F6D6 HUT 1F6D7 ELEVATOR @ Miscellaneous symbols +1F6DD PLAYGROUND SLIDE +1F6DE WHEEL +1F6DF RING BUOY 1F6E0 HAMMER AND WRENCH = tools, repair facility x (hammer and pick - 2692) @@ -50267,6 +51788,14 @@ FFFF <not a character> 1F7E9 LARGE GREEN SQUARE 1F7EA LARGE PURPLE SQUARE 1F7EB LARGE BROWN SQUARE +@ Miscellaneous symbol +1F7F0 HEAVY EQUALS SIGN + * symbol of equality + x (equals sign - 003D) + x (heavy multiplication x - 2716) + x (heavy plus sign - 2795) + x (geta mark - 3013) + x (roman sextans sign - 10190) @@ 1F800 Supplemental Arrows-C 1F8FF @ Arrows with triangle arrowheads 1F800 LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD @@ -50490,9 +52019,12 @@ FFFF <not a character> 1F919 CALL ME HAND 1F91A RAISED BACK OF HAND 1F91B LEFT-FACING FIST + x (leftwards hand - 1FAF2) 1F91C RIGHT-FACING FIST + x (rightwards hand - 1FAF1) 1F91D HANDSHAKE 1F91E HAND WITH INDEX AND MIDDLE FINGERS CROSSED + x (hand with index finger and thumb crossed - 1FAF0) 1F91F I LOVE YOU HAND SIGN * can be abbreviated ILY @ Emoticon faces @@ -50517,6 +52049,7 @@ FFFF <not a character> 1F92F SHOCKED FACE WITH EXPLODING HEAD @ Portrait and role symbols 1F930 PREGNANT WOMAN + x (pregnant person - 1FAC4) 1F931 BREAST-FEEDING 1F932 PALMS UP TOGETHER * used for prayer in some cultures @@ -50594,6 +52127,7 @@ FFFF <not a character> = chicken egg 1F95B GLASS OF MILK = milk + x (pouring liquid - 1FAD7) 1F95C PEANUTS 1F95D KIWIFRUIT 1F95E PANCAKES @@ -50635,6 +52169,7 @@ FFFF <not a character> 1F976 FREEZING FACE 1F977 NINJA 1F978 DISGUISED FACE +1F979 FACE HOLDING BACK TEARS 1F97A FACE WITH PLEADING EYES @ Clothing 1F97B SARI @@ -50737,6 +52272,8 @@ FFFF <not a character> 1F9C9 MATE DRINK 1F9CA ICE CUBE 1F9CB BUBBLE TEA +@ Fantasy being +1F9CC TROLL @ Portrait and accessibility symbols 1F9CD STANDING PERSON 1F9CE KNEELING PERSON @@ -50981,10 +52518,14 @@ FFFF <not a character> 1FA72 BRIEFS 1FA73 SHORTS 1FA74 THONG SANDAL + = flip flop @ Medical symbols 1FA78 DROP OF BLOOD + x (droplet - 1F4A7) 1FA79 ADHESIVE BANDAGE 1FA7A STETHOSCOPE +1FA7B X-RAY +1FA7C CRUTCH @ Toys and sport symbols 1FA80 YO-YO 1FA81 KITE @@ -51019,6 +52560,12 @@ FFFF <not a character> 1FAA6 HEADSTONE 1FAA7 PLACARD 1FAA8 ROCK +1FAA9 MIRROR BALL +1FAAA IDENTIFICATION CARD + = ID +1FAAB LOW BATTERY + x (battery - 1F50B) +1FAAC HAMSA @ Animals and nature 1FAB0 FLY 1FAB1 WORM @@ -51027,11 +52574,20 @@ FFFF <not a character> 1FAB4 POTTED PLANT 1FAB5 WOOD 1FAB6 FEATHER +1FAB7 LOTUS +1FAB8 CORAL +1FAB9 EMPTY NEST +1FABA NEST WITH EGGS @ Body parts 1FAC0 ANATOMICAL HEART 1FAC1 LUNGS @ People 1FAC2 PEOPLE HUGGING +1FAC3 PREGNANT MAN +1FAC4 PREGNANT PERSON + x (pregnant woman - 1F930) +1FAC5 PERSON WITH CROWN + x (princess - 1F478) @ Food and drink 1FAD0 BLUEBERRIES 1FAD1 BELL PEPPER @@ -51040,6 +52596,30 @@ FFFF <not a character> 1FAD4 TAMALE 1FAD5 FONDUE 1FAD6 TEAPOT +1FAD7 POURING LIQUID + x (glass of milk - 1F95B) +1FAD8 BEANS +1FAD9 JAR +@ Faces +1FAE0 MELTING FACE +1FAE1 SALUTING FACE +1FAE2 FACE WITH OPEN EYES AND HAND OVER MOUTH +1FAE3 FACE WITH PEEKING EYE +1FAE4 FACE WITH DIAGONAL MOUTH +1FAE5 DOTTED LINE FACE +@ Emotion +1FAE6 BITING LIP + x (lips - 1F5E2) +1FAE7 BUBBLES +@ Hand symbols +1FAF0 HAND WITH INDEX FINGER AND THUMB CROSSED + x (hand with index and middle fingers crossed - 1F91E) +1FAF1 RIGHTWARDS HAND +1FAF2 LEFTWARDS HAND +1FAF3 PALM DOWN HAND +1FAF4 PALM UP HAND +1FAF5 INDEX POINTING AT THE VIEWER +1FAF6 HEART HANDS @@ 1FB00 Symbols for Legacy Computing 1FBFF @ Block mosaic terminal graphic characters @+ The term "sextant" refers to block mosaics divided into six parts. @@ -51355,8 +52935,8 @@ FFFF <not a character> @+ These codes are intended for process-internal uses. 1FFFE <not a character> 1FFFF <not a character> -@@ 20000 CJK Unified Ideographs Extension B 2A6DD -@@ 2A700 CJK Unified Ideographs Extension C 2B734 +@@ 20000 CJK Unified Ideographs Extension B 2A6DF +@@ 2A700 CJK Unified Ideographs Extension C 2B738 @@ 2B740 CJK Unified Ideographs Extension D 2B81D @@ 2B820 CJK Unified Ideographs Extension E 2CEA1 @@ 2CEB0 CJK Unified Ideographs Extension F 2EBE0 @@ -51453,6 +53033,7 @@ FFFF <not a character> 2F82B CJK COMPATIBILITY IDEOGRAPH-2F82B : 5317 2F82C CJK COMPATIBILITY IDEOGRAPH-2F82C + x 20984 : 5349 2F82D CJK COMPATIBILITY IDEOGRAPH-2F82D : 5351 @@ -51483,6 +53064,7 @@ FFFF <not a character> 2F83A CJK COMPATIBILITY IDEOGRAPH-2F83A : 53F1 2F83B CJK COMPATIBILITY IDEOGRAPH-2F83B + x 4DB8 : 5406 2F83C CJK COMPATIBILITY IDEOGRAPH-2F83C : 549E @@ -51559,6 +53141,7 @@ FFFF <not a character> 2F85F CJK COMPATIBILITY IDEOGRAPH-2F85F : 5962 2F860 CJK COMPATIBILITY IDEOGRAPH-2F860 + x 216A7 : 216A8 2F861 CJK COMPATIBILITY IDEOGRAPH-2F861 : 216EA @@ -51599,6 +53182,7 @@ FFFF <not a character> 2F873 CJK COMPATIBILITY IDEOGRAPH-2F873 : 5C06 2F874 CJK COMPATIBILITY IDEOGRAPH-2F874 + x 22450 : 5F53 2F875 CJK COMPATIBILITY IDEOGRAPH-2F875 : 5C22 @@ -51607,6 +53191,7 @@ FFFF <not a character> 2F877 CJK COMPATIBILITY IDEOGRAPH-2F877 : 5C60 2F878 CJK COMPATIBILITY IDEOGRAPH-2F878 + x 4DB9 : 5C6E 2F879 CJK COMPATIBILITY IDEOGRAPH-2F879 : 5CC0 @@ -51848,6 +53433,7 @@ FFFF <not a character> 2F8EF CJK COMPATIBILITY IDEOGRAPH-2F8EF : 6B21 2F8F0 CJK COMPATIBILITY IDEOGRAPH-2F8F0 + x 4DBE : 238A7 2F8F1 CJK COMPATIBILITY IDEOGRAPH-2F8F1 : 6B54 @@ -51874,6 +53460,7 @@ FFFF <not a character> 2F8FC CJK COMPATIBILITY IDEOGRAPH-2F8FC : 6CBF 2F8FD CJK COMPATIBILITY IDEOGRAPH-2F8FD + x 2DC09 : 6CCD 2F8FE CJK COMPATIBILITY IDEOGRAPH-2F8FE : 6C67 @@ -51890,6 +53477,7 @@ FFFF <not a character> 2F904 CJK COMPATIBILITY IDEOGRAPH-2F904 : 6D78 2F905 CJK COMPATIBILITY IDEOGRAPH-2F905 + x 23D40 : 6D85 2F906 CJK COMPATIBILITY IDEOGRAPH-2F906 : 23D1E @@ -51908,6 +53496,7 @@ FFFF <not a character> 2F90D CJK COMPATIBILITY IDEOGRAPH-2F90D : 23ED1 2F90E CJK COMPATIBILITY IDEOGRAPH-2F90E + x 23F1C : 6DF9 2F90F CJK COMPATIBILITY IDEOGRAPH-2F90F : 6F6E @@ -51936,6 +53525,7 @@ FFFF <not a character> 2F91B CJK COMPATIBILITY IDEOGRAPH-2F91B : 20525 2F91C CJK COMPATIBILITY IDEOGRAPH-2F91C + x 242B3 : 7145 2F91D CJK COMPATIBILITY IDEOGRAPH-2F91D : 24263 @@ -51958,6 +53548,7 @@ FFFF <not a character> 2F926 CJK COMPATIBILITY IDEOGRAPH-2F926 : 24735 2F927 CJK COMPATIBILITY IDEOGRAPH-2F927 + x 2AEC5 : 24814 2F928 CJK COMPATIBILITY IDEOGRAPH-2F928 : 737A @@ -52014,6 +53605,7 @@ FFFF <not a character> 2F942 CJK COMPATIBILITY IDEOGRAPH-2F942 : 250F2 2F943 CJK COMPATIBILITY IDEOGRAPH-2F943 + x 2511A : 25119 2F944 CJK COMPATIBILITY IDEOGRAPH-2F944 : 25133 @@ -52030,6 +53622,7 @@ FFFF <not a character> 2F94A CJK COMPATIBILITY IDEOGRAPH-2F94A : 778B 2F94B CJK COMPATIBILITY IDEOGRAPH-2F94B + x 25271 : 4046 2F94C CJK COMPATIBILITY IDEOGRAPH-2F94C : 4096 diff --git a/lib/unicore/NormalizationCorrections.txt b/lib/unicore/NormalizationCorrections.txt index 7144fb8935..a1a34d6bb6 100644 --- a/lib/unicore/NormalizationCorrections.txt +++ b/lib/unicore/NormalizationCorrections.txt @@ -1,6 +1,6 @@ -# NormalizationCorrections-13.0.0.txt -# Date: 2019-09-09, 19:50:00 GMT [KW, LI] -# © 2019 Unicode®, Inc. +# NormalizationCorrections-14.0.0.txt +# Date: 2021-03-16, 22:07:00 GMT [KW, LI] +# © 2021 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database diff --git a/lib/unicore/PropList.txt b/lib/unicore/PropList.txt index 7d2f44c56f..0a5a934682 100644 --- a/lib/unicore/PropList.txt +++ b/lib/unicore/PropList.txt @@ -1,6 +1,6 @@ -# PropList-13.0.0.txt -# Date: 2019-11-27, 03:13:28 GMT -# © 2019 Unicode®, Inc. +# PropList-14.0.0.txt +# Date: 2021-08-12, 23:13:05 GMT +# © 2021 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 # @@ -54,6 +54,7 @@ 2E1A ; Dash # Pd HYPHEN WITH DIAERESIS 2E3A..2E3B ; Dash # Pd [2] TWO-EM DASH..THREE-EM DASH 2E40 ; Dash # Pd DOUBLE HYPHEN +2E5D ; Dash # Pd OBLIQUE HYPHEN 301C ; Dash # Pd WAVE DASH 3030 ; Dash # Pd WAVY DASH 30A0 ; Dash # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN @@ -63,7 +64,7 @@ FE63 ; Dash # Pd SMALL HYPHEN-MINUS FF0D ; Dash # Pd FULLWIDTH HYPHEN-MINUS 10EAD ; Dash # Pd YEZIDI HYPHENATION MARK -# Total code points: 29 +# Total code points: 30 # ================================================ @@ -126,7 +127,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET 05C3 ; Terminal_Punctuation # Po HEBREW PUNCTUATION SOF PASUQ 060C ; Terminal_Punctuation # Po ARABIC COMMA 061B ; Terminal_Punctuation # Po ARABIC SEMICOLON -061E..061F ; Terminal_Punctuation # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; Terminal_Punctuation # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 06D4 ; Terminal_Punctuation # Po ARABIC FULL STOP 0700..070A ; Terminal_Punctuation # Po [11] SYRIAC END OF PARAGRAPH..SYRIAC CONTRACTION 070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS @@ -150,6 +151,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET 1AA8..1AAB ; Terminal_Punctuation # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU 1B5A..1B5B ; Terminal_Punctuation # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5D..1B5F ; Terminal_Punctuation # Po [3] BALINESE CARIK PAMUNGKAH..BALINESE CARIK PAREREN +1B7D..1B7E ; Terminal_Punctuation # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1C3B..1C3F ; Terminal_Punctuation # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; Terminal_Punctuation # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 203C..203D ; Terminal_Punctuation # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG @@ -159,6 +161,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET 2E41 ; Terminal_Punctuation # Po REVERSED COMMA 2E4C ; Terminal_Punctuation # Po MEDIEVAL COMMA 2E4E..2E4F ; Terminal_Punctuation # Po [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER +2E53..2E54 ; Terminal_Punctuation # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK 3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK @@ -189,6 +192,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 10B3A..10B3F ; Terminal_Punctuation # Po [6] TINY TWO DOTS OVER ONE DOT PUNCTUATION..LARGE ONE RING OVER TWO RINGS PUNCTUATION 10B99..10B9C ; Terminal_Punctuation # Po [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT 10F55..10F59 ; Terminal_Punctuation # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; Terminal_Punctuation # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 11047..1104D ; Terminal_Punctuation # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 110BE..110C1 ; Terminal_Punctuation # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 11141..11143 ; Terminal_Punctuation # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK @@ -220,7 +224,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 267 +# Total code points: 276 # ================================================ @@ -600,6 +604,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1A6D..1A72 ; Other_Alphabetic # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI 1A73..1A74 ; Other_Alphabetic # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG 1ABF..1AC0 ; Other_Alphabetic # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ACC..1ACE ; Other_Alphabetic # Mn [3] COMBINING LATIN SMALL LETTER INSULAR G..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Other_Alphabetic # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Other_Alphabetic # Mc BALINESE SIGN BISAH 1B35 ; Other_Alphabetic # Mc BALINESE VOWEL SIGN TEDUNG @@ -686,10 +691,12 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA 11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA 11038..11045 ; Other_Alphabetic # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU +11073..11074 ; Other_Alphabetic # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 11082 ; Other_Alphabetic # Mc KAITHI SIGN VISARGA 110B0..110B2 ; Other_Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Other_Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Other_Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110C2 ; Other_Alphabetic # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Other_Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Other_Alphabetic # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Other_Alphabetic # Mc CHAKMA VOWEL SIGN E @@ -815,7 +822,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1398 +# Total code points: 1404 # ================================================ @@ -824,7 +831,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE 3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 3400..4DBF ; Ideographic # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Ideographic # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC +4E00..9FFF ; Ideographic # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 16FE4 ; Ideographic # Mn KHITAN SMALL SCRIPT FILLER @@ -832,15 +839,15 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 18800..18CD5 ; Ideographic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Ideographic # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB -20000..2A6DD ; Ideographic # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Ideographic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 101652 +# Total code points: 101661 # ================================================ @@ -885,6 +892,9 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 07EB..07F3 ; Diacritic # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE 07F4..07F5 ; Diacritic # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE 0818..0819 ; Diacritic # Mn [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH +0898..089F ; Diacritic # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08C9 ; Diacritic # Lm ARABIC SMALL FARSI YEH +08CA..08D2 ; Diacritic # Mn [9] ARABIC SMALL HIGH FARSI YEH..ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW 08E3..08FE ; Diacritic # Mn [28] ARABIC TURNED DAMMA BELOW..ARABIC DAMMA WITH DOT 093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA 094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA @@ -901,6 +911,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA 0B55 ; Diacritic # Mn ORIYA SIGN OVERLINE 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA +0C3C ; Diacritic # Mn TELUGU SIGN NUKTA 0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA 0CBC ; Diacritic # Mn KANNADA SIGN NUKTA 0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA @@ -928,12 +939,16 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 108F ; Diacritic # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5 109A..109B ; Diacritic # Mc [2] MYANMAR SIGN KHAMTI TONE-1..MYANMAR SIGN KHAMTI TONE-3 135D..135F ; Diacritic # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1714 ; Diacritic # Mn TAGALOG SIGN VIRAMA +1715 ; Diacritic # Mc TAGALOG SIGN PAMUDPOD 17C9..17D3 ; Diacritic # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Diacritic # Mn KHMER SIGN ATTHACAN 1939..193B ; Diacritic # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A75..1A7C ; Diacritic # Mn [8] TAI THAM SIGN TONE-1..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Diacritic # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Diacritic # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; Diacritic # Me COMBINING PARENTHESES OVERLAY +1AC1..1ACB ; Diacritic # Mn [11] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING TRIPLE ACUTE ACCENT 1B34 ; Diacritic # Mn BALINESE SIGN REREKAN 1B44 ; Diacritic # Mc BALINESE ADEG ADEG 1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG @@ -952,8 +967,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1CF8..1CF9 ; Diacritic # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW -1DF5..1DF9 ; Diacritic # Mn [5] COMBINING UP TACK ABOVE..COMBINING WIDE INVERTED BRIDGE BELOW -1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DF5..1DFF ; Diacritic # Mn [11] COMBINING UP TACK ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Diacritic # Sk GREEK KORONIS 1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI 1FCD..1FCF ; Diacritic # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -1008,10 +1022,16 @@ FF70 ; Diacritic # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND FF9E..FF9F ; Diacritic # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK FFE3 ; Diacritic # Sk FULLWIDTH MACRON 102E0 ; Diacritic # Mn COPTIC EPACT THOUSANDS MARK +10780..10785 ; Diacritic # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Diacritic # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Diacritic # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10AE5..10AE6 ; Diacritic # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D22..10D23 ; Diacritic # Lo [2] HANIFI ROHINGYA MARK SAKIN..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Diacritic # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11046 ; Diacritic # Mn BRAHMI VIRAMA +11070 ; Diacritic # Mn BRAHMI SIGN OLD TAMIL VIRAMA 110B9..110BA ; Diacritic # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA 11133..11134 ; Diacritic # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA 11173 ; Diacritic # Mn MAHAJANI SIGN NUKTA @@ -1049,18 +1069,24 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FF0..16FF1 ; Diacritic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY +1AFF0..1AFF3 ; Diacritic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Diacritic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Diacritic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1CF00..1CF2D ; Diacritic # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Diacritic # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Diacritic # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; Diacritic # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO 1E130..1E136 ; Diacritic # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Diacritic # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Diacritic # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Diacritic # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 882 +# Total code points: 1064 # ================================================ @@ -1088,6 +1114,7 @@ AA70 ; Extender # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION AADD ; Extender # Lm TAI VIET SYMBOL SAM AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK +10781..10782 ; Extender # Lm [2] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON 1135D ; Extender # Lo GRANTHA SIGN PLUTA 115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3 11A98 ; Extender # Mn SOYOMBO GEMINATION MARK @@ -1097,7 +1124,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 1E13C..1E13D ; Extender # Lm [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 48 +# Total code points: 50 # ================================================ @@ -1121,8 +1148,12 @@ A69C..A69D ; Other_Lowercase # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..M A770 ; Other_Lowercase # Lm MODIFIER LETTER US A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Other_Lowercase # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK +10780 ; Other_Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Other_Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Other_Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL -# Total code points: 189 +# Total code points: 244 # ================================================ @@ -1211,7 +1242,7 @@ E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG # ================================================ 3400..4DBF ; Unified_Ideograph # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Unified_Ideograph # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC +4E00..9FFF ; Unified_Ideograph # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11 FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14 @@ -1219,14 +1250,14 @@ FA1F ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA1F FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21 FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24 FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29 -20000..2A6DD ; Unified_Ideograph # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Unified_Ideograph # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Unified_Ideograph # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 30000..3134A ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 92856 +# Total code points: 92865 # ================================================ @@ -1291,8 +1322,9 @@ E0001 ; Deprecated # Cf LANGUAGE TAG 1D62A..1D62B ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF ITALIC SMALL I..MATHEMATICAL SANS-SERIF ITALIC SMALL J 1D65E..1D65F ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J 1D692..1D693 ; Soft_Dotted # L& [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J +1DF1A ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK -# Total code points: 46 +# Total code points: 47 # ================================================ @@ -1330,7 +1362,7 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET 002E ; Sentence_Terminal # Po FULL STOP 003F ; Sentence_Terminal # Po QUESTION MARK 0589 ; Sentence_Terminal # Po ARMENIAN FULL STOP -061E..061F ; Sentence_Terminal # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; Sentence_Terminal # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 06D4 ; Sentence_Terminal # Po ARABIC FULL STOP 0700..0702 ; Sentence_Terminal # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP 07F9 ; Sentence_Terminal # Po NKO EXCLAMATION MARK @@ -1349,12 +1381,14 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET 1AA8..1AAB ; Sentence_Terminal # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU 1B5A..1B5B ; Sentence_Terminal # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5E..1B5F ; Sentence_Terminal # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN +1B7D..1B7E ; Sentence_Terminal # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1C3B..1C3C ; Sentence_Terminal # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL 1C7E..1C7F ; Sentence_Terminal # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 203C..203D ; Sentence_Terminal # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG 2047..2049 ; Sentence_Terminal # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK 2E2E ; Sentence_Terminal # Po REVERSED QUESTION MARK 2E3C ; Sentence_Terminal # Po STENOGRAPHIC FULL STOP +2E53..2E54 ; Sentence_Terminal # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK 3002 ; Sentence_Terminal # Po IDEOGRAPHIC FULL STOP A4FF ; Sentence_Terminal # Po LISU PUNCTUATION FULL STOP A60E..A60F ; Sentence_Terminal # Po [2] VAI FULL STOP..VAI QUESTION MARK @@ -1375,6 +1409,7 @@ FF1F ; Sentence_Terminal # Po FULLWIDTH QUESTION MARK FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP 10A56..10A57 ; Sentence_Terminal # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA 10F55..10F59 ; Sentence_Terminal # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; Sentence_Terminal # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 11047..11048 ; Sentence_Terminal # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA 110BE..110C1 ; Sentence_Terminal # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 11141..11143 ; Sentence_Terminal # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK @@ -1403,15 +1438,16 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP 1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP -# Total code points: 143 +# Total code points: 152 # ================================================ 180B..180D ; Variation_Selector # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Variation_Selector # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR FE00..FE0F ; Variation_Selector # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 259 +# Total code points: 260 # ================================================ @@ -1644,8 +1680,17 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; Pattern_Syntax # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; Pattern_Syntax # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; Pattern_Syntax # Po TIRONIAN SIGN CAPITAL ET -2E53..2E7F ; Pattern_Syntax # Cn [45] <reserved-2E53>..<reserved-2E7F> +2E52..2E54 ; Pattern_Syntax # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Pattern_Syntax # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Pattern_Syntax # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Pattern_Syntax # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Pattern_Syntax # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Pattern_Syntax # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Pattern_Syntax # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; Pattern_Syntax # Pd OBLIQUE HYPHEN +2E5E..2E7F ; Pattern_Syntax # Cn [34] <reserved-2E5E>..<reserved-2E7F> 3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK 3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET 3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET @@ -1682,11 +1727,12 @@ FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT 0600..0605 ; Prepended_Concatenation_Mark # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE 06DD ; Prepended_Concatenation_Mark # Cf ARABIC END OF AYAH 070F ; Prepended_Concatenation_Mark # Cf SYRIAC ABBREVIATION MARK +0890..0891 ; Prepended_Concatenation_Mark # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Prepended_Concatenation_Mark # Cf ARABIC DISPUTED END OF AYAH 110BD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN 110CD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN ABOVE -# Total code points: 11 +# Total code points: 13 # ================================================ diff --git a/lib/unicore/PropValueAliases.txt b/lib/unicore/PropValueAliases.txt index 2023baf4d2..f0cb26bdab 100644 --- a/lib/unicore/PropValueAliases.txt +++ b/lib/unicore/PropValueAliases.txt @@ -1,6 +1,6 @@ -# PropertyValueAliases-13.0.0.txt -# Date: 2019-11-13, 21:52:10 GMT -# © 2019 Unicode®, Inc. +# PropertyValueAliases-14.0.0.txt +# Date: 2021-05-10, 21:08:53 GMT +# © 2021 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 # @@ -89,6 +89,7 @@ age; 11.0 ; V11_0 age; 12.0 ; V12_0 age; 12.1 ; V12_1 age; 13.0 ; V13_0 +age; 14.0 ; V14_0 age; NA ; Unassigned # Alphabetic (Alpha) @@ -160,6 +161,7 @@ blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers blk; Ancient_Symbols ; Ancient_Symbols blk; Arabic ; Arabic blk; Arabic_Ext_A ; Arabic_Extended_A +blk; Arabic_Ext_B ; Arabic_Extended_B blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A blk; Arabic_PF_B ; Arabic_Presentation_Forms_B @@ -216,6 +218,7 @@ blk; Cuneiform ; Cuneiform blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation blk; Currency_Symbols ; Currency_Symbols blk; Cypriot_Syllabary ; Cypriot_Syllabary +blk; Cypro_Minoan ; Cypro_Minoan blk; Cyrillic ; Cyrillic blk; Cyrillic_Ext_A ; Cyrillic_Extended_A blk; Cyrillic_Ext_B ; Cyrillic_Extended_B @@ -246,6 +249,7 @@ blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement blk; Ethiopic ; Ethiopic blk; Ethiopic_Ext ; Ethiopic_Extended blk; Ethiopic_Ext_A ; Ethiopic_Extended_A +blk; Ethiopic_Ext_B ; Ethiopic_Extended_B blk; Ethiopic_Sup ; Ethiopic_Supplement blk; Geometric_Shapes ; Geometric_Shapes blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended @@ -285,6 +289,7 @@ blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B blk; Javanese ; Javanese blk; Kaithi ; Kaithi blk; Kana_Ext_A ; Kana_Extended_A +blk; Kana_Ext_B ; Kana_Extended_B blk; Kana_Sup ; Kana_Supplement blk; Kanbun ; Kanbun blk; Kangxi ; Kangxi_Radicals @@ -306,6 +311,8 @@ blk; Latin_Ext_B ; Latin_Extended_B blk; Latin_Ext_C ; Latin_Extended_C blk; Latin_Ext_D ; Latin_Extended_D blk; Latin_Ext_E ; Latin_Extended_E +blk; Latin_Ext_F ; Latin_Extended_F +blk; Latin_Ext_G ; Latin_Extended_G blk; Lepcha ; Lepcha blk; Letterlike_Symbols ; Letterlike_Symbols blk; Limbu ; Limbu @@ -372,6 +379,7 @@ blk; Old_Persian ; Old_Persian blk; Old_Sogdian ; Old_Sogdian blk; Old_South_Arabian ; Old_South_Arabian blk; Old_Turkic ; Old_Turkic +blk; Old_Uyghur ; Old_Uyghur blk; Oriya ; Oriya blk; Ornamental_Dingbats ; Ornamental_Dingbats blk; Osage ; Osage @@ -433,6 +441,7 @@ blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols blk; Takri ; Takri blk; Tamil ; Tamil blk; Tamil_Sup ; Tamil_Supplement +blk; Tangsa ; Tangsa blk; Tangut ; Tangut blk; Tangut_Components ; Tangut_Components blk; Tangut_Sup ; Tangut_Supplement @@ -442,13 +451,16 @@ blk; Thai ; Thai blk; Tibetan ; Tibetan blk; Tifinagh ; Tifinagh blk; Tirhuta ; Tirhuta +blk; Toto ; Toto blk; Transport_And_Map ; Transport_And_Map_Symbols blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended +blk; UCAS_Ext_A ; Unified_Canadian_Aboriginal_Syllabics_Extended_A blk; Ugaritic ; Ugaritic blk; Vai ; Vai blk; Vedic_Ext ; Vedic_Extensions blk; Vertical_Forms ; Vertical_Forms +blk; Vithkuqi ; Vithkuqi blk; VS ; Variation_Selectors blk; VS_Sup ; Variation_Selectors_Supplement blk; Wancho ; Wancho @@ -458,6 +470,7 @@ blk; Yi_Radicals ; Yi_Radicals blk; Yi_Syllables ; Yi_Syllables blk; Yijing ; Yijing_Hexagram_Symbols blk; Zanabazar_Square ; Zanabazar_Square +blk; Znamenny_Music ; Znamenny_Musical_Notation # Canonical_Combining_Class (ccc) @@ -1032,6 +1045,8 @@ jg ; Taw ; Taw jg ; Teh_Marbuta ; Teh_Marbuta jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal jg ; Teth ; Teth +jg ; Thin_Yeh ; Thin_Yeh +jg ; Vertical_Tail ; Vertical_Tail jg ; Waw ; Waw jg ; Yeh ; Yeh jg ; Yeh_Barree ; Yeh_Barree @@ -1262,6 +1277,7 @@ sc ; Cham ; Cham sc ; Cher ; Cherokee sc ; Chrs ; Chorasmian sc ; Copt ; Coptic ; Qaac +sc ; Cpmn ; Cypro_Minoan sc ; Cprt ; Cypriot sc ; Cyrl ; Cyrillic sc ; Deva ; Devanagari @@ -1341,6 +1357,7 @@ sc ; Orkh ; Old_Turkic sc ; Orya ; Oriya sc ; Osge ; Osage sc ; Osma ; Osmanya +sc ; Ougr ; Old_Uyghur sc ; Palm ; Palmyrene sc ; Pauc ; Pau_Cin_Hau sc ; Perm ; Old_Permic @@ -1383,8 +1400,11 @@ sc ; Thaa ; Thaana sc ; Thai ; Thai sc ; Tibt ; Tibetan sc ; Tirh ; Tirhuta +sc ; Tnsa ; Tangsa +sc ; Toto ; Toto sc ; Ugar ; Ugaritic sc ; Vaii ; Vai +sc ; Vith ; Vithkuqi sc ; Wara ; Warang_Citi sc ; Wcho ; Wancho sc ; Xpeo ; Old_Persian diff --git a/lib/unicore/PropertyAliases.txt b/lib/unicore/PropertyAliases.txt index 04644b8a28..3e4b429e45 100644 --- a/lib/unicore/PropertyAliases.txt +++ b/lib/unicore/PropertyAliases.txt @@ -1,6 +1,6 @@ -# PropertyAliases-13.0.0.txt -# Date: 2019-10-23, 03:46:32 GMT -# © 2019 Unicode®, Inc. +# PropertyAliases-14.0.0.txt +# Date: 2021-03-08, 19:35:48 GMT +# © 2021 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 # diff --git a/lib/unicore/ReadMe.txt b/lib/unicore/ReadMe.txt index 390624de3d..e7c080f9f0 100644 --- a/lib/unicore/ReadMe.txt +++ b/lib/unicore/ReadMe.txt @@ -1,6 +1,6 @@ # Unicode Character Database -# Date: 2019-09-11, 16:03:00 GMT [KW] -# © 2019 Unicode®, Inc. +# Date: 2021-09-10, 17:22:00 GMT [KW] +# © 2021 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 https://www.unicode.org/terms_of_use.html # @@ -10,7 +10,7 @@ # UAX #44, "Unicode Character Database" # UTS #51, "Unicode Emoji" # -# The UAXes and UTS #51 can be accessed at https://www.unicode.org/versions/Unicode13.0.0/ +# The UAXes and UTS #51 can be accessed at https://www.unicode.org/versions/Unicode14.0.0/ -This directory contains the preliminary data files under development -for the Unicode Character Database, for Version 13.0.0 of the Unicode Standard. +This directory contains the final data files +for the Unicode Character Database, for Version 14.0.0 of the Unicode Standard. diff --git a/lib/unicore/ScriptExtensions.txt b/lib/unicore/ScriptExtensions.txt index b561feeb29..3f5cd1c0db 100644 --- a/lib/unicore/ScriptExtensions.txt +++ b/lib/unicore/ScriptExtensions.txt @@ -1,6 +1,6 @@ -# ScriptExtensions-13.0.0.txt -# Date: 2020-01-22, 00:07:43 GMT -# © 2020 Unicode®, Inc. +# ScriptExtensions-14.0.0.txt +# Date: 2021-06-04, 02:19:38 GMT +# © 2021 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 # @@ -11,10 +11,10 @@ # with more than one script, but with a limited number of scripts. # For each code point, there is one or more property values. Each such value is a Script property value. # For more information, see: -# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/ +# UAX #24, Unicode Script Property: https://www.unicode.org/reports/tr24/ # Especially the sections: -# http://www.unicode.org/reports/tr24/#Assignment_Script_Values -# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values +# https://www.unicode.org/reports/tr24/#Assignment_Script_Values +# https://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values # # Each Script_Extensions value in this file consists of a set # of one or more abbreviated Script property values. The ordering of the @@ -119,6 +119,14 @@ # ================================================ +# Script_Extensions=Syrc + +1DFA ; Syrc # Mn COMBINING DOT BELOW LEFT + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Arab Copt 102E0 ; Arab Copt # Mn COPTIC EPACT THOUSANDS MARK @@ -136,6 +144,15 @@ # ================================================ +# Script_Extensions=Arab Nkoo + +FD3E ; Arab Nkoo # Pe ORNATE LEFT PARENTHESIS +FD3F ; Arab Nkoo # Ps ORNATE RIGHT PARENTHESIS + +# Total code points: 2 + +# ================================================ + # Script_Extensions=Arab Syrc 064B..0655 ; Arab Syrc # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW @@ -186,10 +203,10 @@ A9CF ; Bugi Java # Lm JAVANESE PANGRANGKEP # Script_Extensions=Cprt Linb -10100..10102 ; Cprt Linb # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK +10102 ; Cprt Linb # Po AEGEAN CHECK MARK 10137..1013F ; Cprt Linb # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT -# Total code points: 12 +# Total code points: 10 # ================================================ @@ -342,6 +359,14 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW # ================================================ +# Script_Extensions=Mani Ougr + +10AF2 ; Mani Ougr # Po MANICHAEAN PUNCTUATION DOUBLE DOT WITHIN DOT + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Mong Phag 1802..1803 ; Mong Phag # Po [2] MONGOLIAN COMMA..MONGOLIAN FULL STOP @@ -383,6 +408,14 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW # ================================================ +# Script_Extensions=Cpmn Cprt Linb + +10100..10101 ; Cpmn Cprt Linb # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT + +# Total code points: 2 + +# ================================================ + # Script_Extensions=Cprt Lina Linb 10107..10133 ; Cprt Lina Linb # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND @@ -449,16 +482,6 @@ A92E ; Kali Latn Mymr # Po KAYAH LI SIGN CWI # ================================================ -# Script_Extensions=Arab Rohg Syrc Thaa Yezi - -060C ; Arab Rohg Syrc Thaa Yezi # Po ARABIC COMMA -061B ; Arab Rohg Syrc Thaa Yezi # Po ARABIC SEMICOLON -061F ; Arab Rohg Syrc Thaa Yezi # Po ARABIC QUESTION MARK - -# Total code points: 3 - -# ================================================ - # Script_Extensions=Bopo Hang Hani Hira Kana 3003 ; Bopo Hang Hani Hira Kana # Po DITTO MARK @@ -474,6 +497,15 @@ FE45..FE46 ; Bopo Hang Hani Hira Kana # Po [2] SESAME DOT..WHITE SESAME DOT # ================================================ +# Script_Extensions=Arab Nkoo Rohg Syrc Thaa Yezi + +060C ; Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC COMMA +061B ; Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC SEMICOLON + +# Total code points: 2 + +# ================================================ + # Script_Extensions=Bopo Hang Hani Hira Kana Yiii 3001..3002 ; Bopo Hang Hani Hira Kana Yiii # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP @@ -513,9 +545,9 @@ FF64..FF65 ; Bopo Hang Hani Hira Kana Yiii # Po [2] HALFWIDTH IDEOGRAPHIC C # ================================================ -# Script_Extensions=Adlm Arab Mand Mani Phlp Rohg Sogd Syrc +# Script_Extensions=Adlm Arab Nkoo Rohg Syrc Thaa Yezi -0640 ; Adlm Arab Mand Mani Phlp Rohg Sogd Syrc # Lm ARABIC TATWEEL +061F ; Adlm Arab Nkoo Rohg Syrc Thaa Yezi # Po ARABIC QUESTION MARK # Total code points: 1 @@ -529,6 +561,14 @@ FF64..FF65 ; Bopo Hang Hani Hira Kana Yiii # Po [2] HALFWIDTH IDEOGRAPHIC C # ================================================ +# Script_Extensions=Adlm Arab Mand Mani Ougr Phlp Rohg Sogd Syrc + +0640 ; Adlm Arab Mand Mani Ougr Phlp Rohg Sogd Syrc # Lm ARABIC TATWEEL + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Deva Dogr Gujr Guru Khoj Kthi Mahj Modi Sind Takr Tirh A836..A837 ; Deva Dogr Gujr Guru Khoj Kthi Mahj Modi Sind Takr Tirh # So [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK diff --git a/lib/unicore/Scripts.txt b/lib/unicore/Scripts.txt index e0363f54d1..a138373011 100644 --- a/lib/unicore/Scripts.txt +++ b/lib/unicore/Scripts.txt @@ -1,16 +1,16 @@ -# Scripts-13.0.0.txt -# Date: 2020-01-22, 00:07:43 GMT -# © 2020 Unicode®, Inc. +# Scripts-14.0.0.txt +# Date: 2021-07-10, 00:35:31 GMT +# © 2021 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see http://www.unicode.org/reports/tr44/ # For more information, see: -# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/ +# UAX #24, Unicode Script Property: https://www.unicode.org/reports/tr24/ # Especially the sections: -# http://www.unicode.org/reports/tr24/#Assignment_Script_Values -# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values +# https://www.unicode.org/reports/tr24/#Assignment_Script_Values +# https://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values # # ================================================ @@ -154,7 +154,7 @@ 208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN 208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS -20A0..20BF ; Common # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; Common # Sc [33] EURO-CURRENCY SIGN..SOM SIGN 2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT 2102 ; Common # L& DOUBLE-STRUCK CAPITAL C 2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA @@ -347,7 +347,16 @@ 2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; Common # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; Common # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; Common # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; Common # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; Common # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Common # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Common # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Common # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Common # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Common # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Common # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Common # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; Common # Pd OBLIQUE HYPHEN 2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 3000 ; Common # Zs IDEOGRAPHIC SPACE 3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK @@ -511,9 +520,8 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 10190..1019C ; Common # So [13] ROMAN SEXTANS SIGN..ASCIA SYMBOL 101D0..101FC ; Common # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 102E1..102FB ; Common # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED -16FE2 ; Common # Po OLD CHINESE HOOK MARK -16FE3 ; Common # Lm OLD CHINESE ITERATION MARK 1BCA0..1BCA3 ; Common # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF50..1CFC3 ; Common # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Common # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Common # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; Common # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -523,7 +531,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1D173..1D17A ; Common # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D183..1D184 ; Common # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; Common # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; Common # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; Common # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D2E0..1D2F3 ; Common # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN 1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING 1D360..1D378 ; Common # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE @@ -593,35 +601,36 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F400..1F6D7 ; Common # So [728] RAT..ELEVATOR -1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DD..1F6EC ; Common # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6F0..1F6FC ; Common # So [13] SATELLITE..ROLLER SKATE 1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8 ; Common # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; Common # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; Common # So HEAVY EQUALS SIGN 1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; Common # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; Common # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; Common # So [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; Common # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; Common # So [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; Common # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Common # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74 ; Common # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; Common # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; Common # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; Common # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; Common # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; Common # So [7] FLY..FEATHER -1FAC0..1FAC2 ; Common # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; Common # So [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC ; Common # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; Common # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; Common # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; Common # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; Common # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; Common # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; Common # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; Common # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; Common # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 8087 +# Total code points: 8252 # ================================================ @@ -664,8 +673,11 @@ A770 ; Latin # Lm MODIFIER LETTER US A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; Latin # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Latin # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Latin # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Latin # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Latin # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Latin # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Latin # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Latin # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -679,8 +691,14 @@ AB69 ; Latin # Lm MODIFIER LETTER SMALL TURNED W FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z +10780..10785 ; Latin # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Latin # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Latin # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +1DF00..1DF09 ; Latin # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; Latin # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL -# Total code points: 1374 +# Total code points: 1475 # ================================================ @@ -820,7 +838,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 060E..060F ; Arabic # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 0610..061A ; Arabic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061C ; Arabic # Cf ARABIC LETTER MARK -061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK +061D..061E ; Arabic # Po [2] ARABIC END OF TEXT MARK..ARABIC TRIPLE DOT PUNCTUATION MARK 0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH 0656..065F ; Arabic # Mn [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW @@ -843,18 +861,25 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN 06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V 0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE -08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; Arabic # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; Arabic # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; Arabic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; Arabic # Sk ARABIC RAISED ROUND DOT +0889..088E ; Arabic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891 ; Arabic # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; Arabic # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; Arabic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; Arabic # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; Arabic # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Arabic # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM +FD40..FD4F ; Arabic # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Arabic # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; Arabic # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; Arabic # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Arabic # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; Arabic # Sc RIAL SIGN -FDFD ; Arabic # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; Arabic # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM 10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS @@ -893,7 +918,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1291 +# Total code points: 1365 # ================================================ @@ -1113,6 +1138,7 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0C0E..0C10 ; Telugu # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; Telugu # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; Telugu # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; Telugu # Mn TELUGU SIGN NUKTA 0C3D ; Telugu # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; Telugu # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; Telugu # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -1120,6 +1146,7 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0C4A..0C4D ; Telugu # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; Telugu # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Telugu # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Telugu # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Telugu # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Telugu # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; Telugu # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -1127,7 +1154,7 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; Telugu # So TELUGU SIGN TUUMU -# Total code points: 98 +# Total code points: 100 # ================================================ @@ -1150,13 +1177,13 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0CCA..0CCB ; Kannada # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; Kannada # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Kannada # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; Kannada # Lo KANNADA LETTER FA +0CDD..0CDE ; Kannada # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Kannada # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Kannada # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -# Total code points: 89 +# Total code points: 90 # ================================================ @@ -1411,8 +1438,12 @@ AB09..AB0E ; Ethiopic # Lo [6] ETHIOPIC SYLLABLE DDHU..ETHIOPIC SYLLABLE DD AB11..AB16 ; Ethiopic # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO AB20..AB26 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO AB28..AB2E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO +1E7E0..1E7E6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Ethiopic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Ethiopic # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE -# Total code points: 495 +# Total code points: 523 # ================================================ @@ -1430,8 +1461,9 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT 166E ; Canadian_Aboriginal # Po CANADIAN SYLLABICS FULL STOP 166F..167F ; Canadian_Aboriginal # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W 18B0..18F5 ; Canadian_Aboriginal # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S +11AB0..11ABF ; Canadian_Aboriginal # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA -# Total code points: 710 +# Total code points: 726 # ================================================ @@ -1480,6 +1512,7 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT 1807..180A ; Mongolian # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; Mongolian # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Mongolian # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Mongolian # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; Mongolian # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -1491,18 +1524,18 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT 18AA ; Mongolian # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 11660..1166C ; Mongolian # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT -# Total code points: 167 +# Total code points: 168 # ================================================ 3041..3096 ; Hiragana # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE 309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK 309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI -1B001..1B11E ; Hiragana # Lo [286] HIRAGANA LETTER ARCHAIC YE..HENTAIGANA LETTER N-MU-MO-2 +1B001..1B11F ; Hiragana # Lo [287] HIRAGANA LETTER ARCHAIC YE..HIRAGANA LETTER ARCHAIC WU 1B150..1B152 ; Hiragana # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1F200 ; Hiragana # So SQUARE HIRAGANA HOKA -# Total code points: 379 +# Total code points: 380 # ================================================ @@ -1514,10 +1547,14 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT 3300..3357 ; Katakana # So [88] SQUARE APAATO..SQUARE WATTO FF66..FF6F ; Katakana # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +1AFF0..1AFF3 ; Katakana # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Katakana # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E +1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU 1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N -# Total code points: 304 +# Total code points: 320 # ================================================ @@ -1538,19 +1575,21 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK 3400..4DBF ; Han # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Han # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC +4E00..9FFF ; Han # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 +16FE2 ; Han # Po OLD CHINESE HOOK MARK +16FE3 ; Han # Lm OLD CHINESE ITERATION MARK 16FF0..16FF1 ; Han # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY -20000..2A6DD ; Han # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Han # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Han # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Han # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 94204 +# Total code points: 94215 # ================================================ @@ -1593,15 +1632,14 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE 0951..0954 ; Inherited # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT 1AB0..1ABD ; Inherited # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Inherited # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Inherited # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Inherited # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1CD0..1CD2 ; Inherited # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; Inherited # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE2..1CE8 ; Inherited # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL 1CED ; Inherited # Mn VEDIC SIGN TIRYAK 1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Inherited # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Inherited # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Inherited # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Inherited # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Inherited # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -1615,26 +1653,30 @@ FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CON 101FD ; Inherited # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE 102E0 ; Inherited # Mn COPTIC EPACT THOUSANDS MARK 1133B ; Inherited # Mn COMBINING BINDU BELOW +1CF00..1CF2D ; Inherited # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Inherited # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Inherited # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D17B..1D182 ; Inherited # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Inherited # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 573 +# Total code points: 657 # ================================================ -1700..170C ; Tagalog # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Tagalog # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; Tagalog # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; Tagalog # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1715 ; Tagalog # Mc TAGALOG SIGN PAMUDPOD +171F ; Tagalog # Lo TAGALOG LETTER ARCHAIC RA -# Total code points: 20 +# Total code points: 23 # ================================================ 1720..1731 ; Hanunoo # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; Hanunoo # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Hanunoo # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; Hanunoo # Mc HANUNOO SIGN PAMUDPOD # Total code points: 21 @@ -1762,15 +1804,14 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2 # ================================================ -2C00..2C2E ; Glagolitic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Glagolitic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C00..2C5F ; Glagolitic # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 1E000..1E006 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Glagolitic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Glagolitic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Glagolitic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA -# Total code points: 132 +# Total code points: 134 # ================================================ @@ -1836,14 +1877,15 @@ A82C ; Syloti_Nagri # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA 1B3D..1B41 ; Balinese # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; Balinese # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; Balinese # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; Balinese # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Balinese # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; Balinese # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; Balinese # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; Balinese # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73 ; Balinese # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C ; Balinese # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; Balinese # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG -# Total code points: 121 +# Total code points: 124 # ================================================ @@ -2178,9 +2220,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 110BB..110BC ; Kaithi # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD ; Kaithi # Cf KAITHI NUMBER SIGN 110BE..110C1 ; Kaithi # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110C2 ; Kaithi # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; Kaithi # Cf KAITHI NUMBER SIGN ABOVE -# Total code points: 67 +# Total code points: 68 # ================================================ @@ -2207,9 +2250,13 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 11047..1104D ; Brahmi # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; Brahmi # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; Brahmi # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; Brahmi # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; Brahmi # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; Brahmi # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; Brahmi # Lo BRAHMI LETTER OLD TAMIL LLA 1107F ; Brahmi # Mn BRAHMI NUMBER JOINER -# Total code points: 109 +# Total code points: 115 # ================================================ @@ -2301,9 +2348,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 116B6 ; Takri # Mc TAKRI SIGN VIRAMA 116B7 ; Takri # Mn TAKRI SIGN NUKTA 116B8 ; Takri # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; Takri # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; Takri # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE -# Total code points: 67 +# Total code points: 68 # ================================================ @@ -2561,8 +2609,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 1173A..1173B ; Ahom # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; Ahom # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; Ahom # So AHOM SYMBOL VI +11740..11746 ; Ahom # Lo [7] AHOM LETTER CA..AHOM LETTER LLA -# Total code points: 58 +# Total code points: 65 # ================================================ @@ -2897,4 +2946,46 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 47 +# ================================================ + +12F90..12FF0 ; Cypro_Minoan # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; Cypro_Minoan # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 + +# Total code points: 99 + +# ================================================ + +10F70..10F81 ; Old_Uyghur # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; Old_Uyghur # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +10F86..10F89 ; Old_Uyghur # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS + +# Total code points: 26 + +# ================================================ + +16A70..16ABE ; Tangsa # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; Tangsa # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE + +# Total code points: 89 + +# ================================================ + +1E290..1E2AD ; Toto # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; Toto # Mn TOTO SIGN RISING TONE + +# Total code points: 31 + +# ================================================ + +10570..1057A ; Vithkuqi # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Vithkuqi # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Vithkuqi # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Vithkuqi # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Vithkuqi # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Vithkuqi # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Vithkuqi # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Vithkuqi # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE + +# Total code points: 70 + # EOF diff --git a/lib/unicore/SpecialCasing.txt b/lib/unicore/SpecialCasing.txt index 2a1a5a1d6b..1c2e968a8c 100644 --- a/lib/unicore/SpecialCasing.txt +++ b/lib/unicore/SpecialCasing.txt @@ -1,6 +1,6 @@ -# SpecialCasing-13.0.0.txt -# Date: 2019-09-08, 23:31:24 GMT -# © 2019 Unicode®, Inc. +# SpecialCasing-14.0.0.txt +# Date: 2021-03-08, 19:35:55 GMT +# © 2021 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 # diff --git a/lib/unicore/StandardizedVariants.txt b/lib/unicore/StandardizedVariants.txt index ee386cd920..5c3c0149ba 100644 --- a/lib/unicore/StandardizedVariants.txt +++ b/lib/unicore/StandardizedVariants.txt @@ -1,7 +1,7 @@ -# StandardizedVariants-13.0.0.txt -# Date: 2019-05-21, 17:56:00 GMT [KW, LI, RP] -# © 2019 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# StandardizedVariants-14.0.0.txt +# Date: 2021-01-26, 18:20:00 GMT [KW, LI, RP] +# © 2021 Unicode®, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Specification of the variation sequences that are defined in the # Unicode Standard. @@ -26,13 +26,13 @@ # # For more information on standardized variation sequences, # see Section 23.4, Variation Selectors, -# in The Unicode Standard, Version 13.0. +# in The Unicode Standard, Version 14.0. # # For more information on the Ideographic Variation Database, -# see http://www.unicode.org/ivd/ +# see https://www.unicode.org/ivd/ # # For more information on emoji variation sequences, -# see http://www.unicode.org/reports/tr51/ +# see https://www.unicode.org/reports/tr51/ # # Format: # Field 0: the variation sequence @@ -77,6 +77,62 @@ 2ACC FE00; with stroke through bottom members; # SUPERSET OF ABOVE NOT EQUAL TO FF10 FE00; short diagonal stroke form; # FULLWIDTH DIGIT ZERO +# Mathematical alphabet script variants + +1D49C FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL A +212C FE00; chancery style; # SCRIPT CAPITAL B +1D49E FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL C +1D49F FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL D +2130 FE00; chancery style; # SCRIPT CAPITAL E +2131 FE00; chancery style; # SCRIPT CAPITAL F +1D4A2 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL G +210B FE00; chancery style; # SCRIPT CAPITAL H +2110 FE00; chancery style; # SCRIPT CAPITAL I +1D4A5 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL J +1D4A6 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL K +2112 FE00; chancery style; # SCRIPT CAPITAL L +2133 FE00; chancery style; # SCRIPT CAPITAL M +1D4A9 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL N +1D4AA FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL O +1D4AB FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL P +1D4AC FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL Q +211B FE00; chancery style; # SCRIPT CAPITAL R +1D4AE FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL S +1D4AF FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL T +1D4B0 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL U +1D4B1 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL V +1D4B2 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL W +1D4B3 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL X +1D4B4 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL Y +1D4B5 FE00; chancery style; # MATHEMATICAL SCRIPT CAPITAL Z + +1D49C FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL A +212C FE01; roundhand style; # SCRIPT CAPITAL B +1D49E FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL C +1D49F FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL D +2130 FE01; roundhand style; # SCRIPT CAPITAL E +2131 FE01; roundhand style; # SCRIPT CAPITAL F +1D4A2 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL G +210B FE01; roundhand style; # SCRIPT CAPITAL H +2110 FE01; roundhand style; # SCRIPT CAPITAL I +1D4A5 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL J +1D4A6 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL K +2112 FE01; roundhand style; # SCRIPT CAPITAL L +2133 FE01; roundhand style; # SCRIPT CAPITAL M +1D4A9 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL N +1D4AA FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL O +1D4AB FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL P +1D4AC FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL Q +211B FE01; roundhand style; # SCRIPT CAPITAL R +1D4AE FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL S +1D4AF FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL T +1D4B0 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL U +1D4B1 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL V +1D4B2 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL W +1D4B3 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL X +1D4B4 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL Y +1D4B5 FE01; roundhand style; # MATHEMATICAL SCRIPT CAPITAL Z + # East Asian punctuation positional variants 3001 FE00; corner-justified form; # IDEOGRAPHIC COMMA diff --git a/lib/unicore/UnicodeData.txt b/lib/unicore/UnicodeData.txt index e22f967bba..b5abef7ed4 100644 --- a/lib/unicore/UnicodeData.txt +++ b/lib/unicore/UnicodeData.txt @@ -1525,6 +1525,7 @@ 061A;ARABIC SMALL KASRA;Mn;32;NSM;;;;;N;;;;; 061B;ARABIC SEMICOLON;Po;0;AL;;;;;N;;;;; 061C;ARABIC LETTER MARK;Cf;0;AL;;;;;N;;;;; +061D;ARABIC END OF TEXT MARK;Po;0;AL;;;;;N;;;;; 061E;ARABIC TRIPLE DOT PUNCTUATION MARK;Po;0;AL;;;;;N;;;;; 061F;ARABIC QUESTION MARK;Po;0;AL;;;;;N;;;;; 0620;ARABIC LETTER KASHMIRI YEH;Lo;0;AL;;;;;N;;;;; @@ -2089,6 +2090,47 @@ 0868;SYRIAC LETTER MALAYALAM LLA;Lo;0;AL;;;;;N;;;;; 0869;SYRIAC LETTER MALAYALAM LLLA;Lo;0;AL;;;;;N;;;;; 086A;SYRIAC LETTER MALAYALAM SSA;Lo;0;AL;;;;;N;;;;; +0870;ARABIC LETTER ALEF WITH ATTACHED FATHA;Lo;0;AL;;;;;N;;;;; +0871;ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA;Lo;0;AL;;;;;N;;;;; +0872;ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE;Lo;0;AL;;;;;N;;;;; +0873;ARABIC LETTER ALEF WITH LEFT MIDDLE STROKE;Lo;0;AL;;;;;N;;;;; +0874;ARABIC LETTER ALEF WITH ATTACHED KASRA;Lo;0;AL;;;;;N;;;;; +0875;ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA;Lo;0;AL;;;;;N;;;;; +0876;ARABIC LETTER ALEF WITH ATTACHED ROUND DOT ABOVE;Lo;0;AL;;;;;N;;;;; +0877;ARABIC LETTER ALEF WITH ATTACHED RIGHT ROUND DOT;Lo;0;AL;;;;;N;;;;; +0878;ARABIC LETTER ALEF WITH ATTACHED LEFT ROUND DOT;Lo;0;AL;;;;;N;;;;; +0879;ARABIC LETTER ALEF WITH ATTACHED ROUND DOT BELOW;Lo;0;AL;;;;;N;;;;; +087A;ARABIC LETTER ALEF WITH DOT ABOVE;Lo;0;AL;;;;;N;;;;; +087B;ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA AND DOT ABOVE;Lo;0;AL;;;;;N;;;;; +087C;ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE AND DOT ABOVE;Lo;0;AL;;;;;N;;;;; +087D;ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND DOT ABOVE;Lo;0;AL;;;;;N;;;;; +087E;ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA AND LEFT RING;Lo;0;AL;;;;;N;;;;; +087F;ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE AND LEFT RING;Lo;0;AL;;;;;N;;;;; +0880;ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND LEFT RING;Lo;0;AL;;;;;N;;;;; +0881;ARABIC LETTER ALEF WITH ATTACHED RIGHT HAMZA;Lo;0;AL;;;;;N;;;;; +0882;ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA;Lo;0;AL;;;;;N;;;;; +0883;ARABIC TATWEEL WITH OVERSTRUCK HAMZA;Lo;0;AL;;;;;N;;;;; +0884;ARABIC TATWEEL WITH OVERSTRUCK WAW;Lo;0;AL;;;;;N;;;;; +0885;ARABIC TATWEEL WITH TWO DOTS BELOW;Lo;0;AL;;;;;N;;;;; +0886;ARABIC LETTER THIN YEH;Lo;0;AL;;;;;N;;;;; +0887;ARABIC BASELINE ROUND DOT;Lo;0;AL;;;;;N;;;;; +0888;ARABIC RAISED ROUND DOT;Sk;0;AL;;;;;N;;;;; +0889;ARABIC LETTER NOON WITH INVERTED SMALL V;Lo;0;AL;;;;;N;;;;; +088A;ARABIC LETTER HAH WITH INVERTED SMALL V BELOW;Lo;0;AL;;;;;N;;;;; +088B;ARABIC LETTER TAH WITH DOT BELOW;Lo;0;AL;;;;;N;;;;; +088C;ARABIC LETTER TAH WITH THREE DOTS BELOW;Lo;0;AL;;;;;N;;;;; +088D;ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; +088E;ARABIC VERTICAL TAIL;Lo;0;AL;;;;;N;;;;; +0890;ARABIC POUND MARK ABOVE;Cf;0;AN;;;;;N;;;;; +0891;ARABIC PIASTRE MARK ABOVE;Cf;0;AN;;;;;N;;;;; +0898;ARABIC SMALL HIGH WORD AL-JUZ;Mn;230;NSM;;;;;N;;;;; +0899;ARABIC SMALL LOW WORD ISHMAAM;Mn;220;NSM;;;;;N;;;;; +089A;ARABIC SMALL LOW WORD IMAALA;Mn;220;NSM;;;;;N;;;;; +089B;ARABIC SMALL LOW WORD TASHEEL;Mn;220;NSM;;;;;N;;;;; +089C;ARABIC MADDA WAAJIB;Mn;230;NSM;;;;;N;;;;; +089D;ARABIC SUPERSCRIPT ALEF MOKHASSAS;Mn;230;NSM;;;;;N;;;;; +089E;ARABIC DOUBLED MADDA;Mn;230;NSM;;;;;N;;;;; +089F;ARABIC HALF MADDA OVER MADDA;Mn;230;NSM;;;;;N;;;;; 08A0;ARABIC LETTER BEH WITH SMALL V BELOW;Lo;0;AL;;;;;N;;;;; 08A1;ARABIC LETTER BEH WITH HAMZA ABOVE;Lo;0;AL;;;;;N;;;;; 08A2;ARABIC LETTER JEEM WITH TWO DOTS ABOVE;Lo;0;AL;;;;;N;;;;; @@ -2110,6 +2152,7 @@ 08B2;ARABIC LETTER ZAIN WITH INVERTED V ABOVE;Lo;0;AL;;;;;N;;;;; 08B3;ARABIC LETTER AIN WITH THREE DOTS BELOW;Lo;0;AL;;;;;N;;;;; 08B4;ARABIC LETTER KAF WITH DOT BELOW;Lo;0;AL;;;;;N;;;;; +08B5;ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE;Lo;0;AL;;;;;N;;;;; 08B6;ARABIC LETTER BEH WITH SMALL MEEM ABOVE;Lo;0;AL;;;;;N;;;;; 08B7;ARABIC LETTER PEH WITH SMALL MEEM ABOVE;Lo;0;AL;;;;;N;;;;; 08B8;ARABIC LETTER TEH WITH SMALL TEH ABOVE;Lo;0;AL;;;;;N;;;;; @@ -2128,6 +2171,17 @@ 08C5;ARABIC LETTER JEEM WITH THREE DOTS ABOVE;Lo;0;AL;;;;;N;;;;; 08C6;ARABIC LETTER JEEM WITH THREE DOTS BELOW;Lo;0;AL;;;;;N;;;;; 08C7;ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE;Lo;0;AL;;;;;N;;;;; +08C8;ARABIC LETTER GRAF;Lo;0;AL;;;;;N;;;;; +08C9;ARABIC SMALL FARSI YEH;Lm;0;AL;;;;;N;;;;; +08CA;ARABIC SMALL HIGH FARSI YEH;Mn;230;NSM;;;;;N;;;;; +08CB;ARABIC SMALL HIGH YEH BARREE WITH TWO DOTS BELOW;Mn;230;NSM;;;;;N;;;;; +08CC;ARABIC SMALL HIGH WORD SAH;Mn;230;NSM;;;;;N;;;;; +08CD;ARABIC SMALL HIGH ZAH;Mn;230;NSM;;;;;N;;;;; +08CE;ARABIC LARGE ROUND DOT ABOVE;Mn;230;NSM;;;;;N;;;;; +08CF;ARABIC LARGE ROUND DOT BELOW;Mn;220;NSM;;;;;N;;;;; +08D0;ARABIC SUKUN BELOW;Mn;220;NSM;;;;;N;;;;; +08D1;ARABIC LARGE CIRCLE BELOW;Mn;220;NSM;;;;;N;;;;; +08D2;ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW;Mn;220;NSM;;;;;N;;;;; 08D3;ARABIC SMALL LOW WAW;Mn;220;NSM;;;;;N;;;;; 08D4;ARABIC SMALL HIGH WORD AR-RUB;Mn;230;NSM;;;;;N;;;;; 08D5;ARABIC SMALL HIGH SAD;Mn;230;NSM;;;;;N;;;;; @@ -2786,6 +2840,7 @@ 0C37;TELUGU LETTER SSA;Lo;0;L;;;;;N;;;;; 0C38;TELUGU LETTER SA;Lo;0;L;;;;;N;;;;; 0C39;TELUGU LETTER HA;Lo;0;L;;;;;N;;;;; +0C3C;TELUGU SIGN NUKTA;Mn;7;NSM;;;;;N;;;;; 0C3D;TELUGU SIGN AVAGRAHA;Lo;0;L;;;;;N;;;;; 0C3E;TELUGU VOWEL SIGN AA;Mn;0;NSM;;;;;N;;;;; 0C3F;TELUGU VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; @@ -2806,6 +2861,7 @@ 0C58;TELUGU LETTER TSA;Lo;0;L;;;;;N;;;;; 0C59;TELUGU LETTER DZA;Lo;0;L;;;;;N;;;;; 0C5A;TELUGU LETTER RRRA;Lo;0;L;;;;;N;;;;; +0C5D;TELUGU LETTER NAKAARA POLLU;Lo;0;L;;;;;N;;;;; 0C60;TELUGU LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; 0C61;TELUGU LETTER VOCALIC LL;Lo;0;L;;;;;N;;;;; 0C62;TELUGU VOWEL SIGN VOCALIC L;Mn;0;NSM;;;;;N;;;;; @@ -2901,6 +2957,7 @@ 0CCD;KANNADA SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; 0CD5;KANNADA LENGTH MARK;Mc;0;L;;;;;N;;;;; 0CD6;KANNADA AI LENGTH MARK;Mc;0;L;;;;;N;;;;; +0CDD;KANNADA LETTER NAKAARA POLLU;Lo;0;L;;;;;N;;;;; 0CDE;KANNADA LETTER FA;Lo;0;L;;;;;N;;;;; 0CE0;KANNADA LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; 0CE1;KANNADA LETTER VOCALIC LL;Lo;0;L;;;;;N;;;;; @@ -5258,6 +5315,7 @@ 170A;TAGALOG LETTER BA;Lo;0;L;;;;;N;;;;; 170B;TAGALOG LETTER MA;Lo;0;L;;;;;N;;;;; 170C;TAGALOG LETTER YA;Lo;0;L;;;;;N;;;;; +170D;TAGALOG LETTER RA;Lo;0;L;;;;;N;;;;; 170E;TAGALOG LETTER LA;Lo;0;L;;;;;N;;;;; 170F;TAGALOG LETTER WA;Lo;0;L;;;;;N;;;;; 1710;TAGALOG LETTER SA;Lo;0;L;;;;;N;;;;; @@ -5265,6 +5323,8 @@ 1712;TAGALOG VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; 1713;TAGALOG VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; 1714;TAGALOG SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; +1715;TAGALOG SIGN PAMUDPOD;Mc;9;L;;;;;N;;;;; +171F;TAGALOG LETTER ARCHAIC RA;Lo;0;L;;;;;N;;;;; 1720;HANUNOO LETTER A;Lo;0;L;;;;;N;;;;; 1721;HANUNOO LETTER I;Lo;0;L;;;;;N;;;;; 1722;HANUNOO LETTER U;Lo;0;L;;;;;N;;;;; @@ -5285,7 +5345,7 @@ 1731;HANUNOO LETTER HA;Lo;0;L;;;;;N;;;;; 1732;HANUNOO VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; 1733;HANUNOO VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; -1734;HANUNOO SIGN PAMUDPOD;Mn;9;NSM;;;;;N;;;;; +1734;HANUNOO SIGN PAMUDPOD;Mc;9;L;;;;;N;;;;; 1735;PHILIPPINE SINGLE PUNCTUATION;Po;0;L;;;;;N;;;;; 1736;PHILIPPINE DOUBLE PUNCTUATION;Po;0;L;;;;;N;;;;; 1740;BUHID LETTER A;Lo;0;L;;;;;N;;;;; @@ -5455,6 +5515,7 @@ 180C;MONGOLIAN FREE VARIATION SELECTOR TWO;Mn;0;NSM;;;;;N;;;;; 180D;MONGOLIAN FREE VARIATION SELECTOR THREE;Mn;0;NSM;;;;;N;;;;; 180E;MONGOLIAN VOWEL SEPARATOR;Cf;0;BN;;;;;N;;;;; +180F;MONGOLIAN FREE VARIATION SELECTOR FOUR;Mn;0;NSM;;;;;N;;;;; 1810;MONGOLIAN DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; 1811;MONGOLIAN DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; 1812;MONGOLIAN DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; @@ -6059,6 +6120,20 @@ 1ABE;COMBINING PARENTHESES OVERLAY;Me;0;NSM;;;;;N;;;;; 1ABF;COMBINING LATIN SMALL LETTER W BELOW;Mn;220;NSM;;;;;N;;;;; 1AC0;COMBINING LATIN SMALL LETTER TURNED W BELOW;Mn;220;NSM;;;;;N;;;;; +1AC1;COMBINING LEFT PARENTHESIS ABOVE LEFT;Mn;230;NSM;;;;;N;;;;; +1AC2;COMBINING RIGHT PARENTHESIS ABOVE RIGHT;Mn;230;NSM;;;;;N;;;;; +1AC3;COMBINING LEFT PARENTHESIS BELOW LEFT;Mn;220;NSM;;;;;N;;;;; +1AC4;COMBINING RIGHT PARENTHESIS BELOW RIGHT;Mn;220;NSM;;;;;N;;;;; +1AC5;COMBINING SQUARE BRACKETS ABOVE;Mn;230;NSM;;;;;N;;;;; +1AC6;COMBINING NUMBER SIGN ABOVE;Mn;230;NSM;;;;;N;;;;; +1AC7;COMBINING INVERTED DOUBLE ARCH ABOVE;Mn;230;NSM;;;;;N;;;;; +1AC8;COMBINING PLUS SIGN ABOVE;Mn;230;NSM;;;;;N;;;;; +1AC9;COMBINING DOUBLE PLUS SIGN ABOVE;Mn;230;NSM;;;;;N;;;;; +1ACA;COMBINING DOUBLE PLUS SIGN BELOW;Mn;220;NSM;;;;;N;;;;; +1ACB;COMBINING TRIPLE ACUTE ACCENT;Mn;230;NSM;;;;;N;;;;; +1ACC;COMBINING LATIN SMALL LETTER INSULAR G;Mn;230;NSM;;;;;N;;;;; +1ACD;COMBINING LATIN SMALL LETTER INSULAR R;Mn;230;NSM;;;;;N;;;;; +1ACE;COMBINING LATIN SMALL LETTER INSULAR T;Mn;230;NSM;;;;;N;;;;; 1B00;BALINESE SIGN ULU RICEM;Mn;0;NSM;;;;;N;;;;; 1B01;BALINESE SIGN ULU CANDRA;Mn;0;NSM;;;;;N;;;;; 1B02;BALINESE SIGN CECEK;Mn;0;NSM;;;;;N;;;;; @@ -6135,6 +6210,7 @@ 1B49;BALINESE LETTER VE SASAK;Lo;0;L;;;;;N;;;;; 1B4A;BALINESE LETTER ZAL SASAK;Lo;0;L;;;;;N;;;;; 1B4B;BALINESE LETTER ASYURA SASAK;Lo;0;L;;;;;N;;;;; +1B4C;BALINESE LETTER ARCHAIC JNYA;Lo;0;L;;;;;N;;;;; 1B50;BALINESE DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; 1B51;BALINESE DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; 1B52;BALINESE DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; @@ -6180,6 +6256,8 @@ 1B7A;BALINESE MUSICAL SYMBOL LEFT-HAND CLOSED PLAK;So;0;L;;;;;N;;;;; 1B7B;BALINESE MUSICAL SYMBOL LEFT-HAND CLOSED PLUK;So;0;L;;;;;N;;;;; 1B7C;BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING;So;0;L;;;;;N;;;;; +1B7D;BALINESE PANTI LANTANG;Po;0;L;;;;;N;;;;; +1B7E;BALINESE PAMADA LANTANG;Po;0;L;;;;;N;;;;; 1B80;SUNDANESE SIGN PANYECEK;Mn;0;NSM;;;;;N;;;;; 1B81;SUNDANESE SIGN PANGLAYAR;Mn;0;NSM;;;;;N;;;;; 1B82;SUNDANESE SIGN PANGWISAD;Mc;0;L;;;;;N;;;;; @@ -6778,6 +6856,7 @@ 1DF7;COMBINING KAVYKA ABOVE LEFT;Mn;228;NSM;;;;;N;;;;; 1DF8;COMBINING DOT ABOVE LEFT;Mn;228;NSM;;;;;N;;;;; 1DF9;COMBINING WIDE INVERTED BRIDGE BELOW;Mn;220;NSM;;;;;N;;;;; +1DFA;COMBINING DOT BELOW LEFT;Mn;218;NSM;;;;;N;;;;; 1DFB;COMBINING DELETION MARK;Mn;230;NSM;;;;;N;;;;; 1DFC;COMBINING DOUBLE INVERTED BREVE BELOW;Mn;233;NSM;;;;;N;;;;; 1DFD;COMBINING ALMOST EQUAL TO BELOW;Mn;220;NSM;;;;;N;;;;; @@ -7457,6 +7536,7 @@ 20BD;RUBLE SIGN;Sc;0;ET;;;;;N;;;;; 20BE;LARI SIGN;Sc;0;ET;;;;;N;;;;; 20BF;BITCOIN SIGN;Sc;0;ET;;;;;N;;;;; +20C0;SOM SIGN;Sc;0;ET;;;;;N;;;;; 20D0;COMBINING LEFT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING LEFT HARPOON ABOVE;;;; 20D1;COMBINING RIGHT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING RIGHT HARPOON ABOVE;;;; 20D2;COMBINING LONG VERTICAL LINE OVERLAY;Mn;1;NSM;;;;;N;NON-SPACING LONG VERTICAL BAR OVERLAY;;;; @@ -10300,6 +10380,7 @@ 2C2C;GLAGOLITIC CAPITAL LETTER SHTAPIC;Lu;0;L;;;;;N;;;;2C5C; 2C2D;GLAGOLITIC CAPITAL LETTER TROKUTASTI A;Lu;0;L;;;;;N;;;;2C5D; 2C2E;GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE;Lu;0;L;;;;;N;;;;2C5E; +2C2F;GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI;Lu;0;L;;;;;N;;;;2C5F; 2C30;GLAGOLITIC SMALL LETTER AZU;Ll;0;L;;;;;N;;;2C00;;2C00 2C31;GLAGOLITIC SMALL LETTER BUKY;Ll;0;L;;;;;N;;;2C01;;2C01 2C32;GLAGOLITIC SMALL LETTER VEDE;Ll;0;L;;;;;N;;;2C02;;2C02 @@ -10347,6 +10428,7 @@ 2C5C;GLAGOLITIC SMALL LETTER SHTAPIC;Ll;0;L;;;;;N;;;2C2C;;2C2C 2C5D;GLAGOLITIC SMALL LETTER TROKUTASTI A;Ll;0;L;;;;;N;;;2C2D;;2C2D 2C5E;GLAGOLITIC SMALL LETTER LATINATE MYSLITE;Ll;0;L;;;;;N;;;2C2E;;2C2E +2C5F;GLAGOLITIC SMALL LETTER CAUDATE CHRIVI;Ll;0;L;;;;;N;;;2C2F;;2C2F 2C60;LATIN CAPITAL LETTER L WITH DOUBLE BAR;Lu;0;L;;;;;N;;;;2C61; 2C61;LATIN SMALL LETTER L WITH DOUBLE BAR;Ll;0;L;;;;;N;;;2C60;;2C60 2C62;LATIN CAPITAL LETTER L WITH MIDDLE TILDE;Lu;0;L;;;;;N;;;;026B; @@ -10795,6 +10877,17 @@ 2E50;CROSS PATTY WITH RIGHT CROSSBAR;So;0;ON;;;;;N;;;;; 2E51;CROSS PATTY WITH LEFT CROSSBAR;So;0;ON;;;;;N;;;;; 2E52;TIRONIAN SIGN CAPITAL ET;Po;0;ON;;;;;N;;;;; +2E53;MEDIEVAL EXCLAMATION MARK;Po;0;ON;;;;;N;;;;; +2E54;MEDIEVAL QUESTION MARK;Po;0;ON;;;;;N;;;;; +2E55;LEFT SQUARE BRACKET WITH STROKE;Ps;0;ON;;;;;Y;;;;; +2E56;RIGHT SQUARE BRACKET WITH STROKE;Pe;0;ON;;;;;Y;;;;; +2E57;LEFT SQUARE BRACKET WITH DOUBLE STROKE;Ps;0;ON;;;;;Y;;;;; +2E58;RIGHT SQUARE BRACKET WITH DOUBLE STROKE;Pe;0;ON;;;;;Y;;;;; +2E59;TOP HALF LEFT PARENTHESIS;Ps;0;ON;;;;;Y;;;;; +2E5A;TOP HALF RIGHT PARENTHESIS;Pe;0;ON;;;;;Y;;;;; +2E5B;BOTTOM HALF LEFT PARENTHESIS;Ps;0;ON;;;;;Y;;;;; +2E5C;BOTTOM HALF RIGHT PARENTHESIS;Pe;0;ON;;;;;Y;;;;; +2E5D;OBLIQUE HYPHEN;Pd;0;ON;;;;;N;;;;; 2E80;CJK RADICAL REPEAT;So;0;ON;;;;;N;;;;; 2E81;CJK RADICAL CLIFF;So;0;ON;;;;;N;;;;; 2E82;CJK RADICAL SECOND ONE;So;0;ON;;;;;N;;;;; @@ -12204,7 +12297,7 @@ 4DFE;HEXAGRAM FOR AFTER COMPLETION;So;0;ON;;;;;N;;;;; 4DFF;HEXAGRAM FOR BEFORE COMPLETION;So;0;ON;;;;;N;;;;; 4E00;<CJK Ideograph, First>;Lo;0;L;;;;;N;;;;; -9FFC;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;; +9FFF;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;; A000;YI SYLLABLE IT;Lo;0;L;;;;;N;;;;; A001;YI SYLLABLE IX;Lo;0;L;;;;;N;;;;; A002;YI SYLLABLE I;Lo;0;L;;;;;N;;;;; @@ -14149,6 +14242,8 @@ A7BC;LATIN CAPITAL LETTER GLOTTAL I;Lu;0;L;;;;;N;;;;A7BD; A7BD;LATIN SMALL LETTER GLOTTAL I;Ll;0;L;;;;;N;;;A7BC;;A7BC A7BE;LATIN CAPITAL LETTER GLOTTAL U;Lu;0;L;;;;;N;;;;A7BF; A7BF;LATIN SMALL LETTER GLOTTAL U;Ll;0;L;;;;;N;;;A7BE;;A7BE +A7C0;LATIN CAPITAL LETTER OLD POLISH O;Lu;0;L;;;;;N;;;;A7C1; +A7C1;LATIN SMALL LETTER OLD POLISH O;Ll;0;L;;;;;N;;;A7C0;;A7C0 A7C2;LATIN CAPITAL LETTER ANGLICANA W;Lu;0;L;;;;;N;;;;A7C3; A7C3;LATIN SMALL LETTER ANGLICANA W;Ll;0;L;;;;;N;;;A7C2;;A7C2 A7C4;LATIN CAPITAL LETTER C WITH PALATAL HOOK;Lu;0;L;;;;;N;;;;A794; @@ -14158,6 +14253,17 @@ A7C7;LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY;Lu;0;L;;;;;N;;;;A7C8; A7C8;LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY;Ll;0;L;;;;;N;;;A7C7;;A7C7 A7C9;LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY;Lu;0;L;;;;;N;;;;A7CA; A7CA;LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY;Ll;0;L;;;;;N;;;A7C9;;A7C9 +A7D0;LATIN CAPITAL LETTER CLOSED INSULAR G;Lu;0;L;;;;;N;;;;A7D1; +A7D1;LATIN SMALL LETTER CLOSED INSULAR G;Ll;0;L;;;;;N;;;A7D0;;A7D0 +A7D3;LATIN SMALL LETTER DOUBLE THORN;Ll;0;L;;;;;N;;;;; +A7D5;LATIN SMALL LETTER DOUBLE WYNN;Ll;0;L;;;;;N;;;;; +A7D6;LATIN CAPITAL LETTER MIDDLE SCOTS S;Lu;0;L;;;;;N;;;;A7D7; +A7D7;LATIN SMALL LETTER MIDDLE SCOTS S;Ll;0;L;;;;;N;;;A7D6;;A7D6 +A7D8;LATIN CAPITAL LETTER SIGMOID S;Lu;0;L;;;;;N;;;;A7D9; +A7D9;LATIN SMALL LETTER SIGMOID S;Ll;0;L;;;;;N;;;A7D8;;A7D8 +A7F2;MODIFIER LETTER CAPITAL C;Lm;0;L;<super> 0043;;;;N;;;;; +A7F3;MODIFIER LETTER CAPITAL F;Lm;0;L;<super> 0046;;;;N;;;;; +A7F4;MODIFIER LETTER CAPITAL Q;Lm;0;L;<super> 0051;;;;N;;;;; A7F5;LATIN CAPITAL LETTER REVERSED HALF H;Lu;0;L;;;;;N;;;;A7F6; A7F6;LATIN SMALL LETTER REVERSED HALF H;Ll;0;L;;;;;N;;;A7F5;;A7F5 A7F7;LATIN EPIGRAPHIC LETTER SIDEWAYS I;Lo;0;L;;;;;N;;;;; @@ -15794,6 +15900,7 @@ FBBE;ARABIC SYMBOL TWO DOTS VERTICALLY BELOW;Sk;0;AL;;;;;N;;;;; FBBF;ARABIC SYMBOL RING;Sk;0;AL;;;;;N;;;;; FBC0;ARABIC SYMBOL SMALL TAH ABOVE;Sk;0;AL;;;;;N;;;;; FBC1;ARABIC SYMBOL SMALL TAH BELOW;Sk;0;AL;;;;;N;;;;; +FBC2;ARABIC SYMBOL WASLA ABOVE;Sk;0;AL;;;;;N;;;;; FBD3;ARABIC LETTER NG ISOLATED FORM;Lo;0;AL;<isolated> 06AD;;;;N;;;;; FBD4;ARABIC LETTER NG FINAL FORM;Lo;0;AL;<final> 06AD;;;;N;;;;; FBD5;ARABIC LETTER NG INITIAL FORM;Lo;0;AL;<initial> 06AD;;;;N;;;;; @@ -16159,6 +16266,22 @@ FD3C;ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM;Lo;0;AL;<final> 0627 064B;;;; FD3D;ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM;Lo;0;AL;<isolated> 0627 064B;;;;N;;;;; FD3E;ORNATE LEFT PARENTHESIS;Pe;0;ON;;;;;N;;;;; FD3F;ORNATE RIGHT PARENTHESIS;Ps;0;ON;;;;;N;;;;; +FD40;ARABIC LIGATURE RAHIMAHU ALLAAH;So;0;ON;;;;;N;;;;; +FD41;ARABIC LIGATURE RADI ALLAAHU ANH;So;0;ON;;;;;N;;;;; +FD42;ARABIC LIGATURE RADI ALLAAHU ANHAA;So;0;ON;;;;;N;;;;; +FD43;ARABIC LIGATURE RADI ALLAAHU ANHUM;So;0;ON;;;;;N;;;;; +FD44;ARABIC LIGATURE RADI ALLAAHU ANHUMAA;So;0;ON;;;;;N;;;;; +FD45;ARABIC LIGATURE RADI ALLAAHU ANHUNNA;So;0;ON;;;;;N;;;;; +FD46;ARABIC LIGATURE SALLALLAAHU ALAYHI WA-AALIH;So;0;ON;;;;;N;;;;; +FD47;ARABIC LIGATURE ALAYHI AS-SALAAM;So;0;ON;;;;;N;;;;; +FD48;ARABIC LIGATURE ALAYHIM AS-SALAAM;So;0;ON;;;;;N;;;;; +FD49;ARABIC LIGATURE ALAYHIMAA AS-SALAAM;So;0;ON;;;;;N;;;;; +FD4A;ARABIC LIGATURE ALAYHI AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; +FD4B;ARABIC LIGATURE QUDDISA SIRRAH;So;0;ON;;;;;N;;;;; +FD4C;ARABIC LIGATURE SALLALLAHU ALAYHI WAAALIHEE WA-SALLAM;So;0;ON;;;;;N;;;;; +FD4D;ARABIC LIGATURE ALAYHAA AS-SALAAM;So;0;ON;;;;;N;;;;; +FD4E;ARABIC LIGATURE TABAARAKA WA-TAAALAA;So;0;ON;;;;;N;;;;; +FD4F;ARABIC LIGATURE RAHIMAHUM ALLAAH;So;0;ON;;;;;N;;;;; FD50;ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM;Lo;0;AL;<initial> 062A 062C 0645;;;;N;;;;; FD51;ARABIC LIGATURE TEH WITH HAH WITH JEEM FINAL FORM;Lo;0;AL;<final> 062A 062D 062C;;;;N;;;;; FD52;ARABIC LIGATURE TEH WITH HAH WITH JEEM INITIAL FORM;Lo;0;AL;<initial> 062A 062D 062C;;;;N;;;;; @@ -16277,6 +16400,7 @@ FDC4;ARABIC LIGATURE AIN WITH JEEM WITH MEEM INITIAL FORM;Lo;0;AL;<initial> 0639 FDC5;ARABIC LIGATURE SAD WITH MEEM WITH MEEM INITIAL FORM;Lo;0;AL;<initial> 0635 0645 0645;;;;N;;;;; FDC6;ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM;Lo;0;AL;<final> 0633 062E 064A;;;;N;;;;; FDC7;ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM;Lo;0;AL;<final> 0646 062C 064A;;;;N;;;;; +FDCF;ARABIC LIGATURE SALAAMUHU ALAYNAA;So;0;ON;;;;;N;;;;; FDF0;ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM;Lo;0;AL;<isolated> 0635 0644 06D2;;;;N;;;;; FDF1;ARABIC LIGATURE QALA USED AS KORANIC STOP SIGN ISOLATED FORM;Lo;0;AL;<isolated> 0642 0644 06D2;;;;N;;;;; FDF2;ARABIC LIGATURE ALLAH ISOLATED FORM;Lo;0;AL;<isolated> 0627 0644 0644 0647;;;;N;;;;; @@ -16291,6 +16415,8 @@ FDFA;ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM;Lo;0;AL;<isolated> 0635 0644 06 FDFB;ARABIC LIGATURE JALLAJALALOUHOU;Lo;0;AL;<isolated> 062C 0644 0020 062C 0644 0627 0644 0647;;;;N;ARABIC LETTER JALLAJALALOUHOU;;;; FDFC;RIAL SIGN;Sc;0;AL;<isolated> 0631 06CC 0627 0644;;;;N;;;;; FDFD;ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM;So;0;ON;;;;;N;;;;; +FDFE;ARABIC LIGATURE SUBHAANAHU WA TAAALAA;So;0;ON;;;;;N;;;;; +FDFF;ARABIC LIGATURE AZZA WA JALL;So;0;ON;;;;;N;;;;; FE00;VARIATION SELECTOR-1;Mn;0;NSM;;;;;N;;;;; FE01;VARIATION SELECTOR-2;Mn;0;NSM;;;;;N;;;;; FE02;VARIATION SELECTOR-3;Mn;0;NSM;;;;;N;;;;; @@ -17798,6 +17924,76 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10562;CAUCASIAN ALBANIAN LETTER PIWR;Lo;0;L;;;;;N;;;;; 10563;CAUCASIAN ALBANIAN LETTER KIW;Lo;0;L;;;;;N;;;;; 1056F;CAUCASIAN ALBANIAN CITATION MARK;Po;0;L;;;;;N;;;;; +10570;VITHKUQI CAPITAL LETTER A;Lu;0;L;;;;;N;;;;10597; +10571;VITHKUQI CAPITAL LETTER BBE;Lu;0;L;;;;;N;;;;10598; +10572;VITHKUQI CAPITAL LETTER BE;Lu;0;L;;;;;N;;;;10599; +10573;VITHKUQI CAPITAL LETTER CE;Lu;0;L;;;;;N;;;;1059A; +10574;VITHKUQI CAPITAL LETTER CHE;Lu;0;L;;;;;N;;;;1059B; +10575;VITHKUQI CAPITAL LETTER DE;Lu;0;L;;;;;N;;;;1059C; +10576;VITHKUQI CAPITAL LETTER DHE;Lu;0;L;;;;;N;;;;1059D; +10577;VITHKUQI CAPITAL LETTER EI;Lu;0;L;;;;;N;;;;1059E; +10578;VITHKUQI CAPITAL LETTER E;Lu;0;L;;;;;N;;;;1059F; +10579;VITHKUQI CAPITAL LETTER FE;Lu;0;L;;;;;N;;;;105A0; +1057A;VITHKUQI CAPITAL LETTER GA;Lu;0;L;;;;;N;;;;105A1; +1057C;VITHKUQI CAPITAL LETTER HA;Lu;0;L;;;;;N;;;;105A3; +1057D;VITHKUQI CAPITAL LETTER HHA;Lu;0;L;;;;;N;;;;105A4; +1057E;VITHKUQI CAPITAL LETTER I;Lu;0;L;;;;;N;;;;105A5; +1057F;VITHKUQI CAPITAL LETTER IJE;Lu;0;L;;;;;N;;;;105A6; +10580;VITHKUQI CAPITAL LETTER JE;Lu;0;L;;;;;N;;;;105A7; +10581;VITHKUQI CAPITAL LETTER KA;Lu;0;L;;;;;N;;;;105A8; +10582;VITHKUQI CAPITAL LETTER LA;Lu;0;L;;;;;N;;;;105A9; +10583;VITHKUQI CAPITAL LETTER LLA;Lu;0;L;;;;;N;;;;105AA; +10584;VITHKUQI CAPITAL LETTER ME;Lu;0;L;;;;;N;;;;105AB; +10585;VITHKUQI CAPITAL LETTER NE;Lu;0;L;;;;;N;;;;105AC; +10586;VITHKUQI CAPITAL LETTER NJE;Lu;0;L;;;;;N;;;;105AD; +10587;VITHKUQI CAPITAL LETTER O;Lu;0;L;;;;;N;;;;105AE; +10588;VITHKUQI CAPITAL LETTER PE;Lu;0;L;;;;;N;;;;105AF; +10589;VITHKUQI CAPITAL LETTER QA;Lu;0;L;;;;;N;;;;105B0; +1058A;VITHKUQI CAPITAL LETTER RE;Lu;0;L;;;;;N;;;;105B1; +1058C;VITHKUQI CAPITAL LETTER SE;Lu;0;L;;;;;N;;;;105B3; +1058D;VITHKUQI CAPITAL LETTER SHE;Lu;0;L;;;;;N;;;;105B4; +1058E;VITHKUQI CAPITAL LETTER TE;Lu;0;L;;;;;N;;;;105B5; +1058F;VITHKUQI CAPITAL LETTER THE;Lu;0;L;;;;;N;;;;105B6; +10590;VITHKUQI CAPITAL LETTER U;Lu;0;L;;;;;N;;;;105B7; +10591;VITHKUQI CAPITAL LETTER VE;Lu;0;L;;;;;N;;;;105B8; +10592;VITHKUQI CAPITAL LETTER XE;Lu;0;L;;;;;N;;;;105B9; +10594;VITHKUQI CAPITAL LETTER Y;Lu;0;L;;;;;N;;;;105BB; +10595;VITHKUQI CAPITAL LETTER ZE;Lu;0;L;;;;;N;;;;105BC; +10597;VITHKUQI SMALL LETTER A;Ll;0;L;;;;;N;;;10570;;10570 +10598;VITHKUQI SMALL LETTER BBE;Ll;0;L;;;;;N;;;10571;;10571 +10599;VITHKUQI SMALL LETTER BE;Ll;0;L;;;;;N;;;10572;;10572 +1059A;VITHKUQI SMALL LETTER CE;Ll;0;L;;;;;N;;;10573;;10573 +1059B;VITHKUQI SMALL LETTER CHE;Ll;0;L;;;;;N;;;10574;;10574 +1059C;VITHKUQI SMALL LETTER DE;Ll;0;L;;;;;N;;;10575;;10575 +1059D;VITHKUQI SMALL LETTER DHE;Ll;0;L;;;;;N;;;10576;;10576 +1059E;VITHKUQI SMALL LETTER EI;Ll;0;L;;;;;N;;;10577;;10577 +1059F;VITHKUQI SMALL LETTER E;Ll;0;L;;;;;N;;;10578;;10578 +105A0;VITHKUQI SMALL LETTER FE;Ll;0;L;;;;;N;;;10579;;10579 +105A1;VITHKUQI SMALL LETTER GA;Ll;0;L;;;;;N;;;1057A;;1057A +105A3;VITHKUQI SMALL LETTER HA;Ll;0;L;;;;;N;;;1057C;;1057C +105A4;VITHKUQI SMALL LETTER HHA;Ll;0;L;;;;;N;;;1057D;;1057D +105A5;VITHKUQI SMALL LETTER I;Ll;0;L;;;;;N;;;1057E;;1057E +105A6;VITHKUQI SMALL LETTER IJE;Ll;0;L;;;;;N;;;1057F;;1057F +105A7;VITHKUQI SMALL LETTER JE;Ll;0;L;;;;;N;;;10580;;10580 +105A8;VITHKUQI SMALL LETTER KA;Ll;0;L;;;;;N;;;10581;;10581 +105A9;VITHKUQI SMALL LETTER LA;Ll;0;L;;;;;N;;;10582;;10582 +105AA;VITHKUQI SMALL LETTER LLA;Ll;0;L;;;;;N;;;10583;;10583 +105AB;VITHKUQI SMALL LETTER ME;Ll;0;L;;;;;N;;;10584;;10584 +105AC;VITHKUQI SMALL LETTER NE;Ll;0;L;;;;;N;;;10585;;10585 +105AD;VITHKUQI SMALL LETTER NJE;Ll;0;L;;;;;N;;;10586;;10586 +105AE;VITHKUQI SMALL LETTER O;Ll;0;L;;;;;N;;;10587;;10587 +105AF;VITHKUQI SMALL LETTER PE;Ll;0;L;;;;;N;;;10588;;10588 +105B0;VITHKUQI SMALL LETTER QA;Ll;0;L;;;;;N;;;10589;;10589 +105B1;VITHKUQI SMALL LETTER RE;Ll;0;L;;;;;N;;;1058A;;1058A +105B3;VITHKUQI SMALL LETTER SE;Ll;0;L;;;;;N;;;1058C;;1058C +105B4;VITHKUQI SMALL LETTER SHE;Ll;0;L;;;;;N;;;1058D;;1058D +105B5;VITHKUQI SMALL LETTER TE;Ll;0;L;;;;;N;;;1058E;;1058E +105B6;VITHKUQI SMALL LETTER THE;Ll;0;L;;;;;N;;;1058F;;1058F +105B7;VITHKUQI SMALL LETTER U;Ll;0;L;;;;;N;;;10590;;10590 +105B8;VITHKUQI SMALL LETTER VE;Ll;0;L;;;;;N;;;10591;;10591 +105B9;VITHKUQI SMALL LETTER XE;Ll;0;L;;;;;N;;;10592;;10592 +105BB;VITHKUQI SMALL LETTER Y;Ll;0;L;;;;;N;;;10594;;10594 +105BC;VITHKUQI SMALL LETTER ZE;Ll;0;L;;;;;N;;;10595;;10595 10600;LINEAR A SIGN AB001;Lo;0;L;;;;;N;;;;; 10601;LINEAR A SIGN AB002;Lo;0;L;;;;;N;;;;; 10602;LINEAR A SIGN AB003;Lo;0;L;;;;;N;;;;; @@ -18139,6 +18335,63 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10765;LINEAR A SIGN A805;Lo;0;L;;;;;N;;;;; 10766;LINEAR A SIGN A806;Lo;0;L;;;;;N;;;;; 10767;LINEAR A SIGN A807;Lo;0;L;;;;;N;;;;; +10780;MODIFIER LETTER SMALL CAPITAL AA;Lm;0;L;;;;;N;;;;; +10781;MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON;Lm;0;L;<super> 02D0;;;;N;;;;; +10782;MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON;Lm;0;L;<super> 02D1;;;;N;;;;; +10783;MODIFIER LETTER SMALL AE;Lm;0;L;<super> 00E6;;;;N;;;;; +10784;MODIFIER LETTER SMALL CAPITAL B;Lm;0;L;<super> 0299;;;;N;;;;; +10785;MODIFIER LETTER SMALL B WITH HOOK;Lm;0;L;<super> 0253;;;;N;;;;; +10787;MODIFIER LETTER SMALL DZ DIGRAPH;Lm;0;L;<super> 02A3;;;;N;;;;; +10788;MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK;Lm;0;L;<super> AB66;;;;N;;;;; +10789;MODIFIER LETTER SMALL DZ DIGRAPH WITH CURL;Lm;0;L;<super> 02A5;;;;N;;;;; +1078A;MODIFIER LETTER SMALL DEZH DIGRAPH;Lm;0;L;<super> 02A4;;;;N;;;;; +1078B;MODIFIER LETTER SMALL D WITH TAIL;Lm;0;L;<super> 0256;;;;N;;;;; +1078C;MODIFIER LETTER SMALL D WITH HOOK;Lm;0;L;<super> 0257;;;;N;;;;; +1078D;MODIFIER LETTER SMALL D WITH HOOK AND TAIL;Lm;0;L;<super> 1D91;;;;N;;;;; +1078E;MODIFIER LETTER SMALL REVERSED E;Lm;0;L;<super> 0258;;;;N;;;;; +1078F;MODIFIER LETTER SMALL CLOSED REVERSED OPEN E;Lm;0;L;<super> 025E;;;;N;;;;; +10790;MODIFIER LETTER SMALL FENG DIGRAPH;Lm;0;L;<super> 02A9;;;;N;;;;; +10791;MODIFIER LETTER SMALL RAMS HORN;Lm;0;L;<super> 0264;;;;N;;;;; +10792;MODIFIER LETTER SMALL CAPITAL G;Lm;0;L;<super> 0262;;;;N;;;;; +10793;MODIFIER LETTER SMALL G WITH HOOK;Lm;0;L;<super> 0260;;;;N;;;;; +10794;MODIFIER LETTER SMALL CAPITAL G WITH HOOK;Lm;0;L;<super> 029B;;;;N;;;;; +10795;MODIFIER LETTER SMALL H WITH STROKE;Lm;0;L;<super> 0127;;;;N;;;;; +10796;MODIFIER LETTER SMALL CAPITAL H;Lm;0;L;<super> 029C;;;;N;;;;; +10797;MODIFIER LETTER SMALL HENG WITH HOOK;Lm;0;L;<super> 0267;;;;N;;;;; +10798;MODIFIER LETTER SMALL DOTLESS J WITH STROKE AND HOOK;Lm;0;L;<super> 0284;;;;N;;;;; +10799;MODIFIER LETTER SMALL LS DIGRAPH;Lm;0;L;<super> 02AA;;;;N;;;;; +1079A;MODIFIER LETTER SMALL LZ DIGRAPH;Lm;0;L;<super> 02AB;;;;N;;;;; +1079B;MODIFIER LETTER SMALL L WITH BELT;Lm;0;L;<super> 026C;;;;N;;;;; +1079C;MODIFIER LETTER SMALL CAPITAL L WITH BELT;Lm;0;L;<super> 1DF04;;;;N;;;;; +1079D;MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT;Lm;0;L;<super> A78E;;;;N;;;;; +1079E;MODIFIER LETTER SMALL LEZH;Lm;0;L;<super> 026E;;;;N;;;;; +1079F;MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK;Lm;0;L;<super> 1DF05;;;;N;;;;; +107A0;MODIFIER LETTER SMALL TURNED Y;Lm;0;L;<super> 028E;;;;N;;;;; +107A1;MODIFIER LETTER SMALL TURNED Y WITH BELT;Lm;0;L;<super> 1DF06;;;;N;;;;; +107A2;MODIFIER LETTER SMALL O WITH STROKE;Lm;0;L;<super> 00F8;;;;N;;;;; +107A3;MODIFIER LETTER SMALL CAPITAL OE;Lm;0;L;<super> 0276;;;;N;;;;; +107A4;MODIFIER LETTER SMALL CLOSED OMEGA;Lm;0;L;<super> 0277;;;;N;;;;; +107A5;MODIFIER LETTER SMALL Q;Lm;0;L;<super> 0071;;;;N;;;;; +107A6;MODIFIER LETTER SMALL TURNED R WITH LONG LEG;Lm;0;L;<super> 027A;;;;N;;;;; +107A7;MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK;Lm;0;L;<super> 1DF08;;;;N;;;;; +107A8;MODIFIER LETTER SMALL R WITH TAIL;Lm;0;L;<super> 027D;;;;N;;;;; +107A9;MODIFIER LETTER SMALL R WITH FISHHOOK;Lm;0;L;<super> 027E;;;;N;;;;; +107AA;MODIFIER LETTER SMALL CAPITAL R;Lm;0;L;<super> 0280;;;;N;;;;; +107AB;MODIFIER LETTER SMALL TC DIGRAPH WITH CURL;Lm;0;L;<super> 02A8;;;;N;;;;; +107AC;MODIFIER LETTER SMALL TS DIGRAPH;Lm;0;L;<super> 02A6;;;;N;;;;; +107AD;MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK;Lm;0;L;<super> AB67;;;;N;;;;; +107AE;MODIFIER LETTER SMALL TESH DIGRAPH;Lm;0;L;<super> 02A7;;;;N;;;;; +107AF;MODIFIER LETTER SMALL T WITH RETROFLEX HOOK;Lm;0;L;<super> 0288;;;;N;;;;; +107B0;MODIFIER LETTER SMALL V WITH RIGHT HOOK;Lm;0;L;<super> 2C71;;;;N;;;;; +107B2;MODIFIER LETTER SMALL CAPITAL Y;Lm;0;L;<super> 028F;;;;N;;;;; +107B3;MODIFIER LETTER GLOTTAL STOP WITH STROKE;Lm;0;L;<super> 02A1;;;;N;;;;; +107B4;MODIFIER LETTER REVERSED GLOTTAL STOP WITH STROKE;Lm;0;L;<super> 02A2;;;;N;;;;; +107B5;MODIFIER LETTER BILABIAL CLICK;Lm;0;L;<super> 0298;;;;N;;;;; +107B6;MODIFIER LETTER DENTAL CLICK;Lm;0;L;<super> 01C0;;;;N;;;;; +107B7;MODIFIER LETTER LATERAL CLICK;Lm;0;L;<super> 01C1;;;;N;;;;; +107B8;MODIFIER LETTER ALVEOLAR CLICK;Lm;0;L;<super> 01C2;;;;N;;;;; +107B9;MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK;Lm;0;L;<super> 1DF0A;;;;N;;;;; +107BA;MODIFIER LETTER SMALL S WITH CURL;Lm;0;L;<super> 1DF1E;;;;N;;;;; 10800;CYPRIOT SYLLABLE A;Lo;0;R;;;;;N;;;;; 10801;CYPRIOT SYLLABLE E;Lo;0;R;;;;;N;;;;; 10802;CYPRIOT SYLLABLE I;Lo;0;R;;;;;N;;;;; @@ -19222,6 +19475,32 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10F57;SOGDIAN PUNCTUATION CIRCLE WITH DOT;Po;0;AL;;;;;N;;;;; 10F58;SOGDIAN PUNCTUATION TWO CIRCLES WITH DOTS;Po;0;AL;;;;;N;;;;; 10F59;SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT;Po;0;AL;;;;;N;;;;; +10F70;OLD UYGHUR LETTER ALEPH;Lo;0;R;;;;;N;;;;; +10F71;OLD UYGHUR LETTER BETH;Lo;0;R;;;;;N;;;;; +10F72;OLD UYGHUR LETTER GIMEL-HETH;Lo;0;R;;;;;N;;;;; +10F73;OLD UYGHUR LETTER WAW;Lo;0;R;;;;;N;;;;; +10F74;OLD UYGHUR LETTER ZAYIN;Lo;0;R;;;;;N;;;;; +10F75;OLD UYGHUR LETTER FINAL HETH;Lo;0;R;;;;;N;;;;; +10F76;OLD UYGHUR LETTER YODH;Lo;0;R;;;;;N;;;;; +10F77;OLD UYGHUR LETTER KAPH;Lo;0;R;;;;;N;;;;; +10F78;OLD UYGHUR LETTER LAMEDH;Lo;0;R;;;;;N;;;;; +10F79;OLD UYGHUR LETTER MEM;Lo;0;R;;;;;N;;;;; +10F7A;OLD UYGHUR LETTER NUN;Lo;0;R;;;;;N;;;;; +10F7B;OLD UYGHUR LETTER SAMEKH;Lo;0;R;;;;;N;;;;; +10F7C;OLD UYGHUR LETTER PE;Lo;0;R;;;;;N;;;;; +10F7D;OLD UYGHUR LETTER SADHE;Lo;0;R;;;;;N;;;;; +10F7E;OLD UYGHUR LETTER RESH;Lo;0;R;;;;;N;;;;; +10F7F;OLD UYGHUR LETTER SHIN;Lo;0;R;;;;;N;;;;; +10F80;OLD UYGHUR LETTER TAW;Lo;0;R;;;;;N;;;;; +10F81;OLD UYGHUR LETTER LESH;Lo;0;R;;;;;N;;;;; +10F82;OLD UYGHUR COMBINING DOT ABOVE;Mn;230;NSM;;;;;N;;;;; +10F83;OLD UYGHUR COMBINING DOT BELOW;Mn;220;NSM;;;;;N;;;;; +10F84;OLD UYGHUR COMBINING TWO DOTS ABOVE;Mn;230;NSM;;;;;N;;;;; +10F85;OLD UYGHUR COMBINING TWO DOTS BELOW;Mn;220;NSM;;;;;N;;;;; +10F86;OLD UYGHUR PUNCTUATION BAR;Po;0;R;;;;;N;;;;; +10F87;OLD UYGHUR PUNCTUATION TWO BARS;Po;0;R;;;;;N;;;;; +10F88;OLD UYGHUR PUNCTUATION TWO DOTS;Po;0;R;;;;;N;;;;; +10F89;OLD UYGHUR PUNCTUATION FOUR DOTS;Po;0;R;;;;;N;;;;; 10FB0;CHORASMIAN LETTER ALEPH;Lo;0;R;;;;;N;;;;; 10FB1;CHORASMIAN LETTER SMALL ALEPH;Lo;0;R;;;;;N;;;;; 10FB2;CHORASMIAN LETTER BETH;Lo;0;R;;;;;N;;;;; @@ -19381,6 +19660,12 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1106D;BRAHMI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 1106E;BRAHMI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 1106F;BRAHMI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +11070;BRAHMI SIGN OLD TAMIL VIRAMA;Mn;9;NSM;;;;;N;;;;; +11071;BRAHMI LETTER OLD TAMIL SHORT E;Lo;0;L;;;;;N;;;;; +11072;BRAHMI LETTER OLD TAMIL SHORT O;Lo;0;L;;;;;N;;;;; +11073;BRAHMI VOWEL SIGN OLD TAMIL SHORT E;Mn;0;NSM;;;;;N;;;;; +11074;BRAHMI VOWEL SIGN OLD TAMIL SHORT O;Mn;0;NSM;;;;;N;;;;; +11075;BRAHMI LETTER OLD TAMIL LLA;Lo;0;L;;;;;N;;;;; 1107F;BRAHMI NUMBER JOINER;Mn;9;NSM;;;;;N;;;;; 11080;KAITHI SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; 11081;KAITHI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; @@ -19448,6 +19733,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 110BF;KAITHI DOUBLE SECTION MARK;Po;0;L;;;;;N;;;;; 110C0;KAITHI DANDA;Po;0;L;;;;;N;;;;; 110C1;KAITHI DOUBLE DANDA;Po;0;L;;;;;N;;;;; +110C2;KAITHI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; 110CD;KAITHI NUMBER SIGN ABOVE;Cf;0;L;;;;;N;;;;; 110D0;SORA SOMPENG LETTER SAH;Lo;0;L;;;;;N;;;;; 110D1;SORA SOMPENG LETTER TAH;Lo;0;L;;;;;N;;;;; @@ -20385,6 +20671,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 116B6;TAKRI SIGN VIRAMA;Mc;9;L;;;;;N;;;;; 116B7;TAKRI SIGN NUKTA;Mn;7;NSM;;;;;N;;;;; 116B8;TAKRI LETTER ARCHAIC KHA;Lo;0;L;;;;;N;;;;; +116B9;TAKRI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 116C0;TAKRI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; 116C1;TAKRI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; 116C2;TAKRI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; @@ -20453,6 +20740,13 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1173D;AHOM SIGN SECTION;Po;0;L;;;;;N;;;;; 1173E;AHOM SIGN RULAI;Po;0;L;;;;;N;;;;; 1173F;AHOM SYMBOL VI;So;0;L;;;;;N;;;;; +11740;AHOM LETTER CA;Lo;0;L;;;;;N;;;;; +11741;AHOM LETTER TTA;Lo;0;L;;;;;N;;;;; +11742;AHOM LETTER TTHA;Lo;0;L;;;;;N;;;;; +11743;AHOM LETTER DDA;Lo;0;L;;;;;N;;;;; +11744;AHOM LETTER DDHA;Lo;0;L;;;;;N;;;;; +11745;AHOM LETTER NNA;Lo;0;L;;;;;N;;;;; +11746;AHOM LETTER LLA;Lo;0;L;;;;;N;;;;; 11800;DOGRA LETTER A;Lo;0;L;;;;;N;;;;; 11801;DOGRA LETTER AA;Lo;0;L;;;;;N;;;;; 11802;DOGRA LETTER I;Lo;0;L;;;;;N;;;;; @@ -20889,6 +21183,22 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 11AA0;SOYOMBO HEAD MARK WITH MOON AND SUN;Po;0;L;;;;;N;;;;; 11AA1;SOYOMBO TERMINAL MARK-1;Po;0;L;;;;;N;;;;; 11AA2;SOYOMBO TERMINAL MARK-2;Po;0;L;;;;;N;;;;; +11AB0;CANADIAN SYLLABICS NATTILIK HI;Lo;0;L;;;;;N;;;;; +11AB1;CANADIAN SYLLABICS NATTILIK HII;Lo;0;L;;;;;N;;;;; +11AB2;CANADIAN SYLLABICS NATTILIK HO;Lo;0;L;;;;;N;;;;; +11AB3;CANADIAN SYLLABICS NATTILIK HOO;Lo;0;L;;;;;N;;;;; +11AB4;CANADIAN SYLLABICS NATTILIK HA;Lo;0;L;;;;;N;;;;; +11AB5;CANADIAN SYLLABICS NATTILIK HAA;Lo;0;L;;;;;N;;;;; +11AB6;CANADIAN SYLLABICS NATTILIK SHRI;Lo;0;L;;;;;N;;;;; +11AB7;CANADIAN SYLLABICS NATTILIK SHRII;Lo;0;L;;;;;N;;;;; +11AB8;CANADIAN SYLLABICS NATTILIK SHRO;Lo;0;L;;;;;N;;;;; +11AB9;CANADIAN SYLLABICS NATTILIK SHROO;Lo;0;L;;;;;N;;;;; +11ABA;CANADIAN SYLLABICS NATTILIK SHRA;Lo;0;L;;;;;N;;;;; +11ABB;CANADIAN SYLLABICS NATTILIK SHRAA;Lo;0;L;;;;;N;;;;; +11ABC;CANADIAN SYLLABICS SPE;Lo;0;L;;;;;N;;;;; +11ABD;CANADIAN SYLLABICS SPI;Lo;0;L;;;;;N;;;;; +11ABE;CANADIAN SYLLABICS SPO;Lo;0;L;;;;;N;;;;; +11ABF;CANADIAN SYLLABICS SPA;Lo;0;L;;;;;N;;;;; 11AC0;PAU CIN HAU LETTER PA;Lo;0;L;;;;;N;;;;; 11AC1;PAU CIN HAU LETTER KA;Lo;0;L;;;;;N;;;;; 11AC2;PAU CIN HAU LETTER LA;Lo;0;L;;;;;N;;;;; @@ -22560,6 +22870,105 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 12541;CUNEIFORM SIGN ZA7;Lo;0;L;;;;;N;;;;; 12542;CUNEIFORM SIGN ZU OVER ZU PLUS SAR;Lo;0;L;;;;;N;;;;; 12543;CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU;Lo;0;L;;;;;N;;;;; +12F90;CYPRO-MINOAN SIGN CM001;Lo;0;L;;;;;N;;;;; +12F91;CYPRO-MINOAN SIGN CM002;Lo;0;L;;;;;N;;;;; +12F92;CYPRO-MINOAN SIGN CM004;Lo;0;L;;;;;N;;;;; +12F93;CYPRO-MINOAN SIGN CM005;Lo;0;L;;;;;N;;;;; +12F94;CYPRO-MINOAN SIGN CM006;Lo;0;L;;;;;N;;;;; +12F95;CYPRO-MINOAN SIGN CM007;Lo;0;L;;;;;N;;;;; +12F96;CYPRO-MINOAN SIGN CM008;Lo;0;L;;;;;N;;;;; +12F97;CYPRO-MINOAN SIGN CM009;Lo;0;L;;;;;N;;;;; +12F98;CYPRO-MINOAN SIGN CM010;Lo;0;L;;;;;N;;;;; +12F99;CYPRO-MINOAN SIGN CM011;Lo;0;L;;;;;N;;;;; +12F9A;CYPRO-MINOAN SIGN CM012;Lo;0;L;;;;;N;;;;; +12F9B;CYPRO-MINOAN SIGN CM012B;Lo;0;L;;;;;N;;;;; +12F9C;CYPRO-MINOAN SIGN CM013;Lo;0;L;;;;;N;;;;; +12F9D;CYPRO-MINOAN SIGN CM015;Lo;0;L;;;;;N;;;;; +12F9E;CYPRO-MINOAN SIGN CM017;Lo;0;L;;;;;N;;;;; +12F9F;CYPRO-MINOAN SIGN CM019;Lo;0;L;;;;;N;;;;; +12FA0;CYPRO-MINOAN SIGN CM021;Lo;0;L;;;;;N;;;;; +12FA1;CYPRO-MINOAN SIGN CM023;Lo;0;L;;;;;N;;;;; +12FA2;CYPRO-MINOAN SIGN CM024;Lo;0;L;;;;;N;;;;; +12FA3;CYPRO-MINOAN SIGN CM025;Lo;0;L;;;;;N;;;;; +12FA4;CYPRO-MINOAN SIGN CM026;Lo;0;L;;;;;N;;;;; +12FA5;CYPRO-MINOAN SIGN CM027;Lo;0;L;;;;;N;;;;; +12FA6;CYPRO-MINOAN SIGN CM028;Lo;0;L;;;;;N;;;;; +12FA7;CYPRO-MINOAN SIGN CM029;Lo;0;L;;;;;N;;;;; +12FA8;CYPRO-MINOAN SIGN CM030;Lo;0;L;;;;;N;;;;; +12FA9;CYPRO-MINOAN SIGN CM033;Lo;0;L;;;;;N;;;;; +12FAA;CYPRO-MINOAN SIGN CM034;Lo;0;L;;;;;N;;;;; +12FAB;CYPRO-MINOAN SIGN CM035;Lo;0;L;;;;;N;;;;; +12FAC;CYPRO-MINOAN SIGN CM036;Lo;0;L;;;;;N;;;;; +12FAD;CYPRO-MINOAN SIGN CM037;Lo;0;L;;;;;N;;;;; +12FAE;CYPRO-MINOAN SIGN CM038;Lo;0;L;;;;;N;;;;; +12FAF;CYPRO-MINOAN SIGN CM039;Lo;0;L;;;;;N;;;;; +12FB0;CYPRO-MINOAN SIGN CM040;Lo;0;L;;;;;N;;;;; +12FB1;CYPRO-MINOAN SIGN CM041;Lo;0;L;;;;;N;;;;; +12FB2;CYPRO-MINOAN SIGN CM044;Lo;0;L;;;;;N;;;;; +12FB3;CYPRO-MINOAN SIGN CM046;Lo;0;L;;;;;N;;;;; +12FB4;CYPRO-MINOAN SIGN CM047;Lo;0;L;;;;;N;;;;; +12FB5;CYPRO-MINOAN SIGN CM049;Lo;0;L;;;;;N;;;;; +12FB6;CYPRO-MINOAN SIGN CM050;Lo;0;L;;;;;N;;;;; +12FB7;CYPRO-MINOAN SIGN CM051;Lo;0;L;;;;;N;;;;; +12FB8;CYPRO-MINOAN SIGN CM052;Lo;0;L;;;;;N;;;;; +12FB9;CYPRO-MINOAN SIGN CM053;Lo;0;L;;;;;N;;;;; +12FBA;CYPRO-MINOAN SIGN CM054;Lo;0;L;;;;;N;;;;; +12FBB;CYPRO-MINOAN SIGN CM055;Lo;0;L;;;;;N;;;;; +12FBC;CYPRO-MINOAN SIGN CM056;Lo;0;L;;;;;N;;;;; +12FBD;CYPRO-MINOAN SIGN CM058;Lo;0;L;;;;;N;;;;; +12FBE;CYPRO-MINOAN SIGN CM059;Lo;0;L;;;;;N;;;;; +12FBF;CYPRO-MINOAN SIGN CM060;Lo;0;L;;;;;N;;;;; +12FC0;CYPRO-MINOAN SIGN CM061;Lo;0;L;;;;;N;;;;; +12FC1;CYPRO-MINOAN SIGN CM062;Lo;0;L;;;;;N;;;;; +12FC2;CYPRO-MINOAN SIGN CM063;Lo;0;L;;;;;N;;;;; +12FC3;CYPRO-MINOAN SIGN CM064;Lo;0;L;;;;;N;;;;; +12FC4;CYPRO-MINOAN SIGN CM066;Lo;0;L;;;;;N;;;;; +12FC5;CYPRO-MINOAN SIGN CM067;Lo;0;L;;;;;N;;;;; +12FC6;CYPRO-MINOAN SIGN CM068;Lo;0;L;;;;;N;;;;; +12FC7;CYPRO-MINOAN SIGN CM069;Lo;0;L;;;;;N;;;;; +12FC8;CYPRO-MINOAN SIGN CM070;Lo;0;L;;;;;N;;;;; +12FC9;CYPRO-MINOAN SIGN CM071;Lo;0;L;;;;;N;;;;; +12FCA;CYPRO-MINOAN SIGN CM072;Lo;0;L;;;;;N;;;;; +12FCB;CYPRO-MINOAN SIGN CM073;Lo;0;L;;;;;N;;;;; +12FCC;CYPRO-MINOAN SIGN CM074;Lo;0;L;;;;;N;;;;; +12FCD;CYPRO-MINOAN SIGN CM075;Lo;0;L;;;;;N;;;;; +12FCE;CYPRO-MINOAN SIGN CM075B;Lo;0;L;;;;;N;;;;; +12FCF;CYPRO-MINOAN SIGN CM076;Lo;0;L;;;;;N;;;;; +12FD0;CYPRO-MINOAN SIGN CM078;Lo;0;L;;;;;N;;;;; +12FD1;CYPRO-MINOAN SIGN CM079;Lo;0;L;;;;;N;;;;; +12FD2;CYPRO-MINOAN SIGN CM080;Lo;0;L;;;;;N;;;;; +12FD3;CYPRO-MINOAN SIGN CM081;Lo;0;L;;;;;N;;;;; +12FD4;CYPRO-MINOAN SIGN CM082;Lo;0;L;;;;;N;;;;; +12FD5;CYPRO-MINOAN SIGN CM083;Lo;0;L;;;;;N;;;;; +12FD6;CYPRO-MINOAN SIGN CM084;Lo;0;L;;;;;N;;;;; +12FD7;CYPRO-MINOAN SIGN CM085;Lo;0;L;;;;;N;;;;; +12FD8;CYPRO-MINOAN SIGN CM086;Lo;0;L;;;;;N;;;;; +12FD9;CYPRO-MINOAN SIGN CM087;Lo;0;L;;;;;N;;;;; +12FDA;CYPRO-MINOAN SIGN CM088;Lo;0;L;;;;;N;;;;; +12FDB;CYPRO-MINOAN SIGN CM089;Lo;0;L;;;;;N;;;;; +12FDC;CYPRO-MINOAN SIGN CM090;Lo;0;L;;;;;N;;;;; +12FDD;CYPRO-MINOAN SIGN CM091;Lo;0;L;;;;;N;;;;; +12FDE;CYPRO-MINOAN SIGN CM092;Lo;0;L;;;;;N;;;;; +12FDF;CYPRO-MINOAN SIGN CM094;Lo;0;L;;;;;N;;;;; +12FE0;CYPRO-MINOAN SIGN CM095;Lo;0;L;;;;;N;;;;; +12FE1;CYPRO-MINOAN SIGN CM096;Lo;0;L;;;;;N;;;;; +12FE2;CYPRO-MINOAN SIGN CM097;Lo;0;L;;;;;N;;;;; +12FE3;CYPRO-MINOAN SIGN CM098;Lo;0;L;;;;;N;;;;; +12FE4;CYPRO-MINOAN SIGN CM099;Lo;0;L;;;;;N;;;;; +12FE5;CYPRO-MINOAN SIGN CM100;Lo;0;L;;;;;N;;;;; +12FE6;CYPRO-MINOAN SIGN CM101;Lo;0;L;;;;;N;;;;; +12FE7;CYPRO-MINOAN SIGN CM102;Lo;0;L;;;;;N;;;;; +12FE8;CYPRO-MINOAN SIGN CM103;Lo;0;L;;;;;N;;;;; +12FE9;CYPRO-MINOAN SIGN CM104;Lo;0;L;;;;;N;;;;; +12FEA;CYPRO-MINOAN SIGN CM105;Lo;0;L;;;;;N;;;;; +12FEB;CYPRO-MINOAN SIGN CM107;Lo;0;L;;;;;N;;;;; +12FEC;CYPRO-MINOAN SIGN CM108;Lo;0;L;;;;;N;;;;; +12FED;CYPRO-MINOAN SIGN CM109;Lo;0;L;;;;;N;;;;; +12FEE;CYPRO-MINOAN SIGN CM110;Lo;0;L;;;;;N;;;;; +12FEF;CYPRO-MINOAN SIGN CM112;Lo;0;L;;;;;N;;;;; +12FF0;CYPRO-MINOAN SIGN CM114;Lo;0;L;;;;;N;;;;; +12FF1;CYPRO-MINOAN SIGN CM301;Po;0;L;;;;;N;;;;; +12FF2;CYPRO-MINOAN SIGN CM302;Po;0;L;;;;;N;;;;; 13000;EGYPTIAN HIEROGLYPH A001;Lo;0;L;;;;;N;;;;; 13001;EGYPTIAN HIEROGLYPH A002;Lo;0;L;;;;;N;;;;; 13002;EGYPTIAN HIEROGLYPH A003;Lo;0;L;;;;;N;;;;; @@ -24835,6 +25244,95 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 16A69;MRO DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 16A6E;MRO DANDA;Po;0;L;;;;;N;;;;; 16A6F;MRO DOUBLE DANDA;Po;0;L;;;;;N;;;;; +16A70;TANGSA LETTER OZ;Lo;0;L;;;;;N;;;;; +16A71;TANGSA LETTER OC;Lo;0;L;;;;;N;;;;; +16A72;TANGSA LETTER OQ;Lo;0;L;;;;;N;;;;; +16A73;TANGSA LETTER OX;Lo;0;L;;;;;N;;;;; +16A74;TANGSA LETTER AZ;Lo;0;L;;;;;N;;;;; +16A75;TANGSA LETTER AC;Lo;0;L;;;;;N;;;;; +16A76;TANGSA LETTER AQ;Lo;0;L;;;;;N;;;;; +16A77;TANGSA LETTER AX;Lo;0;L;;;;;N;;;;; +16A78;TANGSA LETTER VZ;Lo;0;L;;;;;N;;;;; +16A79;TANGSA LETTER VC;Lo;0;L;;;;;N;;;;; +16A7A;TANGSA LETTER VQ;Lo;0;L;;;;;N;;;;; +16A7B;TANGSA LETTER VX;Lo;0;L;;;;;N;;;;; +16A7C;TANGSA LETTER EZ;Lo;0;L;;;;;N;;;;; +16A7D;TANGSA LETTER EC;Lo;0;L;;;;;N;;;;; +16A7E;TANGSA LETTER EQ;Lo;0;L;;;;;N;;;;; +16A7F;TANGSA LETTER EX;Lo;0;L;;;;;N;;;;; +16A80;TANGSA LETTER IZ;Lo;0;L;;;;;N;;;;; +16A81;TANGSA LETTER IC;Lo;0;L;;;;;N;;;;; +16A82;TANGSA LETTER IQ;Lo;0;L;;;;;N;;;;; +16A83;TANGSA LETTER IX;Lo;0;L;;;;;N;;;;; +16A84;TANGSA LETTER UZ;Lo;0;L;;;;;N;;;;; +16A85;TANGSA LETTER UC;Lo;0;L;;;;;N;;;;; +16A86;TANGSA LETTER UQ;Lo;0;L;;;;;N;;;;; +16A87;TANGSA LETTER UX;Lo;0;L;;;;;N;;;;; +16A88;TANGSA LETTER AWZ;Lo;0;L;;;;;N;;;;; +16A89;TANGSA LETTER AWC;Lo;0;L;;;;;N;;;;; +16A8A;TANGSA LETTER AWQ;Lo;0;L;;;;;N;;;;; +16A8B;TANGSA LETTER AWX;Lo;0;L;;;;;N;;;;; +16A8C;TANGSA LETTER UIZ;Lo;0;L;;;;;N;;;;; +16A8D;TANGSA LETTER UIC;Lo;0;L;;;;;N;;;;; +16A8E;TANGSA LETTER UIQ;Lo;0;L;;;;;N;;;;; +16A8F;TANGSA LETTER UIX;Lo;0;L;;;;;N;;;;; +16A90;TANGSA LETTER FINAL NG;Lo;0;L;;;;;N;;;;; +16A91;TANGSA LETTER LONG UEX;Lo;0;L;;;;;N;;;;; +16A92;TANGSA LETTER SHORT UEZ;Lo;0;L;;;;;N;;;;; +16A93;TANGSA LETTER SHORT AWX;Lo;0;L;;;;;N;;;;; +16A94;TANGSA LETTER UEC;Lo;0;L;;;;;N;;;;; +16A95;TANGSA LETTER UEZ;Lo;0;L;;;;;N;;;;; +16A96;TANGSA LETTER UEQ;Lo;0;L;;;;;N;;;;; +16A97;TANGSA LETTER UEX;Lo;0;L;;;;;N;;;;; +16A98;TANGSA LETTER UIUZ;Lo;0;L;;;;;N;;;;; +16A99;TANGSA LETTER UIUC;Lo;0;L;;;;;N;;;;; +16A9A;TANGSA LETTER UIUQ;Lo;0;L;;;;;N;;;;; +16A9B;TANGSA LETTER UIUX;Lo;0;L;;;;;N;;;;; +16A9C;TANGSA LETTER MZ;Lo;0;L;;;;;N;;;;; +16A9D;TANGSA LETTER MC;Lo;0;L;;;;;N;;;;; +16A9E;TANGSA LETTER MQ;Lo;0;L;;;;;N;;;;; +16A9F;TANGSA LETTER MX;Lo;0;L;;;;;N;;;;; +16AA0;TANGSA LETTER KA;Lo;0;L;;;;;N;;;;; +16AA1;TANGSA LETTER KHA;Lo;0;L;;;;;N;;;;; +16AA2;TANGSA LETTER GA;Lo;0;L;;;;;N;;;;; +16AA3;TANGSA LETTER NGA;Lo;0;L;;;;;N;;;;; +16AA4;TANGSA LETTER SA;Lo;0;L;;;;;N;;;;; +16AA5;TANGSA LETTER YA;Lo;0;L;;;;;N;;;;; +16AA6;TANGSA LETTER WA;Lo;0;L;;;;;N;;;;; +16AA7;TANGSA LETTER PA;Lo;0;L;;;;;N;;;;; +16AA8;TANGSA LETTER NYA;Lo;0;L;;;;;N;;;;; +16AA9;TANGSA LETTER PHA;Lo;0;L;;;;;N;;;;; +16AAA;TANGSA LETTER BA;Lo;0;L;;;;;N;;;;; +16AAB;TANGSA LETTER MA;Lo;0;L;;;;;N;;;;; +16AAC;TANGSA LETTER NA;Lo;0;L;;;;;N;;;;; +16AAD;TANGSA LETTER HA;Lo;0;L;;;;;N;;;;; +16AAE;TANGSA LETTER LA;Lo;0;L;;;;;N;;;;; +16AAF;TANGSA LETTER HTA;Lo;0;L;;;;;N;;;;; +16AB0;TANGSA LETTER TA;Lo;0;L;;;;;N;;;;; +16AB1;TANGSA LETTER DA;Lo;0;L;;;;;N;;;;; +16AB2;TANGSA LETTER RA;Lo;0;L;;;;;N;;;;; +16AB3;TANGSA LETTER NHA;Lo;0;L;;;;;N;;;;; +16AB4;TANGSA LETTER SHA;Lo;0;L;;;;;N;;;;; +16AB5;TANGSA LETTER CA;Lo;0;L;;;;;N;;;;; +16AB6;TANGSA LETTER TSA;Lo;0;L;;;;;N;;;;; +16AB7;TANGSA LETTER GHA;Lo;0;L;;;;;N;;;;; +16AB8;TANGSA LETTER HTTA;Lo;0;L;;;;;N;;;;; +16AB9;TANGSA LETTER THA;Lo;0;L;;;;;N;;;;; +16ABA;TANGSA LETTER XA;Lo;0;L;;;;;N;;;;; +16ABB;TANGSA LETTER FA;Lo;0;L;;;;;N;;;;; +16ABC;TANGSA LETTER DHA;Lo;0;L;;;;;N;;;;; +16ABD;TANGSA LETTER CHA;Lo;0;L;;;;;N;;;;; +16ABE;TANGSA LETTER ZA;Lo;0;L;;;;;N;;;;; +16AC0;TANGSA DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +16AC1;TANGSA DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +16AC2;TANGSA DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +16AC3;TANGSA DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +16AC4;TANGSA DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +16AC5;TANGSA DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +16AC6;TANGSA DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +16AC7;TANGSA DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +16AC8;TANGSA DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +16AC9;TANGSA DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 16AD0;BASSA VAH LETTER ENNI;Lo;0;L;;;;;N;;;;; 16AD1;BASSA VAH LETTER KA;Lo;0;L;;;;;N;;;;; 16AD2;BASSA VAH LETTER SE;Lo;0;L;;;;;N;;;;; @@ -26487,6 +26985,19 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 18CD5;KHITAN SMALL SCRIPT CHARACTER-18CD5;Lo;0;L;;;;;N;;;;; 18D00;<Tangut Ideograph Supplement, First>;Lo;0;L;;;;;N;;;;; 18D08;<Tangut Ideograph Supplement, Last>;Lo;0;L;;;;;N;;;;; +1AFF0;KATAKANA LETTER MINNAN TONE-2;Lm;0;L;;;;;N;;;;; +1AFF1;KATAKANA LETTER MINNAN TONE-3;Lm;0;L;;;;;N;;;;; +1AFF2;KATAKANA LETTER MINNAN TONE-4;Lm;0;L;;;;;N;;;;; +1AFF3;KATAKANA LETTER MINNAN TONE-5;Lm;0;L;;;;;N;;;;; +1AFF5;KATAKANA LETTER MINNAN TONE-7;Lm;0;L;;;;;N;;;;; +1AFF6;KATAKANA LETTER MINNAN TONE-8;Lm;0;L;;;;;N;;;;; +1AFF7;KATAKANA LETTER MINNAN NASALIZED TONE-1;Lm;0;L;;;;;N;;;;; +1AFF8;KATAKANA LETTER MINNAN NASALIZED TONE-2;Lm;0;L;;;;;N;;;;; +1AFF9;KATAKANA LETTER MINNAN NASALIZED TONE-3;Lm;0;L;;;;;N;;;;; +1AFFA;KATAKANA LETTER MINNAN NASALIZED TONE-4;Lm;0;L;;;;;N;;;;; +1AFFB;KATAKANA LETTER MINNAN NASALIZED TONE-5;Lm;0;L;;;;;N;;;;; +1AFFD;KATAKANA LETTER MINNAN NASALIZED TONE-7;Lm;0;L;;;;;N;;;;; +1AFFE;KATAKANA LETTER MINNAN NASALIZED TONE-8;Lm;0;L;;;;;N;;;;; 1B000;KATAKANA LETTER ARCHAIC E;Lo;0;L;;;;;N;;;;; 1B001;HIRAGANA LETTER ARCHAIC YE;Lo;0;L;;;;;N;;;;; 1B002;HENTAIGANA LETTER A-1;Lo;0;L;;;;;N;;;;; @@ -26774,6 +27285,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1B11C;HENTAIGANA LETTER WO-7;Lo;0;L;;;;;N;;;;; 1B11D;HENTAIGANA LETTER N-MU-MO-1;Lo;0;L;;;;;N;;;;; 1B11E;HENTAIGANA LETTER N-MU-MO-2;Lo;0;L;;;;;N;;;;; +1B11F;HIRAGANA LETTER ARCHAIC WU;Lo;0;L;;;;;N;;;;; +1B120;KATAKANA LETTER ARCHAIC YI;Lo;0;L;;;;;N;;;;; +1B121;KATAKANA LETTER ARCHAIC YE;Lo;0;L;;;;;N;;;;; +1B122;KATAKANA LETTER ARCHAIC WU;Lo;0;L;;;;;N;;;;; 1B150;HIRAGANA LETTER SMALL WI;Lo;0;L;;;;;N;;;;; 1B151;HIRAGANA LETTER SMALL WE;Lo;0;L;;;;;N;;;;; 1B152;HIRAGANA LETTER SMALL WO;Lo;0;L;;;;;N;;;;; @@ -27324,6 +27839,191 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1BCA1;SHORTHAND FORMAT CONTINUING OVERLAP;Cf;0;BN;;;;;N;;;;; 1BCA2;SHORTHAND FORMAT DOWN STEP;Cf;0;BN;;;;;N;;;;; 1BCA3;SHORTHAND FORMAT UP STEP;Cf;0;BN;;;;;N;;;;; +1CF00;ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF01;ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF02;ZNAMENNY COMBINING MARK TSATA ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF03;ZNAMENNY COMBINING MARK GORAZDO NIZKO ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF04;ZNAMENNY COMBINING MARK NIZKO ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF05;ZNAMENNY COMBINING MARK SREDNE ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF06;ZNAMENNY COMBINING MARK MALO POVYSHE ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF07;ZNAMENNY COMBINING MARK POVYSHE ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF08;ZNAMENNY COMBINING MARK VYSOKO ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF09;ZNAMENNY COMBINING MARK MALO POVYSHE S KHOKHLOM ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF0A;ZNAMENNY COMBINING MARK POVYSHE S KHOKHLOM ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF0B;ZNAMENNY COMBINING MARK VYSOKO S KHOKHLOM ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF0C;ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF0D;ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF0E;ZNAMENNY COMBINING MARK TSATA ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF0F;ZNAMENNY COMBINING MARK GORAZDO NIZKO ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF10;ZNAMENNY COMBINING MARK NIZKO ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF11;ZNAMENNY COMBINING MARK SREDNE ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF12;ZNAMENNY COMBINING MARK MALO POVYSHE ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF13;ZNAMENNY COMBINING MARK POVYSHE ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF14;ZNAMENNY COMBINING MARK VYSOKO ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF15;ZNAMENNY COMBINING MARK MALO POVYSHE S KHOKHLOM ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF16;ZNAMENNY COMBINING MARK POVYSHE S KHOKHLOM ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF17;ZNAMENNY COMBINING MARK VYSOKO S KHOKHLOM ON RIGHT;Mn;0;NSM;;;;;N;;;;; +1CF18;ZNAMENNY COMBINING MARK TSATA S KRYZHEM;Mn;0;NSM;;;;;N;;;;; +1CF19;ZNAMENNY COMBINING MARK MALO POVYSHE S KRYZHEM;Mn;0;NSM;;;;;N;;;;; +1CF1A;ZNAMENNY COMBINING MARK STRANNO MALO POVYSHE;Mn;0;NSM;;;;;N;;;;; +1CF1B;ZNAMENNY COMBINING MARK POVYSHE S KRYZHEM;Mn;0;NSM;;;;;N;;;;; +1CF1C;ZNAMENNY COMBINING MARK POVYSHE STRANNO;Mn;0;NSM;;;;;N;;;;; +1CF1D;ZNAMENNY COMBINING MARK VYSOKO S KRYZHEM;Mn;0;NSM;;;;;N;;;;; +1CF1E;ZNAMENNY COMBINING MARK MALO POVYSHE STRANNO;Mn;0;NSM;;;;;N;;;;; +1CF1F;ZNAMENNY COMBINING MARK GORAZDO VYSOKO;Mn;0;NSM;;;;;N;;;;; +1CF20;ZNAMENNY COMBINING MARK ZELO;Mn;0;NSM;;;;;N;;;;; +1CF21;ZNAMENNY COMBINING MARK ON;Mn;0;NSM;;;;;N;;;;; +1CF22;ZNAMENNY COMBINING MARK RAVNO;Mn;0;NSM;;;;;N;;;;; +1CF23;ZNAMENNY COMBINING MARK TIKHAYA;Mn;0;NSM;;;;;N;;;;; +1CF24;ZNAMENNY COMBINING MARK BORZAYA;Mn;0;NSM;;;;;N;;;;; +1CF25;ZNAMENNY COMBINING MARK UDARKA;Mn;0;NSM;;;;;N;;;;; +1CF26;ZNAMENNY COMBINING MARK PODVERTKA;Mn;0;NSM;;;;;N;;;;; +1CF27;ZNAMENNY COMBINING MARK LOMKA;Mn;0;NSM;;;;;N;;;;; +1CF28;ZNAMENNY COMBINING MARK KUPNAYA;Mn;0;NSM;;;;;N;;;;; +1CF29;ZNAMENNY COMBINING MARK KACHKA;Mn;0;NSM;;;;;N;;;;; +1CF2A;ZNAMENNY COMBINING MARK ZEVOK;Mn;0;NSM;;;;;N;;;;; +1CF2B;ZNAMENNY COMBINING MARK SKOBA;Mn;0;NSM;;;;;N;;;;; +1CF2C;ZNAMENNY COMBINING MARK RAZSEKA;Mn;0;NSM;;;;;N;;;;; +1CF2D;ZNAMENNY COMBINING MARK KRYZH ON LEFT;Mn;0;NSM;;;;;N;;;;; +1CF30;ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO;Mn;0;NSM;;;;;N;;;;; +1CF31;ZNAMENNY COMBINING TONAL RANGE MARK SVETLO;Mn;0;NSM;;;;;N;;;;; +1CF32;ZNAMENNY COMBINING TONAL RANGE MARK TRESVETLO;Mn;0;NSM;;;;;N;;;;; +1CF33;ZNAMENNY COMBINING MARK ZADERZHKA;Mn;0;NSM;;;;;N;;;;; +1CF34;ZNAMENNY COMBINING MARK DEMESTVENNY ZADERZHKA;Mn;0;NSM;;;;;N;;;;; +1CF35;ZNAMENNY COMBINING MARK OTSECHKA;Mn;0;NSM;;;;;N;;;;; +1CF36;ZNAMENNY COMBINING MARK PODCHASHIE;Mn;0;NSM;;;;;N;;;;; +1CF37;ZNAMENNY COMBINING MARK PODCHASHIE WITH VERTICAL STROKE;Mn;0;NSM;;;;;N;;;;; +1CF38;ZNAMENNY COMBINING MARK CHASHKA;Mn;0;NSM;;;;;N;;;;; +1CF39;ZNAMENNY COMBINING MARK CHASHKA POLNAYA;Mn;0;NSM;;;;;N;;;;; +1CF3A;ZNAMENNY COMBINING MARK OBLACHKO;Mn;0;NSM;;;;;N;;;;; +1CF3B;ZNAMENNY COMBINING MARK SOROCHYA NOZHKA;Mn;0;NSM;;;;;N;;;;; +1CF3C;ZNAMENNY COMBINING MARK TOCHKA;Mn;0;NSM;;;;;N;;;;; +1CF3D;ZNAMENNY COMBINING MARK DVOETOCHIE;Mn;0;NSM;;;;;N;;;;; +1CF3E;ZNAMENNY COMBINING ATTACHING VERTICAL OMET;Mn;0;NSM;;;;;N;;;;; +1CF3F;ZNAMENNY COMBINING MARK CURVED OMET;Mn;0;NSM;;;;;N;;;;; +1CF40;ZNAMENNY COMBINING MARK KRYZH;Mn;0;NSM;;;;;N;;;;; +1CF41;ZNAMENNY COMBINING LOWER TONAL RANGE INDICATOR;Mn;0;NSM;;;;;N;;;;; +1CF42;ZNAMENNY PRIZNAK MODIFIER LEVEL-2;Mn;0;NSM;;;;;N;;;;; +1CF43;ZNAMENNY PRIZNAK MODIFIER LEVEL-3;Mn;0;NSM;;;;;N;;;;; +1CF44;ZNAMENNY PRIZNAK MODIFIER DIRECTION FLIP;Mn;0;NSM;;;;;N;;;;; +1CF45;ZNAMENNY PRIZNAK MODIFIER KRYZH;Mn;0;NSM;;;;;N;;;;; +1CF46;ZNAMENNY PRIZNAK MODIFIER ROG;Mn;0;NSM;;;;;N;;;;; +1CF50;ZNAMENNY NEUME KRYUK;So;0;L;;;;;N;;;;; +1CF51;ZNAMENNY NEUME KRYUK TIKHY;So;0;L;;;;;N;;;;; +1CF52;ZNAMENNY NEUME PARAKLIT;So;0;L;;;;;N;;;;; +1CF53;ZNAMENNY NEUME DVA V CHELNU;So;0;L;;;;;N;;;;; +1CF54;ZNAMENNY NEUME KLYUCH;So;0;L;;;;;N;;;;; +1CF55;ZNAMENNY NEUME ZANOZHEK;So;0;L;;;;;N;;;;; +1CF56;ZNAMENNY NEUME STOPITSA;So;0;L;;;;;N;;;;; +1CF57;ZNAMENNY NEUME STOPITSA S OCHKOM;So;0;L;;;;;N;;;;; +1CF58;ZNAMENNY NEUME PEREVODKA;So;0;L;;;;;N;;;;; +1CF59;ZNAMENNY NEUME PEREVODKA NEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CF5A;ZNAMENNY NEUME STOPITSA WITH SOROCHYA NOZHKA;So;0;L;;;;;N;;;;; +1CF5B;ZNAMENNY NEUME CHELYUSTKA;So;0;L;;;;;N;;;;; +1CF5C;ZNAMENNY NEUME PALKA;So;0;L;;;;;N;;;;; +1CF5D;ZNAMENNY NEUME ZAPYATAYA;So;0;L;;;;;N;;;;; +1CF5E;ZNAMENNY NEUME GOLUBCHIK BORZY;So;0;L;;;;;N;;;;; +1CF5F;ZNAMENNY NEUME GOLUBCHIK TIKHY;So;0;L;;;;;N;;;;; +1CF60;ZNAMENNY NEUME GOLUBCHIK MRACHNY;So;0;L;;;;;N;;;;; +1CF61;ZNAMENNY NEUME GOLUBCHIK SVETLY;So;0;L;;;;;N;;;;; +1CF62;ZNAMENNY NEUME GOLUBCHIK TRESVETLY;So;0;L;;;;;N;;;;; +1CF63;ZNAMENNY NEUME VRAKHIYA PROSTAYA;So;0;L;;;;;N;;;;; +1CF64;ZNAMENNY NEUME VRAKHIYA MRACHNAYA;So;0;L;;;;;N;;;;; +1CF65;ZNAMENNY NEUME VRAKHIYA SVETLAYA;So;0;L;;;;;N;;;;; +1CF66;ZNAMENNY NEUME VRAKHIYA TRESVETLAYA;So;0;L;;;;;N;;;;; +1CF67;ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA PROSTAYA;So;0;L;;;;;N;;;;; +1CF68;ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA MRACHNAYA;So;0;L;;;;;N;;;;; +1CF69;ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA SVETLAYA;So;0;L;;;;;N;;;;; +1CF6A;ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA TRESVETLAYA;So;0;L;;;;;N;;;;; +1CF6B;ZNAMENNY NEUME DOUBLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CF6C;ZNAMENNY NEUME REVERSED CHELYUSTKA;So;0;L;;;;;N;;;;; +1CF6D;ZNAMENNY NEUME DERBITSA;So;0;L;;;;;N;;;;; +1CF6E;ZNAMENNY NEUME KHAMILO;So;0;L;;;;;N;;;;; +1CF6F;ZNAMENNY NEUME CHASHKA;So;0;L;;;;;N;;;;; +1CF70;ZNAMENNY NEUME PODCHASHIE;So;0;L;;;;;N;;;;; +1CF71;ZNAMENNY NEUME SKAMEYTSA MRACHNAYA;So;0;L;;;;;N;;;;; +1CF72;ZNAMENNY NEUME SKAMEYTSA SVETLAYA;So;0;L;;;;;N;;;;; +1CF73;ZNAMENNY NEUME SKAMEYTSA TRESVETLAYA;So;0;L;;;;;N;;;;; +1CF74;ZNAMENNY NEUME SKAMEYTSA TIKHAYA;So;0;L;;;;;N;;;;; +1CF75;ZNAMENNY NEUME DEMESTVENNY KLYUCH;So;0;L;;;;;N;;;;; +1CF76;ZNAMENNY NEUME SKAMEYTSA KLYUCHEVAYA SVETLAYA;So;0;L;;;;;N;;;;; +1CF77;ZNAMENNY NEUME SKAMEYTSA KLYUCHENEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CF78;ZNAMENNY NEUME SKAMEYTSA KLYUCHEVAYA TIKHAYA;So;0;L;;;;;N;;;;; +1CF79;ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA PROSTAYA;So;0;L;;;;;N;;;;; +1CF7A;ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA SVETLAYA;So;0;L;;;;;N;;;;; +1CF7B;ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA NEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CF7C;ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA KLYUCHEVAYA;So;0;L;;;;;N;;;;; +1CF7D;ZNAMENNY NEUME SLOZHITIE;So;0;L;;;;;N;;;;; +1CF7E;ZNAMENNY NEUME SLOZHITIE S ZAPYATOY;So;0;L;;;;;N;;;;; +1CF7F;ZNAMENNY NEUME SLOZHITIE ZAKRYTOE;So;0;L;;;;;N;;;;; +1CF80;ZNAMENNY NEUME SLOZHITIE S KRYZHEM;So;0;L;;;;;N;;;;; +1CF81;ZNAMENNY NEUME KRYZH;So;0;L;;;;;N;;;;; +1CF82;ZNAMENNY NEUME ROG;So;0;L;;;;;N;;;;; +1CF83;ZNAMENNY NEUME FITA;So;0;L;;;;;N;;;;; +1CF84;ZNAMENNY NEUME KOBYLA;So;0;L;;;;;N;;;;; +1CF85;ZNAMENNY NEUME ZMEYTSA;So;0;L;;;;;N;;;;; +1CF86;ZNAMENNY NEUME STATYA;So;0;L;;;;;N;;;;; +1CF87;ZNAMENNY NEUME STATYA S ZAPYATOY;So;0;L;;;;;N;;;;; +1CF88;ZNAMENNY NEUME STATYA S KRYZHEM;So;0;L;;;;;N;;;;; +1CF89;ZNAMENNY NEUME STATYA S ZAPYATOY I KRYZHEM;So;0;L;;;;;N;;;;; +1CF8A;ZNAMENNY NEUME STATYA S KRYZHEM I ZAPYATOY;So;0;L;;;;;N;;;;; +1CF8B;ZNAMENNY NEUME STATYA ZAKRYTAYA;So;0;L;;;;;N;;;;; +1CF8C;ZNAMENNY NEUME STATYA ZAKRYTAYA S ZAPYATOY;So;0;L;;;;;N;;;;; +1CF8D;ZNAMENNY NEUME STATYA S ROGOM;So;0;L;;;;;N;;;;; +1CF8E;ZNAMENNY NEUME STATYA S DVUMYA ZAPYATYMI;So;0;L;;;;;N;;;;; +1CF8F;ZNAMENNY NEUME STATYA S ZAPYATOY I PODCHASHIEM;So;0;L;;;;;N;;;;; +1CF90;ZNAMENNY NEUME POLKULIZMY;So;0;L;;;;;N;;;;; +1CF91;ZNAMENNY NEUME STATYA NEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CF92;ZNAMENNY NEUME STRELA PROSTAYA;So;0;L;;;;;N;;;;; +1CF93;ZNAMENNY NEUME STRELA MRACHNOTIKHAYA;So;0;L;;;;;N;;;;; +1CF94;ZNAMENNY NEUME STRELA KRYZHEVAYA;So;0;L;;;;;N;;;;; +1CF95;ZNAMENNY NEUME STRELA POLUPOVODNAYA;So;0;L;;;;;N;;;;; +1CF96;ZNAMENNY NEUME STRELA POVODNAYA;So;0;L;;;;;N;;;;; +1CF97;ZNAMENNY NEUME STRELA NEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CF98;ZNAMENNY NEUME STRELA KLYUCHEPOVODNAYA;So;0;L;;;;;N;;;;; +1CF99;ZNAMENNY NEUME STRELA KLYUCHENEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CF9A;ZNAMENNY NEUME STRELA TIKHAYA PUTNAYA;So;0;L;;;;;N;;;;; +1CF9B;ZNAMENNY NEUME STRELA DVOECHELNAYA;So;0;L;;;;;N;;;;; +1CF9C;ZNAMENNY NEUME STRELA DVOECHELNOKRYZHEVAYA;So;0;L;;;;;N;;;;; +1CF9D;ZNAMENNY NEUME STRELA DVOECHELNOPOVODNAYA;So;0;L;;;;;N;;;;; +1CF9E;ZNAMENNY NEUME STRELA DVOECHELNAYA KLYUCHEVAYA;So;0;L;;;;;N;;;;; +1CF9F;ZNAMENNY NEUME STRELA DVOECHELNOPOVODNAYA KLYUCHEVAYA;So;0;L;;;;;N;;;;; +1CFA0;ZNAMENNY NEUME STRELA GROMNAYA WITH SINGLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CFA1;ZNAMENNY NEUME STRELA GROMOPOVODNAYA WITH SINGLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CFA2;ZNAMENNY NEUME STRELA GROMNAYA;So;0;L;;;;;N;;;;; +1CFA3;ZNAMENNY NEUME STRELA GROMOPOVODNAYA;So;0;L;;;;;N;;;;; +1CFA4;ZNAMENNY NEUME STRELA GROMOPOVODNAYA WITH DOUBLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CFA5;ZNAMENNY NEUME STRELA GROMOKRYZHEVAYA;So;0;L;;;;;N;;;;; +1CFA6;ZNAMENNY NEUME STRELA GROMOKRYZHEVAYA POVODNAYA;So;0;L;;;;;N;;;;; +1CFA7;ZNAMENNY NEUME MECHIK;So;0;L;;;;;N;;;;; +1CFA8;ZNAMENNY NEUME MECHIK POVODNY;So;0;L;;;;;N;;;;; +1CFA9;ZNAMENNY NEUME MECHIK KLYUCHEVOY;So;0;L;;;;;N;;;;; +1CFAA;ZNAMENNY NEUME MECHIK KLYUCHEPOVODNY;So;0;L;;;;;N;;;;; +1CFAB;ZNAMENNY NEUME MECHIK KLYUCHENEPOSTOYANNY;So;0;L;;;;;N;;;;; +1CFAC;ZNAMENNY NEUME STRELA TRYASOGLASNAYA;So;0;L;;;;;N;;;;; +1CFAD;ZNAMENNY NEUME STRELA TRYASOPOVODNAYA;So;0;L;;;;;N;;;;; +1CFAE;ZNAMENNY NEUME STRELA TRYASOSTRELNAYA;So;0;L;;;;;N;;;;; +1CFAF;ZNAMENNY NEUME OSOKA;So;0;L;;;;;N;;;;; +1CFB0;ZNAMENNY NEUME OSOKA SVETLAYA;So;0;L;;;;;N;;;;; +1CFB1;ZNAMENNY NEUME OSOKA TRESVETLAYA;So;0;L;;;;;N;;;;; +1CFB2;ZNAMENNY NEUME OSOKA KRYUKOVAYA SVETLAYA;So;0;L;;;;;N;;;;; +1CFB3;ZNAMENNY NEUME OSOKA KLYUCHEVAYA SVETLAYA;So;0;L;;;;;N;;;;; +1CFB4;ZNAMENNY NEUME OSOKA KLYUCHEVAYA NEPOSTOYANNAYA;So;0;L;;;;;N;;;;; +1CFB5;ZNAMENNY NEUME STRELA KRYUKOVAYA;So;0;L;;;;;N;;;;; +1CFB6;ZNAMENNY NEUME STRELA KRYUKOVAYA POVODNAYA;So;0;L;;;;;N;;;;; +1CFB7;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMNAYA WITH SINGLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CFB8;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA WITH SINGLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CFB9;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMNAYA;So;0;L;;;;;N;;;;; +1CFBA;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA;So;0;L;;;;;N;;;;; +1CFBB;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA WITH DOUBLE ZAPYATAYA;So;0;L;;;;;N;;;;; +1CFBC;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOKRYZHEVAYA;So;0;L;;;;;N;;;;; +1CFBD;ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOKRYZHEVAYA POVODNAYA;So;0;L;;;;;N;;;;; +1CFBE;ZNAMENNY NEUME STRELA KRYUKOVAYA TRYASKA;So;0;L;;;;;N;;;;; +1CFBF;ZNAMENNY NEUME KUFISMA;So;0;L;;;;;N;;;;; +1CFC0;ZNAMENNY NEUME OBLAKO;So;0;L;;;;;N;;;;; +1CFC1;ZNAMENNY NEUME DUDA;So;0;L;;;;;N;;;;; +1CFC2;ZNAMENNY NEUME NEMKA;So;0;L;;;;;N;;;;; +1CFC3;ZNAMENNY NEUME PAUK;So;0;L;;;;;N;;;;; 1D000;BYZANTINE MUSICAL SYMBOL PSILI;So;0;L;;;;;N;;;;; 1D001;BYZANTINE MUSICAL SYMBOL DASEIA;So;0;L;;;;;N;;;;; 1D002;BYZANTINE MUSICAL SYMBOL PERISPOMENI;So;0;L;;;;;N;;;;; @@ -27801,6 +28501,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D1E6;MUSICAL SYMBOL KIEVAN EIGHTH NOTE STEM DOWN;So;0;L;;;;;N;;;;; 1D1E7;MUSICAL SYMBOL KIEVAN EIGHTH NOTE STEM UP;So;0;L;;;;;N;;;;; 1D1E8;MUSICAL SYMBOL KIEVAN FLAT SIGN;So;0;L;;;;;N;;;;; +1D1E9;MUSICAL SYMBOL SORI;So;0;ON;;;;;N;;;;; +1D1EA;MUSICAL SYMBOL KORON;So;0;ON;;;;;N;;;;; 1D200;GREEK VOCAL NOTATION SYMBOL-1;So;0;ON;;;;;N;;;;; 1D201;GREEK VOCAL NOTATION SYMBOL-2;So;0;ON;;;;;N;;;;; 1D202;GREEK VOCAL NOTATION SYMBOL-3;So;0;ON;;;;;N;;;;; @@ -29671,6 +30373,37 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1DAAD;SIGNWRITING ROTATION MODIFIER-14;Mn;0;NSM;;;;;N;;;;; 1DAAE;SIGNWRITING ROTATION MODIFIER-15;Mn;0;NSM;;;;;N;;;;; 1DAAF;SIGNWRITING ROTATION MODIFIER-16;Mn;0;NSM;;;;;N;;;;; +1DF00;LATIN SMALL LETTER FENG DIGRAPH WITH TRILL;Ll;0;L;;;;;N;;;;; +1DF01;LATIN SMALL LETTER REVERSED SCRIPT G;Ll;0;L;;;;;N;;;;; +1DF02;LATIN LETTER SMALL CAPITAL TURNED G;Ll;0;L;;;;;N;;;;; +1DF03;LATIN SMALL LETTER REVERSED K;Ll;0;L;;;;;N;;;;; +1DF04;LATIN LETTER SMALL CAPITAL L WITH BELT;Ll;0;L;;;;;N;;;;; +1DF05;LATIN SMALL LETTER LEZH WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF06;LATIN SMALL LETTER TURNED Y WITH BELT;Ll;0;L;;;;;N;;;;; +1DF07;LATIN SMALL LETTER REVERSED ENG;Ll;0;L;;;;;N;;;;; +1DF08;LATIN SMALL LETTER TURNED R WITH LONG LEG AND RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF09;LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF0A;LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK;Lo;0;L;;;;;N;;;;; +1DF0B;LATIN SMALL LETTER ESH WITH DOUBLE BAR;Ll;0;L;;;;;N;;;;; +1DF0C;LATIN SMALL LETTER ESH WITH DOUBLE BAR AND CURL;Ll;0;L;;;;;N;;;;; +1DF0D;LATIN SMALL LETTER TURNED T WITH CURL;Ll;0;L;;;;;N;;;;; +1DF0E;LATIN LETTER INVERTED GLOTTAL STOP WITH CURL;Ll;0;L;;;;;N;;;;; +1DF0F;LATIN LETTER STRETCHED C WITH CURL;Ll;0;L;;;;;N;;;;; +1DF10;LATIN LETTER SMALL CAPITAL TURNED K;Ll;0;L;;;;;N;;;;; +1DF11;LATIN SMALL LETTER L WITH FISHHOOK;Ll;0;L;;;;;N;;;;; +1DF12;LATIN SMALL LETTER DEZH DIGRAPH WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF13;LATIN SMALL LETTER L WITH BELT AND PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF14;LATIN SMALL LETTER ENG WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF15;LATIN SMALL LETTER TURNED R WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF16;LATIN SMALL LETTER R WITH FISHHOOK AND PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF17;LATIN SMALL LETTER TESH DIGRAPH WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF18;LATIN SMALL LETTER EZH WITH PALATAL HOOK;Ll;0;L;;;;;N;;;;; +1DF19;LATIN SMALL LETTER DEZH DIGRAPH WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF1A;LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF1B;LATIN SMALL LETTER O WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF1C;LATIN SMALL LETTER TESH DIGRAPH WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF1D;LATIN SMALL LETTER C WITH RETROFLEX HOOK;Ll;0;L;;;;;N;;;;; +1DF1E;LATIN SMALL LETTER S WITH CURL;Ll;0;L;;;;;N;;;;; 1E000;COMBINING GLAGOLITIC LETTER AZU;Mn;230;NSM;;;;;N;;;;; 1E001;COMBINING GLAGOLITIC LETTER BUKY;Mn;230;NSM;;;;;N;;;;; 1E002;COMBINING GLAGOLITIC LETTER VEDE;Mn;230;NSM;;;;;N;;;;; @@ -29780,6 +30513,37 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1E149;NYIAKENG PUACHUE HMONG DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 1E14E;NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ;Lo;0;L;;;;;N;;;;; 1E14F;NYIAKENG PUACHUE HMONG CIRCLED CA;So;0;L;;;;;N;;;;; +1E290;TOTO LETTER PA;Lo;0;L;;;;;N;;;;; +1E291;TOTO LETTER BA;Lo;0;L;;;;;N;;;;; +1E292;TOTO LETTER TA;Lo;0;L;;;;;N;;;;; +1E293;TOTO LETTER DA;Lo;0;L;;;;;N;;;;; +1E294;TOTO LETTER KA;Lo;0;L;;;;;N;;;;; +1E295;TOTO LETTER GA;Lo;0;L;;;;;N;;;;; +1E296;TOTO LETTER MA;Lo;0;L;;;;;N;;;;; +1E297;TOTO LETTER NA;Lo;0;L;;;;;N;;;;; +1E298;TOTO LETTER NGA;Lo;0;L;;;;;N;;;;; +1E299;TOTO LETTER SA;Lo;0;L;;;;;N;;;;; +1E29A;TOTO LETTER CHA;Lo;0;L;;;;;N;;;;; +1E29B;TOTO LETTER YA;Lo;0;L;;;;;N;;;;; +1E29C;TOTO LETTER WA;Lo;0;L;;;;;N;;;;; +1E29D;TOTO LETTER JA;Lo;0;L;;;;;N;;;;; +1E29E;TOTO LETTER HA;Lo;0;L;;;;;N;;;;; +1E29F;TOTO LETTER RA;Lo;0;L;;;;;N;;;;; +1E2A0;TOTO LETTER LA;Lo;0;L;;;;;N;;;;; +1E2A1;TOTO LETTER I;Lo;0;L;;;;;N;;;;; +1E2A2;TOTO LETTER BREATHY I;Lo;0;L;;;;;N;;;;; +1E2A3;TOTO LETTER IU;Lo;0;L;;;;;N;;;;; +1E2A4;TOTO LETTER BREATHY IU;Lo;0;L;;;;;N;;;;; +1E2A5;TOTO LETTER U;Lo;0;L;;;;;N;;;;; +1E2A6;TOTO LETTER E;Lo;0;L;;;;;N;;;;; +1E2A7;TOTO LETTER BREATHY E;Lo;0;L;;;;;N;;;;; +1E2A8;TOTO LETTER EO;Lo;0;L;;;;;N;;;;; +1E2A9;TOTO LETTER BREATHY EO;Lo;0;L;;;;;N;;;;; +1E2AA;TOTO LETTER O;Lo;0;L;;;;;N;;;;; +1E2AB;TOTO LETTER AE;Lo;0;L;;;;;N;;;;; +1E2AC;TOTO LETTER BREATHY AE;Lo;0;L;;;;;N;;;;; +1E2AD;TOTO LETTER A;Lo;0;L;;;;;N;;;;; +1E2AE;TOTO SIGN RISING TONE;Mn;230;NSM;;;;;N;;;;; 1E2C0;WANCHO LETTER AA;Lo;0;L;;;;;N;;;;; 1E2C1;WANCHO LETTER A;Lo;0;L;;;;;N;;;;; 1E2C2;WANCHO LETTER BA;Lo;0;L;;;;;N;;;;; @@ -29839,6 +30603,34 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1E2F8;WANCHO DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 1E2F9;WANCHO DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 1E2FF;WANCHO NGUN SIGN;Sc;0;ET;;;;;N;;;;; +1E7E0;ETHIOPIC SYLLABLE HHYA;Lo;0;L;;;;;N;;;;; +1E7E1;ETHIOPIC SYLLABLE HHYU;Lo;0;L;;;;;N;;;;; +1E7E2;ETHIOPIC SYLLABLE HHYI;Lo;0;L;;;;;N;;;;; +1E7E3;ETHIOPIC SYLLABLE HHYAA;Lo;0;L;;;;;N;;;;; +1E7E4;ETHIOPIC SYLLABLE HHYEE;Lo;0;L;;;;;N;;;;; +1E7E5;ETHIOPIC SYLLABLE HHYE;Lo;0;L;;;;;N;;;;; +1E7E6;ETHIOPIC SYLLABLE HHYO;Lo;0;L;;;;;N;;;;; +1E7E8;ETHIOPIC SYLLABLE GURAGE HHWA;Lo;0;L;;;;;N;;;;; +1E7E9;ETHIOPIC SYLLABLE HHWI;Lo;0;L;;;;;N;;;;; +1E7EA;ETHIOPIC SYLLABLE HHWEE;Lo;0;L;;;;;N;;;;; +1E7EB;ETHIOPIC SYLLABLE HHWE;Lo;0;L;;;;;N;;;;; +1E7ED;ETHIOPIC SYLLABLE GURAGE MWI;Lo;0;L;;;;;N;;;;; +1E7EE;ETHIOPIC SYLLABLE GURAGE MWEE;Lo;0;L;;;;;N;;;;; +1E7F0;ETHIOPIC SYLLABLE GURAGE QWI;Lo;0;L;;;;;N;;;;; +1E7F1;ETHIOPIC SYLLABLE GURAGE QWEE;Lo;0;L;;;;;N;;;;; +1E7F2;ETHIOPIC SYLLABLE GURAGE QWE;Lo;0;L;;;;;N;;;;; +1E7F3;ETHIOPIC SYLLABLE GURAGE BWI;Lo;0;L;;;;;N;;;;; +1E7F4;ETHIOPIC SYLLABLE GURAGE BWEE;Lo;0;L;;;;;N;;;;; +1E7F5;ETHIOPIC SYLLABLE GURAGE KWI;Lo;0;L;;;;;N;;;;; +1E7F6;ETHIOPIC SYLLABLE GURAGE KWEE;Lo;0;L;;;;;N;;;;; +1E7F7;ETHIOPIC SYLLABLE GURAGE KWE;Lo;0;L;;;;;N;;;;; +1E7F8;ETHIOPIC SYLLABLE GURAGE GWI;Lo;0;L;;;;;N;;;;; +1E7F9;ETHIOPIC SYLLABLE GURAGE GWEE;Lo;0;L;;;;;N;;;;; +1E7FA;ETHIOPIC SYLLABLE GURAGE GWE;Lo;0;L;;;;;N;;;;; +1E7FB;ETHIOPIC SYLLABLE GURAGE FWI;Lo;0;L;;;;;N;;;;; +1E7FC;ETHIOPIC SYLLABLE GURAGE FWEE;Lo;0;L;;;;;N;;;;; +1E7FD;ETHIOPIC SYLLABLE GURAGE PWI;Lo;0;L;;;;;N;;;;; +1E7FE;ETHIOPIC SYLLABLE GURAGE PWEE;Lo;0;L;;;;;N;;;;; 1E800;MENDE KIKAKUI SYLLABLE M001 KI;Lo;0;R;;;;;N;;;;; 1E801;MENDE KIKAKUI SYLLABLE M002 KA;Lo;0;R;;;;;N;;;;; 1E802;MENDE KIKAKUI SYLLABLE M003 KU;Lo;0;R;;;;;N;;;;; @@ -31886,6 +32678,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F6D5;HINDU TEMPLE;So;0;ON;;;;;N;;;;; 1F6D6;HUT;So;0;ON;;;;;N;;;;; 1F6D7;ELEVATOR;So;0;ON;;;;;N;;;;; +1F6DD;PLAYGROUND SLIDE;So;0;ON;;;;;N;;;;; +1F6DE;WHEEL;So;0;ON;;;;;N;;;;; +1F6DF;RING BUOY;So;0;ON;;;;;N;;;;; 1F6E0;HAMMER AND WRENCH;So;0;ON;;;;;N;;;;; 1F6E1;SHIELD;So;0;ON;;;;;N;;;;; 1F6E2;OIL DRUM;So;0;ON;;;;;N;;;;; @@ -32129,6 +32924,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F7E9;LARGE GREEN SQUARE;So;0;ON;;;;;N;;;;; 1F7EA;LARGE PURPLE SQUARE;So;0;ON;;;;;N;;;;; 1F7EB;LARGE BROWN SQUARE;So;0;ON;;;;;N;;;;; +1F7F0;HEAVY EQUALS SIGN;So;0;ON;;;;;N;;;;; 1F800;LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD;So;0;ON;;;;;N;;;;; 1F801;UPWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD;So;0;ON;;;;;N;;;;; 1F802;RIGHTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD;So;0;ON;;;;;N;;;;; @@ -32400,6 +33196,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F976;FREEZING FACE;So;0;ON;;;;;N;;;;; 1F977;NINJA;So;0;ON;;;;;N;;;;; 1F978;DISGUISED FACE;So;0;ON;;;;;N;;;;; +1F979;FACE HOLDING BACK TEARS;So;0;ON;;;;;N;;;;; 1F97A;FACE WITH PLEADING EYES;So;0;ON;;;;;N;;;;; 1F97B;SARI;So;0;ON;;;;;N;;;;; 1F97C;LAB COAT;So;0;ON;;;;;N;;;;; @@ -32482,6 +33279,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F9C9;MATE DRINK;So;0;ON;;;;;N;;;;; 1F9CA;ICE CUBE;So;0;ON;;;;;N;;;;; 1F9CB;BUBBLE TEA;So;0;ON;;;;;N;;;;; +1F9CC;TROLL;So;0;ON;;;;;N;;;;; 1F9CD;STANDING PERSON;So;0;ON;;;;;N;;;;; 1F9CE;KNEELING PERSON;So;0;ON;;;;;N;;;;; 1F9CF;DEAF PERSON;So;0;ON;;;;;N;;;;; @@ -32639,6 +33437,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1FA78;DROP OF BLOOD;So;0;ON;;;;;N;;;;; 1FA79;ADHESIVE BANDAGE;So;0;ON;;;;;N;;;;; 1FA7A;STETHOSCOPE;So;0;ON;;;;;N;;;;; +1FA7B;X-RAY;So;0;ON;;;;;N;;;;; +1FA7C;CRUTCH;So;0;ON;;;;;N;;;;; 1FA80;YO-YO;So;0;ON;;;;;N;;;;; 1FA81;KITE;So;0;ON;;;;;N;;;;; 1FA82;PARACHUTE;So;0;ON;;;;;N;;;;; @@ -32671,6 +33471,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1FAA6;HEADSTONE;So;0;ON;;;;;N;;;;; 1FAA7;PLACARD;So;0;ON;;;;;N;;;;; 1FAA8;ROCK;So;0;ON;;;;;N;;;;; +1FAA9;MIRROR BALL;So;0;ON;;;;;N;;;;; +1FAAA;IDENTIFICATION CARD;So;0;ON;;;;;N;;;;; +1FAAB;LOW BATTERY;So;0;ON;;;;;N;;;;; +1FAAC;HAMSA;So;0;ON;;;;;N;;;;; 1FAB0;FLY;So;0;ON;;;;;N;;;;; 1FAB1;WORM;So;0;ON;;;;;N;;;;; 1FAB2;BEETLE;So;0;ON;;;;;N;;;;; @@ -32678,9 +33482,16 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1FAB4;POTTED PLANT;So;0;ON;;;;;N;;;;; 1FAB5;WOOD;So;0;ON;;;;;N;;;;; 1FAB6;FEATHER;So;0;ON;;;;;N;;;;; +1FAB7;LOTUS;So;0;ON;;;;;N;;;;; +1FAB8;CORAL;So;0;ON;;;;;N;;;;; +1FAB9;EMPTY NEST;So;0;ON;;;;;N;;;;; +1FABA;NEST WITH EGGS;So;0;ON;;;;;N;;;;; 1FAC0;ANATOMICAL HEART;So;0;ON;;;;;N;;;;; 1FAC1;LUNGS;So;0;ON;;;;;N;;;;; 1FAC2;PEOPLE HUGGING;So;0;ON;;;;;N;;;;; +1FAC3;PREGNANT MAN;So;0;ON;;;;;N;;;;; +1FAC4;PREGNANT PERSON;So;0;ON;;;;;N;;;;; +1FAC5;PERSON WITH CROWN;So;0;ON;;;;;N;;;;; 1FAD0;BLUEBERRIES;So;0;ON;;;;;N;;;;; 1FAD1;BELL PEPPER;So;0;ON;;;;;N;;;;; 1FAD2;OLIVE;So;0;ON;;;;;N;;;;; @@ -32688,6 +33499,24 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1FAD4;TAMALE;So;0;ON;;;;;N;;;;; 1FAD5;FONDUE;So;0;ON;;;;;N;;;;; 1FAD6;TEAPOT;So;0;ON;;;;;N;;;;; +1FAD7;POURING LIQUID;So;0;ON;;;;;N;;;;; +1FAD8;BEANS;So;0;ON;;;;;N;;;;; +1FAD9;JAR;So;0;ON;;;;;N;;;;; +1FAE0;MELTING FACE;So;0;ON;;;;;N;;;;; +1FAE1;SALUTING FACE;So;0;ON;;;;;N;;;;; +1FAE2;FACE WITH OPEN EYES AND HAND OVER MOUTH;So;0;ON;;;;;N;;;;; +1FAE3;FACE WITH PEEKING EYE;So;0;ON;;;;;N;;;;; +1FAE4;FACE WITH DIAGONAL MOUTH;So;0;ON;;;;;N;;;;; +1FAE5;DOTTED LINE FACE;So;0;ON;;;;;N;;;;; +1FAE6;BITING LIP;So;0;ON;;;;;N;;;;; +1FAE7;BUBBLES;So;0;ON;;;;;N;;;;; +1FAF0;HAND WITH INDEX FINGER AND THUMB CROSSED;So;0;ON;;;;;N;;;;; +1FAF1;RIGHTWARDS HAND;So;0;ON;;;;;N;;;;; +1FAF2;LEFTWARDS HAND;So;0;ON;;;;;N;;;;; +1FAF3;PALM DOWN HAND;So;0;ON;;;;;N;;;;; +1FAF4;PALM UP HAND;So;0;ON;;;;;N;;;;; +1FAF5;INDEX POINTING AT THE VIEWER;So;0;ON;;;;;N;;;;; +1FAF6;HEART HANDS;So;0;ON;;;;;N;;;;; 1FB00;BLOCK SEXTANT-1;So;0;ON;;;;;N;;;;; 1FB01;BLOCK SEXTANT-2;So;0;ON;;;;;N;;;;; 1FB02;BLOCK SEXTANT-12;So;0;ON;;;;;N;;;;; @@ -32901,9 +33730,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1FBF8;SEGMENTED DIGIT EIGHT;Nd;0;EN;<font> 0038;8;8;8;N;;;;; 1FBF9;SEGMENTED DIGIT NINE;Nd;0;EN;<font> 0039;9;9;9;N;;;;; 20000;<CJK Ideograph Extension B, First>;Lo;0;L;;;;;N;;;;; -2A6DD;<CJK Ideograph Extension B, Last>;Lo;0;L;;;;;N;;;;; +2A6DF;<CJK Ideograph Extension B, Last>;Lo;0;L;;;;;N;;;;; 2A700;<CJK Ideograph Extension C, First>;Lo;0;L;;;;;N;;;;; -2B734;<CJK Ideograph Extension C, Last>;Lo;0;L;;;;;N;;;;; +2B738;<CJK Ideograph Extension C, Last>;Lo;0;L;;;;;N;;;;; 2B740;<CJK Ideograph Extension D, First>;Lo;0;L;;;;;N;;;;; 2B81D;<CJK Ideograph Extension D, Last>;Lo;0;L;;;;;N;;;;; 2B820;<CJK Ideograph Extension E, First>;Lo;0;L;;;;;N;;;;; diff --git a/lib/unicore/VerticalOrientation.txt b/lib/unicore/VerticalOrientation.txt index 1cc92e31f9..35caa05bf1 100644 --- a/lib/unicore/VerticalOrientation.txt +++ b/lib/unicore/VerticalOrientation.txt @@ -1,16 +1,16 @@ -# VerticalOrientation-13.0.0.txt -# Date: 2019-10-07, 05:27:01 GMT [EM, KI, LI] -# © 2019 Unicode®, Inc. +# VerticalOrientation-14.0.0.txt +# Date: 2021-07-06, 09:58:53 GMT [EM, KI, LI, KW, MS] +# © 2021 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 +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Vertical_Orientation (vo) Property # # This file defines the Vertical_Orientation property. See UAX #50: -# Unicode Vertical Text Layout, at http://www.unicode.org/reports/tr50/ +# Unicode Vertical Text Layout, at https://www.unicode.org/reports/tr50/ # # The format of the file is two fields separated by a semicolon. # Field 0: Unicode code point value or range of code point values in @@ -45,9 +45,11 @@ # Egyptian Hieroglyphs & Controls: U+13000..U+1343F # Anatolian Hieroglyphs: U+14400..U+1467F # Ideographic Symbols & Tangut: U+16FE0..U+18AFF -# Khitan Small Script & Tangut Sup: U+18B00..U+18D8F +# Khitan Small Script & Tangut Sup: U+18B00..U+18D7F +# Kana Extended-B: U+1AFF0..U+1AFFF # Kana Extended-A & Small Kana Ext: U+1B100..U+1B16F # Nushu: U+1B170..U+1B2FF +# Musical Symbols: U+1CF00..U+1CFCF # Musical Symbols: U+1D000..U+1D1FF # Mayan Numerals: U+1D2E0..U+1D2FF # Symbols & Rods: U+1D300..U+1D37F @@ -205,7 +207,7 @@ 0610..061A ; R # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061B ; R # Po ARABIC SEMICOLON 061C ; R # Cf ARABIC LETTER MARK -061E..061F ; R # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; R # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F ; R # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; R # Lm ARABIC TATWEEL 0641..064A ; R # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -263,9 +265,14 @@ 0859..085B ; R # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E ; R # Po MANDAIC PUNCTUATION 0860..086A ; R # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; R # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; R # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; R # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; R # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; R # Sk ARABIC RAISED ROUND DOT +0889..088E ; R # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891 ; R # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; R # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; R # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; R # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; R # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; R # Cf ARABIC DISPUTED END OF AYAH 08E3..08FF ; R # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA 0900..0902 ; R # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA @@ -422,6 +429,7 @@ 0C0E..0C10 ; R # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; R # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; R # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; R # Mn TELUGU SIGN NUKTA 0C3D ; R # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; R # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; R # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -429,6 +437,7 @@ 0C4A..0C4D ; R # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; R # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; R # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; R # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; R # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; R # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; R # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -454,7 +463,7 @@ 0CCA..0CCB ; R # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; R # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; R # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; R # Lo KANNADA LETTER FA +0CDD..0CDE ; R # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; R # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; R # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; R # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -640,11 +649,13 @@ 16EB..16ED ; R # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0 ; R # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; R # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; R # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; R # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; R # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; R # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1715 ; R # Mc TAGALOG SIGN PAMUDPOD +171F ; R # Lo TAGALOG LETTER ARCHAIC RA 1720..1731 ; R # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; R # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; R # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; R # Mc HANUNOO SIGN PAMUDPOD 1735..1736 ; R # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751 ; R # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; R # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -672,6 +683,7 @@ 1807..180A ; R # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; R # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; R # Cf MONGOLIAN VOWEL SEPARATOR +180F ; R # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; R # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; R # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; R # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -728,7 +740,7 @@ 1AA8..1AAD ; R # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; R # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; R # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; R # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; R # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; R # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; R # Mc BALINESE SIGN BISAH 1B05..1B33 ; R # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -740,12 +752,13 @@ 1B3D..1B41 ; R # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; R # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; R # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; R # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; R # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; R # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; R # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; R # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73 ; R # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C ; R # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; R # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B80..1B81 ; R # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; R # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; R # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -804,8 +817,7 @@ 1D79..1D7F ; R # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE 1D80..1D9A ; R # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; R # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; R # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; R # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; R # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1EFF ; R # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP 1F00..1F15 ; R # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; R # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -886,7 +898,7 @@ 208D ; R # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; R # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; R # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BF ; R # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; R # Sc [33] EURO-CURRENCY SIGN..SOM SIGN 20D0..20DC ; R # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; U # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; R # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1087,8 +1099,7 @@ 2BD3..2BEB ; U # So [25] PLUTO FORM TWO..STAR WITH RIGHT HALF BLACK 2BEC..2BEF ; R # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2BF0..2BFF ; U # So [16] ERIS FORM ONE..HELLSCHREIBER PAUSE SYMBOL -2C00..2C2E ; R # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; R # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C00..2C5F ; R # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60..2C7B ; R # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; R # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2C7F ; R # Lu [2] LATIN CAPITAL LETTER S WITH SWASH TAIL..LATIN CAPITAL LETTER Z WITH SWASH TAIL @@ -1156,7 +1167,16 @@ 2E42 ; R # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; R # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; U # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; R # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; R # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; R # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; R # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; R # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; R # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; R # Ps TOP HALF LEFT PARENTHESIS +2E5A ; R # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; R # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; R # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; R # Pd OBLIQUE HYPHEN 2E80..2E99 ; U # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9A ; U # Cn <reserved-2E9A> 2E9B..2EF3 ; U # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE @@ -1294,8 +1314,7 @@ 3380..33FF ; U # So [128] SQUARE PA AMPS..SQUARE GAL 3400..4DBF ; U # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF 4DC0..4DFF ; U # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FFC ; U # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -9FFD..9FFF ; U # Cn [3] <reserved-9FFD>..<reserved-9FFF> +4E00..9FFF ; U # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF A000..A014 ; U # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; U # Lm YI SYLLABLE WU A016..A48C ; U # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1336,8 +1355,11 @@ A788 ; R # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; R # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; R # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; R # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; R # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; R # Ll LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; R # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; R # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; R # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; R # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; R # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1495,15 +1517,17 @@ FB40..FB41 ; R # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SA FB43..FB44 ; R # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1 ; R # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; R # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; R # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; R # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; R # Pe ORNATE LEFT PARENTHESIS FD3F ; R # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F ; R # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; R # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; R # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; R # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; R # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; R # Sc RIAL SIGN -FDFD ; R # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; R # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F ; R # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE10..FE16 ; U # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; U # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET @@ -1660,9 +1684,20 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10500..10527 ; R # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; R # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; R # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; R # Lu [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; R # Lu [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; R # Lu [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; R # Lu [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; R # Ll [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; R # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; R # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; R # Ll [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; R # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; R # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; R # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; R # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; R # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; R # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; R # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; R # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; R # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1741,6 +1776,9 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10F46..10F50 ; R # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F51..10F54 ; R # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; R # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81 ; R # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; R # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +10F86..10F89 ; R # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4 ; R # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; R # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6 ; R # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -1752,6 +1790,10 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 11047..1104D ; R # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; R # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; R # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; R # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; R # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; R # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; R # Lo BRAHMI LETTER OLD TAMIL LLA 1107F ; R # Mn BRAHMI NUMBER JOINER 11080..11081 ; R # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11082 ; R # Mc KAITHI SIGN VISARGA @@ -1763,6 +1805,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 110BB..110BC ; R # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD ; R # Cf KAITHI NUMBER SIGN 110BE..110C1 ; R # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110C2 ; R # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; R # Cf KAITHI NUMBER SIGN ABOVE 110D0..110E8 ; R # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; R # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -1899,6 +1942,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 116B6 ; R # Mc TAKRI SIGN VIRAMA 116B7 ; R # Mn TAKRI SIGN NUKTA 116B8 ; R # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; R # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; R # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A ; R # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F ; R # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA @@ -1910,6 +1954,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1173A..1173B ; R # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; R # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; R # So AHOM SYMBOL VI +11740..11746 ; R # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; R # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; R # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; R # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -1970,6 +2015,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 11A9D ; U # Lo SOYOMBO MARK PLUTA 11A9E..11AA2 ; U # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AA3..11AAF ; U # Cn [13] <reserved-11AA3>..<reserved-11AAF> +11AB0..11ABF ; U # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11AC0..11AF8 ; R # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; R # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; R # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -2026,6 +2072,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 12400..1246E ; R # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; R # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 12480..12543 ; R # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; R # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; R # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E ; U # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 1342F ; U # Cn <reserved-1342F> 13430..13438 ; U # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT @@ -2036,6 +2084,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 16A40..16A5E ; R # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; R # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F ; R # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE ; R # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; R # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; R # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; R # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16AF5 ; R # Po BASSA VAH FULL STOP @@ -2062,7 +2112,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 16FE0..16FE1 ; U # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE2 ; U # Po OLD CHINESE HOOK MARK 16FE3 ; U # Lm OLD CHINESE ITERATION MARK -16FE4 ; U # Lo KHITAN SMALL SCRIPT FILLER +16FE4 ; U # Mn KHITAN SMALL SCRIPT FILLER 16FE5..16FEF ; U # Cn [11] <reserved-16FE5>..<reserved-16FEF> 16FF0..16FF1 ; U # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 16FF2..16FFF ; U # Cn [14] <reserved-16FF2>..<reserved-16FFF> @@ -2072,10 +2122,16 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 18B00..18CD5 ; U # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CD6..18CFF ; U # Cn [42] <reserved-18CD6>..<reserved-18CFF> 18D00..18D08 ; U # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -18D09..18D8F ; U # Cn [135] <reserved-18D09>..<reserved-18D8F> +18D09..18D7F ; U # Cn [119] <reserved-18D09>..<reserved-18D7F> +1AFF0..1AFF3 ; U # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF4 ; U # Cn <reserved-1AFF4> +1AFF5..1AFFB ; U # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFC ; U # Cn <reserved-1AFFC> +1AFFD..1AFFE ; U # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1AFFF ; U # Cn <reserved-1AFFF> 1B000..1B0FF ; U # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 -1B100..1B11E ; U # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 -1B11F..1B12F ; U # Cn [17] <reserved-1B11F>..<reserved-1B12F> +1B100..1B122 ; U # Lo [35] HENTAIGANA LETTER RE-3..KATAKANA LETTER ARCHAIC WU +1B123..1B12F ; U # Cn [13] <reserved-1B123>..<reserved-1B12F> 1B130..1B14F ; U # Cn [32] <reserved-1B130>..<reserved-1B14F> 1B150..1B152 ; U # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B153..1B163 ; U # Cn [17] <reserved-1B153>..<reserved-1B163> @@ -2091,6 +2147,12 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1BC9D..1BC9E ; R # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; R # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; R # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; U # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF2E..1CF2F ; U # Cn [2] <reserved-1CF2E>..<reserved-1CF2F> +1CF30..1CF46 ; U # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF47..1CF4F ; U # Cn [9] <reserved-1CF47>..<reserved-1CF4F> +1CF50..1CFC3 ; U # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK +1CFC4..1CFCF ; U # Cn [12] <reserved-1CFC4>..<reserved-1CFCF> 1D000..1D0F5 ; U # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D0F6..1D0FF ; U # Cn [10] <reserved-1D0F6>..<reserved-1D0FF> 1D100..1D126 ; U # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -2106,8 +2168,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1D185..1D18B ; U # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D18C..1D1A9 ; U # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH 1D1AA..1D1AD ; U # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO -1D1AE..1D1E8 ; U # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN -1D1E9..1D1FF ; U # Cn [23] <reserved-1D1E9>..<reserved-1D1FF> +1D1AE..1D1EA ; U # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON +1D1EB..1D1FF ; U # Cn [21] <reserved-1D1EB>..<reserved-1D1FF> 1D200..1D241 ; R # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D242..1D244 ; R # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME 1D245 ; R # So GREEK MUSICAL LEIMMA @@ -2172,6 +2234,9 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1DA9B..1DA9F ; U # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA0 ; U # Cn <reserved-1DAA0> 1DAA1..1DAAF ; U # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; R # Ll [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; R # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; R # Ll [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; R # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; R # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; R # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -2183,10 +2248,16 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1E140..1E149 ; R # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; R # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; R # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; R # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; R # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; R # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; R # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; R # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF ; R # Sc WANCHO NGUN SIGN +1E7E0..1E7E6 ; R # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; R # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; R # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; R # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; R # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; R # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6 ; R # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS @@ -2270,8 +2341,8 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1F600..1F64F ; U # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS 1F650..1F67F ; U # So [48] NORTH WEST POINTING LEAF..REVERSE CHECKER BOARD 1F680..1F6D7 ; U # So [88] ROCKET..ELEVATOR -1F6D8..1F6DF ; U # Cn [8] <reserved-1F6D8>..<reserved-1F6DF> -1F6E0..1F6EC ; U # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6D8..1F6DC ; U # Cn [5] <reserved-1F6D8>..<reserved-1F6DC> +1F6DD..1F6EC ; U # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6ED..1F6EF ; U # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> 1F6F0..1F6FC ; U # So [13] SATELLITE..ROLLER SKATE 1F6FD..1F6FF ; U # Cn [3] <reserved-1F6FD>..<reserved-1F6FF> @@ -2280,43 +2351,45 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1F780..1F7D8 ; U # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7D9..1F7DF ; U # Cn [7] <reserved-1F7D9>..<reserved-1F7DF> 1F7E0..1F7EB ; U # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE -1F7EC..1F7FF ; U # Cn [20] <reserved-1F7EC>..<reserved-1F7FF> +1F7EC..1F7EF ; U # Cn [4] <reserved-1F7EC>..<reserved-1F7EF> +1F7F0 ; U # So HEAVY EQUALS SIGN +1F7F1..1F7FF ; U # Cn [15] <reserved-1F7F1>..<reserved-1F7FF> 1F800..1F80B ; R # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; R # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; R # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; R # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; R # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; R # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; U # So [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F979 ; U # Cn <reserved-1F979> -1F97A..1F9CB ; U # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CC ; U # Cn <reserved-1F9CC> -1F9CD..1F9FF ; U # So [51] STANDING PERSON..NAZAR AMULET +1F900..1F9FF ; U # So [256] CIRCLED CROSS FORMEE WITH FOUR DOTS..NAZAR AMULET 1FA00..1FA53 ; U # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 1FA54..1FA5F ; U # Cn [12] <reserved-1FA54>..<reserved-1FA5F> 1FA60..1FA6D ; U # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA6E..1FA6F ; U # Cn [2] <reserved-1FA6E>..<reserved-1FA6F> 1FA70..1FA74 ; U # So [5] BALLET SHOES..THONG SANDAL 1FA75..1FA77 ; U # Cn [3] <reserved-1FA75>..<reserved-1FA77> -1FA78..1FA7A ; U # So [3] DROP OF BLOOD..STETHOSCOPE -1FA7B..1FA7F ; U # Cn [5] <reserved-1FA7B>..<reserved-1FA7F> +1FA78..1FA7C ; U # So [5] DROP OF BLOOD..CRUTCH +1FA7D..1FA7F ; U # Cn [3] <reserved-1FA7D>..<reserved-1FA7F> 1FA80..1FA86 ; U # So [7] YO-YO..NESTING DOLLS 1FA87..1FA8F ; U # Cn [9] <reserved-1FA87>..<reserved-1FA8F> -1FA90..1FAA8 ; U # So [25] RINGED PLANET..ROCK -1FAA9..1FAAF ; U # Cn [7] <reserved-1FAA9>..<reserved-1FAAF> -1FAB0..1FAB6 ; U # So [7] FLY..FEATHER -1FAB7..1FABF ; U # Cn [9] <reserved-1FAB7>..<reserved-1FABF> -1FAC0..1FAC2 ; U # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAC3..1FACF ; U # Cn [13] <reserved-1FAC3>..<reserved-1FACF> -1FAD0..1FAD6 ; U # So [7] BLUEBERRIES..TEAPOT -1FAD7..1FAFF ; U # Cn [41] <reserved-1FAD7>..<reserved-1FAFF> +1FA90..1FAAC ; U # So [29] RINGED PLANET..HAMSA +1FAAD..1FAAF ; U # Cn [3] <reserved-1FAAD>..<reserved-1FAAF> +1FAB0..1FABA ; U # So [11] FLY..NEST WITH EGGS +1FABB..1FABF ; U # Cn [5] <reserved-1FABB>..<reserved-1FABF> +1FAC0..1FAC5 ; U # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAC6..1FACF ; U # Cn [10] <reserved-1FAC6>..<reserved-1FACF> +1FAD0..1FAD9 ; U # So [10] BLUEBERRIES..JAR +1FADA..1FADF ; U # Cn [6] <reserved-1FADA>..<reserved-1FADF> +1FAE0..1FAE7 ; U # So [8] MELTING FACE..BUBBLES +1FAE8..1FAEF ; U # Cn [8] <reserved-1FAE8>..<reserved-1FAEF> +1FAF0..1FAF6 ; U # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS +1FAF7..1FAFF ; U # Cn [9] <reserved-1FAF7>..<reserved-1FAFF> 1FB00..1FB92 ; R # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; R # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; R # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; U # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF ; U # Cn [34] <reserved-2A6DE>..<reserved-2A6FF> -2A700..2B734 ; U # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F ; U # Cn [11] <reserved-2B735>..<reserved-2B73F> +20000..2A6DF ; U # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF ; U # Cn [32] <reserved-2A6E0>..<reserved-2A6FF> +2A700..2B738 ; U # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F ; U # Cn [7] <reserved-2B739>..<reserved-2B73F> 2B740..2B81D ; U # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; U # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1 ; U # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 diff --git a/lib/unicore/auxiliary/GCBTest.txt b/lib/unicore/auxiliary/GCBTest.txt index 5baf292a07..eff2fd33b0 100644 --- a/lib/unicore/auxiliary/GCBTest.txt +++ b/lib/unicore/auxiliary/GCBTest.txt @@ -1,6 +1,6 @@ -# GraphemeBreakTest-13.0.0.txt -# Date: 2019-11-15, 19:49:10 GMT -# © 2019 Unicode®, Inc. +# GraphemeBreakTest-14.0.0.txt +# Date: 2021-03-08, 06:22:32 GMT +# © 2021 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 # diff --git a/lib/unicore/auxiliary/GraphemeBreakProperty.txt b/lib/unicore/auxiliary/GraphemeBreakProperty.txt index 6ee92f6eec..dd2569064a 100644 --- a/lib/unicore/auxiliary/GraphemeBreakProperty.txt +++ b/lib/unicore/auxiliary/GraphemeBreakProperty.txt @@ -1,6 +1,6 @@ -# GraphemeBreakProperty-13.0.0.txt -# Date: 2019-10-21, 14:30:35 GMT -# © 2019 Unicode®, Inc. +# GraphemeBreakProperty-14.0.0.txt +# Date: 2021-08-12, 23:13:02 GMT +# © 2021 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 # @@ -21,6 +21,7 @@ 0600..0605 ; Prepend # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE 06DD ; Prepend # Cf ARABIC END OF AYAH 070F ; Prepend # Cf SYRIAC ABBREVIATION MARK +0890..0891 ; Prepend # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Prepend # Cf ARABIC DISPUTED END OF AYAH 0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH 110BD ; Prepend # Cf KAITHI NUMBER SIGN @@ -32,7 +33,7 @@ 11A84..11A89 ; Prepend # Lo [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA 11D46 ; Prepend # Lo MASARAM GONDI REPHA -# Total code points: 24 +# Total code points: 26 # ================================================ @@ -104,7 +105,8 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE 093C ; Extend # Mn DEVANAGARI SIGN NUKTA @@ -151,6 +153,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0BD7 ; Extend # Mc TAMIL AU LENGTH MARK 0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Extend # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -206,7 +209,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -215,6 +218,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -232,7 +236,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Extend # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Extend # Mn BALINESE SIGN REREKAN 1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -256,8 +260,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -322,11 +325,15 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Extend # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -412,6 +419,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165 ; Extend # Mc MUSICAL SYMBOL COMBINING STEM 1D167..1D169 ; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16E..1D172 ; Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5 @@ -431,6 +440,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA @@ -438,7 +448,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1984 +# Total code points: 2095 # ================================================ @@ -495,6 +505,8 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 103B..103C ; SpacingMark # Mc [2] MYANMAR CONSONANT SIGN MEDIAL YA..MYANMAR CONSONANT SIGN MEDIAL RA 1056..1057 ; SpacingMark # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR 1084 ; SpacingMark # Mc MYANMAR VOWEL SIGN SHAN E +1715 ; SpacingMark # Mc TAGALOG SIGN PAMUDPOD +1734 ; SpacingMark # Mc HANUNOO SIGN PAMUDPOD 17B6 ; SpacingMark # Mc KHMER VOWEL SIGN AA 17BE..17C5 ; SpacingMark # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU 17C7..17C8 ; SpacingMark # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU @@ -579,7 +591,6 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 116AC ; SpacingMark # Mc TAKRI SIGN VISARGA 116AE..116AF ; SpacingMark # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II 116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA -11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11726 ; SpacingMark # Mc AHOM VOWEL SIGN E 1182C..1182E ; SpacingMark # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 11838 ; SpacingMark # Mc DOGRA SIGN VISARGA diff --git a/lib/unicore/auxiliary/LBTest.txt b/lib/unicore/auxiliary/LBTest.txt index d8666c458f..8d1cef0f78 100644 --- a/lib/unicore/auxiliary/LBTest.txt +++ b/lib/unicore/auxiliary/LBTest.txt @@ -1,6 +1,6 @@ -# LineBreakTest-13.0.0.txt -# Date: 2019-11-21, 16:13:36 GMT -# © 2019 Unicode®, Inc. +# LineBreakTest-14.0.0.txt +# Date: 2021-08-20, 21:08:45 GMT +# © 2021 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 # @@ -1846,9 +1846,9 @@ × AC00 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × AC00 × 0308 ÷ 2329 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_CM) ÷ [999.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × AC00 × 0308 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] -× AC00 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× AC00 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × AC00 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] -× AC00 × 0308 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× AC00 × 0308 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × AC00 × 0308 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] × AC00 ÷ 0024 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) ÷ [999.0] DOLLAR SIGN (PR) ÷ [0.3] × AC00 × 0020 ÷ 0024 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP) ÷ [18.0] DOLLAR SIGN (PR) ÷ [0.3] @@ -2018,9 +2018,9 @@ × AC01 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × AC01 × 0308 ÷ 2329 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_CM) ÷ [999.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × AC01 × 0308 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] -× AC01 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× AC01 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × AC01 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] -× AC01 × 0308 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× AC01 × 0308 × 0025 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × AC01 × 0308 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] × AC01 ÷ 0024 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) ÷ [999.0] DOLLAR SIGN (PR) ÷ [0.3] × AC01 × 0020 ÷ 0024 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP) ÷ [18.0] DOLLAR SIGN (PR) ÷ [0.3] @@ -3050,9 +3050,9 @@ × 1100 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × 1100 × 0308 ÷ 2329 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_CM) ÷ [999.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × 1100 × 0308 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] -× 1100 × 0025 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× 1100 × 0025 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × 1100 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] -× 1100 × 0308 × 0025 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× 1100 × 0308 × 0025 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × 1100 × 0308 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] × 1100 ÷ 0024 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) ÷ [999.0] DOLLAR SIGN (PR) ÷ [0.3] × 1100 × 0020 ÷ 0024 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP) ÷ [18.0] DOLLAR SIGN (PR) ÷ [0.3] @@ -3222,9 +3222,9 @@ × 11A8 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × 11A8 × 0308 ÷ 2329 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [9.0] COMBINING DIAERESIS (CM1_CM) ÷ [999.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × 11A8 × 0308 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] -× 11A8 × 0025 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× 11A8 × 0025 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × 11A8 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] -× 11A8 × 0308 × 0025 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× 11A8 × 0308 × 0025 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × 11A8 × 0308 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] × 11A8 ÷ 0024 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) ÷ [999.0] DOLLAR SIGN (PR) ÷ [0.3] × 11A8 × 0020 ÷ 0024 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [7.01] SPACE (SP) ÷ [18.0] DOLLAR SIGN (PR) ÷ [0.3] @@ -3394,9 +3394,9 @@ × 1160 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × 1160 × 0308 ÷ 2329 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [9.0] COMBINING DIAERESIS (CM1_CM) ÷ [999.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] × 1160 × 0308 × 0020 ÷ 2329 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] LEFT-POINTING ANGLE BRACKET (OP) ÷ [0.3] -× 1160 × 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× 1160 × 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × 1160 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] -× 1160 × 0308 × 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] PERCENT SIGN (PO) ÷ [0.3] +× 1160 × 0308 × 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.01] PERCENT SIGN (PO) ÷ [0.3] × 1160 × 0308 × 0020 ÷ 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] PERCENT SIGN (PO) ÷ [0.3] × 1160 ÷ 0024 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) ÷ [999.0] DOLLAR SIGN (PR) ÷ [0.3] × 1160 × 0020 ÷ 0024 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [7.01] SPACE (SP) ÷ [18.0] DOLLAR SIGN (PR) ÷ [0.3] @@ -4538,13 +4538,13 @@ × 0024 × 0020 ÷ 00A0 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] NO-BREAK SPACE (GL) ÷ [0.3] × 0024 × 0308 × 00A0 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [12.2] NO-BREAK SPACE (GL) ÷ [0.3] × 0024 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] NO-BREAK SPACE (GL) ÷ [0.3] -× 0024 × AC00 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.03] HANGUL SYLLABLE GA (H2) ÷ [0.3] +× 0024 × AC00 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0024 × 0020 ÷ AC00 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] -× 0024 × 0308 × AC00 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.03] HANGUL SYLLABLE GA (H2) ÷ [0.3] +× 0024 × 0308 × AC00 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0024 × 0308 × 0020 ÷ AC00 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] -× 0024 × AC01 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.03] HANGUL SYLLABLE GAG (H3) ÷ [0.3] +× 0024 × AC01 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.02] HANGUL SYLLABLE GAG (H3) ÷ [0.3] × 0024 × 0020 ÷ AC01 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE GAG (H3) ÷ [0.3] -× 0024 × 0308 × AC01 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.03] HANGUL SYLLABLE GAG (H3) ÷ [0.3] +× 0024 × 0308 × AC01 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] HANGUL SYLLABLE GAG (H3) ÷ [0.3] × 0024 × 0308 × 0020 ÷ AC01 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] HANGUL SYLLABLE GAG (H3) ÷ [0.3] × 0024 × 05D0 ÷ # × [0.3] DOLLAR SIGN (PR) × [24.02] HEBREW LETTER ALEF (HL) ÷ [0.3] × 0024 × 0020 ÷ 05D0 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] HEBREW LETTER ALEF (HL) ÷ [0.3] @@ -4566,17 +4566,17 @@ × 0024 × 0020 × 002C ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) × [13.02] COMMA (IS) ÷ [0.3] × 0024 × 0308 × 002C ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [13.03] COMMA (IS) ÷ [0.3] × 0024 × 0308 × 0020 × 002C ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) × [13.02] COMMA (IS) ÷ [0.3] -× 0024 × 1100 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.03] HANGUL CHOSEONG KIYEOK (JL) ÷ [0.3] +× 0024 × 1100 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.02] HANGUL CHOSEONG KIYEOK (JL) ÷ [0.3] × 0024 × 0020 ÷ 1100 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] HANGUL CHOSEONG KIYEOK (JL) ÷ [0.3] -× 0024 × 0308 × 1100 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.03] HANGUL CHOSEONG KIYEOK (JL) ÷ [0.3] +× 0024 × 0308 × 1100 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] HANGUL CHOSEONG KIYEOK (JL) ÷ [0.3] × 0024 × 0308 × 0020 ÷ 1100 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] HANGUL CHOSEONG KIYEOK (JL) ÷ [0.3] -× 0024 × 11A8 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.03] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] +× 0024 × 11A8 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.02] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] × 0024 × 0020 ÷ 11A8 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] -× 0024 × 0308 × 11A8 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.03] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] +× 0024 × 0308 × 11A8 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] × 0024 × 0308 × 0020 ÷ 11A8 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] -× 0024 × 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.03] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] +× 0024 × 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.02] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] × 0024 × 0020 ÷ 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) ÷ [18.0] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] -× 0024 × 0308 × 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.03] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] +× 0024 × 0308 × 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [27.02] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] × 0024 × 0308 × 0020 ÷ 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] × 0024 × 000A ÷ # × [0.3] DOLLAR SIGN (PR) × [6.0] <LINE FEED (LF)> (LF) ÷ [0.3] × 0024 × 0020 × 000A ÷ # × [0.3] DOLLAR SIGN (PR) × [7.01] SPACE (SP) × [6.0] <LINE FEED (LF)> (LF) ÷ [0.3] @@ -5838,9 +5838,9 @@ × 261D × 0020 ÷ 261D ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [7.01] SPACE (SP) ÷ [18.0] WHITE UP POINTING INDEX (EB) ÷ [0.3] × 261D × 0308 ÷ 261D ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [9.0] COMBINING DIAERESIS (CM1_CM) ÷ [999.0] WHITE UP POINTING INDEX (EB) ÷ [0.3] × 261D × 0308 × 0020 ÷ 261D ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] WHITE UP POINTING INDEX (EB) ÷ [0.3] -× 261D × 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [30.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] +× 261D × 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [30.21] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] × 261D × 0020 ÷ 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [7.01] SPACE (SP) ÷ [18.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] -× 261D × 0308 × 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [9.0] COMBINING DIAERESIS (CM1_CM) × [30.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] +× 261D × 0308 × 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [9.0] COMBINING DIAERESIS (CM1_CM) × [30.21] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] × 261D × 0308 × 0020 ÷ 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [9.0] COMBINING DIAERESIS (CM1_CM) × [7.01] SPACE (SP) ÷ [18.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] × 261D × 0029 ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [13.02] RIGHT PARENTHESIS (CP_CP30) ÷ [0.3] × 261D × 0020 × 0029 ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [7.01] SPACE (SP) × [13.02] RIGHT PARENTHESIS (CP_CP30) ÷ [0.3] @@ -7452,9 +7452,9 @@ × 1160 × 1160 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [26.02] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] × 11A8 × 11A8 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT) × [26.03] HANGUL JONGSEONG KIYEOK (JT) ÷ [0.3] × 1160 × 2024 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [22.0] ONE DOT LEADER (IN) ÷ [0.3] -× 1160 × 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [27.02] PERCENT SIGN (PO) ÷ [0.3] -× 0024 × 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.03] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] -× 261D × 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [30.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] +× 1160 × 0025 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV) × [27.01] PERCENT SIGN (PO) ÷ [0.3] +× 0024 × 1160 ÷ # × [0.3] DOLLAR SIGN (PR) × [27.02] HANGUL JUNGSEONG FILLER (JV) ÷ [0.3] +× 261D × 1F3FB ÷ # × [0.3] WHITE UP POINTING INDEX (EB) × [30.21] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [0.3] × 0066 × 0069 × 006E × 0061 × 006C ÷ # × [0.3] LATIN SMALL LETTER F (AL) × [28.0] LATIN SMALL LETTER I (AL) × [28.0] LATIN SMALL LETTER N (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER L (AL) ÷ [0.3] × 0063 × 0061 × 006E × 0027 × 0074 ÷ # × [0.3] LATIN SMALL LETTER C (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER N (AL) × [19.01] APOSTROPHE (QU) × [19.02] LATIN SMALL LETTER T (AL) ÷ [0.3] × 0063 × 0061 × 006E × 2019 × 0074 ÷ # × [0.3] LATIN SMALL LETTER C (AL) × [28.0] LATIN SMALL LETTER A (AL) × [28.0] LATIN SMALL LETTER N (AL) × [19.01] RIGHT SINGLE QUOTATION MARK (QU) × [19.02] LATIN SMALL LETTER T (AL) ÷ [0.3] @@ -7678,7 +7678,9 @@ × 1F1F7 × 1F1FA ÷ 1F1F8 × 1F1EA ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER R (RI) × [30.11] REGIONAL INDICATOR SYMBOL LETTER U (RI) ÷ [30.13] REGIONAL INDICATOR SYMBOL LETTER S (RI) × [30.11] REGIONAL INDICATOR SYMBOL LETTER E (RI) ÷ [0.3] × 1F1F7 × 1F1FA × 200B ÷ 1F1F8 × 1F1EA ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER R (RI) × [30.11] REGIONAL INDICATOR SYMBOL LETTER U (RI) × [7.02] ZERO WIDTH SPACE (ZW) ÷ [8.0] REGIONAL INDICATOR SYMBOL LETTER S (RI) × [30.12] REGIONAL INDICATOR SYMBOL LETTER E (RI) ÷ [0.3] × 05D0 × 002D × 05D0 ÷ # × [0.3] HEBREW LETTER ALEF (HL) × [21.02] HYPHEN-MINUS (HY) × [21.1] HEBREW LETTER ALEF (HL) ÷ [0.3] +× 1F02C × 1F3FF ÷ # × [0.3] <reserved-1F02C> (Other) × [30.22] EMOJI MODIFIER FITZPATRICK TYPE-6 (EM) ÷ [0.3] +× 00A9 ÷ 1F3FF ÷ # × [0.3] COPYRIGHT SIGN (AL) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (EM) ÷ [0.3] # -# Lines: 7652 +# Lines: 7654 # # EOF diff --git a/lib/unicore/auxiliary/SBTest.txt b/lib/unicore/auxiliary/SBTest.txt index 5ae1f88110..61ea42cf1a 100644 --- a/lib/unicore/auxiliary/SBTest.txt +++ b/lib/unicore/auxiliary/SBTest.txt @@ -1,6 +1,6 @@ -# SentenceBreakTest-13.0.0.txt -# Date: 2019-11-20, 22:27:22 GMT -# © 2019 Unicode®, Inc. +# SentenceBreakTest-14.0.0.txt +# Date: 2021-03-08, 06:22:40 GMT +# © 2021 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 # diff --git a/lib/unicore/auxiliary/SentenceBreakProperty.txt b/lib/unicore/auxiliary/SentenceBreakProperty.txt index 432385b269..4b12b85492 100644 --- a/lib/unicore/auxiliary/SentenceBreakProperty.txt +++ b/lib/unicore/auxiliary/SentenceBreakProperty.txt @@ -1,6 +1,6 @@ -# SentenceBreakProperty-13.0.0.txt -# Date: 2019-11-27, 03:13:39 GMT -# © 2019 Unicode®, Inc. +# SentenceBreakProperty-14.0.0.txt +# Date: 2021-08-12, 23:13:21 GMT +# © 2021 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 # @@ -55,7 +55,8 @@ 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -124,6 +125,7 @@ 0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA 0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Extend # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; Extend # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI @@ -202,7 +204,9 @@ 109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; Extend # Mc TAGALOG SIGN PAMUDPOD +1732..1733 ; Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; Extend # Mc HANUNOO SIGN PAMUDPOD 1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -214,6 +218,7 @@ 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -241,7 +246,7 @@ 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Extend # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -281,8 +286,7 @@ 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -368,16 +372,20 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA 11002 ; Extend # Mc BRAHMI SIGN VISARGA 11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; Extend # Mc KAITHI SIGN VISARGA 110B0..110B2 ; Extend # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Extend # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Extend # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Extend # Mc CHAKMA VOWEL SIGN E @@ -516,6 +524,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER 16FF0..16FF1 ; Extend # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; Extend # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -535,13 +545,14 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2395 +# Total code points: 2508 # ================================================ @@ -558,6 +569,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK +0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 200B ; Format # Cf ZERO WIDTH SPACE @@ -574,7 +586,7 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Format # Cf LANGUAGE TAG -# Total code points: 63 +# Total code points: 65 # ================================================ @@ -1035,7 +1047,7 @@ E0001 ; Format # Cf LANGUAGE TAG 2170..217F ; Lower # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Lower # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Lower # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Lower # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Lower # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Lower # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Lower # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Lower # L& LATIN SMALL LETTER H WITH DESCENDER @@ -1207,9 +1219,15 @@ A7B9 ; Lower # L& LATIN SMALL LETTER U WITH STROKE A7BB ; Lower # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Lower # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Lower # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Lower # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Lower # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lower # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lower # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Lower # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Lower # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Lower # L& LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Lower # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Lower # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Lower # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -1222,6 +1240,14 @@ FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Lower # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Lower # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Lower # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Lower # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Lower # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Lower # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Lower # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lower # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lower # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lower # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y @@ -1253,9 +1279,11 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7AA..1D7C2 ; Lower # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Lower # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Lower # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2297 +# Total code points: 2424 # ================================================ @@ -1693,7 +1721,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 2160..216F ; Upper # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Upper # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Upper # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Upper # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Upper # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Upper # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Upper # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Upper # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -1858,13 +1886,21 @@ A7B8 ; Upper # L& LATIN CAPITAL LETTER U WITH STROKE A7BA ; Upper # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Upper # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Upper # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Upper # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Upper # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Upper # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Upper # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Upper # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Upper # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Upper # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Upper # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Upper # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Upper # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Upper # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Upper # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -1904,7 +1940,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1896 +# Total code points: 1936 # ================================================ @@ -1943,8 +1979,10 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; OLetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; OLetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; OLetter # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; OLetter # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; OLetter # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; OLetter # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; OLetter # Lm ARABIC SMALL FARSI YEH 0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; OLetter # Lo DEVANAGARI OM @@ -2010,6 +2048,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0C2A..0C39 ; OLetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; OLetter # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; OLetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -2018,7 +2057,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0CAA..0CB3 ; OLetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; OLetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; OLetter # Lo KANNADA SIGN AVAGRAHA -0CDE ; OLetter # Lo KANNADA LETTER FA +0CDD..0CDE ; OLetter # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; OLetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; OLetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; OLetter # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -2088,9 +2127,8 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 16A0..16EA ; OLetter # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; OLetter # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; OLetter # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; OLetter # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; OLetter # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; OLetter # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; OLetter # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; OLetter # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; OLetter # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; OLetter # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; OLetter # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -2113,7 +2151,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1A20..1A54 ; OLetter # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; OLetter # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; OLetter # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; OLetter # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; OLetter # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; OLetter # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; OLetter # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; OLetter # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -2161,8 +2199,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 31A0..31BF ; OLetter # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; OLetter # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; OLetter # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; OLetter # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; OLetter # Lm YI SYLLABLE WU A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; OLetter # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -2178,6 +2215,7 @@ A6E6..A6EF ; OLetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM A717..A71F ; OLetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A788 ; OLetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78F ; OLetter # Lo LATIN LETTER SINOLOGICAL DOT +A7F2..A7F4 ; OLetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F7 ; OLetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7FB..A801 ; OLetter # Lo [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I A803..A805 ; OLetter # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O @@ -2275,6 +2313,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10600..10736 ; OLetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; OLetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; OLetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10781..10782 ; OLetter # Lm [2] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON 10800..10805 ; OLetter # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; OLetter # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; OLetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -2308,9 +2347,12 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; OLetter # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; OLetter # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; OLetter # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; OLetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; OLetter # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; OLetter # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; OLetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; OLetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; OLetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -2352,6 +2394,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; OLetter # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; OLetter # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; OLetter # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; OLetter # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118FF..11906 ; OLetter # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E 11909 ; OLetter # Lo DIVES AKURU LETTER O @@ -2370,7 +2413,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; OLetter # Lo SOYOMBO LETTER A 11A5C..11A89 ; OLetter # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; OLetter # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; OLetter # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; OLetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; OLetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; OLetter # Lo BHAIKSUKI SIGN AVAGRAHA @@ -2388,10 +2431,12 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; OLetter # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; OLetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; OLetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; OLetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; OLetter # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; OLetter # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; OLetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; OLetter # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; OLetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -2405,7 +2450,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17000..187F7 ; OLetter # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; OLetter # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; OLetter # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; OLetter # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; OLetter # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; OLetter # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; OLetter # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; OLetter # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; OLetter # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; OLetter # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -2413,10 +2461,16 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; OLetter # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1DF0A ; OLetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1E100..1E12C ; OLetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; OLetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; OLetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; OLetter # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; OLetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; OLetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; OLetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; OLetter # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; OLetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E94B ; OLetter # Lm ADLAM NASALIZATION MARK 1EE00..1EE03 ; OLetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL @@ -2452,15 +2506,15 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1EEA1..1EEA3 ; OLetter # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; OLetter # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; OLetter # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; OLetter # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; OLetter # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; OLetter # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; OLetter # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 127413 +# Total code points: 127761 # ================================================ @@ -2520,6 +2574,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -2527,7 +2582,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 652 +# Total code points: 662 # ================================================ @@ -2543,7 +2598,7 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP 0021 ; STerm # Po EXCLAMATION MARK 003F ; STerm # Po QUESTION MARK 0589 ; STerm # Po ARMENIAN FULL STOP -061E..061F ; STerm # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; STerm # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 06D4 ; STerm # Po ARABIC FULL STOP 0700..0702 ; STerm # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP 07F9 ; STerm # Po NKO EXCLAMATION MARK @@ -2562,12 +2617,14 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP 1AA8..1AAB ; STerm # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU 1B5A..1B5B ; STerm # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5E..1B5F ; STerm # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN +1B7D..1B7E ; STerm # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1C3B..1C3C ; STerm # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL 1C7E..1C7F ; STerm # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 203C..203D ; STerm # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG 2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK 2E2E ; STerm # Po REVERSED QUESTION MARK 2E3C ; STerm # Po STENOGRAPHIC FULL STOP +2E53..2E54 ; STerm # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK 3002 ; STerm # Po IDEOGRAPHIC FULL STOP A4FF ; STerm # Po LISU PUNCTUATION FULL STOP A60E..A60F ; STerm # Po [2] VAI FULL STOP..VAI QUESTION MARK @@ -2586,6 +2643,7 @@ FF1F ; STerm # Po FULLWIDTH QUESTION MARK FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA 10F55..10F59 ; STerm # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; STerm # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA 110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK @@ -2614,7 +2672,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; STerm # Po SIGNWRITING FULL STOP -# Total code points: 140 +# Total code points: 149 # ================================================ @@ -2734,6 +2792,14 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 2E28 ; Close # Ps LEFT DOUBLE PARENTHESIS 2E29 ; Close # Pe RIGHT DOUBLE PARENTHESIS 2E42 ; Close # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E55 ; Close # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Close # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Close # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Close # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Close # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Close # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Close # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Close # Pe BOTTOM HALF RIGHT PARENTHESIS 3008 ; Close # Ps LEFT ANGLE BRACKET 3009 ; Close # Pe RIGHT ANGLE BRACKET 300A ; Close # Ps LEFT DOUBLE ANGLE BRACKET @@ -2794,7 +2860,7 @@ FF62 ; Close # Ps HALFWIDTH LEFT CORNER BRACKET FF63 ; Close # Pe HALFWIDTH RIGHT CORNER BRACKET 1F676..1F678 ; Close # So [3] SANS-SERIF HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT..SANS-SERIF HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT -# Total code points: 187 +# Total code points: 195 # ================================================ diff --git a/lib/unicore/auxiliary/WBTest.txt b/lib/unicore/auxiliary/WBTest.txt index 3e85759b85..1d1435bfc7 100644 --- a/lib/unicore/auxiliary/WBTest.txt +++ b/lib/unicore/auxiliary/WBTest.txt @@ -1,6 +1,6 @@ -# WordBreakTest-13.0.0.txt -# Date: 2019-11-20, 22:27:23 GMT -# © 2019 Unicode®, Inc. +# WordBreakTest-14.0.0.txt +# Date: 2021-03-08, 06:22:40 GMT +# © 2021 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 # diff --git a/lib/unicore/auxiliary/WordBreakProperty.txt b/lib/unicore/auxiliary/WordBreakProperty.txt index 36d1438c26..73cd069dcb 100644 --- a/lib/unicore/auxiliary/WordBreakProperty.txt +++ b/lib/unicore/auxiliary/WordBreakProperty.txt @@ -1,6 +1,6 @@ -# WordBreakProperty-13.0.0.txt -# Date: 2020-01-22, 00:07:44 GMT -# © 2020 Unicode®, Inc. +# WordBreakProperty-14.0.0.txt +# Date: 2021-07-10, 00:35:32 GMT +# © 2021 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 # @@ -91,7 +91,8 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -160,6 +161,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA 0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Extend # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; Extend # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI @@ -238,7 +240,9 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; Extend # Mc TAGALOG SIGN PAMUDPOD +1732..1733 ; Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; Extend # Mc HANUNOO SIGN PAMUDPOD 1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -250,6 +254,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -277,7 +282,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Extend # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -317,8 +322,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -404,16 +408,20 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA 11002 ; Extend # Mc BRAHMI SIGN VISARGA 11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; Extend # Mc KAITHI SIGN VISARGA 110B0..110B2 ; Extend # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Extend # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Extend # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Extend # Mc CHAKMA VOWEL SIGN E @@ -552,6 +560,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER 16FF0..16FF1 ; Extend # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; Extend # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -571,6 +581,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA @@ -578,7 +589,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2399 +# Total code points: 2512 # ================================================ @@ -593,6 +604,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK +0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -608,7 +620,7 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Format # Cf LANGUAGE TAG -# Total code points: 62 +# Total code points: 64 # ================================================ @@ -624,10 +636,14 @@ E0001 ; Format # Cf LANGUAGE TAG FF66..FF6F ; Katakana # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU FF70 ; Katakana # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +1AFF0..1AFF3 ; Katakana # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Katakana # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E +1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU 1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N -# Total code points: 314 +# Total code points: 330 # ================================================ @@ -699,8 +715,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ALetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; ALetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; ALetter # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; ALetter # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ALetter # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; ALetter # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ALetter # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ALetter # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ALetter # Lo DEVANAGARI OM @@ -766,6 +784,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0C2A..0C39 ; ALetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ALetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ALetter # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ALetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -774,7 +793,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0CAA..0CB3 ; ALetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ALetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ALetter # Lo KANNADA SIGN AVAGRAHA -0CDE ; ALetter # Lo KANNADA LETTER FA +0CDD..0CDE ; ALetter # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ALetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ALetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ALetter # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -825,9 +844,8 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 16A0..16EA ; ALetter # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ALetter # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ALetter # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ALetter # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ALetter # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; ALetter # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; ALetter # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; ALetter # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; ALetter # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; ALetter # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; ALetter # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -841,7 +859,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 1900..191E ; ALetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA 1A00..1A16 ; ALetter # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1B05..1B33 ; ALetter # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; ALetter # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ALetter # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; ALetter # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; ALetter # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; ALetter # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -903,9 +921,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 2183..2184 ; ALetter # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ALetter # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND 24B6..24E9 ; ALetter # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; ALetter # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ALetter # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ALetter # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ALetter # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ALetter # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ALetter # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ALetter # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -957,8 +973,11 @@ A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ALetter # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ALetter # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ALetter # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ALetter # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ALetter # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ALetter # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ALetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ALetter # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1040,9 +1059,20 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 104D8..104FB ; ALetter # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ALetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ALetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ALetter # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ALetter # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ALetter # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ALetter # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ALetter # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ALetter # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ALetter # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ALetter # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ALetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ALetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ALetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ALetter # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ALetter # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ALetter # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ALetter # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ALetter # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ALetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1078,9 +1108,12 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10F00..10F1C ; ALetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ALetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ALetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; ALetter # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; ALetter # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ALetter # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; ALetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; ALetter # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; ALetter # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; ALetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; ALetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; ALetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -1140,7 +1173,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; ALetter # Lo SOYOMBO LETTER A 11A5C..11A89 ; ALetter # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; ALetter # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ALetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ALetter # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ALetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ALetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; ALetter # Lo BHAIKSUKI SIGN AVAGRAHA @@ -1158,10 +1191,12 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; ALetter # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; ALetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; ALetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ALetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ALetter # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; ALetter # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; ALetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; ALetter # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; ALetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -1207,10 +1242,18 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78A..1D7A8 ; ALetter # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; ALetter # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ALetter # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; ALetter # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ALetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ALetter # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; ALetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ALetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; ALetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ALetter # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; ALetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ALetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ALetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ALetter # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ALetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; ALetter # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; ALetter # Lm ADLAM NASALIZATION MARK @@ -1251,7 +1294,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 28854 +# Total code points: 29336 # ================================================ @@ -1356,6 +1399,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -1363,7 +1407,7 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 651 +# Total code points: 661 # ================================================ diff --git a/lib/unicore/emoji/emoji.txt b/lib/unicore/emoji/emoji.txt index 5d7dc1b156..7806c7ab53 100644 --- a/lib/unicore/emoji/emoji.txt +++ b/lib/unicore/emoji/emoji.txt @@ -1,11 +1,11 @@ -# emoji-data.txt -# Date: 2020-01-28, 20:52:38 GMT -# © 2020 Unicode®, Inc. +# emoji-data-14.0.0.txt +# Date: 2021-08-26, 17:22:22 GMT +# © 2021 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 # # Emoji Data for UTS #51 -# Version: 13.0 +# Used with Emoji Version 14.0 and subsequent minor revisions (if any) # # For documentation and usage, see http://www.unicode.org/reports/tr51 # @@ -22,7 +22,7 @@ # All omitted code points have Emoji=No # @missing: 0000..10FFFF ; Emoji ; No -0023 ; Emoji # E0.0 [1] (#️) number sign +0023 ; Emoji # E0.0 [1] (#️) hash sign 002A ; Emoji # E0.0 [1] (*️) asterisk 0030..0039 ; Emoji # E0.0 [10] (0️..9️) digit zero..digit nine 00A9 ; Emoji # E0.6 [1] (©️) copyright @@ -119,8 +119,8 @@ 2747 ; Emoji # E0.6 [1] (❇️) sparkle 274C ; Emoji # E0.6 [1] (❌) cross mark 274E ; Emoji # E0.6 [1] (❎) cross mark button -2753..2755 ; Emoji # E0.6 [3] (❓..❕) question mark..white exclamation mark -2757 ; Emoji # E0.6 [1] (❗) exclamation mark +2753..2755 ; Emoji # E0.6 [3] (❓..❕) red question mark..white exclamation mark +2757 ; Emoji # E0.6 [1] (❗) red exclamation mark 2763 ; Emoji # E1.0 [1] (❣️) heart exclamation 2764 ; Emoji # E0.6 [1] (❤️) red heart 2795..2797 ; Emoji # E0.6 [3] (➕..➗) plus..divide @@ -239,7 +239,7 @@ 1F509 ; Emoji # E1.0 [1] (🔉) speaker medium volume 1F50A..1F514 ; Emoji # E0.6 [11] (🔊..🔔) speaker high volume..bell 1F515 ; Emoji # E1.0 [1] (🔕) bell with slash -1F516..1F52B ; Emoji # E0.6 [22] (🔖..🔫) bookmark..pistol +1F516..1F52B ; Emoji # E0.6 [22] (🔖..🔫) bookmark..water pistol 1F52C..1F52D ; Emoji # E1.0 [2] (🔬..🔭) microscope..telescope 1F52E..1F53D ; Emoji # E0.6 [16] (🔮..🔽) crystal ball..downwards button 1F549..1F54A ; Emoji # E0.7 [2] (🕉️..🕊️) om..dove @@ -294,7 +294,7 @@ 1F62E..1F62F ; Emoji # E1.0 [2] (😮..😯) face with open mouth..hushed face 1F630..1F633 ; Emoji # E0.6 [4] (😰..😳) anxious face with sweat..flushed face 1F634 ; Emoji # E1.0 [1] (😴) sleeping face -1F635 ; Emoji # E0.6 [1] (😵) dizzy face +1F635 ; Emoji # E0.6 [1] (😵) face with crossed-out eyes 1F636 ; Emoji # E1.0 [1] (😶) face without mouth 1F637..1F640 ; Emoji # E0.6 [10] (😷..🙀) face with medical mask..weary cat 1F641..1F644 ; Emoji # E1.0 [4] (🙁..🙄) slightly frowning face..face with rolling eyes @@ -341,6 +341,7 @@ 1F6D1..1F6D2 ; Emoji # E3.0 [2] (🛑..🛒) stop sign..shopping cart 1F6D5 ; Emoji # E12.0 [1] (🛕) hindu temple 1F6D6..1F6D7 ; Emoji # E13.0 [2] (🛖..🛗) hut..elevator +1F6DD..1F6DF ; Emoji # E14.0 [3] (🛝..🛟) playground slide..ring buoy 1F6E0..1F6E5 ; Emoji # E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat 1F6E9 ; Emoji # E0.7 [1] (🛩️) small airplane 1F6EB..1F6EC ; Emoji # E1.0 [2] (🛫..🛬) airplane departure..airplane arrival @@ -352,6 +353,7 @@ 1F6FA ; Emoji # E12.0 [1] (🛺) auto rickshaw 1F6FB..1F6FC ; Emoji # E13.0 [2] (🛻..🛼) pickup truck..roller skate 1F7E0..1F7EB ; Emoji # E12.0 [12] (🟠..🟫) orange circle..brown square +1F7F0 ; Emoji # E14.0 [1] (🟰) heavy equals sign 1F90C ; Emoji # E13.0 [1] (🤌) pinched fingers 1F90D..1F90F ; Emoji # E12.0 [3] (🤍..🤏) white heart..pinching hand 1F910..1F918 ; Emoji # E1.0 [9] (🤐..🤘) zipper-mouth face..sign of the horns @@ -375,6 +377,7 @@ 1F972 ; Emoji # E13.0 [1] (🥲) smiling face with tear 1F973..1F976 ; Emoji # E11.0 [4] (🥳..🥶) partying face..cold face 1F977..1F978 ; Emoji # E13.0 [2] (🥷..🥸) ninja..disguised face +1F979 ; Emoji # E14.0 [1] (🥹) face holding back tears 1F97A ; Emoji # E11.0 [1] (🥺) pleading face 1F97B ; Emoji # E12.0 [1] (🥻) sari 1F97C..1F97F ; Emoji # E11.0 [4] (🥼..🥿) lab coat..flat shoe @@ -392,21 +395,29 @@ 1F9C1..1F9C2 ; Emoji # E11.0 [2] (🧁..🧂) cupcake..salt 1F9C3..1F9CA ; Emoji # E12.0 [8] (🧃..🧊) beverage box..ice 1F9CB ; Emoji # E13.0 [1] (🧋) bubble tea +1F9CC ; Emoji # E14.0 [1] (🧌) troll 1F9CD..1F9CF ; Emoji # E12.0 [3] (🧍..🧏) person standing..deaf person 1F9D0..1F9E6 ; Emoji # E5.0 [23] (🧐..🧦) face with monocle..socks 1F9E7..1F9FF ; Emoji # E11.0 [25] (🧧..🧿) red envelope..nazar amulet 1FA70..1FA73 ; Emoji # E12.0 [4] (🩰..🩳) ballet shoes..shorts 1FA74 ; Emoji # E13.0 [1] (🩴) thong sandal 1FA78..1FA7A ; Emoji # E12.0 [3] (🩸..🩺) drop of blood..stethoscope +1FA7B..1FA7C ; Emoji # E14.0 [2] (🩻..🩼) x-ray..crutch 1FA80..1FA82 ; Emoji # E12.0 [3] (🪀..🪂) yo-yo..parachute 1FA83..1FA86 ; Emoji # E13.0 [4] (🪃..🪆) boomerang..nesting dolls 1FA90..1FA95 ; Emoji # E12.0 [6] (🪐..🪕) ringed planet..banjo 1FA96..1FAA8 ; Emoji # E13.0 [19] (🪖..🪨) military helmet..rock +1FAA9..1FAAC ; Emoji # E14.0 [4] (🪩..🪬) mirror ball..hamsa 1FAB0..1FAB6 ; Emoji # E13.0 [7] (🪰..🪶) fly..feather +1FAB7..1FABA ; Emoji # E14.0 [4] (🪷..🪺) lotus..nest with eggs 1FAC0..1FAC2 ; Emoji # E13.0 [3] (🫀..🫂) anatomical heart..people hugging +1FAC3..1FAC5 ; Emoji # E14.0 [3] (🫃..🫅) pregnant man..person with crown 1FAD0..1FAD6 ; Emoji # E13.0 [7] (🫐..🫖) blueberries..teapot +1FAD7..1FAD9 ; Emoji # E14.0 [3] (🫗..🫙) pouring liquid..jar +1FAE0..1FAE7 ; Emoji # E14.0 [8] (🫠..🫧) melting face..bubbles +1FAF0..1FAF6 ; Emoji # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands -# Total elements: 1367 +# Total elements: 1404 # ================================================ @@ -438,8 +449,8 @@ 2728 ; Emoji_Presentation # E0.6 [1] (✨) sparkles 274C ; Emoji_Presentation # E0.6 [1] (❌) cross mark 274E ; Emoji_Presentation # E0.6 [1] (❎) cross mark button -2753..2755 ; Emoji_Presentation # E0.6 [3] (❓..❕) question mark..white exclamation mark -2757 ; Emoji_Presentation # E0.6 [1] (❗) exclamation mark +2753..2755 ; Emoji_Presentation # E0.6 [3] (❓..❕) red question mark..white exclamation mark +2757 ; Emoji_Presentation # E0.6 [1] (❗) red exclamation mark 2795..2797 ; Emoji_Presentation # E0.6 [3] (➕..➗) plus..divide 27B0 ; Emoji_Presentation # E0.6 [1] (➰) curly loop 27BF ; Emoji_Presentation # E1.0 [1] (➿) double curly loop @@ -533,7 +544,7 @@ 1F509 ; Emoji_Presentation # E1.0 [1] (🔉) speaker medium volume 1F50A..1F514 ; Emoji_Presentation # E0.6 [11] (🔊..🔔) speaker high volume..bell 1F515 ; Emoji_Presentation # E1.0 [1] (🔕) bell with slash -1F516..1F52B ; Emoji_Presentation # E0.6 [22] (🔖..🔫) bookmark..pistol +1F516..1F52B ; Emoji_Presentation # E0.6 [22] (🔖..🔫) bookmark..water pistol 1F52C..1F52D ; Emoji_Presentation # E1.0 [2] (🔬..🔭) microscope..telescope 1F52E..1F53D ; Emoji_Presentation # E0.6 [16] (🔮..🔽) crystal ball..downwards button 1F54B..1F54E ; Emoji_Presentation # E1.0 [4] (🕋..🕎) kaaba..menorah @@ -569,7 +580,7 @@ 1F62E..1F62F ; Emoji_Presentation # E1.0 [2] (😮..😯) face with open mouth..hushed face 1F630..1F633 ; Emoji_Presentation # E0.6 [4] (😰..😳) anxious face with sweat..flushed face 1F634 ; Emoji_Presentation # E1.0 [1] (😴) sleeping face -1F635 ; Emoji_Presentation # E0.6 [1] (😵) dizzy face +1F635 ; Emoji_Presentation # E0.6 [1] (😵) face with crossed-out eyes 1F636 ; Emoji_Presentation # E1.0 [1] (😶) face without mouth 1F637..1F640 ; Emoji_Presentation # E0.6 [10] (😷..🙀) face with medical mask..weary cat 1F641..1F644 ; Emoji_Presentation # E1.0 [4] (🙁..🙄) slightly frowning face..face with rolling eyes @@ -614,6 +625,7 @@ 1F6D1..1F6D2 ; Emoji_Presentation # E3.0 [2] (🛑..🛒) stop sign..shopping cart 1F6D5 ; Emoji_Presentation # E12.0 [1] (🛕) hindu temple 1F6D6..1F6D7 ; Emoji_Presentation # E13.0 [2] (🛖..🛗) hut..elevator +1F6DD..1F6DF ; Emoji_Presentation # E14.0 [3] (🛝..🛟) playground slide..ring buoy 1F6EB..1F6EC ; Emoji_Presentation # E1.0 [2] (🛫..🛬) airplane departure..airplane arrival 1F6F4..1F6F6 ; Emoji_Presentation # E3.0 [3] (🛴..🛶) kick scooter..canoe 1F6F7..1F6F8 ; Emoji_Presentation # E5.0 [2] (🛷..🛸) sled..flying saucer @@ -621,6 +633,7 @@ 1F6FA ; Emoji_Presentation # E12.0 [1] (🛺) auto rickshaw 1F6FB..1F6FC ; Emoji_Presentation # E13.0 [2] (🛻..🛼) pickup truck..roller skate 1F7E0..1F7EB ; Emoji_Presentation # E12.0 [12] (🟠..🟫) orange circle..brown square +1F7F0 ; Emoji_Presentation # E14.0 [1] (🟰) heavy equals sign 1F90C ; Emoji_Presentation # E13.0 [1] (🤌) pinched fingers 1F90D..1F90F ; Emoji_Presentation # E12.0 [3] (🤍..🤏) white heart..pinching hand 1F910..1F918 ; Emoji_Presentation # E1.0 [9] (🤐..🤘) zipper-mouth face..sign of the horns @@ -644,6 +657,7 @@ 1F972 ; Emoji_Presentation # E13.0 [1] (🥲) smiling face with tear 1F973..1F976 ; Emoji_Presentation # E11.0 [4] (🥳..🥶) partying face..cold face 1F977..1F978 ; Emoji_Presentation # E13.0 [2] (🥷..🥸) ninja..disguised face +1F979 ; Emoji_Presentation # E14.0 [1] (🥹) face holding back tears 1F97A ; Emoji_Presentation # E11.0 [1] (🥺) pleading face 1F97B ; Emoji_Presentation # E12.0 [1] (🥻) sari 1F97C..1F97F ; Emoji_Presentation # E11.0 [4] (🥼..🥿) lab coat..flat shoe @@ -661,21 +675,29 @@ 1F9C1..1F9C2 ; Emoji_Presentation # E11.0 [2] (🧁..🧂) cupcake..salt 1F9C3..1F9CA ; Emoji_Presentation # E12.0 [8] (🧃..🧊) beverage box..ice 1F9CB ; Emoji_Presentation # E13.0 [1] (🧋) bubble tea +1F9CC ; Emoji_Presentation # E14.0 [1] (🧌) troll 1F9CD..1F9CF ; Emoji_Presentation # E12.0 [3] (🧍..🧏) person standing..deaf person 1F9D0..1F9E6 ; Emoji_Presentation # E5.0 [23] (🧐..🧦) face with monocle..socks 1F9E7..1F9FF ; Emoji_Presentation # E11.0 [25] (🧧..🧿) red envelope..nazar amulet 1FA70..1FA73 ; Emoji_Presentation # E12.0 [4] (🩰..🩳) ballet shoes..shorts 1FA74 ; Emoji_Presentation # E13.0 [1] (🩴) thong sandal 1FA78..1FA7A ; Emoji_Presentation # E12.0 [3] (🩸..🩺) drop of blood..stethoscope +1FA7B..1FA7C ; Emoji_Presentation # E14.0 [2] (🩻..🩼) x-ray..crutch 1FA80..1FA82 ; Emoji_Presentation # E12.0 [3] (🪀..🪂) yo-yo..parachute 1FA83..1FA86 ; Emoji_Presentation # E13.0 [4] (🪃..🪆) boomerang..nesting dolls 1FA90..1FA95 ; Emoji_Presentation # E12.0 [6] (🪐..🪕) ringed planet..banjo 1FA96..1FAA8 ; Emoji_Presentation # E13.0 [19] (🪖..🪨) military helmet..rock +1FAA9..1FAAC ; Emoji_Presentation # E14.0 [4] (🪩..🪬) mirror ball..hamsa 1FAB0..1FAB6 ; Emoji_Presentation # E13.0 [7] (🪰..🪶) fly..feather +1FAB7..1FABA ; Emoji_Presentation # E14.0 [4] (🪷..🪺) lotus..nest with eggs 1FAC0..1FAC2 ; Emoji_Presentation # E13.0 [3] (🫀..🫂) anatomical heart..people hugging +1FAC3..1FAC5 ; Emoji_Presentation # E14.0 [3] (🫃..🫅) pregnant man..person with crown 1FAD0..1FAD6 ; Emoji_Presentation # E13.0 [7] (🫐..🫖) blueberries..teapot +1FAD7..1FAD9 ; Emoji_Presentation # E14.0 [3] (🫗..🫙) pouring liquid..jar +1FAE0..1FAE7 ; Emoji_Presentation # E14.0 [8] (🫠..🫧) melting face..bubbles +1FAF0..1FAF6 ; Emoji_Presentation # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands -# Total elements: 1148 +# Total elements: 1185 # ================================================ @@ -738,15 +760,17 @@ 1F9BB ; Emoji_Modifier_Base # E12.0 [1] (🦻) ear with hearing aid 1F9CD..1F9CF ; Emoji_Modifier_Base # E12.0 [3] (🧍..🧏) person standing..deaf person 1F9D1..1F9DD ; Emoji_Modifier_Base # E5.0 [13] (🧑..🧝) person..elf +1FAC3..1FAC5 ; Emoji_Modifier_Base # E14.0 [3] (🫃..🫅) pregnant man..person with crown +1FAF0..1FAF6 ; Emoji_Modifier_Base # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands -# Total elements: 122 +# Total elements: 132 # ================================================ # All omitted code points have Emoji_Component=No # @missing: 0000..10FFFF ; Emoji_Component ; No -0023 ; Emoji_Component # E0.0 [1] (#️) number sign +0023 ; Emoji_Component # E0.0 [1] (#️) hash sign 002A ; Emoji_Component # E0.0 [1] (*️) asterisk 0030..0039 ; Emoji_Component # E0.0 [10] (0️..9️) digit zero..digit nine 200D ; Emoji_Component # E0.0 [1] () zero width joiner @@ -902,8 +926,8 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 2747 ; Extended_Pictographic# E0.6 [1] (❇️) sparkle 274C ; Extended_Pictographic# E0.6 [1] (❌) cross mark 274E ; Extended_Pictographic# E0.6 [1] (❎) cross mark button -2753..2755 ; Extended_Pictographic# E0.6 [3] (❓..❕) question mark..white exclamation mark -2757 ; Extended_Pictographic# E0.6 [1] (❗) exclamation mark +2753..2755 ; Extended_Pictographic# E0.6 [3] (❓..❕) red question mark..white exclamation mark +2757 ; Extended_Pictographic# E0.6 [1] (❗) red exclamation mark 2763 ; Extended_Pictographic# E1.0 [1] (❣️) heart exclamation 2764 ; Extended_Pictographic# E0.6 [1] (❤️) red heart 2765..2767 ; Extended_Pictographic# E0.0 [3] (❥..❧) ROTATED HEAVY BLACK HEART BULLET..ROTATED FLORAL HEART BULLET @@ -1041,7 +1065,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1F509 ; Extended_Pictographic# E1.0 [1] (🔉) speaker medium volume 1F50A..1F514 ; Extended_Pictographic# E0.6 [11] (🔊..🔔) speaker high volume..bell 1F515 ; Extended_Pictographic# E1.0 [1] (🔕) bell with slash -1F516..1F52B ; Extended_Pictographic# E0.6 [22] (🔖..🔫) bookmark..pistol +1F516..1F52B ; Extended_Pictographic# E0.6 [22] (🔖..🔫) bookmark..water pistol 1F52C..1F52D ; Extended_Pictographic# E1.0 [2] (🔬..🔭) microscope..telescope 1F52E..1F53D ; Extended_Pictographic# E0.6 [16] (🔮..🔽) crystal ball..downwards button 1F546..1F548 ; Extended_Pictographic# E0.0 [3] (🕆..🕈) WHITE LATIN CROSS..CELTIC CROSS @@ -1117,7 +1141,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1F62E..1F62F ; Extended_Pictographic# E1.0 [2] (😮..😯) face with open mouth..hushed face 1F630..1F633 ; Extended_Pictographic# E0.6 [4] (😰..😳) anxious face with sweat..flushed face 1F634 ; Extended_Pictographic# E1.0 [1] (😴) sleeping face -1F635 ; Extended_Pictographic# E0.6 [1] (😵) dizzy face +1F635 ; Extended_Pictographic# E0.6 [1] (😵) face with crossed-out eyes 1F636 ; Extended_Pictographic# E1.0 [1] (😶) face without mouth 1F637..1F640 ; Extended_Pictographic# E0.6 [10] (😷..🙀) face with medical mask..weary cat 1F641..1F644 ; Extended_Pictographic# E1.0 [4] (🙁..🙄) slightly frowning face..face with rolling eyes @@ -1166,7 +1190,8 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1F6D3..1F6D4 ; Extended_Pictographic# E0.0 [2] (🛓..🛔) STUPA..PAGODA 1F6D5 ; Extended_Pictographic# E12.0 [1] (🛕) hindu temple 1F6D6..1F6D7 ; Extended_Pictographic# E13.0 [2] (🛖..🛗) hut..elevator -1F6D8..1F6DF ; Extended_Pictographic# E0.0 [8] (..🛟) <reserved-1F6D8>..<reserved-1F6DF> +1F6D8..1F6DC ; Extended_Pictographic# E0.0 [5] (..🛜) <reserved-1F6D8>..<reserved-1F6DC> +1F6DD..1F6DF ; Extended_Pictographic# E14.0 [3] (🛝..🛟) playground slide..ring buoy 1F6E0..1F6E5 ; Extended_Pictographic# E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat 1F6E6..1F6E8 ; Extended_Pictographic# E0.0 [3] (🛦..🛨) UP-POINTING MILITARY AIRPLANE..UP-POINTING SMALL AIRPLANE 1F6E9 ; Extended_Pictographic# E0.7 [1] (🛩️) small airplane @@ -1185,7 +1210,9 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1F774..1F77F ; Extended_Pictographic# E0.0 [12] (🝴..🝿) <reserved-1F774>..<reserved-1F77F> 1F7D5..1F7DF ; Extended_Pictographic# E0.0 [11] (🟕..) CIRCLED TRIANGLE..<reserved-1F7DF> 1F7E0..1F7EB ; Extended_Pictographic# E12.0 [12] (🟠..🟫) orange circle..brown square -1F7EC..1F7FF ; Extended_Pictographic# E0.0 [20] (..) <reserved-1F7EC>..<reserved-1F7FF> +1F7EC..1F7EF ; Extended_Pictographic# E0.0 [4] (..) <reserved-1F7EC>..<reserved-1F7EF> +1F7F0 ; Extended_Pictographic# E14.0 [1] (🟰) heavy equals sign +1F7F1..1F7FF ; Extended_Pictographic# E0.0 [15] (..) <reserved-1F7F1>..<reserved-1F7FF> 1F80C..1F80F ; Extended_Pictographic# E0.0 [4] (..) <reserved-1F80C>..<reserved-1F80F> 1F848..1F84F ; Extended_Pictographic# E0.0 [8] (..) <reserved-1F848>..<reserved-1F84F> 1F85A..1F85F ; Extended_Pictographic# E0.0 [6] (..) <reserved-1F85A>..<reserved-1F85F> @@ -1214,7 +1241,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1F972 ; Extended_Pictographic# E13.0 [1] (🥲) smiling face with tear 1F973..1F976 ; Extended_Pictographic# E11.0 [4] (🥳..🥶) partying face..cold face 1F977..1F978 ; Extended_Pictographic# E13.0 [2] (🥷..🥸) ninja..disguised face -1F979 ; Extended_Pictographic# E0.0 [1] (🥹) <reserved-1F979> +1F979 ; Extended_Pictographic# E14.0 [1] (🥹) face holding back tears 1F97A ; Extended_Pictographic# E11.0 [1] (🥺) pleading face 1F97B ; Extended_Pictographic# E12.0 [1] (🥻) sari 1F97C..1F97F ; Extended_Pictographic# E11.0 [4] (🥼..🥿) lab coat..flat shoe @@ -1232,7 +1259,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1F9C1..1F9C2 ; Extended_Pictographic# E11.0 [2] (🧁..🧂) cupcake..salt 1F9C3..1F9CA ; Extended_Pictographic# E12.0 [8] (🧃..🧊) beverage box..ice 1F9CB ; Extended_Pictographic# E13.0 [1] (🧋) bubble tea -1F9CC ; Extended_Pictographic# E0.0 [1] (🧌) <reserved-1F9CC> +1F9CC ; Extended_Pictographic# E14.0 [1] (🧌) troll 1F9CD..1F9CF ; Extended_Pictographic# E12.0 [3] (🧍..🧏) person standing..deaf person 1F9D0..1F9E6 ; Extended_Pictographic# E5.0 [23] (🧐..🧦) face with monocle..socks 1F9E7..1F9FF ; Extended_Pictographic# E11.0 [25] (🧧..🧿) red envelope..nazar amulet @@ -1241,19 +1268,28 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (..) tag space..c 1FA74 ; Extended_Pictographic# E13.0 [1] (🩴) thong sandal 1FA75..1FA77 ; Extended_Pictographic# E0.0 [3] (🩵..🩷) <reserved-1FA75>..<reserved-1FA77> 1FA78..1FA7A ; Extended_Pictographic# E12.0 [3] (🩸..🩺) drop of blood..stethoscope -1FA7B..1FA7F ; Extended_Pictographic# E0.0 [5] (🩻..) <reserved-1FA7B>..<reserved-1FA7F> +1FA7B..1FA7C ; Extended_Pictographic# E14.0 [2] (🩻..🩼) x-ray..crutch +1FA7D..1FA7F ; Extended_Pictographic# E0.0 [3] (..) <reserved-1FA7D>..<reserved-1FA7F> 1FA80..1FA82 ; Extended_Pictographic# E12.0 [3] (🪀..🪂) yo-yo..parachute 1FA83..1FA86 ; Extended_Pictographic# E13.0 [4] (🪃..🪆) boomerang..nesting dolls 1FA87..1FA8F ; Extended_Pictographic# E0.0 [9] (🪇..) <reserved-1FA87>..<reserved-1FA8F> 1FA90..1FA95 ; Extended_Pictographic# E12.0 [6] (🪐..🪕) ringed planet..banjo 1FA96..1FAA8 ; Extended_Pictographic# E13.0 [19] (🪖..🪨) military helmet..rock -1FAA9..1FAAF ; Extended_Pictographic# E0.0 [7] (🪩..🪯) <reserved-1FAA9>..<reserved-1FAAF> +1FAA9..1FAAC ; Extended_Pictographic# E14.0 [4] (🪩..🪬) mirror ball..hamsa +1FAAD..1FAAF ; Extended_Pictographic# E0.0 [3] (🪭..🪯) <reserved-1FAAD>..<reserved-1FAAF> 1FAB0..1FAB6 ; Extended_Pictographic# E13.0 [7] (🪰..🪶) fly..feather -1FAB7..1FABF ; Extended_Pictographic# E0.0 [9] (🪷..🪿) <reserved-1FAB7>..<reserved-1FABF> +1FAB7..1FABA ; Extended_Pictographic# E14.0 [4] (🪷..🪺) lotus..nest with eggs +1FABB..1FABF ; Extended_Pictographic# E0.0 [5] (🪻..🪿) <reserved-1FABB>..<reserved-1FABF> 1FAC0..1FAC2 ; Extended_Pictographic# E13.0 [3] (🫀..🫂) anatomical heart..people hugging -1FAC3..1FACF ; Extended_Pictographic# E0.0 [13] (🫃..🫏) <reserved-1FAC3>..<reserved-1FACF> +1FAC3..1FAC5 ; Extended_Pictographic# E14.0 [3] (🫃..🫅) pregnant man..person with crown +1FAC6..1FACF ; Extended_Pictographic# E0.0 [10] (..🫏) <reserved-1FAC6>..<reserved-1FACF> 1FAD0..1FAD6 ; Extended_Pictographic# E13.0 [7] (🫐..🫖) blueberries..teapot -1FAD7..1FAFF ; Extended_Pictographic# E0.0 [41] (🫗..) <reserved-1FAD7>..<reserved-1FAFF> +1FAD7..1FAD9 ; Extended_Pictographic# E14.0 [3] (🫗..🫙) pouring liquid..jar +1FADA..1FADF ; Extended_Pictographic# E0.0 [6] (🫚..) <reserved-1FADA>..<reserved-1FADF> +1FAE0..1FAE7 ; Extended_Pictographic# E14.0 [8] (🫠..🫧) melting face..bubbles +1FAE8..1FAEF ; Extended_Pictographic# E0.0 [8] (🫨..) <reserved-1FAE8>..<reserved-1FAEF> +1FAF0..1FAF6 ; Extended_Pictographic# E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands +1FAF7..1FAFF ; Extended_Pictographic# E0.0 [9] (🫷..) <reserved-1FAF7>..<reserved-1FAFF> 1FC00..1FFFD ; Extended_Pictographic# E0.0[1022] (..) <reserved-1FC00>..<reserved-1FFFD> # Total elements: 3537 diff --git a/lib/unicore/extracted/DBidiClass.txt b/lib/unicore/extracted/DBidiClass.txt index 2454abd480..4012dc25da 100644 --- a/lib/unicore/extracted/DBidiClass.txt +++ b/lib/unicore/extracted/DBidiClass.txt @@ -1,6 +1,6 @@ -# DerivedBidiClass-13.0.0.txt -# Date: 2019-10-21, 14:30:28 GMT -# © 2019 Unicode®, Inc. +# DerivedBidiClass-14.0.0.txt +# Date: 2021-07-10, 00:35:02 GMT +# © 2021 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 # @@ -9,19 +9,19 @@ # ================================================ -# Bidi Class (listing UnicodeData.txt, field 4: see UAX #44: http://www.unicode.org/reports/tr44/) +# Bidi Class (listing UnicodeData.txt, field 4: see UAX #44: https://www.unicode.org/reports/tr44/) # Unlike other properties, unassigned code points in blocks # reserved for right-to-left scripts are given either types R or AL. # # The unassigned code points that default to AL are in the ranges: -# [\u0600-\u07BF \u0860-\u086F \u08A0-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF +# [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF # \U00010D00-\U00010D3F \U00010F30-\U00010F6F # \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF] # # This includes code points in the Arabic, Syriac, and Thaana blocks, among others. # # The unassigned code points that default to R are in the ranges: -# [\u0590-\u05FF \u07C0-\u085F \u0870-\u089F \uFB1D-\uFB4F +# [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F # \U00010800-\U00010CFF \U00010D40-\U00010F2F \U00010F70-\U00010FFF # \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF] # @@ -194,6 +194,7 @@ 0C3D ; L # Lo TELUGU SIGN AVAGRAHA 0C41..0C44 ; L # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C58..0C5A ; L # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; L # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; L # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; L # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C77 ; L # Po TELUGU SIGN SIDDHAM @@ -214,7 +215,7 @@ 0CC7..0CC8 ; L # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI 0CCA..0CCB ; L # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CD5..0CD6 ; L # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; L # Lo KANNADA LETTER FA +0CDD..0CDE ; L # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; L # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE6..0CEF ; L # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; L # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -351,9 +352,10 @@ 16EB..16ED ; L # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0 ; L # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; L # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; L # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; L # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; L # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; L # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +1715 ; L # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; L # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1734 ; L # Mc HANUNOO SIGN PAMUDPOD 1735..1736 ; L # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751 ; L # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; L # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -407,11 +409,12 @@ 1B3B ; L # Mc BALINESE VOWEL SIGN RA REPA TEDUNG 1B3D..1B41 ; L # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B43..1B44 ; L # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; L # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; L # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; L # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; L # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; L # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; L # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; L # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B82 ; L # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; L # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BA1 ; L # Mc SUNDANESE CONSONANT SIGN PAMINGKAL @@ -499,9 +502,7 @@ 249C..24E9 ; L # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z 26AC ; L # So MEDIUM SMALL WHITE CIRCLE 2800..28FF ; L # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678 -2C00..2C2E ; L # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; L # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; L # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; L # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; L # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; L # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; L # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -556,8 +557,7 @@ 337B..33DD ; L # So [99] SQUARE ERA NAME HEISEI..SQUARE WB 33E0..33FE ; L # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE 3400..4DBF ; L # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; L # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; L # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; L # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; L # Lm YI SYLLABLE WU A016..A48C ; L # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; L # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -581,8 +581,11 @@ A771..A787 ; L # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; L # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; L # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; L # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; L # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; L # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; L # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; L # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; L # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; L # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; L # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -731,14 +734,27 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 10500..10527 ; L # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; L # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; L # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; L # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; L # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; L # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; L # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; L # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; L # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; L # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; L # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; L # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; L # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; L # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; L # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; L # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; L # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 11000 ; L # Mc BRAHMI SIGN CANDRABINDU 11002 ; L # Mc BRAHMI SIGN VISARGA 11003..11037 ; L # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11047..1104D ; L # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11066..1106F ; L # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11071..11072 ; L # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; L # Lo BRAHMI LETTER OLD TAMIL LLA 11082 ; L # Mc KAITHI SIGN VISARGA 11083..110AF ; L # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; L # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II @@ -841,6 +857,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 116AE..116AF ; L # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II 116B6 ; L # Mc TAKRI SIGN VIRAMA 116B8 ; L # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; L # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; L # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A ; L # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 11720..11721 ; L # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA @@ -849,6 +866,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1173A..1173B ; L # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; L # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; L # So AHOM SYMBOL VI +11740..11746 ; L # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; L # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; L # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 11838 ; L # Mc DOGRA SIGN VISARGA @@ -891,7 +909,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 11A9A..11A9C ; L # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9D ; L # Lo SOYOMBO MARK PLUTA 11A9E..11AA2 ; L # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 -11AC0..11AF8 ; L # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; L # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; L # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; L # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; L # Mc BHAIKSUKI VOWEL SIGN AA @@ -929,6 +947,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 12400..1246E ; L # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; L # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 12480..12543 ; L # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; L # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; L # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E ; L # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 13430..13438 ; L # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT 14400..14646 ; L # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 @@ -936,6 +956,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16A40..16A5E ; L # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; L # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F ; L # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE ; L # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; L # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; L # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF5 ; L # Po BASSA VAH FULL STOP 16B00..16B2F ; L # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -961,7 +983,10 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 17000..187F7 ; L # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; L # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; L # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; L # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; L # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; L # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; L # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; L # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; L # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; L # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; L # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -971,6 +996,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1BC90..1BC99 ; L # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; L # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; L # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1CF50..1CFC3 ; L # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; L # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; L # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; L # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -1023,13 +1049,21 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1DA76..1DA83 ; L # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH 1DA85..1DA86 ; L # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS 1DA87..1DA8B ; L # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS +1DF00..1DF09 ; L # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; L # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; L # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; L # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; L # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; L # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; L # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; L # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; L # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; L # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2F0..1E2F9 ; L # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E7E0..1E7E6 ; L # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; L # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; L # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; L # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1F110..1F12E ; L # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ 1F130..1F169 ; L # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F1AC ; L # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD @@ -1037,8 +1071,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1F210..1F23B ; L # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; L # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; L # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -20000..2A6DD ; L # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; L # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; L # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; L # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; L # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; L # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; L # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 @@ -1047,8 +1081,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; L # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 826312 code points not listed here. -# Total code points: 1096473 +# The above property value applies to 825575 code points not listed here. +# Total code points: 1096333 # ================================================ @@ -1082,7 +1116,6 @@ F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 085C..085D ; R # Cn [2] <reserved-085C>..<reserved-085D> 085E ; R # Po MANDAIC PUNCTUATION 085F ; R # Cn <reserved-085F> -0870..089F ; R # Cn [48] <reserved-0870>..<reserved-089F> 200F ; R # Cf RIGHT-TO-LEFT MARK FB1D ; R # Lo HEBREW LETTER YOD WITH HIRIQ FB1F..FB28 ; R # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV @@ -1197,7 +1230,9 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 10F1D..10F26 ; R # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; R # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F28..10F2F ; R # Cn [8] <reserved-10F28>..<reserved-10F2F> -10F70..10FAF ; R # Cn [64] <reserved-10F70>..<reserved-10FAF> +10F70..10F81 ; R # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F86..10F89 ; R # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS +10F8A..10FAF ; R # Cn [38] <reserved-10F8A>..<reserved-10FAF> 10FB0..10FC4 ; R # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; R # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FCC..10FDF ; R # Cn [20] <reserved-10FCC>..<reserved-10FDF> @@ -1218,7 +1253,7 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1ED50..1EDFF ; R # Cn [176] <reserved-1ED50>..<reserved-1EDFF> 1EF00..1EFFF ; R # Cn [256] <reserved-1EF00>..<reserved-1EFFF> -# Total code points: 3763 +# Total code points: 3711 # ================================================ @@ -1277,8 +1312,8 @@ FF0D ; ES # Pd FULLWIDTH HYPHEN-MINUS 0E3F ; ET # Sc THAI CURRENCY SYMBOL BAHT 17DB ; ET # Sc KHMER CURRENCY SYMBOL RIEL 2030..2034 ; ET # Po [5] PER MILLE SIGN..TRIPLE PRIME -20A0..20BF ; ET # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN -20C0..20CF ; ET # Cn [16] <reserved-20C0>..<reserved-20CF> +20A0..20C0 ; ET # Sc [33] EURO-CURRENCY SIGN..SOM SIGN +20C1..20CF ; ET # Cn [15] <reserved-20C1>..<reserved-20CF> 212E ; ET # So ESTIMATED SYMBOL 2213 ; ET # Sm MINUS-OR-PLUS SIGN A838 ; ET # Sc NORTH INDIC RUPEE MARK @@ -1304,11 +1339,12 @@ FFE5..FFE6 ; ET # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 0660..0669 ; AN # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE 066B..066C ; AN # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR 06DD ; AN # Cf ARABIC END OF AYAH +0890..0891 ; AN # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; AN # Cf ARABIC DISPUTED END OF AYAH 10D30..10D39 ; AN # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE 10E60..10E7E ; AN # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS -# Total code points: 61 +# Total code points: 63 # ================================================ @@ -1663,7 +1699,16 @@ FF1A ; CS # Po FULLWIDTH COLON 2E42 ; ON # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; ON # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; ON # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; ON # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; ON # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; ON # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; ON # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; ON # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; ON # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; ON # Ps TOP HALF LEFT PARENTHESIS +2E5A ; ON # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; ON # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; ON # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; ON # Pd OBLIQUE HYPHEN 2E80..2E99 ; ON # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; ON # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; ON # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1725,7 +1770,9 @@ A874..A877 ; ON # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SH AB6A..AB6B ; ON # Sk [2] MODIFIER LETTER LEFT TACK..MODIFIER LETTER RIGHT TACK FD3E ; ON # Pe ORNATE LEFT PARENTHESIS FD3F ; ON # Ps ORNATE RIGHT PARENTHESIS -FDFD ; ON # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FD40..FD4F ; ON # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FDCF ; ON # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDFD..FDFF ; ON # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE10..FE16 ; ON # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; ON # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET FE18 ; ON # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET @@ -1815,6 +1862,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 11FD5..11FDC ; ON # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI 11FE1..11FF1 ; ON # So [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA 16FE2 ; ON # Po OLD CHINESE HOOK MARK +1D1E9..1D1EA ; ON # So [2] MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON 1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; ON # So GREEK MUSICAL LEIMMA 1D300..1D356 ; ON # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING @@ -1839,32 +1887,33 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F300..1F3FA ; ON # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; ON # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F400..1F6D7 ; ON # So [728] RAT..ELEVATOR -1F6E0..1F6EC ; ON # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DD..1F6EC ; ON # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6F0..1F6FC ; ON # So [13] SATELLITE..ROLLER SKATE 1F700..1F773 ; ON # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8 ; ON # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; ON # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; ON # So HEAVY EQUALS SIGN 1F800..1F80B ; ON # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; ON # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; ON # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; ON # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; ON # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; ON # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; ON # So [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; ON # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; ON # So [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; ON # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; ON # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74 ; ON # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; ON # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; ON # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; ON # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; ON # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; ON # So [7] FLY..FEATHER -1FAC0..1FAC2 ; ON # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; ON # So [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC ; ON # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; ON # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; ON # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; ON # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; ON # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; ON # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; ON # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 5931 +# Total code points: 6000 # ================================================ @@ -1939,7 +1988,8 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0825..0827 ; NSM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; NSM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; NSM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; NSM # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; NSM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; NSM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; NSM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; NSM # Mn DEVANAGARI VOWEL SIGN OE 093C ; NSM # Mn DEVANAGARI SIGN NUKTA @@ -1980,6 +2030,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0BCD ; NSM # Mn TAMIL SIGN VIRAMA 0C00 ; NSM # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; NSM # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; NSM # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; NSM # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; NSM # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; NSM # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -2027,7 +2078,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 109D ; NSM # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; NSM # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; NSM # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; NSM # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; NSM # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; NSM # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; NSM # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; NSM # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -2036,6 +2087,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 17C9..17D3 ; NSM # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; NSM # Mn KHMER SIGN ATTHACAN 180B..180D ; NSM # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; NSM # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; NSM # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; NSM # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; NSM # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -2053,7 +2105,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 1A7F ; NSM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; NSM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; NSM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; NSM # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; NSM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; NSM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; NSM # Mn BALINESE SIGN REREKAN 1B36..1B3A ; NSM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2076,8 +2128,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 1CED ; NSM # Mn VEDIC SIGN TIRYAK 1CF4 ; NSM # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; NSM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; NSM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; NSM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; NSM # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; NSM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; NSM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; NSM # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -2139,11 +2190,15 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 10D24..10D27 ; NSM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; NSM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; NSM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; NSM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; NSM # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; NSM # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; NSM # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; NSM # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; NSM # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; NSM # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; NSM # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; NSM # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; NSM # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; NSM # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; NSM # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -2223,6 +2278,8 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 16F8F..16F92 ; NSM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; NSM # Mn KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; NSM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; NSM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; NSM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; NSM # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D17B..1D182 ; NSM # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; NSM # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE @@ -2240,12 +2297,13 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E023..1E024 ; NSM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; NSM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; NSM # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; NSM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; NSM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; NSM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1847 +# Total code points: 1958 # ================================================ @@ -2256,8 +2314,7 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 060D ; AL # Po ARABIC DATE SEPARATOR 061B ; AL # Po ARABIC SEMICOLON 061C ; AL # Cf ARABIC LETTER MARK -061D ; AL # Cn <reserved-061D> -061E..061F ; AL # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; AL # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F ; AL # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; AL # Lm ARABIC TATWEEL 0641..064A ; AL # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -2282,22 +2339,23 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 07B2..07BF ; AL # Cn [14] <reserved-07B2>..<reserved-07BF> 0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 086B..086F ; AL # Cn [5] <reserved-086B>..<reserved-086F> -08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B5 ; AL # Cn <reserved-08B5> -08B6..08C7 ; AL # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08C8..08D2 ; AL # Cn [11] <reserved-08C8>..<reserved-08D2> +0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; AL # Sk ARABIC RAISED ROUND DOT +0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +088F ; AL # Cn <reserved-088F> +0892..0897 ; AL # Cn [6] <reserved-0892>..<reserved-0897> +08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; AL # Lm ARABIC SMALL FARSI YEH FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; AL # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW -FBC2..FBD2 ; AL # Cn [17] <reserved-FBC2>..<reserved-FBD2> +FBB2..FBC2 ; AL # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; AL # Cn [16] <reserved-FBC3>..<reserved-FBD2> FBD3..FD3D ; AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM -FD40..FD4F ; AL # Cn [16] <reserved-FD40>..<reserved-FD4F> FD50..FD8F ; AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD90..FD91 ; AL # Cn [2] <reserved-FD90>..<reserved-FD91> FD92..FDC7 ; AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDC8..FDCF ; AL # Cn [8] <reserved-FDC8>..<reserved-FDCF> +FDC8..FDCE ; AL # Cn [7] <reserved-FDC8>..<reserved-FDCE> FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; AL # Sc RIAL SIGN -FDFE..FDFF ; AL # Cn [2] <reserved-FDFE>..<reserved-FDFF> FE70..FE74 ; AL # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM FE75 ; AL # Cn <reserved-FE75> FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM @@ -2389,7 +2447,7 @@ FEFD..FEFE ; AL # Cn [2] <reserved-FEFD>..<reserved-FEFE> 1EEBC..1EEEF ; AL # Cn [52] <reserved-1EEBC>..<reserved-1EEEF> 1EEF2..1EEFF ; AL # Cn [14] <reserved-1EEF2>..<reserved-1EEFF> -# Total code points: 1698 +# Total code points: 1708 # ================================================ diff --git a/lib/unicore/extracted/DBinaryProperties.txt b/lib/unicore/extracted/DBinaryProperties.txt index 4c31bac119..60409c05ba 100644 --- a/lib/unicore/extracted/DBinaryProperties.txt +++ b/lib/unicore/extracted/DBinaryProperties.txt @@ -1,6 +1,6 @@ -# DerivedBinaryProperties-13.0.0.txt -# Date: 2019-09-08, 23:31:04 GMT -# © 2019 Unicode®, Inc. +# DerivedBinaryProperties-14.0.0.txt +# Date: 2021-06-04, 02:19:15 GMT +# © 2021 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 # @@ -9,7 +9,7 @@ # ================================================ -# Bidi_Mirrored (listing UnicodeData.txt, field 9: see UAX #44: http://www.unicode.org/reports/tr44/) +# Bidi_Mirrored (listing UnicodeData.txt, field 9: see UAX #44: https://www.unicode.org/reports/tr44/) 0028 ; Bidi_Mirrored # Ps LEFT PARENTHESIS 0029 ; Bidi_Mirrored # Pe RIGHT PARENTHESIS @@ -185,6 +185,14 @@ 2E27 ; Bidi_Mirrored # Pe RIGHT SIDEWAYS U BRACKET 2E28 ; Bidi_Mirrored # Ps LEFT DOUBLE PARENTHESIS 2E29 ; Bidi_Mirrored # Pe RIGHT DOUBLE PARENTHESIS +2E55 ; Bidi_Mirrored # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Bidi_Mirrored # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Bidi_Mirrored # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Bidi_Mirrored # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Bidi_Mirrored # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Bidi_Mirrored # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Bidi_Mirrored # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Bidi_Mirrored # Pe BOTTOM HALF RIGHT PARENTHESIS 3008 ; Bidi_Mirrored # Ps LEFT ANGLE BRACKET 3009 ; Bidi_Mirrored # Pe RIGHT ANGLE BRACKET 300A ; Bidi_Mirrored # Ps LEFT DOUBLE ANGLE BRACKET @@ -228,6 +236,6 @@ FF63 ; Bidi_Mirrored # Pe HALFWIDTH RIGHT CORNER BRACKET 1D789 ; Bidi_Mirrored # Sm MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL 1D7C3 ; Bidi_Mirrored # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL -# Total code points: 545 +# Total code points: 553 # EOF diff --git a/lib/unicore/extracted/DCombiningClass.txt b/lib/unicore/extracted/DCombiningClass.txt index b4c75cd459..4ad8205790 100644 --- a/lib/unicore/extracted/DCombiningClass.txt +++ b/lib/unicore/extracted/DCombiningClass.txt @@ -1,6 +1,6 @@ -# DerivedCombiningClass-13.0.0.txt -# Date: 2019-11-13, 21:51:57 GMT -# © 2019 Unicode®, Inc. +# DerivedCombiningClass-14.0.0.txt +# Date: 2021-07-10, 00:35:05 GMT +# © 2021 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 # @@ -9,7 +9,7 @@ # ================================================ -# Combining Class (listing UnicodeData.txt, field 3: see UAX #44: http://www.unicode.org/reports/tr44/) +# Combining Class (listing UnicodeData.txt, field 3: see UAX #44: https://www.unicode.org/reports/tr44/) # All code points not explicitly listed for Canonical_Combining_Class # have the value Not_Reordered (0). @@ -139,7 +139,7 @@ 060E..060F ; 0 # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 061B ; 0 # Po ARABIC SEMICOLON 061C ; 0 # Cf ARABIC LETTER MARK -061E..061F ; 0 # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; 0 # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F ; 0 # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; 0 # Lm ARABIC TATWEEL 0641..064A ; 0 # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -180,8 +180,12 @@ 0840..0858 ; 0 # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; 0 # Po MANDAIC PUNCTUATION 0860..086A ; 0 # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; 0 # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; 0 # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; 0 # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; 0 # Sk ARABIC RAISED ROUND DOT +0889..088E ; 0 # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891 ; 0 # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +08A0..08C8 ; 0 # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; 0 # Lm ARABIC SMALL FARSI YEH 08E2 ; 0 # Cf ARABIC DISPUTED END OF AYAH 0900..0902 ; 0 # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0903 ; 0 # Mc DEVANAGARI SIGN VISARGA @@ -331,6 +335,7 @@ 0C46..0C48 ; 0 # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4C ; 0 # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C58..0C5A ; 0 # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; 0 # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; 0 # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; 0 # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; 0 # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -355,7 +360,7 @@ 0CCA..0CCB ; 0 # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; 0 # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; 0 # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; 0 # Lo KANNADA LETTER FA +0CDD..0CDE ; 0 # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; 0 # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; 0 # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; 0 # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -532,10 +537,9 @@ 16EB..16ED ; 0 # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0 ; 0 # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; 0 # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; 0 # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; 0 # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; 0 # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1713 ; 0 # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U -1720..1731 ; 0 # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +171F..1731 ; 0 # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1732..1733 ; 0 # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1735..1736 ; 0 # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751 ; 0 # Lo [18] BUHID LETTER A..BUHID LETTER HA @@ -564,6 +568,7 @@ 1807..180A ; 0 # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; 0 # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; 0 # Cf MONGOLIAN VOWEL SEPARATOR +180F ; 0 # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; 0 # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; 0 # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; 0 # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -622,11 +627,12 @@ 1B3D..1B41 ; 0 # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; 0 # Mn BALINESE VOWEL SIGN PEPET 1B43 ; 0 # Mc BALINESE VOWEL SIGN PEPET TEDUNG -1B45..1B4B ; 0 # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; 0 # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; 0 # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; 0 # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; 0 # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; 0 # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; 0 # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B80..1B81 ; 0 # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; 0 # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; 0 # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -744,7 +750,7 @@ 208D ; 0 # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; 0 # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; 0 # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BF ; 0 # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; 0 # Sc [33] EURO-CURRENCY SIGN..SOM SIGN 20DD..20E0 ; 0 # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E2..20E4 ; 0 # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE 2100..2101 ; 0 # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT @@ -905,9 +911,7 @@ 2B4D..2B73 ; 0 # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95 ; 0 # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF ; 0 # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -2C00..2C2E ; 0 # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; 0 # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; 0 # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; 0 # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; 0 # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; 0 # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CE5..2CEA ; 0 # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA @@ -970,7 +974,16 @@ 2E42 ; 0 # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; 0 # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; 0 # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; 0 # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; 0 # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; 0 # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; 0 # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; 0 # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; 0 # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; 0 # Ps TOP HALF LEFT PARENTHESIS +2E5A ; 0 # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; 0 # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; 0 # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; 0 # Pd OBLIQUE HYPHEN 2E80..2E99 ; 0 # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; 0 # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; 0 # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1043,8 +1056,7 @@ 32C0..33FF ; 0 # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL 3400..4DBF ; 0 # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF 4DC0..4DFF ; 0 # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FFC ; 0 # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; 0 # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; 0 # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; 0 # Lm YI SYLLABLE WU A016..A48C ; 0 # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; 0 # So [55] YI RADICAL QOT..YI RADICAL KE @@ -1078,8 +1090,11 @@ A788 ; 0 # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; 0 # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; 0 # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; 0 # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; 0 # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; 0 # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; 0 # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; 0 # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; 0 # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; 0 # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; 0 # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; 0 # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; 0 # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1215,15 +1230,17 @@ FB3E ; 0 # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; 0 # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; 0 # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; 0 # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; 0 # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; 0 # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; 0 # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; 0 # Pe ORNATE LEFT PARENTHESIS FD3F ; 0 # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F ; 0 # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; 0 # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; 0 # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; 0 # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; 0 # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; 0 # Sc RIAL SIGN -FDFD ; 0 # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; 0 # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F ; 0 # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE10..FE16 ; 0 # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; 0 # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET @@ -1365,9 +1382,20 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10500..10527 ; 0 # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; 0 # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; 0 # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; 0 # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; 0 # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; 0 # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; 0 # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; 0 # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; 0 # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; 0 # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; 0 # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; 0 # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; 0 # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; 0 # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; 0 # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; 0 # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; 0 # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; 0 # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; 0 # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; 0 # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1439,6 +1467,8 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10F30..10F45 ; 0 # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; 0 # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; 0 # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81 ; 0 # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F86..10F89 ; 0 # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4 ; 0 # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; 0 # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6 ; 0 # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -1450,6 +1480,9 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11047..1104D ; 0 # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; 0 # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; 0 # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11071..11072 ; 0 # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; 0 # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; 0 # Lo BRAHMI LETTER OLD TAMIL LLA 11080..11081 ; 0 # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11082 ; 0 # Mc KAITHI SIGN VISARGA 11083..110AF ; 0 # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -1459,6 +1492,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 110BB..110BC ; 0 # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD ; 0 # Cf KAITHI NUMBER SIGN 110BE..110C1 ; 0 # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110C2 ; 0 # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; 0 # Cf KAITHI NUMBER SIGN ABOVE 110D0..110E8 ; 0 # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; 0 # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -1582,6 +1616,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 116AE..116AF ; 0 # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II 116B0..116B5 ; 0 # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU 116B8 ; 0 # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; 0 # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; 0 # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A ; 0 # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F ; 0 # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA @@ -1593,6 +1628,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1173A..1173B ; 0 # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; 0 # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; 0 # So AHOM SYMBOL VI +11740..11746 ; 0 # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; 0 # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; 0 # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; 0 # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -1645,7 +1681,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11A9A..11A9C ; 0 # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9D ; 0 # Lo SOYOMBO MARK PLUTA 11A9E..11AA2 ; 0 # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 -11AC0..11AF8 ; 0 # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; 0 # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; 0 # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; 0 # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; 0 # Mc BHAIKSUKI VOWEL SIGN AA @@ -1700,6 +1736,8 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 12400..1246E ; 0 # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; 0 # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 12480..12543 ; 0 # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; 0 # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; 0 # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E ; 0 # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 13430..13438 ; 0 # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT 14400..14646 ; 0 # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 @@ -1707,6 +1745,8 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16A40..16A5E ; 0 # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; 0 # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F ; 0 # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE ; 0 # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; 0 # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; 0 # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF5 ; 0 # Po BASSA VAH FULL STOP 16B00..16B2F ; 0 # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -1735,7 +1775,10 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 17000..187F7 ; 0 # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; 0 # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; 0 # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; 0 # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; 0 # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; 0 # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; 0 # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; 0 # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; 0 # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; 0 # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; 0 # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -1747,6 +1790,9 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1BC9D ; 0 # Mn DUPLOYAN THICK LETTER SELECTOR 1BC9F ; 0 # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; 0 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; 0 # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; 0 # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF50..1CFC3 ; 0 # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; 0 # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; 0 # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; 0 # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -1754,7 +1800,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1D173..1D17A ; 0 # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D183..1D184 ; 0 # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; 0 # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; 0 # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; 0 # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; 0 # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; 0 # So GREEK MUSICAL LEIMMA 1D2E0..1D2F3 ; 0 # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN @@ -1813,14 +1859,22 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1DA87..1DA8B ; 0 # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1DA9B..1DA9F ; 0 # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; 0 # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; 0 # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; 0 # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; 0 # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; 0 # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; 0 # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; 0 # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; 0 # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; 0 # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; 0 # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; 0 # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2F0..1E2F9 ; 0 # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF ; 0 # Sc WANCHO NGUN SIGN +1E7E0..1E7E6 ; 0 # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; 0 # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; 0 # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; 0 # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; 0 # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; 0 # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E900..1E943 ; 0 # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -1885,33 +1939,34 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F300..1F3FA ; 0 # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; 0 # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F400..1F6D7 ; 0 # So [728] RAT..ELEVATOR -1F6E0..1F6EC ; 0 # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DD..1F6EC ; 0 # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6F0..1F6FC ; 0 # So [13] SATELLITE..ROLLER SKATE 1F700..1F773 ; 0 # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8 ; 0 # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; 0 # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; 0 # So HEAVY EQUALS SIGN 1F800..1F80B ; 0 # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; 0 # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; 0 # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; 0 # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; 0 # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; 0 # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; 0 # So [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; 0 # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; 0 # So [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; 0 # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; 0 # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74 ; 0 # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; 0 # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; 0 # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; 0 # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; 0 # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; 0 # So [7] FLY..FEATHER -1FAC0..1FAC2 ; 0 # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; 0 # So [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC ; 0 # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; 0 # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; 0 # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; 0 # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; 0 # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; 0 # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; 0 # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; 0 # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; 0 # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; 0 # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; 0 # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; 0 # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; 0 # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; 0 # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; 0 # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; 0 # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 @@ -1923,8 +1978,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; 0 # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 832720 code points not listed here. -# Total code points: 1113240 +# The above property value applies to 831882 code points not listed here. +# Total code points: 1113200 # ================================================ @@ -1961,6 +2016,7 @@ F0000..FFFFD ; 0 # Co [65534] <private-use-F0000>..<private-use-FFFFD> 0A3C ; 7 # Mn GURMUKHI SIGN NUKTA 0ABC ; 7 # Mn GUJARATI SIGN NUKTA 0B3C ; 7 # Mn ORIYA SIGN NUKTA +0C3C ; 7 # Mn TELUGU SIGN NUKTA 0CBC ; 7 # Mn KANNADA SIGN NUKTA 1037 ; 7 # Mn MYANMAR SIGN DOT BELOW 1B34 ; 7 # Mn BALINESE SIGN REREKAN @@ -1982,7 +2038,7 @@ A9B3 ; 7 # Mn JAVANESE SIGN CECAK TELU 11D42 ; 7 # Mn MASARAM GONDI SIGN NUKTA 1E94A ; 7 # Mn ADLAM NUKTA -# Total code points: 26 +# Total code points: 27 # ================================================ @@ -2012,7 +2068,8 @@ A9B3 ; 7 # Mn JAVANESE SIGN CECAK TELU 0F84 ; 9 # Mn TIBETAN MARK HALANTA 1039..103A ; 9 # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT 1714 ; 9 # Mn TAGALOG SIGN VIRAMA -1734 ; 9 # Mn HANUNOO SIGN PAMUDPOD +1715 ; 9 # Mc TAGALOG SIGN PAMUDPOD +1734 ; 9 # Mc HANUNOO SIGN PAMUDPOD 17D2 ; 9 # Mn KHMER SIGN COENG 1A60 ; 9 # Mn TAI THAM SIGN SAKOT 1B44 ; 9 # Mc BALINESE ADEG ADEG @@ -2029,6 +2086,7 @@ AAF6 ; 9 # Mn MEETEI MAYEK VIRAMA ABED ; 9 # Mn MEETEI MAYEK APUN IYEK 10A3F ; 9 # Mn KHAROSHTHI VIRAMA 11046 ; 9 # Mn BRAHMI VIRAMA +11070 ; 9 # Mn BRAHMI SIGN OLD TAMIL VIRAMA 1107F ; 9 # Mn BRAHMI NUMBER JOINER 110B9 ; 9 # Mn KAITHI SIGN VIRAMA 11133..11134 ; 9 # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA @@ -2053,7 +2111,7 @@ ABED ; 9 # Mn MEETEI MAYEK APUN IYEK 11D44..11D45 ; 9 # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA 11D97 ; 9 # Mn GUNJALA GONDI VIRAMA -# Total code points: 61 +# Total code points: 63 # ================================================ @@ -2385,9 +2443,10 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA # Canonical_Combining_Class=Below_Left +1DFA ; 218 # Mn COMBINING DOT BELOW LEFT 302A ; 218 # Mn IDEOGRAPHIC LEVEL TONE MARK -# Total code points: 1 +# Total code points: 2 # ================================================ @@ -2426,7 +2485,8 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA 07F2 ; 220 # Mn NKO COMBINING NASALIZATION MARK 07FD ; 220 # Mn NKO DANTAYALAN 0859..085B ; 220 # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3 ; 220 # Mn ARABIC SMALL LOW WAW +0899..089B ; 220 # Mn [3] ARABIC SMALL LOW WORD ISHMAAM..ARABIC SMALL LOW WORD TASHEEL +08CF..08D3 ; 220 # Mn [5] ARABIC LARGE ROUND DOT BELOW..ARABIC SMALL LOW WAW 08E3 ; 220 # Mn ARABIC TURNED DAMMA BELOW 08E6 ; 220 # Mn ARABIC CURLY KASRA 08E9 ; 220 # Mn ARABIC CURLY KASRATAN @@ -2445,6 +2505,8 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1AB5..1ABA ; 220 # Mn [6] COMBINING X-X BELOW..COMBINING STRONG CENTRALIZATION STROKE BELOW 1ABD ; 220 # Mn COMBINING PARENTHESES BELOW 1ABF..1AC0 ; 220 # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1AC3..1AC4 ; 220 # Mn [2] COMBINING LEFT PARENTHESIS BELOW LEFT..COMBINING RIGHT PARENTHESIS BELOW RIGHT +1ACA ; 220 # Mn COMBINING DOUBLE PLUS SIGN BELOW 1B6C ; 220 # Mn BALINESE MUSICAL SYMBOL COMBINING ENDEP 1CD5..1CD9 ; 220 # Mn [5] VEDIC TONE YAJURVEDIC AGGRAVATED INDEPENDENT SVARITA..VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER 1CDC..1CDF ; 220 # Mn [4] VEDIC TONE KATHAKA ANUDATTA..VEDIC TONE THREE DOTS BELOW @@ -2468,11 +2530,13 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 10F46..10F47 ; 220 # Mn [2] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING TWO DOTS BELOW 10F4B ; 220 # Mn SOGDIAN COMBINING CURVE BELOW 10F4D..10F50 ; 220 # Mn [4] SOGDIAN COMBINING HOOK BELOW..SOGDIAN COMBINING STROKE BELOW +10F83 ; 220 # Mn OLD UYGHUR COMBINING DOT BELOW +10F85 ; 220 # Mn OLD UYGHUR COMBINING TWO DOTS BELOW 1D17B..1D182 ; 220 # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D18A..1D18B ; 220 # Mn [2] MUSICAL SYMBOL COMBINING DOUBLE TONGUE..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 165 +# Total code points: 177 # ================================================ @@ -2557,6 +2621,9 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 081B..0823 ; 230 # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; 230 # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; 230 # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0898 ; 230 # Mn ARABIC SMALL HIGH WORD AL-JUZ +089C..089F ; 230 # Mn [4] ARABIC MADDA WAAJIB..ARABIC HALF MADDA OVER MADDA +08CA..08CE ; 230 # Mn [5] ARABIC SMALL HIGH FARSI YEH..ARABIC LARGE ROUND DOT ABOVE 08D4..08E1 ; 230 # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E4..08E5 ; 230 # Mn [2] ARABIC CURLY FATHA..ARABIC CURLY DAMMA 08E7..08E8 ; 230 # Mn [2] ARABIC CURLY FATHATAN..ARABIC CURLY DAMMATAN @@ -2576,6 +2643,9 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1A75..1A7C ; 230 # Mn [8] TAI THAM SIGN TONE-1..TAI THAM SIGN KHUEN-LUE KARAN 1AB0..1AB4 ; 230 # Mn [5] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING TRIPLE DOT 1ABB..1ABC ; 230 # Mn [2] COMBINING PARENTHESES ABOVE..COMBINING DOUBLE PARENTHESES ABOVE +1AC1..1AC2 ; 230 # Mn [2] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING RIGHT PARENTHESIS ABOVE RIGHT +1AC5..1AC9 ; 230 # Mn [5] COMBINING SQUARE BRACKETS ABOVE..COMBINING DOUBLE PLUS SIGN ABOVE +1ACB..1ACE ; 230 # Mn [4] COMBINING TRIPLE ACUTE ACCENT..COMBINING LATIN SMALL LETTER INSULAR T 1B6B ; 230 # Mn BALINESE MUSICAL SYMBOL COMBINING TEGEH 1B6D..1B73 ; 230 # Mn [7] BALINESE MUSICAL SYMBOL COMBINING KEMPUL..BALINESE MUSICAL SYMBOL COMBINING GONG 1CD0..1CD2 ; 230 # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA @@ -2618,6 +2688,8 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 10EAB..10EAC ; 230 # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F48..10F4A ; 230 # Mn [3] SOGDIAN COMBINING DOT ABOVE..SOGDIAN COMBINING CURVE ABOVE 10F4C ; 230 # Mn SOGDIAN COMBINING HOOK ABOVE +10F82 ; 230 # Mn OLD UYGHUR COMBINING DOT ABOVE +10F84 ; 230 # Mn OLD UYGHUR COMBINING TWO DOTS ABOVE 11100..11102 ; 230 # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11366..1136C ; 230 # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; 230 # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA @@ -2632,10 +2704,11 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E023..1E024 ; 230 # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; 230 # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; 230 # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; 230 # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; 230 # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 484 +# Total code points: 508 # ================================================ diff --git a/lib/unicore/extracted/DDecompositionType.txt b/lib/unicore/extracted/DDecompositionType.txt index a0bc563643..5af556b0d4 100644 --- a/lib/unicore/extracted/DDecompositionType.txt +++ b/lib/unicore/extracted/DDecompositionType.txt @@ -1,6 +1,6 @@ -# DerivedDecompositionType-13.0.0.txt -# Date: 2019-09-08, 23:31:06 GMT -# © 2019 Unicode®, Inc. +# DerivedDecompositionType-14.0.0.txt +# Date: 2021-06-04, 02:19:17 GMT +# © 2021 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 # @@ -9,7 +9,7 @@ # ================================================ -# Decomposition_Type (from UnicodeData.txt, field 5: see UAX #44: http://www.unicode.org/reports/tr44/) +# Decomposition_Type (from UnicodeData.txt, field 5: see UAX #44: https://www.unicode.org/reports/tr44/) # All code points not explicitly listed for Decomposition_Type # have the value None. @@ -861,12 +861,16 @@ FEFB ; Isolated # Lo ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM 3196..319F ; Super # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK A69C..A69D ; Super # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; Super # Lm MODIFIER LETTER US +A7F2..A7F4 ; Super # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Super # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Super # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; Super # Lm MODIFIER LETTER SMALL TURNED W +10781..10785 ; Super # Lm [5] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Super # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Super # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1F16A..1F16C ; Super # So [3] RAISED MC SIGN..RAISED MR SIGN -# Total code points: 154 +# Total code points: 213 # ================================================ diff --git a/lib/unicore/extracted/DEastAsianWidth.txt b/lib/unicore/extracted/DEastAsianWidth.txt index 79fe3ebec5..6bc84ff98d 100644 --- a/lib/unicore/extracted/DEastAsianWidth.txt +++ b/lib/unicore/extracted/DEastAsianWidth.txt @@ -1,6 +1,6 @@ -# DerivedEastAsianWidth-13.0.0.txt -# Date: 2019-10-21, 14:30:31 GMT -# © 2019 Unicode®, Inc. +# DerivedEastAsianWidth-14.0.0.txt +# Date: 2021-07-10, 00:35:07 GMT +# © 2021 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 # @@ -143,7 +143,7 @@ 0610..061A ; N # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 061B ; N # Po ARABIC SEMICOLON 061C ; N # Cf ARABIC LETTER MARK -061E..061F ; N # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; N # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F ; N # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; N # Lm ARABIC TATWEEL 0641..064A ; N # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -199,9 +199,14 @@ 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..08C7 ; N # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; N # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; N # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; N # Sk ARABIC RAISED ROUND DOT +0889..088E ; N # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891 ; N # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; N # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; N # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; N # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; N # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; N # Cf ARABIC DISPUTED END OF AYAH 08E3..0902 ; N # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; N # Mc DEVANAGARI SIGN VISARGA @@ -356,6 +361,7 @@ 0C0E..0C10 ; N # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; N # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; N # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; N # Mn TELUGU SIGN NUKTA 0C3D ; N # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; N # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; N # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -363,6 +369,7 @@ 0C4A..0C4D ; N # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; N # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; N # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; N # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; N # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; N # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -388,7 +395,7 @@ 0CCA..0CCB ; N # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; N # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; N # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; N # Lo KANNADA LETTER FA +0CDD..0CDE ; N # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; N # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 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 @@ -573,11 +580,12 @@ 16EB..16ED ; N # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0 ; N # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; N # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; N # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; N # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; N # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; N # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; N # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; N # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; N # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; N # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; N # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; N # Mc HANUNOO SIGN PAMUDPOD 1735..1736 ; N # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751 ; N # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; N # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -605,6 +613,7 @@ 1807..180A ; N # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; N # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; N # Cf MONGOLIAN VOWEL SEPARATOR +180F ; N # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; N # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; N # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; N # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -659,7 +668,7 @@ 1AA8..1AAD ; N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; N # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; N # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -671,12 +680,13 @@ 1B3D..1B41 ; N # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; N # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; N # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; N # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; N # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; N # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; N # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; N # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73 ; N # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C ; N # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; N # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B80..1B81 ; N # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; N # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; N # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -733,8 +743,7 @@ 1D78 ; N # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; N # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; N # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -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 +1DC0..1DFF ; N # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; N # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; N # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; N # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -806,7 +815,7 @@ 2090..209C ; N # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T 20A0..20A8 ; N # Sc [9] EURO-CURRENCY SIGN..RUPEE SIGN 20AA..20AB ; N # Sc [2] NEW SHEQEL SIGN..DONG SIGN -20AD..20BF ; N # Sc [19] KIP SIGN..BITCOIN SIGN +20AD..20C0 ; N # Sc [20] KIP SIGN..SOM 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 @@ -1036,9 +1045,7 @@ 2B5A..2B73 ; N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95 ; N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF ; N # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -2C00..2C2E ; N # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; N # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; N # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; N # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; N # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; N # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CE5..2CEA ; N # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA @@ -1104,7 +1111,16 @@ 2E42 ; N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; N # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; N # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; N # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; N # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; N # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; N # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; N # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; N # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; N # Ps TOP HALF LEFT PARENTHESIS +2E5A ; N # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; N # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; N # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; N # Pd OBLIQUE HYPHEN 303F ; N # So IDEOGRAPHIC HALF FILL SPACE 4DC0..4DFF ; N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION A4D0..A4F7 ; N # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -1141,8 +1157,11 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; N # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; N # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; N # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; N # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; N # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1285,15 +1304,17 @@ FB3E ; N # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; N # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; N # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; N # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; N # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; N # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; N # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; N # Pe ORNATE LEFT PARENTHESIS FD3F ; N # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F ; N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; N # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; N # Sc RIAL SIGN -FDFD ; N # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; N # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE20..FE2F ; N # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF FE70..FE74 ; N # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM FE76..FEFC ; N # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM @@ -1345,9 +1366,20 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10500..10527 ; N # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; N # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; N # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; N # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; N # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; N # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; N # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; N # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; N # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; N # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; N # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; N # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; N # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; N # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; N # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; N # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; N # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; N # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; N # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; N # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1424,6 +1456,9 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10F46..10F50 ; N # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F51..10F54 ; N # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; N # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81 ; N # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; N # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +10F86..10F89 ; N # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4 ; N # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; N # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6 ; N # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -1435,6 +1470,10 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11047..1104D ; N # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; N # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; N # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; N # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; N # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; N # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; N # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; N # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; N # Mc KAITHI SIGN VISARGA 11083..110AF ; N # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -1445,6 +1484,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 110BB..110BC ; N # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD ; N # Cf KAITHI NUMBER SIGN 110BE..110C1 ; N # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +110C2 ; N # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; N # Cf KAITHI NUMBER SIGN ABOVE 110D0..110E8 ; N # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; N # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -1579,6 +1619,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 116B6 ; N # Mc TAKRI SIGN VIRAMA 116B7 ; N # Mn TAKRI SIGN NUKTA 116B8 ; N # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; N # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; N # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A ; N # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F ; N # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA @@ -1590,6 +1631,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1173A..1173B ; N # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; N # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; N # So AHOM SYMBOL VI +11740..11746 ; N # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; N # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; N # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; N # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -1647,7 +1689,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11A9A..11A9C ; N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9D ; N # Lo SOYOMBO MARK PLUTA 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 +11AB0..11AF8 ; N # Lo [73] CANADIAN SYLLABICS NATTILIK HI..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 11C2F ; N # Mc BHAIKSUKI VOWEL SIGN AA @@ -1703,6 +1745,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 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 12480..12543 ; N # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; N # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; N # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E ; N # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 13430..13438 ; N # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT 14400..14646 ; N # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 @@ -1710,6 +1754,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 16A40..16A5E ; N # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; N # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F ; N # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE ; N # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; N # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; N # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; N # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16AF5 ; N # Po BASSA VAH FULL STOP @@ -1741,6 +1787,9 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1BC9D..1BC9E ; N # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; N # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; N # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; N # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; N # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -1754,7 +1803,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1D185..1D18B ; N # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D18C..1D1A9 ; N # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH 1D1AA..1D1AD ; N # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO -1D1AE..1D1E8 ; N # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; N # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; N # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D242..1D244 ; N # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME 1D245 ; N # So GREEK MUSICAL LEIMMA @@ -1814,6 +1863,9 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1DA87..1DA8B ; N # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1DA9B..1DA9F ; N # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; N # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; N # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; N # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; N # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -1825,10 +1877,16 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1E140..1E149 ; N # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; N # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; N # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; N # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; N # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; N # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; N # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; N # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF ; N # Sc WANCHO NGUN SIGN +1E7E0..1E7E6 ; N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; N # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; N # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; N # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6 ; N # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS @@ -1934,8 +1992,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 767414 code points not listed here. -# Total code points: 792699 +# The above property value applies to 766585 code points not listed here. +# Total code points: 792645 # ================================================ @@ -2278,9 +2336,7 @@ FFED..FFEE ; H # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 32B1..32BF ; W # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY 32C0..33FF ; W # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL 3400..4DBF ; W # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; W # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -9FFD..9FFF ; W # Cn [3] <reserved-9FFD>..<reserved-9FFF> -A000..A014 ; W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; W # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; W # Lm YI SYLLABLE WU A016..A48C ; W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; W # So [55] YI RADICAL QOT..YI RADICAL KE @@ -2342,7 +2398,10 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 17000..187F7 ; W # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; W # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; W # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; W # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; W # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; W # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; W # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -2379,25 +2438,27 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 1F6CC ; W # So SLEEPING ACCOMMODATION 1F6D0..1F6D2 ; W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY 1F6D5..1F6D7 ; W # So [3] HINDU TEMPLE..ELEVATOR +1F6DD..1F6DF ; W # So [3] PLAYGROUND SLIDE..RING BUOY 1F6EB..1F6EC ; W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING 1F6F4..1F6FC ; W # So [9] SCOOTER..ROLLER SKATE 1F7E0..1F7EB ; W # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; W # So HEAVY EQUALS SIGN 1F90C..1F93A ; W # So [47] PINCHED FINGERS..FENCER 1F93C..1F945 ; W # So [10] WRESTLERS..GOAL NET -1F947..1F978 ; W # So [50] FIRST PLACE MEDAL..DISGUISED FACE -1F97A..1F9CB ; W # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1F9FF ; W # So [51] STANDING PERSON..NAZAR AMULET +1F947..1F9FF ; W # So [185] FIRST PLACE MEDAL..NAZAR AMULET 1FA70..1FA74 ; W # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; W # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; W # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; W # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; W # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; W # So [7] FLY..FEATHER -1FAC0..1FAC2 ; W # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; W # So [7] BLUEBERRIES..TEAPOT -20000..2A6DD ; W # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF ; W # Cn [34] <reserved-2A6DE>..<reserved-2A6FF> -2A700..2B734 ; W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F ; W # Cn [11] <reserved-2B735>..<reserved-2B73F> +1FA90..1FAAC ; W # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; W # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; W # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; W # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; W # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; W # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS +20000..2A6DF ; W # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF ; W # Cn [32] <reserved-2A6E0>..<reserved-2A6FF> +2A700..2B738 ; W # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F ; W # Cn [7] <reserved-2B739>..<reserved-2B73F> 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 @@ -2409,7 +2470,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 30000..3134A ; W # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 3134B..3FFFD ; W # Cn [60595] <reserved-3134B>..<reserved-3FFFD> -# Total code points: 182336 +# Total code points: 182390 # ================================================ diff --git a/lib/unicore/extracted/DGeneralCategory.txt b/lib/unicore/extracted/DGeneralCategory.txt index 3e82c7fc53..a36d42a3e8 100644 --- a/lib/unicore/extracted/DGeneralCategory.txt +++ b/lib/unicore/extracted/DGeneralCategory.txt @@ -1,6 +1,6 @@ -# DerivedGeneralCategory-13.0.0.txt -# Date: 2019-10-21, 14:30:32 GMT -# © 2019 Unicode®, Inc. +# DerivedGeneralCategory-14.0.0.txt +# Date: 2021-07-10, 00:35:08 GMT +# © 2021 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 # @@ -27,7 +27,6 @@ 05C8..05CF ; Cn # [8] <reserved-05C8>..<reserved-05CF> 05EB..05EE ; Cn # [4] <reserved-05EB>..<reserved-05EE> 05F5..05FF ; Cn # [11] <reserved-05F5>..<reserved-05FF> -061D ; Cn # <reserved-061D> 070E ; Cn # <reserved-070E> 074B..074C ; Cn # [2] <reserved-074B>..<reserved-074C> 07B2..07BF ; Cn # [14] <reserved-07B2>..<reserved-07BF> @@ -36,9 +35,9 @@ 083F ; Cn # <reserved-083F> 085C..085D ; Cn # [2] <reserved-085C>..<reserved-085D> 085F ; Cn # <reserved-085F> -086B..089F ; Cn # [53] <reserved-086B>..<reserved-089F> -08B5 ; Cn # <reserved-08B5> -08C8..08D2 ; Cn # [11] <reserved-08C8>..<reserved-08D2> +086B..086F ; Cn # [5] <reserved-086B>..<reserved-086F> +088F ; Cn # <reserved-088F> +0892..0897 ; Cn # [6] <reserved-0892>..<reserved-0897> 0984 ; Cn # <reserved-0984> 098D..098E ; Cn # [2] <reserved-098D>..<reserved-098E> 0991..0992 ; Cn # [2] <reserved-0991>..<reserved-0992> @@ -116,12 +115,13 @@ 0C0D ; Cn # <reserved-0C0D> 0C11 ; Cn # <reserved-0C11> 0C29 ; Cn # <reserved-0C29> -0C3A..0C3C ; Cn # [3] <reserved-0C3A>..<reserved-0C3C> +0C3A..0C3B ; Cn # [2] <reserved-0C3A>..<reserved-0C3B> 0C45 ; Cn # <reserved-0C45> 0C49 ; Cn # <reserved-0C49> 0C4E..0C54 ; Cn # [7] <reserved-0C4E>..<reserved-0C54> 0C57 ; Cn # <reserved-0C57> -0C5B..0C5F ; Cn # [5] <reserved-0C5B>..<reserved-0C5F> +0C5B..0C5C ; Cn # [2] <reserved-0C5B>..<reserved-0C5C> +0C5E..0C5F ; Cn # [2] <reserved-0C5E>..<reserved-0C5F> 0C64..0C65 ; Cn # [2] <reserved-0C64>..<reserved-0C65> 0C70..0C76 ; Cn # [7] <reserved-0C70>..<reserved-0C76> 0C8D ; Cn # <reserved-0C8D> @@ -132,7 +132,7 @@ 0CC5 ; Cn # <reserved-0CC5> 0CC9 ; Cn # <reserved-0CC9> 0CCE..0CD4 ; Cn # [7] <reserved-0CCE>..<reserved-0CD4> -0CD7..0CDD ; Cn # [7] <reserved-0CD7>..<reserved-0CDD> +0CD7..0CDC ; Cn # [6] <reserved-0CD7>..<reserved-0CDC> 0CDF ; Cn # <reserved-0CDF> 0CE4..0CE5 ; Cn # [2] <reserved-0CE4>..<reserved-0CE5> 0CF0 ; Cn # <reserved-0CF0> @@ -200,8 +200,7 @@ 13FE..13FF ; Cn # [2] <reserved-13FE>..<reserved-13FF> 169D..169F ; Cn # [3] <reserved-169D>..<reserved-169F> 16F9..16FF ; Cn # [7] <reserved-16F9>..<reserved-16FF> -170D ; Cn # <reserved-170D> -1715..171F ; Cn # [11] <reserved-1715>..<reserved-171F> +1716..171E ; Cn # [9] <reserved-1716>..<reserved-171E> 1737..173F ; Cn # [9] <reserved-1737>..<reserved-173F> 1754..175F ; Cn # [12] <reserved-1754>..<reserved-175F> 176D ; Cn # <reserved-176D> @@ -210,7 +209,6 @@ 17DE..17DF ; Cn # [2] <reserved-17DE>..<reserved-17DF> 17EA..17EF ; Cn # [6] <reserved-17EA>..<reserved-17EF> 17FA..17FF ; Cn # [6] <reserved-17FA>..<reserved-17FF> -180F ; Cn # <reserved-180F> 181A..181F ; Cn # [6] <reserved-181A>..<reserved-181F> 1879..187F ; Cn # [7] <reserved-1879>..<reserved-187F> 18AB..18AF ; Cn # [5] <reserved-18AB>..<reserved-18AF> @@ -230,9 +228,9 @@ 1A8A..1A8F ; Cn # [6] <reserved-1A8A>..<reserved-1A8F> 1A9A..1A9F ; Cn # [6] <reserved-1A9A>..<reserved-1A9F> 1AAE..1AAF ; Cn # [2] <reserved-1AAE>..<reserved-1AAF> -1AC1..1AFF ; Cn # [63] <reserved-1AC1>..<reserved-1AFF> -1B4C..1B4F ; Cn # [4] <reserved-1B4C>..<reserved-1B4F> -1B7D..1B7F ; Cn # [3] <reserved-1B7D>..<reserved-1B7F> +1ACF..1AFF ; Cn # [49] <reserved-1ACF>..<reserved-1AFF> +1B4D..1B4F ; Cn # [3] <reserved-1B4D>..<reserved-1B4F> +1B7F ; Cn # <reserved-1B7F> 1BF4..1BFB ; Cn # [8] <reserved-1BF4>..<reserved-1BFB> 1C38..1C3A ; Cn # [3] <reserved-1C38>..<reserved-1C3A> 1C4A..1C4C ; Cn # [3] <reserved-1C4A>..<reserved-1C4C> @@ -240,7 +238,6 @@ 1CBB..1CBC ; Cn # [2] <reserved-1CBB>..<reserved-1CBC> 1CC8..1CCF ; Cn # [8] <reserved-1CC8>..<reserved-1CCF> 1CFB..1CFF ; Cn # [5] <reserved-1CFB>..<reserved-1CFF> -1DFA ; Cn # <reserved-1DFA> 1F16..1F17 ; Cn # [2] <reserved-1F16>..<reserved-1F17> 1F1E..1F1F ; Cn # [2] <reserved-1F1E>..<reserved-1F1F> 1F46..1F47 ; Cn # [2] <reserved-1F46>..<reserved-1F47> @@ -261,15 +258,13 @@ 2072..2073 ; Cn # [2] <reserved-2072>..<reserved-2073> 208F ; Cn # <reserved-208F> 209D..209F ; Cn # [3] <reserved-209D>..<reserved-209F> -20C0..20CF ; Cn # [16] <reserved-20C0>..<reserved-20CF> +20C1..20CF ; Cn # [15] <reserved-20C1>..<reserved-20CF> 20F1..20FF ; Cn # [15] <reserved-20F1>..<reserved-20FF> 218C..218F ; Cn # [4] <reserved-218C>..<reserved-218F> 2427..243F ; Cn # [25] <reserved-2427>..<reserved-243F> 244B..245F ; Cn # [21] <reserved-244B>..<reserved-245F> 2B74..2B75 ; Cn # [2] <reserved-2B74>..<reserved-2B75> 2B96 ; Cn # <reserved-2B96> -2C2F ; Cn # <reserved-2C2F> -2C5F ; Cn # <reserved-2C5F> 2CF4..2CF8 ; Cn # [5] <reserved-2CF4>..<reserved-2CF8> 2D26 ; Cn # <reserved-2D26> 2D28..2D2C ; Cn # [5] <reserved-2D28>..<reserved-2D2C> @@ -285,7 +280,7 @@ 2DCF ; Cn # <reserved-2DCF> 2DD7 ; Cn # <reserved-2DD7> 2DDF ; Cn # <reserved-2DDF> -2E53..2E7F ; Cn # [45] <reserved-2E53>..<reserved-2E7F> +2E5E..2E7F ; Cn # [34] <reserved-2E5E>..<reserved-2E7F> 2E9A ; Cn # <reserved-2E9A> 2EF4..2EFF ; Cn # [12] <reserved-2EF4>..<reserved-2EFF> 2FD6..2FEF ; Cn # [26] <reserved-2FD6>..<reserved-2FEF> @@ -297,13 +292,14 @@ 318F ; Cn # <reserved-318F> 31E4..31EF ; Cn # [12] <reserved-31E4>..<reserved-31EF> 321F ; Cn # <reserved-321F> -9FFD..9FFF ; Cn # [3] <reserved-9FFD>..<reserved-9FFF> A48D..A48F ; Cn # [3] <reserved-A48D>..<reserved-A48F> A4C7..A4CF ; Cn # [9] <reserved-A4C7>..<reserved-A4CF> A62C..A63F ; Cn # [20] <reserved-A62C>..<reserved-A63F> A6F8..A6FF ; Cn # [8] <reserved-A6F8>..<reserved-A6FF> -A7C0..A7C1 ; Cn # [2] <reserved-A7C0>..<reserved-A7C1> -A7CB..A7F4 ; Cn # [42] <reserved-A7CB>..<reserved-A7F4> +A7CB..A7CF ; Cn # [5] <reserved-A7CB>..<reserved-A7CF> +A7D2 ; Cn # <reserved-A7D2> +A7D4 ; Cn # <reserved-A7D4> +A7DA..A7F1 ; Cn # [24] <reserved-A7DA>..<reserved-A7F1> A82D..A82F ; Cn # [3] <reserved-A82D>..<reserved-A82F> A83A..A83F ; Cn # [6] <reserved-A83A>..<reserved-A83F> A878..A87F ; Cn # [8] <reserved-A878>..<reserved-A87F> @@ -339,11 +335,10 @@ FB3D ; Cn # <reserved-FB3D> FB3F ; Cn # <reserved-FB3F> FB42 ; Cn # <reserved-FB42> FB45 ; Cn # <reserved-FB45> -FBC2..FBD2 ; Cn # [17] <reserved-FBC2>..<reserved-FBD2> -FD40..FD4F ; Cn # [16] <reserved-FD40>..<reserved-FD4F> +FBC3..FBD2 ; Cn # [16] <reserved-FBC3>..<reserved-FBD2> FD90..FD91 ; Cn # [2] <reserved-FD90>..<reserved-FD91> -FDC8..FDEF ; Cn # [40] <reserved-FDC8>..<noncharacter-FDEF> -FDFE..FDFF ; Cn # [2] <reserved-FDFE>..<reserved-FDFF> +FDC8..FDCE ; Cn # [7] <reserved-FDC8>..<reserved-FDCE> +FDD0..FDEF ; Cn # [32] <noncharacter-FDD0>..<noncharacter-FDEF> FE1A..FE1F ; Cn # [6] <reserved-FE1A>..<reserved-FE1F> FE53 ; Cn # <reserved-FE53> FE67 ; Cn # <reserved-FE67> @@ -387,10 +382,20 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 104FC..104FF ; Cn # [4] <reserved-104FC>..<reserved-104FF> 10528..1052F ; Cn # [8] <reserved-10528>..<reserved-1052F> 10564..1056E ; Cn # [11] <reserved-10564>..<reserved-1056E> -10570..105FF ; Cn # [144] <reserved-10570>..<reserved-105FF> +1057B ; Cn # <reserved-1057B> +1058B ; Cn # <reserved-1058B> +10593 ; Cn # <reserved-10593> +10596 ; Cn # <reserved-10596> +105A2 ; Cn # <reserved-105A2> +105B2 ; Cn # <reserved-105B2> +105BA ; Cn # <reserved-105BA> +105BD..105FF ; Cn # [67] <reserved-105BD>..<reserved-105FF> 10737..1073F ; Cn # [9] <reserved-10737>..<reserved-1073F> 10756..1075F ; Cn # [10] <reserved-10756>..<reserved-1075F> -10768..107FF ; Cn # [152] <reserved-10768>..<reserved-107FF> +10768..1077F ; Cn # [24] <reserved-10768>..<reserved-1077F> +10786 ; Cn # <reserved-10786> +107B1 ; Cn # <reserved-107B1> +107BB..107FF ; Cn # [69] <reserved-107BB>..<reserved-107FF> 10806..10807 ; Cn # [2] <reserved-10806>..<reserved-10807> 10809 ; Cn # <reserved-10809> 10836 ; Cn # <reserved-10836> @@ -433,12 +438,13 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 10EAE..10EAF ; Cn # [2] <reserved-10EAE>..<reserved-10EAF> 10EB2..10EFF ; Cn # [78] <reserved-10EB2>..<reserved-10EFF> 10F28..10F2F ; Cn # [8] <reserved-10F28>..<reserved-10F2F> -10F5A..10FAF ; Cn # [86] <reserved-10F5A>..<reserved-10FAF> +10F5A..10F6F ; Cn # [22] <reserved-10F5A>..<reserved-10F6F> +10F8A..10FAF ; Cn # [38] <reserved-10F8A>..<reserved-10FAF> 10FCC..10FDF ; Cn # [20] <reserved-10FCC>..<reserved-10FDF> 10FF7..10FFF ; Cn # [9] <reserved-10FF7>..<reserved-10FFF> 1104E..11051 ; Cn # [4] <reserved-1104E>..<reserved-11051> -11070..1107E ; Cn # [15] <reserved-11070>..<reserved-1107E> -110C2..110CC ; Cn # [11] <reserved-110C2>..<reserved-110CC> +11076..1107E ; Cn # [9] <reserved-11076>..<reserved-1107E> +110C3..110CC ; Cn # [10] <reserved-110C3>..<reserved-110CC> 110CE..110CF ; Cn # [2] <reserved-110CE>..<reserved-110CF> 110E9..110EF ; Cn # [7] <reserved-110E9>..<reserved-110EF> 110FA..110FF ; Cn # [6] <reserved-110FA>..<reserved-110FF> @@ -480,11 +486,11 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 11645..1164F ; Cn # [11] <reserved-11645>..<reserved-1164F> 1165A..1165F ; Cn # [6] <reserved-1165A>..<reserved-1165F> 1166D..1167F ; Cn # [19] <reserved-1166D>..<reserved-1167F> -116B9..116BF ; Cn # [7] <reserved-116B9>..<reserved-116BF> +116BA..116BF ; Cn # [6] <reserved-116BA>..<reserved-116BF> 116CA..116FF ; Cn # [54] <reserved-116CA>..<reserved-116FF> 1171B..1171C ; Cn # [2] <reserved-1171B>..<reserved-1171C> 1172C..1172F ; Cn # [4] <reserved-1172C>..<reserved-1172F> -11740..117FF ; Cn # [192] <reserved-11740>..<reserved-117FF> +11747..117FF ; Cn # [185] <reserved-11747>..<reserved-117FF> 1183C..1189F ; Cn # [100] <reserved-1183C>..<reserved-1189F> 118F3..118FE ; Cn # [12] <reserved-118F3>..<reserved-118FE> 11907..11908 ; Cn # [2] <reserved-11907>..<reserved-11908> @@ -499,7 +505,7 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 119D8..119D9 ; Cn # [2] <reserved-119D8>..<reserved-119D9> 119E5..119FF ; Cn # [27] <reserved-119E5>..<reserved-119FF> 11A48..11A4F ; Cn # [8] <reserved-11A48>..<reserved-11A4F> -11AA3..11ABF ; Cn # [29] <reserved-11AA3>..<reserved-11ABF> +11AA3..11AAF ; Cn # [13] <reserved-11AA3>..<reserved-11AAF> 11AF9..11BFF ; Cn # [263] <reserved-11AF9>..<reserved-11BFF> 11C09 ; Cn # <reserved-11C09> 11C37 ; Cn # <reserved-11C37> @@ -527,14 +533,16 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1239A..123FF ; Cn # [102] <reserved-1239A>..<reserved-123FF> 1246F ; Cn # <reserved-1246F> 12475..1247F ; Cn # [11] <reserved-12475>..<reserved-1247F> -12544..12FFF ; Cn # [2748] <reserved-12544>..<reserved-12FFF> +12544..12F8F ; Cn # [2636] <reserved-12544>..<reserved-12F8F> +12FF3..12FFF ; Cn # [13] <reserved-12FF3>..<reserved-12FFF> 1342F ; Cn # <reserved-1342F> 13439..143FF ; Cn # [4039] <reserved-13439>..<reserved-143FF> 14647..167FF ; Cn # [8633] <reserved-14647>..<reserved-167FF> 16A39..16A3F ; Cn # [7] <reserved-16A39>..<reserved-16A3F> 16A5F ; Cn # <reserved-16A5F> 16A6A..16A6D ; Cn # [4] <reserved-16A6A>..<reserved-16A6D> -16A70..16ACF ; Cn # [96] <reserved-16A70>..<reserved-16ACF> +16ABF ; Cn # <reserved-16ABF> +16ACA..16ACF ; Cn # [6] <reserved-16ACA>..<reserved-16ACF> 16AEE..16AEF ; Cn # [2] <reserved-16AEE>..<reserved-16AEF> 16AF6..16AFF ; Cn # [10] <reserved-16AF6>..<reserved-16AFF> 16B46..16B4F ; Cn # [10] <reserved-16B46>..<reserved-16B4F> @@ -550,8 +558,11 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 16FF2..16FFF ; Cn # [14] <reserved-16FF2>..<reserved-16FFF> 187F8..187FF ; Cn # [8] <reserved-187F8>..<reserved-187FF> 18CD6..18CFF ; Cn # [42] <reserved-18CD6>..<reserved-18CFF> -18D09..1AFFF ; Cn # [8951] <reserved-18D09>..<reserved-1AFFF> -1B11F..1B14F ; Cn # [49] <reserved-1B11F>..<reserved-1B14F> +18D09..1AFEF ; Cn # [8935] <reserved-18D09>..<reserved-1AFEF> +1AFF4 ; Cn # <reserved-1AFF4> +1AFFC ; Cn # <reserved-1AFFC> +1AFFF ; Cn # <reserved-1AFFF> +1B123..1B14F ; Cn # [45] <reserved-1B123>..<reserved-1B14F> 1B153..1B163 ; Cn # [17] <reserved-1B153>..<reserved-1B163> 1B168..1B16F ; Cn # [8] <reserved-1B168>..<reserved-1B16F> 1B2FC..1BBFF ; Cn # [2308] <reserved-1B2FC>..<reserved-1BBFF> @@ -559,10 +570,13 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1BC7D..1BC7F ; Cn # [3] <reserved-1BC7D>..<reserved-1BC7F> 1BC89..1BC8F ; Cn # [7] <reserved-1BC89>..<reserved-1BC8F> 1BC9A..1BC9B ; Cn # [2] <reserved-1BC9A>..<reserved-1BC9B> -1BCA4..1CFFF ; Cn # [4956] <reserved-1BCA4>..<reserved-1CFFF> +1BCA4..1CEFF ; Cn # [4700] <reserved-1BCA4>..<reserved-1CEFF> +1CF2E..1CF2F ; Cn # [2] <reserved-1CF2E>..<reserved-1CF2F> +1CF47..1CF4F ; Cn # [9] <reserved-1CF47>..<reserved-1CF4F> +1CFC4..1CFFF ; Cn # [60] <reserved-1CFC4>..<reserved-1CFFF> 1D0F6..1D0FF ; Cn # [10] <reserved-1D0F6>..<reserved-1D0FF> 1D127..1D128 ; Cn # [2] <reserved-1D127>..<reserved-1D128> -1D1E9..1D1FF ; Cn # [23] <reserved-1D1E9>..<reserved-1D1FF> +1D1EB..1D1FF ; Cn # [21] <reserved-1D1EB>..<reserved-1D1FF> 1D246..1D2DF ; Cn # [154] <reserved-1D246>..<reserved-1D2DF> 1D2F4..1D2FF ; Cn # [12] <reserved-1D2F4>..<reserved-1D2FF> 1D357..1D35F ; Cn # [9] <reserved-1D357>..<reserved-1D35F> @@ -589,7 +603,8 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1D7CC..1D7CD ; Cn # [2] <reserved-1D7CC>..<reserved-1D7CD> 1DA8C..1DA9A ; Cn # [15] <reserved-1DA8C>..<reserved-1DA9A> 1DAA0 ; Cn # <reserved-1DAA0> -1DAB0..1DFFF ; Cn # [1360] <reserved-1DAB0>..<reserved-1DFFF> +1DAB0..1DEFF ; Cn # [1104] <reserved-1DAB0>..<reserved-1DEFF> +1DF1F..1DFFF ; Cn # [225] <reserved-1DF1F>..<reserved-1DFFF> 1E007 ; Cn # <reserved-1E007> 1E019..1E01A ; Cn # [2] <reserved-1E019>..<reserved-1E01A> 1E022 ; Cn # <reserved-1E022> @@ -598,9 +613,14 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1E12D..1E12F ; Cn # [3] <reserved-1E12D>..<reserved-1E12F> 1E13E..1E13F ; Cn # [2] <reserved-1E13E>..<reserved-1E13F> 1E14A..1E14D ; Cn # [4] <reserved-1E14A>..<reserved-1E14D> -1E150..1E2BF ; Cn # [368] <reserved-1E150>..<reserved-1E2BF> +1E150..1E28F ; Cn # [320] <reserved-1E150>..<reserved-1E28F> +1E2AF..1E2BF ; Cn # [17] <reserved-1E2AF>..<reserved-1E2BF> 1E2FA..1E2FE ; Cn # [5] <reserved-1E2FA>..<reserved-1E2FE> -1E300..1E7FF ; Cn # [1280] <reserved-1E300>..<reserved-1E7FF> +1E300..1E7DF ; Cn # [1248] <reserved-1E300>..<reserved-1E7DF> +1E7E7 ; Cn # <reserved-1E7E7> +1E7EC ; Cn # <reserved-1E7EC> +1E7EF ; Cn # <reserved-1E7EF> +1E7FF ; Cn # <reserved-1E7FF> 1E8C5..1E8C6 ; Cn # [2] <reserved-1E8C5>..<reserved-1E8C6> 1E8D7..1E8FF ; Cn # [41] <reserved-1E8D7>..<reserved-1E8FF> 1E94C..1E94F ; Cn # [4] <reserved-1E94C>..<reserved-1E94F> @@ -654,34 +674,35 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1F249..1F24F ; Cn # [7] <reserved-1F249>..<reserved-1F24F> 1F252..1F25F ; Cn # [14] <reserved-1F252>..<reserved-1F25F> 1F266..1F2FF ; Cn # [154] <reserved-1F266>..<reserved-1F2FF> -1F6D8..1F6DF ; Cn # [8] <reserved-1F6D8>..<reserved-1F6DF> +1F6D8..1F6DC ; Cn # [5] <reserved-1F6D8>..<reserved-1F6DC> 1F6ED..1F6EF ; Cn # [3] <reserved-1F6ED>..<reserved-1F6EF> 1F6FD..1F6FF ; Cn # [3] <reserved-1F6FD>..<reserved-1F6FF> 1F774..1F77F ; Cn # [12] <reserved-1F774>..<reserved-1F77F> 1F7D9..1F7DF ; Cn # [7] <reserved-1F7D9>..<reserved-1F7DF> -1F7EC..1F7FF ; Cn # [20] <reserved-1F7EC>..<reserved-1F7FF> +1F7EC..1F7EF ; Cn # [4] <reserved-1F7EC>..<reserved-1F7EF> +1F7F1..1F7FF ; Cn # [15] <reserved-1F7F1>..<reserved-1F7FF> 1F80C..1F80F ; Cn # [4] <reserved-1F80C>..<reserved-1F80F> 1F848..1F84F ; Cn # [8] <reserved-1F848>..<reserved-1F84F> 1F85A..1F85F ; Cn # [6] <reserved-1F85A>..<reserved-1F85F> 1F888..1F88F ; Cn # [8] <reserved-1F888>..<reserved-1F88F> 1F8AE..1F8AF ; Cn # [2] <reserved-1F8AE>..<reserved-1F8AF> 1F8B2..1F8FF ; Cn # [78] <reserved-1F8B2>..<reserved-1F8FF> -1F979 ; Cn # <reserved-1F979> -1F9CC ; Cn # <reserved-1F9CC> 1FA54..1FA5F ; Cn # [12] <reserved-1FA54>..<reserved-1FA5F> 1FA6E..1FA6F ; Cn # [2] <reserved-1FA6E>..<reserved-1FA6F> 1FA75..1FA77 ; Cn # [3] <reserved-1FA75>..<reserved-1FA77> -1FA7B..1FA7F ; Cn # [5] <reserved-1FA7B>..<reserved-1FA7F> +1FA7D..1FA7F ; Cn # [3] <reserved-1FA7D>..<reserved-1FA7F> 1FA87..1FA8F ; Cn # [9] <reserved-1FA87>..<reserved-1FA8F> -1FAA9..1FAAF ; Cn # [7] <reserved-1FAA9>..<reserved-1FAAF> -1FAB7..1FABF ; Cn # [9] <reserved-1FAB7>..<reserved-1FABF> -1FAC3..1FACF ; Cn # [13] <reserved-1FAC3>..<reserved-1FACF> -1FAD7..1FAFF ; Cn # [41] <reserved-1FAD7>..<reserved-1FAFF> +1FAAD..1FAAF ; Cn # [3] <reserved-1FAAD>..<reserved-1FAAF> +1FABB..1FABF ; Cn # [5] <reserved-1FABB>..<reserved-1FABF> +1FAC6..1FACF ; Cn # [10] <reserved-1FAC6>..<reserved-1FACF> +1FADA..1FADF ; Cn # [6] <reserved-1FADA>..<reserved-1FADF> +1FAE8..1FAEF ; Cn # [8] <reserved-1FAE8>..<reserved-1FAEF> +1FAF7..1FAFF ; Cn # [9] <reserved-1FAF7>..<reserved-1FAFF> 1FB93 ; Cn # <reserved-1FB93> 1FBCB..1FBEF ; Cn # [37] <reserved-1FBCB>..<reserved-1FBEF> 1FBFA..1FFFF ; Cn # [1030] <reserved-1FBFA>..<noncharacter-1FFFF> -2A6DE..2A6FF ; Cn # [34] <reserved-2A6DE>..<reserved-2A6FF> -2B735..2B73F ; Cn # [11] <reserved-2B735>..<reserved-2B73F> +2A6E0..2A6FF ; Cn # [32] <reserved-2A6E0>..<reserved-2A6FF> +2B739..2B73F ; Cn # [7] <reserved-2B739>..<reserved-2B73F> 2B81E..2B81F ; Cn # [2] <reserved-2B81E>..<reserved-2B81F> 2CEA2..2CEAF ; Cn # [14] <reserved-2CEA2>..<reserved-2CEAF> 2EBE1..2F7FF ; Cn # [3103] <reserved-2EBE1>..<reserved-2F7FF> @@ -693,7 +714,7 @@ E01F0..EFFFF ; Cn # [65040] <reserved-E01F0>..<noncharacter-EFFFF> FFFFE..FFFFF ; Cn # [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 10FFFE..10FFFF; Cn # [2] <noncharacter-10FFFE>..<noncharacter-10FFFF> -# Total code points: 830672 +# Total code points: 829834 # ================================================ @@ -1130,7 +1151,7 @@ FFFFE..FFFFF ; Cn # [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 213E..213F ; Lu # [2] DOUBLE-STRUCK CAPITAL GAMMA..DOUBLE-STRUCK CAPITAL PI 2145 ; Lu # DOUBLE-STRUCK ITALIC CAPITAL D 2183 ; Lu # ROMAN NUMERAL REVERSED ONE HUNDRED -2C00..2C2E ; Lu # [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Lu # [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Lu # LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Lu # [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Lu # LATIN CAPITAL LETTER H WITH DESCENDER @@ -1295,13 +1316,21 @@ A7B8 ; Lu # LATIN CAPITAL LETTER U WITH STROKE A7BA ; Lu # LATIN CAPITAL LETTER GLOTTAL A A7BC ; Lu # LATIN CAPITAL LETTER GLOTTAL I A7BE ; Lu # LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Lu # LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Lu # LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Lu # [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Lu # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Lu # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S A7F5 ; Lu # LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Lu # [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Lu # [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Lu # [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Lu # [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Lu # [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Lu # [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Lu # [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Lu # [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Lu # [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -1338,7 +1367,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA 1E900..1E921 ; Lu # [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1791 +# Total code points: 1831 # ================================================ @@ -1775,7 +1804,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 2146..2149 ; Ll # [4] DOUBLE-STRUCK ITALIC SMALL D..DOUBLE-STRUCK ITALIC SMALL J 214E ; Ll # TURNED SMALL F 2184 ; Ll # LATIN SMALL LETTER REVERSED C -2C30..2C5E ; Ll # [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Ll # [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Ll # LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Ll # [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Ll # LATIN SMALL LETTER H WITH DESCENDER @@ -1944,9 +1973,15 @@ A7B9 ; Ll # LATIN SMALL LETTER U WITH STROKE A7BB ; Ll # LATIN SMALL LETTER GLOTTAL A A7BD ; Ll # LATIN SMALL LETTER GLOTTAL I A7BF ; Ll # LATIN SMALL LETTER GLOTTAL U +A7C1 ; Ll # LATIN SMALL LETTER OLD POLISH O A7C3 ; Ll # LATIN SMALL LETTER ANGLICANA W A7C8 ; Ll # LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Ll # LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Ll # LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Ll # LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Ll # LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Ll # LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Ll # LATIN SMALL LETTER SIGMOID S A7F6 ; Ll # LATIN SMALL LETTER REVERSED HALF H A7FA ; Ll # LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Ll # [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG @@ -1957,6 +1992,10 @@ FB13..FB17 ; Ll # [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGAT FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Ll # [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Ll # [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Ll # [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Ll # [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Ll # [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Ll # [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Ll # [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Ll # [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Ll # [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y @@ -1988,9 +2027,11 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 1D7AA..1D7C2 ; Ll # [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Ll # [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Ll # MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Ll # [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Ll # [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E922..1E943 ; Ll # [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2155 +# Total code points: 2227 # ================================================ @@ -2028,6 +2069,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 081A ; Lm # SAMARITAN MODIFIER LETTER EPENTHETIC YUT 0824 ; Lm # SAMARITAN MODIFIER LETTER SHORT A 0828 ; Lm # SAMARITAN MODIFIER LETTER I +08C9 ; Lm # ARABIC SMALL FARSI YEH 0971 ; Lm # DEVANAGARI SIGN HIGH SPACING DOT 0E46 ; Lm # THAI CHARACTER MAIYAMOK 0EC6 ; Lm # LAO KO LA @@ -2058,6 +2100,7 @@ A69C..A69D ; Lm # [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER C A717..A71F ; Lm # [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A770 ; Lm # MODIFIER LETTER US A788 ; Lm # MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A7F2..A7F4 ; Lm # [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Lm # [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A9CF ; Lm # JAVANESE PANGRANGKEP A9E6 ; Lm # MYANMAR MODIFIER LETTER SHAN REDUPLICATION @@ -2068,14 +2111,20 @@ AB5C..AB5F ; Lm # [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U W AB69 ; Lm # MODIFIER LETTER SMALL TURNED W FF70 ; Lm # HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +10780..10785 ; Lm # [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lm # [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lm # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F93..16F9F ; Lm # [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; Lm # [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Lm # OLD CHINESE ITERATION MARK +1AFF0..1AFF3 ; Lm # [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Lm # [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Lm # [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1E137..1E13D ; Lm # [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 260 +# Total code points: 334 # ================================================ @@ -2104,8 +2153,9 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0800..0815 ; Lo # [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Lo # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; Lo # [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; Lo # [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Lo # [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Lo # [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Lo # [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 0904..0939 ; Lo # [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; Lo # DEVANAGARI SIGN AVAGRAHA 0950 ; Lo # DEVANAGARI OM @@ -2170,6 +2220,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0C2A..0C39 ; Lo # [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; Lo # TELUGU SIGN AVAGRAHA 0C58..0C5A ; Lo # [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Lo # TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Lo # [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; Lo # KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; Lo # [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -2178,7 +2229,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0CAA..0CB3 ; Lo # [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; Lo # [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; Lo # KANNADA SIGN AVAGRAHA -0CDE ; Lo # KANNADA LETTER FA +0CDD..0CDE ; Lo # [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Lo # [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; Lo # [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; Lo # [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -2242,9 +2293,8 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1681..169A ; Lo # [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH 16A0..16EA ; Lo # [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16F1..16F8 ; Lo # [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Lo # [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Lo # [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; Lo # [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; Lo # [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; Lo # [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; Lo # [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; Lo # [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; Lo # [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -2264,7 +2314,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1A00..1A16 ; Lo # [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A20..1A54 ; Lo # [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1B05..1B33 ; Lo # [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; Lo # [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Lo # [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; Lo # [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; Lo # [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; Lo # [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -2297,8 +2347,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 31A0..31BF ; Lo # [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; Lo # [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; Lo # [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Lo # [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Lo # [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Lo # [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A016..A48C ; Lo # [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Lo # [40] LISU LETTER BA..LISU LETTER OE A500..A60B ; Lo # [268] VAI SYLLABLE EE..VAI SYLLABLE NG @@ -2426,9 +2475,12 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10F00..10F1C ; Lo # [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Lo # OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Lo # [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; Lo # [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; Lo # [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; Lo # [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; Lo # [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; Lo # [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; Lo # BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; Lo # [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; Lo # [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; Lo # [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -2470,6 +2522,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11680..116AA ; Lo # [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; Lo # TAKRI LETTER ARCHAIC KHA 11700..1171A ; Lo # [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; Lo # [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Lo # [44] DOGRA LETTER A..DOGRA LETTER RRA 118FF..11906 ; Lo # [8] WARANG CITI OM..DIVES AKURU LETTER E 11909 ; Lo # DIVES AKURU LETTER O @@ -2488,7 +2541,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11A50 ; Lo # SOYOMBO LETTER A 11A5C..11A89 ; Lo # [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; Lo # SOYOMBO MARK PLUTA -11AC0..11AF8 ; Lo # [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; Lo # [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Lo # [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Lo # [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; Lo # BHAIKSUKI SIGN AVAGRAHA @@ -2505,10 +2558,12 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11FB0 ; Lo # LISU LETTER YHA 12000..12399 ; Lo # [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12480..12543 ; Lo # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; Lo # [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; Lo # [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; Lo # [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Lo # [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Lo # [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; Lo # [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; Lo # [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; Lo # [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B63..16B77 ; Lo # [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS @@ -2518,7 +2573,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 17000..187F7 ; Lo # [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Lo # [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Lo # [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Lo # [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B000..1B122 ; Lo # [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Lo # [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Lo # [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Lo # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -2526,9 +2581,15 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1BC70..1BC7C ; Lo # [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Lo # [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; Lo # [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1DF0A ; Lo # LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1E100..1E12C ; Lo # [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E14E ; Lo # NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; Lo # [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Lo # [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; Lo # [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Lo # [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Lo # [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Lo # [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Lo # [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1EE00..1EE03 ; Lo # [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Lo # [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF @@ -2563,15 +2624,15 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1EEA1..1EEA3 ; Lo # [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; Lo # [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; Lo # [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; Lo # [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Lo # [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Lo # [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Lo # [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Lo # [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Lo # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Lo # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Lo # [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 127004 +# Total code points: 127333 # ================================================ @@ -2601,7 +2662,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0825..0827 ; Mn # [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Mn # [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Mn # [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Mn # [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Mn # [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Mn # [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Mn # [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Mn # DEVANAGARI VOWEL SIGN OE 093C ; Mn # DEVANAGARI SIGN NUKTA @@ -2642,6 +2704,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0BCD ; Mn # TAMIL SIGN VIRAMA 0C00 ; Mn # TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Mn # TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Mn # TELUGU SIGN NUKTA 0C3E..0C40 ; Mn # [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Mn # [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Mn # [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -2691,7 +2754,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 109D ; Mn # MYANMAR VOWEL SIGN AITON AI 135D..135F ; Mn # [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Mn # [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Mn # [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Mn # [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Mn # [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Mn # [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Mn # [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -2700,6 +2763,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 17C9..17D3 ; Mn # [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Mn # KHMER SIGN ATTHACAN 180B..180D ; Mn # [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Mn # MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Mn # [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Mn # MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Mn # [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -2716,7 +2780,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A73..1A7C ; Mn # [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; Mn # [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Mn # [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2739,8 +2803,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1CED ; Mn # VEDIC SIGN TIRYAK 1CF4 ; Mn # VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Mn # [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Mn # [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Mn # [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Mn # [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; Mn # [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20E1 ; Mn # COMBINING LEFT RIGHT ARROW ABOVE 20E5..20F0 ; Mn # [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE @@ -2799,11 +2862,15 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 10D24..10D27 ; Mn # [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Mn # [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Mn # [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Mn # [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Mn # BRAHMI SIGN ANUSVARA 11038..11046 ; Mn # [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Mn # BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Mn # [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Mn # [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Mn # [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Mn # [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Mn # KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Mn # [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Mn # [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; Mn # [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -2883,6 +2950,8 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Mn # KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; Mn # [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Mn # [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Mn # [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Mn # [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D17B..1D182 ; Mn # [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Mn # [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE @@ -2900,12 +2969,13 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E023..1E024 ; Mn # [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Mn # [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Mn # [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Mn # TOTO SIGN RISING TONE 1E2EC..1E2EF ; Mn # [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Mn # [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1839 +# Total code points: 1950 # ================================================ @@ -2980,6 +3050,8 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL 1087..108C ; Mc # [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3 108F ; Mc # MYANMAR SIGN RUMAI PALAUNG TONE-5 109A..109C ; Mc # [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A +1715 ; Mc # TAGALOG SIGN PAMUDPOD +1734 ; Mc # HANUNOO SIGN PAMUDPOD 17B6 ; Mc # KHMER VOWEL SIGN AA 17BE..17C5 ; Mc # [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU 17C7..17C8 ; Mc # [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU @@ -3099,7 +3171,7 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 1D165..1D166 ; Mc # [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D..1D172 ; Mc # [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 -# Total code points: 443 +# Total code points: 445 # ================================================ @@ -3160,6 +3232,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11D50..11D59 ; Nd # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Nd # [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Nd # [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -3167,7 +3240,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 650 +# Total code points: 660 # ================================================ @@ -3314,6 +3387,7 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 061C ; Cf # ARABIC LETTER MARK 06DD ; Cf # ARABIC END OF AYAH 070F ; Cf # SYRIAC ABBREVIATION MARK +0890..0891 ; Cf # [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Cf # ARABIC DISPUTED END OF AYAH 180E ; Cf # MONGOLIAN VOWEL SEPARATOR 200B..200F ; Cf # [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK @@ -3330,7 +3404,7 @@ FFF9..FFFB ; Cf # [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION E0001 ; Cf # LANGUAGE TAG E0020..E007F ; Cf # [96] TAG SPACE..CANCEL TAG -# Total code points: 161 +# Total code points: 163 # ================================================ @@ -3364,6 +3438,7 @@ D800..DFFF ; Cs # [2048] <surrogate-D800>..<surrogate-DFFF> 2E1A ; Pd # HYPHEN WITH DIAERESIS 2E3A..2E3B ; Pd # [2] TWO-EM DASH..THREE-EM DASH 2E40 ; Pd # DOUBLE HYPHEN +2E5D ; Pd # OBLIQUE HYPHEN 301C ; Pd # WAVE DASH 3030 ; Pd # WAVY DASH 30A0 ; Pd # KATAKANA-HIRAGANA DOUBLE HYPHEN @@ -3373,7 +3448,7 @@ FE63 ; Pd # SMALL HYPHEN-MINUS FF0D ; Pd # FULLWIDTH HYPHEN-MINUS 10EAD ; Pd # YEZIDI HYPHENATION MARK -# Total code points: 25 +# Total code points: 26 # ================================================ @@ -3425,6 +3500,10 @@ FF0D ; Pd # FULLWIDTH HYPHEN-MINUS 2E26 ; Ps # LEFT SIDEWAYS U BRACKET 2E28 ; Ps # LEFT DOUBLE PARENTHESIS 2E42 ; Ps # DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E55 ; Ps # LEFT SQUARE BRACKET WITH STROKE +2E57 ; Ps # LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Ps # TOP HALF LEFT PARENTHESIS +2E5B ; Ps # BOTTOM HALF LEFT PARENTHESIS 3008 ; Ps # LEFT ANGLE BRACKET 300A ; Ps # LEFT DOUBLE ANGLE BRACKET 300C ; Ps # LEFT CORNER BRACKET @@ -3455,7 +3534,7 @@ FF5B ; Ps # FULLWIDTH LEFT CURLY BRACKET FF5F ; Ps # FULLWIDTH LEFT WHITE PARENTHESIS FF62 ; Ps # HALFWIDTH LEFT CORNER BRACKET -# Total code points: 75 +# Total code points: 79 # ================================================ @@ -3504,6 +3583,10 @@ FF62 ; Ps # HALFWIDTH LEFT CORNER BRACKET 2E25 ; Pe # BOTTOM RIGHT HALF BRACKET 2E27 ; Pe # RIGHT SIDEWAYS U BRACKET 2E29 ; Pe # RIGHT DOUBLE PARENTHESIS +2E56 ; Pe # RIGHT SQUARE BRACKET WITH STROKE +2E58 ; Pe # RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E5A ; Pe # TOP HALF RIGHT PARENTHESIS +2E5C ; Pe # BOTTOM HALF RIGHT PARENTHESIS 3009 ; Pe # RIGHT ANGLE BRACKET 300B ; Pe # RIGHT DOUBLE ANGLE BRACKET 300D ; Pe # RIGHT CORNER BRACKET @@ -3534,7 +3617,7 @@ FF5D ; Pe # FULLWIDTH RIGHT CURLY BRACKET FF60 ; Pe # FULLWIDTH RIGHT WHITE PARENTHESIS FF63 ; Pe # HALFWIDTH RIGHT CORNER BRACKET -# Total code points: 73 +# Total code points: 77 # ================================================ @@ -3576,7 +3659,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 0609..060A ; Po # [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN 060C..060D ; Po # [2] ARABIC COMMA..ARABIC DATE SEPARATOR 061B ; Po # ARABIC SEMICOLON -061E..061F ; Po # [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; Po # [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 066A..066D ; Po # [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR 06D4 ; Po # ARABIC FULL STOP 0700..070D ; Po # [14] SYRIAC END OF PARAGRAPH..SYRIAC HARKLEAN ASTERISCUS @@ -3613,6 +3696,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 1AA0..1AA6 ; Po # [7] TAI THAM SIGN WIANG..TAI THAM SIGN REVERSED ROTATED RANA 1AA8..1AAD ; Po # [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1B5A..1B60 ; Po # [7] BALINESE PANTI..BALINESE PAMENENG +1B7D..1B7E ; Po # [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1BFC..1BFF ; Po # [4] BATAK SYMBOL BINDU NA METEK..BATAK SYMBOL BINDU PANGOLAT 1C3B..1C3F ; Po # [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; Po # [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD @@ -3641,7 +3725,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 2E3C..2E3F ; Po # [4] STENOGRAPHIC FULL STOP..CAPITULUM 2E41 ; Po # REVERSED COMMA 2E43..2E4F ; Po # [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER -2E52 ; Po # TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; Po # [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK 3001..3003 ; Po # [3] IDEOGRAPHIC COMMA..DITTO MARK 303D ; Po # PART ALTERNATION MARK 30FB ; Po # KATAKANA MIDDLE DOT @@ -3695,6 +3779,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 10B39..10B3F ; Po # [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION 10B99..10B9C ; Po # [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT 10F55..10F59 ; Po # [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; Po # [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 11047..1104D ; Po # [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 110BB..110BC ; Po # [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BE..110C1 ; Po # [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA @@ -3713,6 +3798,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 115C1..115D7 ; Po # [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11643 ; Po # [3] MODI DANDA..MODI ABBREVIATION SIGN 11660..1166C ; Po # [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +116B9 ; Po # TAKRI ABBREVIATION SIGN 1173C..1173E ; Po # [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1183B ; Po # DOGRA ABBREVIATION SIGN 11944..11946 ; Po # [3] DIVES AKURU DOUBLE DANDA..DIVES AKURU END OF TEXT MARK @@ -3725,6 +3811,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 11EF7..11EF8 ; Po # [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION 11FFF ; Po # TAMIL PUNCTUATION END OF TEXT 12470..12474 ; Po # [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON +12FF1..12FF2 ; Po # [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 16A6E..16A6F ; Po # [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; Po # BASSA VAH FULL STOP 16B37..16B3B ; Po # [5] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS FEEM @@ -3735,7 +3822,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 593 +# Total code points: 605 # ================================================ @@ -3823,7 +3910,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 0BF9 ; Sc # TAMIL RUPEE SIGN 0E3F ; Sc # THAI CURRENCY SYMBOL BAHT 17DB ; Sc # KHMER CURRENCY SYMBOL RIEL -20A0..20BF ; Sc # [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; Sc # [33] EURO-CURRENCY SIGN..SOM SIGN A838 ; Sc # NORTH INDIC RUPEE MARK FDFC ; Sc # RIAL SIGN FE69 ; Sc # SMALL DOLLAR SIGN @@ -3834,7 +3921,7 @@ FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 1E2FF ; Sc # WANCHO NGUN SIGN 1ECB0 ; Sc # INDIC SIYAQ RUPEE MARK -# Total code points: 62 +# Total code points: 63 # ================================================ @@ -3853,6 +3940,7 @@ FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 02EF..02FF ; Sk # [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW 0375 ; Sk # GREEK LOWER NUMERAL SIGN 0384..0385 ; Sk # [2] GREEK TONOS..GREEK DIALYTIKA TONOS +0888 ; Sk # ARABIC RAISED ROUND DOT 1FBD ; Sk # GREEK KORONIS 1FBF..1FC1 ; Sk # [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI 1FCD..1FCF ; Sk # [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -3865,13 +3953,13 @@ A720..A721 ; Sk # [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER A789..A78A ; Sk # [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN AB5B ; Sk # MODIFIER BREVE WITH INVERTED BREVE AB6A..AB6B ; Sk # [2] MODIFIER LETTER LEFT TACK..MODIFIER LETTER RIGHT TACK -FBB2..FBC1 ; Sk # [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Sk # [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FF3E ; Sk # FULLWIDTH CIRCUMFLEX ACCENT FF40 ; Sk # FULLWIDTH GRAVE ACCENT FFE3 ; Sk # FULLWIDTH MACRON 1F3FB..1F3FF ; Sk # [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -# Total code points: 123 +# Total code points: 125 # ================================================ @@ -3984,7 +4072,9 @@ A828..A82B ; So # [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK- A836..A837 ; So # [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK A839 ; So # NORTH INDIC QUANTITY MARK AA77..AA79 ; So # [3] MYANMAR SYMBOL AITON EXCLAMATION..MYANMAR SYMBOL AITON TWO -FDFD ; So # ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FD40..FD4F ; So # [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FDCF ; So # ARABIC LIGATURE SALAAMUHU ALAYNAA +FDFD..FDFF ; So # [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FFE4 ; So # FULLWIDTH BROKEN BAR FFE8 ; So # HALFWIDTH FORMS LIGHT VERTICAL FFED..FFEE ; So # [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE @@ -4003,13 +4093,14 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B3C..16B3F ; So # [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS +1CF50..1CFC3 ; So # [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; So # [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; So # [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; So # [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D16A..1D16C ; So # [3] MUSICAL SYMBOL FINGERED TREMOLO-1..MUSICAL SYMBOL FINGERED TREMOLO-3 1D183..1D184 ; So # [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; So # [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; So # [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; So # [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; So # [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; So # GREEK MUSICAL LEIMMA 1D300..1D356 ; So # [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING @@ -4035,32 +4126,33 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F260..1F265 ; So # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; So # [251] CYCLONE..AMPHORA 1F400..1F6D7 ; So # [728] RAT..ELEVATOR -1F6E0..1F6EC ; So # [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DD..1F6EC ; So # [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6F0..1F6FC ; So # [13] SATELLITE..ROLLER SKATE 1F700..1F773 ; So # [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8 ; So # [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; So # [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; So # HEAVY EQUALS SIGN 1F800..1F80B ; So # [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; So # [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; So # [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; So # [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; So # [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; So # [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; So # [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; So # [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74 ; So # [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; So # [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; So # [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; So # [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; So # [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; So # [7] FLY..FEATHER -1FAC0..1FAC2 ; So # [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; So # [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC ; So # [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; So # [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; So # [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; So # [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; So # [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; So # [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; So # [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6431 +# Total code points: 6605 # ================================================ diff --git a/lib/unicore/extracted/DJoinGroup.txt b/lib/unicore/extracted/DJoinGroup.txt index 0888bf0181..da46dd0a42 100644 --- a/lib/unicore/extracted/DJoinGroup.txt +++ b/lib/unicore/extracted/DJoinGroup.txt @@ -1,6 +1,6 @@ -# DerivedJoiningGroup-13.0.0.txt -# Date: 2019-09-08, 23:31:07 GMT -# © 2019 Unicode®, Inc. +# DerivedJoiningGroup-14.0.0.txt +# Date: 2021-05-11, 21:19:35 GMT +# © 2021 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 # @@ -41,8 +41,9 @@ 0671..0673 ; Alef # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW 0675 ; Alef # Lo ARABIC LETTER HIGH HAMZA ALEF 0773..0774 ; Alef # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0870..0882 ; Alef # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA -# Total code points: 10 +# Total code points: 29 # ================================================ @@ -110,10 +111,12 @@ 06AB ; Gaf # Lo ARABIC LETTER KAF WITH RING 06AF..06B4 ; Gaf # Lo [6] ARABIC LETTER GAF..ARABIC LETTER GAF WITH THREE DOTS ABOVE 0762..0764 ; Gaf # Lo [3] ARABIC LETTER KEHEH WITH DOT ABOVE..ARABIC LETTER KEHEH WITH THREE DOTS POINTING UPWARDS BELOW +088D ; Gaf # Lo ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW 08B0 ; Gaf # Lo ARABIC LETTER GAF WITH INVERTED STROKE 08C2 ; Gaf # Lo ARABIC LETTER KEHEH WITH SMALL V +08C8 ; Gaf # Lo ARABIC LETTER GRAF -# Total code points: 15 +# Total code points: 17 # ================================================ @@ -131,11 +134,12 @@ 076E..076F ; Hah # Lo [2] ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH BELOW..ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH AND TWO DOTS 0772 ; Hah # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE 077C ; Hah # Lo ARABIC LETTER HAH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +088A ; Hah # Lo ARABIC LETTER HAH WITH INVERTED SMALL V BELOW 08A2 ; Hah # Lo ARABIC LETTER JEEM WITH TWO DOTS ABOVE 08C1 ; Hah # Lo ARABIC LETTER TCHEH WITH SMALL V 08C5..08C6 ; Hah # Lo [2] ARABIC LETTER JEEM WITH THREE DOTS ABOVE..ARABIC LETTER JEEM WITH THREE DOTS BELOW -# Total code points: 21 +# Total code points: 22 # ================================================ @@ -224,8 +228,9 @@ 0646 ; Noon # Lo ARABIC LETTER NOON 06B9..06BC ; Noon # Lo [4] ARABIC LETTER NOON WITH DOT BELOW..ARABIC LETTER NOON WITH RING 0767..0769 ; Noon # Lo [3] ARABIC LETTER NOON WITH TWO DOTS BELOW..ARABIC LETTER NOON WITH SMALL V +0889 ; Noon # Lo ARABIC LETTER NOON WITH INVERTED SMALL V -# Total code points: 8 +# Total code points: 9 # ================================================ @@ -245,8 +250,9 @@ 066F ; Qaf # Lo ARABIC LETTER DOTLESS QAF 06A7..06A8 ; Qaf # Lo [2] ARABIC LETTER QAF WITH DOT ABOVE..ARABIC LETTER QAF WITH THREE DOTS ABOVE 08A5 ; Qaf # Lo ARABIC LETTER QAF WITH DOT BELOW +08B5 ; Qaf # Lo ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE -# Total code points: 5 +# Total code points: 6 # ================================================ @@ -323,9 +329,10 @@ 0637..0638 ; Tah # Lo [2] ARABIC LETTER TAH..ARABIC LETTER ZAH 069F ; Tah # Lo ARABIC LETTER TAH WITH THREE DOTS ABOVE +088B..088C ; Tah # Lo [2] ARABIC LETTER TAH WITH DOT BELOW..ARABIC LETTER TAH WITH THREE DOTS BELOW 08A3 ; Tah # Lo ARABIC LETTER TAH WITH TWO DOTS ABOVE -# Total code points: 4 +# Total code points: 6 # ================================================ @@ -723,4 +730,16 @@ # Total code points: 4 +# ================================================ + +0886 ; Thin_Yeh # Lo ARABIC LETTER THIN YEH + +# Total code points: 1 + +# ================================================ + +088E ; Vertical_Tail # Lo ARABIC VERTICAL TAIL + +# Total code points: 1 + # EOF diff --git a/lib/unicore/extracted/DJoinType.txt b/lib/unicore/extracted/DJoinType.txt index 57229cc736..7c36d028a3 100644 --- a/lib/unicore/extracted/DJoinType.txt +++ b/lib/unicore/extracted/DJoinType.txt @@ -1,6 +1,6 @@ -# DerivedJoiningType-13.0.0.txt -# Date: 2020-01-21, 07:36:28 GMT -# © 2020 Unicode®, Inc. +# DerivedJoiningType-14.0.0.txt +# Date: 2021-05-28, 21:49:06 GMT +# © 2021 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 # @@ -22,10 +22,11 @@ 0640 ; C # Lm ARABIC TATWEEL 07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW 180A ; C # Po MONGOLIAN NIRUGU 200D ; C # Cf ZERO WIDTH JOINER -# Total code points: 4 +# Total code points: 7 # ================================================ @@ -67,11 +68,12 @@ 0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA 0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA 0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW 08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE 08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE -08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE -08BA..08C7 ; D # Lo [14] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF 1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER 1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -96,6 +98,8 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL 10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH 10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH 10FB0 ; D # Lo CHORASMIAN LETTER ALEPH 10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL 10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN @@ -106,7 +110,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10FCA ; D # No CHORASMIAN NUMBER TWENTY 1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 586 +# Total code points: 610 # ================================================ @@ -147,6 +151,8 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN 0867 ; R # Lo SYRIAC LETTER MALAYALAM RA 0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL 08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH 08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW 08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE @@ -169,13 +175,14 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN 10F33 ; R # Lo SOGDIAN LETTER HE 10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH 10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW 10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH 10FBD ; R # Lo CHORASMIAN LETTER MEM 10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN 10FC9 ; R # No CHORASMIAN NUMBER TEN -# Total code points: 130 +# Total code points: 152 # ================================================ @@ -221,7 +228,8 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; T # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; T # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; T # Mn DEVANAGARI VOWEL SIGN OE 093C ; T # Mn DEVANAGARI SIGN NUKTA @@ -262,6 +270,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0BCD ; T # Mn TAMIL SIGN VIRAMA 0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -311,7 +320,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 109D ; T # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -320,6 +329,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; T # Mn KHMER SIGN ATTHACAN 180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -337,7 +347,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; T # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; T # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; T # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; T # Mn BALINESE SIGN REREKAN 1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -360,8 +370,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1CED ; T # Mn VEDIC SIGN TIRYAK 1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200B ; T # Cf ZERO WIDTH SPACE 200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE @@ -430,11 +439,15 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; T # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -516,6 +529,8 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE @@ -534,6 +549,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA @@ -542,6 +558,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1997 +# Total code points: 2108 # EOF diff --git a/lib/unicore/extracted/DLineBreak.txt b/lib/unicore/extracted/DLineBreak.txt index 0f326def56..2504c3f7e1 100644 --- a/lib/unicore/extracted/DLineBreak.txt +++ b/lib/unicore/extracted/DLineBreak.txt @@ -1,6 +1,6 @@ -# DerivedLineBreak-13.0.0.txt -# Date: 2020-02-17, 18:43:18 GMT -# © 2020 Unicode®, Inc. +# DerivedLineBreak-14.0.0.txt +# Date: 2021-07-10, 00:35:09 GMT +# © 2021 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 # @@ -24,8 +24,8 @@ E000..F8FF ; XX # Co [6400] <private-use-E000>..<private-use-F8FF> F0000..FFFFD ; XX # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; XX # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 763788 code points not listed here. -# Total code points: 901256 +# The above property value applies to 762997 code points not listed here. +# Total code points: 900465 # ================================================ @@ -80,6 +80,10 @@ F0000..FFFFD ; XX # Co [65534] <private-use-F0000>..<private-use-FFFFD> 2E26 ; OP # Ps LEFT SIDEWAYS U BRACKET 2E28 ; OP # Ps LEFT DOUBLE PARENTHESIS 2E42 ; OP # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E55 ; OP # Ps LEFT SQUARE BRACKET WITH STROKE +2E57 ; OP # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; OP # Ps TOP HALF LEFT PARENTHESIS +2E5B ; OP # Ps BOTTOM HALF LEFT PARENTHESIS 3008 ; OP # Ps LEFT ANGLE BRACKET 300A ; OP # Ps LEFT DOUBLE ANGLE BRACKET 300C ; OP # Ps LEFT CORNER BRACKET @@ -117,7 +121,7 @@ FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET 145CE ; OP # Lo ANATOLIAN HIEROGLYPH A410 BEGIN LOGOGRAM MARK 1E95E..1E95F ; OP # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 88 +# Total code points: 92 # ================================================ @@ -164,6 +168,10 @@ FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET 2E25 ; CL # Pe BOTTOM RIGHT HALF BRACKET 2E27 ; CL # Pe RIGHT SIDEWAYS U BRACKET 2E29 ; CL # Pe RIGHT DOUBLE PARENTHESIS +2E56 ; CL # Pe RIGHT SQUARE BRACKET WITH STROKE +2E58 ; CL # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E5A ; CL # Pe TOP HALF RIGHT PARENTHESIS +2E5C ; CL # Pe BOTTOM HALF RIGHT PARENTHESIS 3001..3002 ; CL # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP 3009 ; CL # Pe RIGHT ANGLE BRACKET 300B ; CL # Pe RIGHT DOUBLE ANGLE BRACKET @@ -209,7 +217,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 13438 ; CL # Cf EGYPTIAN HIEROGLYPH END SEGMENT 145CF ; CL # Lo ANATOLIAN HIEROGLYPH A410A END LOGOGRAM MARK -# Total code points: 91 +# Total code points: 95 # ================================================ @@ -302,7 +310,7 @@ FF9E..FF9F ; NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KA 003F ; EX # Po QUESTION MARK 05C6 ; EX # Po HEBREW PUNCTUATION NUN HAFUKHA 061B ; EX # Po ARABIC SEMICOLON -061E..061F ; EX # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; EX # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 06D4 ; EX # Po ARABIC FULL STOP 07F9 ; EX # Po NKO EXCLAMATION MARK 0F0D..0F11 ; EX # Po [5] TIBETAN MARK SHAD..TIBETAN MARK RIN CHEN SPUNGS SHAD @@ -314,6 +322,7 @@ FF9E..FF9F ; NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KA 2CF9 ; EX # Po COPTIC OLD NUBIAN FULL STOP 2CFE ; EX # Po COPTIC FULL STOP 2E2E ; EX # Po REVERSED QUESTION MARK +2E53..2E54 ; EX # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK A60E ; EX # Po VAI FULL STOP A876..A877 ; EX # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD FE15..FE16 ; EX # Po [2] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK..PRESENTATION FORM FOR VERTICAL QUESTION MARK @@ -323,7 +332,7 @@ FF1F ; EX # Po FULLWIDTH QUESTION MARK 115C4..115C5 ; EX # Po [2] SIDDHAM SEPARATOR DOT..SIDDHAM SEPARATOR BAR 11C71 ; EX # Po MARCHEN MARK SHAD -# Total code points: 37 +# Total code points: 40 # ================================================ @@ -371,7 +380,7 @@ FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION 20B7..20BA ; PR # Sc [4] SPESMILO SIGN..TURKISH LIRA SIGN 20BC..20BD ; PR # Sc [2] MANAT SIGN..RUBLE SIGN 20BF ; PR # Sc BITCOIN SIGN -20C0..20CF ; PR # Cn [16] <reserved-20C0>..<reserved-20CF> +20C1..20CF ; PR # Cn [15] <reserved-20C1>..<reserved-20CF> 2116 ; PR # So NUMERO SIGN 2212..2213 ; PR # Sm [2] MINUS SIGN..MINUS-OR-PLUS SIGN FE69 ; PR # Sc SMALL DOLLAR SIGN @@ -380,7 +389,7 @@ FFE1 ; PR # Sc FULLWIDTH POUND SIGN FFE5..FFE6 ; PR # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 1E2FF ; PR # Sc WANCHO NGUN SIGN -# Total code points: 68 +# Total code points: 67 # ================================================ @@ -400,6 +409,7 @@ FFE5..FFE6 ; PR # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 20B6 ; PO # Sc LIVRE TOURNOIS SIGN 20BB ; PO # Sc NORDIC MARK SIGN 20BE ; PO # Sc LARI SIGN +20C0 ; PO # Sc SOM SIGN 2103 ; PO # So DEGREE CELSIUS 2109 ; PO # So DEGREE FAHRENHEIT A838 ; PO # Sc NORTH INDIC RUPEE MARK @@ -411,7 +421,7 @@ FFE0 ; PO # Sc FULLWIDTH CENT SIGN 1ECAC ; PO # So INDIC SIYAQ PLACEHOLDER 1ECB0 ; PO # Sc INDIC SIYAQ RUPEE MARK -# Total code points: 36 +# Total code points: 37 # ================================================ @@ -472,6 +482,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 11D50..11D59 ; NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; NU # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; NU # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -479,7 +490,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 642 +# Total code points: 652 # ================================================ @@ -588,8 +599,12 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0840..0858 ; AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; AL # Po MANDAIC PUNCTUATION 0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; AL # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; AL # Sk ARABIC RAISED ROUND DOT +0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0890..0891 ; AL # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; AL # Lm ARABIC SMALL FARSI YEH 08E2 ; AL # Cf ARABIC DISPUTED END OF AYAH 0904..0939 ; AL # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; AL # Lo DEVANAGARI SIGN AVAGRAHA @@ -667,6 +682,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0C2A..0C39 ; AL # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; AL # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; AL # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; AL # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; AL # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C78..0C7E ; AL # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; AL # So TELUGU SIGN TUUMU @@ -677,7 +693,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0CAA..0CB3 ; AL # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; AL # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; AL # Lo KANNADA SIGN AVAGRAHA -0CDE ; AL # Lo KANNADA LETTER FA +0CDD..0CDE ; AL # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; AL # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; AL # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -753,9 +769,8 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 16A0..16EA ; AL # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; AL # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; AL # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; AL # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; AL # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; AL # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; AL # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; AL # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; AL # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; AL # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; AL # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -777,7 +792,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1A00..1A16 ; AL # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A1E..1A1F ; AL # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 1B05..1B33 ; AL # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; AL # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; AL # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B5C ; AL # Po BALINESE WINDU 1B61..1B6A ; AL # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; AL # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING @@ -1012,9 +1027,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 2B5A..2B73 ; AL # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95 ; AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF ; AL # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -2C00..2C2E ; AL # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; AL # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; AL # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; AL # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; AL # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; AL # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CE5..2CEA ; AL # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA @@ -1074,8 +1087,11 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; AL # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; AL # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; AL # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; AL # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; AL # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1126,12 +1142,14 @@ FB00..FB06 ; AL # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; AL # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FB29 ; AL # Sm HEBREW LETTER ALTERNATIVE PLUS SIGN FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; AL # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; AL # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM +FD40..FD4F ; AL # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; AL # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU -FDFD ; AL # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; AL # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE70..FE74 ; AL # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM FFE8 ; AL # So HALFWIDTH FORMS LIGHT VERTICAL @@ -1175,9 +1193,20 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10500..10527 ; AL # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; AL # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; AL # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; AL # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; AL # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; AL # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; AL # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; AL # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; AL # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; AL # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; AL # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; AL # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; AL # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; AL # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; AL # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; AL # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; AL # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; AL # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; AL # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1239,12 +1268,16 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10F30..10F45 ; AL # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81 ; AL # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F86..10F89 ; AL # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4 ; AL # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; AL # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6 ; AL # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; AL # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11049..1104D ; AL # Po [5] BRAHMI PUNCTUATION DOT..BRAHMI PUNCTUATION LOTUS 11052..11065 ; AL # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND +11071..11072 ; AL # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; AL # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; AL # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110BB..110BC ; AL # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD ; AL # Cf KAITHI NUMBER SIGN @@ -1299,6 +1332,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 11644 ; AL # Lo MODI SIGN HUVA 11680..116AA ; AL # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; AL # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; AL # Po TAKRI ABBREVIATION SIGN 11800..1182B ; AL # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1183B ; AL # Po DOGRA ABBREVIATION SIGN 118A0..118DF ; AL # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -1322,7 +1356,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 11A50 ; AL # Lo SOYOMBO LETTER A 11A5C..11A89 ; AL # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; AL # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; AL # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; AL # Lo BHAIKSUKI SIGN AVAGRAHA @@ -1345,6 +1379,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 12000..12399 ; AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; AL # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; AL # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; AL # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..13257 ; AL # Lo [600] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH O006 1325E..13281 ; AL # Lo [36] EGYPTIAN HIEROGLYPH O007..EGYPTIAN HIEROGLYPH O033 13283..13285 ; AL # Lo [3] EGYPTIAN HIEROGLYPH O034..EGYPTIAN HIEROGLYPH O036 @@ -1354,6 +1390,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 145D0..14646 ; AL # Lo [119] ANATOLIAN HIEROGLYPH A411..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; AL # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; AL # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; AL # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; AL # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; AL # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B3A..16B3B ; AL # Po [2] PAHAWH HMONG SIGN VOS THIAB..PAHAWH HMONG SIGN VOS FEEM @@ -1370,18 +1407,22 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 16F50 ; AL # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; AL # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 18B00..18CD5 ; AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 +1AFF0..1AFF3 ; AL # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; AL # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; AL # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1BC00..1BC6A ; AL # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; AL # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; AL # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; AL # So DUPLOYAN SIGN O WITH CROSS +1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; AL # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D16A..1D16C ; AL # So [3] MUSICAL SYMBOL FINGERED TREMOLO-1..MUSICAL SYMBOL FINGERED TREMOLO-3 1D183..1D184 ; AL # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; AL # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; AL # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; AL # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; AL # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; AL # So GREEK MUSICAL LEIMMA 1D2E0..1D2F3 ; AL # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN @@ -1433,11 +1474,19 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1DA76..1DA83 ; AL # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH 1DA85..1DA86 ; AL # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS 1DA8B ; AL # Po SIGNWRITING PARENTHESIS +1DF00..1DF09 ; AL # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; AL # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; AL # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; AL # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; AL # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; AL # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; AL # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; AL # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; AL # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; AL # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; AL # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; AL # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E900..1E943 ; AL # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -1511,7 +1560,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21400 +# Total code points: 22043 # ================================================ @@ -1599,9 +1648,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 32B1..32BF ; ID # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY 32C0..33FF ; ID # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL 3400..4DBF ; ID # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -9FFD..9FFF ; ID # Cn [3] <reserved-9FFD>..<reserved-9FFF> -A000..A014 ; ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A016..A48C ; ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; ID # So [55] YI RADICAL QOT..YI RADICAL KE F900..FA6D ; ID # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D @@ -1652,7 +1699,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 17000..187F7 ; ID # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18D00..18D08 ; ID # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B000..1B122 ; ID # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B170..1B2FB ; ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1F000..1F02B ; ID # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK 1F02C..1F02F ; ID # Cn [4] <reserved-1F02C>..<reserved-1F02F> @@ -1718,8 +1765,8 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F6B7..1F6BF ; ID # So [9] NO PEDESTRIANS..SHOWER 1F6C1..1F6CB ; ID # So [11] BATHTUB..COUCH AND LAMP 1F6CD..1F6D7 ; ID # So [11] SHOPPING BAGS..ELEVATOR -1F6D8..1F6DF ; ID # Cn [8] <reserved-1F6D8>..<reserved-1F6DF> -1F6E0..1F6EC ; ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6D8..1F6DC ; ID # Cn [5] <reserved-1F6D8>..<reserved-1F6DC> +1F6DD..1F6EC ; ID # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6ED..1F6EF ; ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> 1F6F0..1F6FC ; ID # So [13] SATELLITE..ROLLER SKATE 1F6FD..1F6FF ; ID # Cn [3] <reserved-1F6FD>..<reserved-1F6FF> @@ -1727,7 +1774,9 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F7D5..1F7D8 ; ID # So [4] CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7D9..1F7DF ; ID # Cn [7] <reserved-1F7D9>..<reserved-1F7DF> 1F7E0..1F7EB ; ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE -1F7EC..1F7FF ; ID # Cn [20] <reserved-1F7EC>..<reserved-1F7FF> +1F7EC..1F7EF ; ID # Cn [4] <reserved-1F7EC>..<reserved-1F7EF> +1F7F0 ; ID # So HEAVY EQUALS SIGN +1F7F1..1F7FF ; ID # Cn [15] <reserved-1F7F1>..<reserved-1F7FF> 1F80C..1F80F ; ID # Cn [4] <reserved-1F80C>..<reserved-1F80F> 1F848..1F84F ; ID # Cn [8] <reserved-1F848>..<reserved-1F84F> 1F85A..1F85F ; ID # Cn [6] <reserved-1F85A>..<reserved-1F85F> @@ -1741,13 +1790,10 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F927..1F92F ; ID # So [9] SNEEZING FACE..SHOCKED FACE WITH EXPLODING HEAD 1F93A..1F93B ; ID # So [2] FENCER..MODERN PENTATHLON 1F93F..1F976 ; ID # So [56] DIVING MASK..FREEZING FACE -1F978 ; ID # So DISGUISED FACE -1F979 ; ID # Cn <reserved-1F979> -1F97A..1F9B4 ; ID # So [59] FACE WITH PLEADING EYES..BONE +1F978..1F9B4 ; ID # So [61] DISGUISED FACE..BONE 1F9B7 ; ID # So TOOTH 1F9BA ; ID # So SAFETY VEST -1F9BC..1F9CB ; ID # So [16] MOTORIZED WHEELCHAIR..BUBBLE TEA -1F9CC ; ID # Cn <reserved-1F9CC> +1F9BC..1F9CC ; ID # So [17] MOTORIZED WHEELCHAIR..TROLL 1F9D0 ; ID # So FACE WITH MONOCLE 1F9DE..1F9FF ; ID # So [34] GENIE..NAZAR AMULET 1FA54..1FA5F ; ID # Cn [12] <reserved-1FA54>..<reserved-1FA5F> @@ -1755,23 +1801,26 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1FA6E..1FA6F ; ID # Cn [2] <reserved-1FA6E>..<reserved-1FA6F> 1FA70..1FA74 ; ID # So [5] BALLET SHOES..THONG SANDAL 1FA75..1FA77 ; ID # Cn [3] <reserved-1FA75>..<reserved-1FA77> -1FA78..1FA7A ; ID # So [3] DROP OF BLOOD..STETHOSCOPE -1FA7B..1FA7F ; ID # Cn [5] <reserved-1FA7B>..<reserved-1FA7F> +1FA78..1FA7C ; ID # So [5] DROP OF BLOOD..CRUTCH +1FA7D..1FA7F ; ID # Cn [3] <reserved-1FA7D>..<reserved-1FA7F> 1FA80..1FA86 ; ID # So [7] YO-YO..NESTING DOLLS 1FA87..1FA8F ; ID # Cn [9] <reserved-1FA87>..<reserved-1FA8F> -1FA90..1FAA8 ; ID # So [25] RINGED PLANET..ROCK -1FAA9..1FAAF ; ID # Cn [7] <reserved-1FAA9>..<reserved-1FAAF> -1FAB0..1FAB6 ; ID # So [7] FLY..FEATHER -1FAB7..1FABF ; ID # Cn [9] <reserved-1FAB7>..<reserved-1FABF> +1FA90..1FAAC ; ID # So [29] RINGED PLANET..HAMSA +1FAAD..1FAAF ; ID # Cn [3] <reserved-1FAAD>..<reserved-1FAAF> +1FAB0..1FABA ; ID # So [11] FLY..NEST WITH EGGS +1FABB..1FABF ; ID # Cn [5] <reserved-1FABB>..<reserved-1FABF> 1FAC0..1FAC2 ; ID # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAC3..1FACF ; ID # Cn [13] <reserved-1FAC3>..<reserved-1FACF> -1FAD0..1FAD6 ; ID # So [7] BLUEBERRIES..TEAPOT -1FAD7..1FAFF ; ID # Cn [41] <reserved-1FAD7>..<reserved-1FAFF> +1FAC6..1FACF ; ID # Cn [10] <reserved-1FAC6>..<reserved-1FACF> +1FAD0..1FAD9 ; ID # So [10] BLUEBERRIES..JAR +1FADA..1FADF ; ID # Cn [6] <reserved-1FADA>..<reserved-1FADF> +1FAE0..1FAE7 ; ID # So [8] MELTING FACE..BUBBLES +1FAE8..1FAEF ; ID # Cn [8] <reserved-1FAE8>..<reserved-1FAEF> +1FAF7..1FAFF ; ID # Cn [9] <reserved-1FAF7>..<reserved-1FAFF> 1FC00..1FFFD ; ID # Cn [1022] <reserved-1FC00>..<reserved-1FFFD> -20000..2A6DD ; ID # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF ; ID # Cn [34] <reserved-2A6DE>..<reserved-2A6FF> -2A700..2B734 ; ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F ; ID # Cn [11] <reserved-2B735>..<reserved-2B73F> +20000..2A6DF ; ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF ; ID # Cn [32] <reserved-2A6E0>..<reserved-2A6FF> +2A700..2B738 ; ID # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F ; ID # Cn [7] <reserved-2B739>..<reserved-2B73F> 2B740..2B81D ; ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; ID # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1 ; ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 @@ -1783,7 +1832,7 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 30000..3134A ; ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 3134B..3FFFD ; ID # Cn [60595] <reserved-3134B>..<reserved-3FFFD> -# Total code points: 172462 +# Total code points: 172456 # ================================================ @@ -1840,7 +1889,8 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0825..0827 ; CM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; CM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; CM # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; CM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; CM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; CM # Mc DEVANAGARI SIGN VISARGA 093A ; CM # Mn DEVANAGARI VOWEL SIGN OE @@ -1909,6 +1959,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0C00 ; CM # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; CM # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA 0C04 ; CM # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; CM # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; CM # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; CM # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C46..0C48 ; CM # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI @@ -1958,10 +2009,13 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0FC6 ; CM # Mn TIBETAN SYMBOL PADMA GDAN 135D..135F ; CM # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; CM # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; CM # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; CM # Mc TAGALOG SIGN PAMUDPOD +1732..1733 ; CM # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; CM # Mc HANUNOO SIGN PAMUDPOD 1752..1753 ; CM # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; CM # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 180B..180D ; CM # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; CM # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; CM # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; CM # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; CM # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -1978,7 +2032,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; CM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; CM # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; CM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -2018,8 +2072,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1CF4 ; CM # Mn VEDIC TONE CANDRA ABOVE 1CF7 ; CM # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; CM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; CM # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; CM # Cf ZERO WIDTH NON-JOINER 200E..200F ; CM # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; CM # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE @@ -2100,16 +2153,20 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; CM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; CM # Mc BRAHMI SIGN CANDRABINDU 11001 ; CM # Mn BRAHMI SIGN ANUSVARA 11002 ; CM # Mc BRAHMI SIGN VISARGA 11038..11046 ; CM # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; CM # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; CM # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; CM # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; CM # Mc KAITHI SIGN VISARGA 110B0..110B2 ; CM # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; CM # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; CM # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; CM # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; CM # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; CM # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; CM # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; CM # Mc CHAKMA VOWEL SIGN E @@ -2243,6 +2300,8 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 16FF0..16FF1 ; CM # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1BC9D..1BC9E ; CM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BCA0..1BCA3 ; CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; CM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; CM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; CM # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; CM # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; CM # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -2263,6 +2322,7 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1E023..1E024 ; CM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; CM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; CM # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; CM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; CM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA @@ -2270,7 +2330,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2286 +# Total code points: 2399 # ================================================ @@ -2333,6 +2393,7 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 1804..1805 ; BA # Po [2] MONGOLIAN COLON..MONGOLIAN FOUR DOTS 1B5A..1B5B ; BA # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5D..1B60 ; BA # Po [4] BALINESE CARIK PAMUNGKAH..BALINESE PAMENENG +1B7D..1B7E ; BA # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1C3B..1C3F ; BA # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; BA # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 2000..2006 ; BA # Zs [7] EN QUAD..SIX-PER-EM SPACE @@ -2359,6 +2420,7 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 2E43..2E4A ; BA # Po [8] DASH WITH LEFT UPTURN..DOTTED SOLIDUS 2E4C ; BA # Po MEDIEVAL COMMA 2E4E..2E4F ; BA # Po [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER +2E5D ; BA # Pd OBLIQUE HYPHEN 3000 ; BA # Zs IDEOGRAPHIC SPACE A4FE..A4FF ; BA # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D ; BA # Po VAI COMMA @@ -2409,7 +2471,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 244 +# Total code points: 247 # ================================================ @@ -2577,8 +2639,9 @@ AADE..AADF ; SA # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI 11727..1172B ; SA # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 1173A..1173B ; SA # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173F ; SA # So AHOM SYMBOL VI +11740..11746 ; SA # Lo [7] AHOM LETTER CA..AHOM LETTER LLA -# Total code points: 750 +# Total code points: 757 # ================================================ @@ -3698,8 +3761,10 @@ FF70 ; CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 1F9BB ; EB # So EAR WITH HEARING AID 1F9CD..1F9CF ; EB # So [3] STANDING PERSON..DEAF PERSON 1F9D1..1F9DD ; EB # So [13] ADULT..ELF +1FAC3..1FAC5 ; EB # So [3] PREGNANT MAN..PERSON WITH CROWN +1FAF0..1FAF6 ; EB # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS -# Total code points: 122 +# Total code points: 132 # ================================================ diff --git a/lib/unicore/extracted/DNumType.txt b/lib/unicore/extracted/DNumType.txt index 984afe2f17..6d819ea990 100644 --- a/lib/unicore/extracted/DNumType.txt +++ b/lib/unicore/extracted/DNumType.txt @@ -1,6 +1,6 @@ -# DerivedNumericType-13.0.0.txt -# Date: 2019-09-08, 23:31:09 GMT -# © 2019 Unicode®, Inc. +# DerivedNumericType-14.0.0.txt +# Date: 2021-03-08, 06:22:31 GMT +# © 2021 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 # @@ -265,6 +265,7 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11D50..11D59 ; Decimal # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Decimal # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; Decimal # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Decimal # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Decimal # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Decimal # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Decimal # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE @@ -272,6 +273,6 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 650 +# Total code points: 660 # EOF diff --git a/lib/unicore/extracted/DNumValues.txt b/lib/unicore/extracted/DNumValues.txt index f70662acc9..84cb90749a 100644 --- a/lib/unicore/extracted/DNumValues.txt +++ b/lib/unicore/extracted/DNumValues.txt @@ -1,6 +1,6 @@ -# DerivedNumericValues-13.0.0.txt -# Date: 2019-09-08, 23:31:10 GMT -# © 2019 Unicode®, Inc. +# DerivedNumericValues-14.0.0.txt +# Date: 2021-03-08, 06:22:32 GMT +# © 2021 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 # @@ -106,6 +106,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 11D50 ; 0.0 ; ; 0 # Nd MASARAM GONDI DIGIT ZERO 11DA0 ; 0.0 ; ; 0 # Nd GUNJALA GONDI DIGIT ZERO 16A60 ; 0.0 ; ; 0 # Nd MRO DIGIT ZERO +16AC0 ; 0.0 ; ; 0 # Nd TANGSA DIGIT ZERO 16B50 ; 0.0 ; ; 0 # Nd PAHAWH HMONG DIGIT ZERO 16E80 ; 0.0 ; ; 0 # No MEDEFAIDRIN DIGIT ZERO 1D2E0 ; 0.0 ; ; 0 # No MAYAN NUMERAL ZERO @@ -121,7 +122,7 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1FBF0 ; 0.0 ; ; 0 # Nd SEGMENTED DIGIT ZERO -# Total code points: 83 +# Total code points: 84 # ================================================ @@ -520,6 +521,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1244F ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE BAN2 12458 ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE ESHE3 16A61 ; 1.0 ; ; 1 # Nd MRO DIGIT ONE +16AC1 ; 1.0 ; ; 1 # Nd TANGSA DIGIT ONE 16B51 ; 1.0 ; ; 1 # Nd PAHAWH HMONG DIGIT ONE 16E81 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE 16E94 ; 1.0 ; ; 1 # No MEDEFAIDRIN DIGIT ONE ALTERNATE FORM @@ -544,7 +546,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1FBF1 ; 1.0 ; ; 1 # Nd SEGMENTED DIGIT ONE 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 140 +# Total code points: 141 # ================================================ @@ -667,6 +669,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 12456 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN NIGIDAMIN 12459 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO ESHE3 16A62 ; 2.0 ; ; 2 # Nd MRO DIGIT TWO +16AC2 ; 2.0 ; ; 2 # Nd TANGSA DIGIT TWO 16B52 ; 2.0 ; ; 2 # Nd PAHAWH HMONG DIGIT TWO 16E82 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO 16E95 ; 2.0 ; ; 2 # No MEDEFAIDRIN DIGIT TWO ALTERNATE FORM @@ -691,7 +694,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1FBF2 ; 2.0 ; ; 2 # Nd SEGMENTED DIGIT TWO 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 139 +# Total code points: 140 # ================================================ @@ -809,6 +812,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 12451 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE BAN2 12457 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN NIGIDAESH 16A63 ; 3.0 ; ; 3 # Nd MRO DIGIT THREE +16AC3 ; 3.0 ; ; 3 # Nd TANGSA DIGIT THREE 16B53 ; 3.0 ; ; 3 # Nd PAHAWH HMONG DIGIT THREE 16E83 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE 16E96 ; 3.0 ; ; 3 # No MEDEFAIDRIN DIGIT THREE ALTERNATE FORM @@ -835,7 +839,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 140 +# Total code points: 141 # ================================================ @@ -948,6 +952,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 12452..12453 ; 4.0 ; ; 4 # Nl [2] CUNEIFORM NUMERIC SIGN FOUR BAN2..CUNEIFORM NUMERIC SIGN FOUR BAN2 VARIANT FORM 12469 ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR U VARIANT FORM 16A64 ; 4.0 ; ; 4 # Nd MRO DIGIT FOUR +16AC4 ; 4.0 ; ; 4 # Nd TANGSA DIGIT FOUR 16B54 ; 4.0 ; ; 4 # Nd PAHAWH HMONG DIGIT FOUR 16E84 ; 4.0 ; ; 4 # No MEDEFAIDRIN DIGIT FOUR 1D2E4 ; 4.0 ; ; 4 # No MAYAN NUMERAL FOUR @@ -972,7 +977,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 131 +# Total code points: 132 # ================================================ @@ -1088,6 +1093,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 12454..12455 ; 5.0 ; ; 5 # Nl [2] CUNEIFORM NUMERIC SIGN FIVE BAN2..CUNEIFORM NUMERIC SIGN FIVE BAN2 VARIANT FORM 1246A ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE U VARIANT FORM 16A65 ; 5.0 ; ; 5 # Nd MRO DIGIT FIVE +16AC5 ; 5.0 ; ; 5 # Nd TANGSA DIGIT FIVE 16B55 ; 5.0 ; ; 5 # Nd PAHAWH HMONG DIGIT FIVE 16E85 ; 5.0 ; ; 5 # No MEDEFAIDRIN DIGIT FIVE 1D2E5 ; 5.0 ; ; 5 # No MAYAN NUMERAL FIVE @@ -1111,7 +1117,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1FBF5 ; 5.0 ; ; 5 # Nd SEGMENTED DIGIT FIVE 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 129 +# Total code points: 130 # ================================================ @@ -1214,6 +1220,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1244E ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX ASH TENU 1246B ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX U VARIANT FORM 16A66 ; 6.0 ; ; 6 # Nd MRO DIGIT SIX +16AC6 ; 6.0 ; ; 6 # Nd TANGSA DIGIT SIX 16B56 ; 6.0 ; ; 6 # Nd PAHAWH HMONG DIGIT SIX 16E86 ; 6.0 ; ; 6 # No MEDEFAIDRIN DIGIT SIX 1D2E6 ; 6.0 ; ; 6 # No MAYAN NUMERAL SIX @@ -1235,7 +1242,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1FBF6 ; 6.0 ; ; 6 # Nd SEGMENTED DIGIT SIX 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 113 +# Total code points: 114 # ================================================ @@ -1335,6 +1342,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 12441..12443 ; 7.0 ; ; 7 # Nl [3] CUNEIFORM NUMERIC SIGN SEVEN VARIANT FORM IMIN3..CUNEIFORM NUMERIC SIGN SEVEN VARIANT FORM IMIN B 1246C ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN U VARIANT FORM 16A67 ; 7.0 ; ; 7 # Nd MRO DIGIT SEVEN +16AC7 ; 7.0 ; ; 7 # Nd TANGSA DIGIT SEVEN 16B57 ; 7.0 ; ; 7 # Nd PAHAWH HMONG DIGIT SEVEN 16E87 ; 7.0 ; ; 7 # No MEDEFAIDRIN DIGIT SEVEN 1D2E7 ; 7.0 ; ; 7 # No MAYAN NUMERAL SEVEN @@ -1356,7 +1364,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1FBF7 ; 7.0 ; ; 7 # Nd SEGMENTED DIGIT SEVEN 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 112 +# Total code points: 113 # ================================================ @@ -1454,6 +1462,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 12444..12445 ; 8.0 ; ; 8 # Nl [2] CUNEIFORM NUMERIC SIGN EIGHT VARIANT FORM USSU..CUNEIFORM NUMERIC SIGN EIGHT VARIANT FORM USSU3 1246D ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT U VARIANT FORM 16A68 ; 8.0 ; ; 8 # Nd MRO DIGIT EIGHT +16AC8 ; 8.0 ; ; 8 # Nd TANGSA DIGIT EIGHT 16B58 ; 8.0 ; ; 8 # Nd PAHAWH HMONG DIGIT EIGHT 16E88 ; 8.0 ; ; 8 # No MEDEFAIDRIN DIGIT EIGHT 1D2E8 ; 8.0 ; ; 8 # No MAYAN NUMERAL EIGHT @@ -1474,7 +1483,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA 1FBF8 ; 8.0 ; ; 8 # Nd SEGMENTED DIGIT EIGHT -# Total code points: 108 +# Total code points: 109 # ================================================ @@ -1573,6 +1582,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 12446..12449 ; 9.0 ; ; 9 # Nl [4] CUNEIFORM NUMERIC SIGN NINE VARIANT FORM ILIMMU..CUNEIFORM NUMERIC SIGN NINE VARIANT FORM ILIMMU A 1246E ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 16A69 ; 9.0 ; ; 9 # Nd MRO DIGIT NINE +16AC9 ; 9.0 ; ; 9 # Nd TANGSA DIGIT NINE 16B59 ; 9.0 ; ; 9 # Nd PAHAWH HMONG DIGIT NINE 16E89 ; 9.0 ; ; 9 # No MEDEFAIDRIN DIGIT NINE 1D2E9 ; 9.0 ; ; 9 # No MAYAN NUMERAL NINE @@ -1594,7 +1604,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1FBF9 ; 9.0 ; ; 9 # Nd SEGMENTED DIGIT NINE 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 112 +# Total code points: 113 # ================================================ diff --git a/lib/unicore/mktables b/lib/unicore/mktables index 89a2e15ef5..187915bc8b 100644 --- a/lib/unicore/mktables +++ b/lib/unicore/mktables @@ -48,7 +48,7 @@ sub NON_ASCII_PLATFORM { ord("A") != 65 } # expected, a warning will be generated. If an older version is being # compiled, any bounds tests that fail in the generated test file (-maketest # option) will be marked as TODO. -my $version_of_mk_invlist_bounds = v13.0.0; +my $version_of_mk_invlist_bounds = v14.0.0; ########################################################################## # diff --git a/lib/unicore/uni_keywords.pl b/lib/unicore/uni_keywords.pl index b08ab3b738..1cb7904a9f 100644 --- a/lib/unicore/uni_keywords.pl +++ b/lib/unicore/uni_keywords.pl @@ -4,19 +4,19 @@ # Any changes made here will be lost! %Unicode::UCD::uni_prop_ptrs_indices = ( - '_perl_any_folds' => 1187, - '_perl_charname_begin' => 1188, - '_perl_charname_continue' => 1189, - '_perl_folds_to_multi_char' => 1190, - '_perl_idcont' => 1191, - '_perl_idstart' => 1192, - '_perl_is_in_multi_char_fold' => 1193, - '_perl_nchar' => 1194, - '_perl_patws' => 1195, - '_perl_problematic_locale_foldeds_start' => 1196, - '_perl_problematic_locale_folds' => 1197, - '_perl_quotemeta' => 1198, - '_perl_surrogate' => 1199, + '_perl_any_folds' => 1211, + '_perl_charname_begin' => 1212, + '_perl_charname_continue' => 1213, + '_perl_folds_to_multi_char' => 1214, + '_perl_idcont' => 1215, + '_perl_idstart' => 1216, + '_perl_is_in_multi_char_fold' => 1217, + '_perl_nchar' => 1218, + '_perl_patws' => 1219, + '_perl_problematic_locale_foldeds_start' => 1220, + '_perl_problematic_locale_folds' => 1221, + '_perl_quotemeta' => 1222, + '_perl_surrogate' => 1223, 'adlm' => 1, 'aegeannumbers' => 2, 'age=10' => 3, @@ -24,1280 +24,1304 @@ 'age=12' => 5, 'age=12.1' => 6, 'age=13' => 7, - 'age=2' => 8, - 'age=2.1' => 9, - 'age=3' => 10, - 'age=3.1' => 11, - 'age=3.2' => 12, - 'age=4' => 13, - 'age=4.1' => 14, - 'age=5' => 15, - 'age=5.1' => 16, - 'age=5.2' => 17, - 'age=6' => 18, - 'age=6.1' => 19, - 'age=6.2' => 20, - 'age=6.3' => 21, - 'age=7' => 22, - 'age=8' => 23, - 'age=9' => 24, - 'age=na' => 25, - 'aghb' => 26, - 'ahex' => 970, - 'ahom' => 27, - 'alchemical' => 28, - 'all' => 29, - 'alnum' => 1161, - 'alpha' => 1162, - 'alphabetic' => 1162, - 'alphabeticpf' => 30, - 'ancientgreekmusic' => 31, - 'ancientgreeknumbers' => 32, - 'ancientsymbols' => 33, - 'any' => 34, - 'arab' => 35, - 'arabicexta' => 36, - 'arabicmath' => 37, - 'arabicpfa' => 38, - 'arabicpfb' => 39, - 'arabicsup' => 40, - 'armi' => 41, - 'armn' => 42, - 'arrows' => 43, - 'ascii' => 44, - 'asciihexdigit' => 970, - 'assigned' => 45, - 'avst' => 46, - 'bali' => 47, - 'bamu' => 48, - 'bamumsup' => 49, - 'basiclatin' => 44, - 'bass' => 50, - 'batk' => 51, - 'bc=al' => 52, - 'bc=an' => 53, - 'bc=b' => 54, - 'bc=bn' => 55, - 'bc=cs' => 56, - 'bc=en' => 57, - 'bc=es' => 58, - 'bc=et' => 59, - 'bc=fsi' => 60, - 'bc=l' => 61, - 'bc=lre' => 62, - 'bc=lri' => 63, - 'bc=lro' => 64, - 'bc=nsm' => 65, - 'bc=on' => 66, - 'bc=pdf' => 67, - 'bc=pdi' => 68, - 'bc=r' => 69, - 'bc=rle' => 70, - 'bc=rli' => 71, - 'bc=rlo' => 72, - 'bc=s' => 73, - 'bc=ws' => 74, - 'beng' => 75, - 'bhks' => 76, - 'bidic' => 77, - 'bidim' => 78, - 'blank' => 1163, - 'blockelements' => 79, - 'bopo' => 80, - 'bopomofoext' => 81, - 'boxdrawing' => 82, - 'bpt=c' => 83, - 'bpt=n' => 84, - 'bpt=o' => 85, - 'brah' => 86, - 'brai' => 87, - 'bugi' => 88, - 'buhd' => 89, - 'byzantinemusic' => 90, - 'c' => 91, - 'cakm' => 92, - 'cans' => 93, - 'cari' => 94, - 'cased' => 95, - 'casedletter' => 96, - 'cc' => 1164, - 'ccc=0' => 97, - 'ccc=1' => 98, - 'ccc=10' => 99, - 'ccc=103' => 100, - 'ccc=107' => 101, - 'ccc=11' => 102, - 'ccc=118' => 103, - 'ccc=12' => 104, - 'ccc=122' => 105, - 'ccc=129' => 106, - 'ccc=13' => 107, - 'ccc=130' => 108, - 'ccc=132' => 109, - 'ccc=14' => 110, - 'ccc=15' => 111, - 'ccc=16' => 112, - 'ccc=17' => 113, - 'ccc=18' => 114, - 'ccc=19' => 115, - 'ccc=20' => 116, - 'ccc=202' => 117, - 'ccc=21' => 118, - 'ccc=214' => 119, - 'ccc=216' => 120, - 'ccc=22' => 121, - 'ccc=23' => 122, - 'ccc=24' => 123, - 'ccc=25' => 124, - 'ccc=26' => 125, - 'ccc=27' => 126, - 'ccc=28' => 127, - 'ccc=29' => 128, - 'ccc=30' => 129, - 'ccc=31' => 130, - 'ccc=32' => 131, - 'ccc=33' => 132, - 'ccc=34' => 133, - 'ccc=35' => 134, - 'ccc=36' => 135, - 'ccc=6' => 136, - 'ccc=7' => 137, - 'ccc=8' => 138, - 'ccc=84' => 139, - 'ccc=9' => 140, - 'ccc=91' => 141, - 'ccc=a' => 142, - 'ccc=al' => 143, - 'ccc=ar' => 144, - 'ccc=b' => 145, - 'ccc=bl' => 146, - 'ccc=br' => 147, - 'ccc=da' => 148, - 'ccc=db' => 149, - 'ccc=is' => 150, - 'ccc=l' => 151, - 'ccc=r' => 152, - 'ce' => 153, - 'cf' => 154, - 'cham' => 155, - 'cher' => 156, - 'cherokeesup' => 157, - 'chesssymbols' => 158, - 'chrs' => 159, - 'ci' => 160, - 'cjk' => 161, - 'cjkcompat' => 162, - 'cjkcompatforms' => 163, - 'cjkcompatideographs' => 164, - 'cjkcompatideographssup' => 165, - 'cjkexta' => 166, - 'cjkextb' => 167, - 'cjkextc' => 168, - 'cjkextd' => 169, - 'cjkexte' => 170, - 'cjkextf' => 171, - 'cjkextg' => 172, - 'cjkradicalssup' => 173, - 'cjkstrokes' => 174, - 'cjksymbols' => 175, - 'cn' => 176, - 'cntrl' => 1164, - 'co' => 177, - 'compatjamo' => 178, - 'compex' => 179, - 'control' => 1164, - 'controlpictures' => 180, - 'copt' => 181, - 'copticepactnumbers' => 182, - 'countingrod' => 183, - 'cprt' => 184, - 'cuneiformnumbers' => 185, - 'currencysymbols' => 186, - 'cwcf' => 187, - 'cwcm' => 188, - 'cwkcf' => 189, - 'cwl' => 190, - 'cwt' => 191, - 'cwu' => 192, - 'cypriotsyllabary' => 193, - 'cyrillicexta' => 194, - 'cyrillicextb' => 195, - 'cyrillicextc' => 196, - 'cyrillicsup' => 197, - 'cyrl' => 198, - 'dash' => 199, - 'decimalnumber' => 1165, - 'dep' => 200, - 'deva' => 201, - 'devanagariext' => 202, - 'di' => 203, - 'dia' => 204, - 'diacriticals' => 205, - 'diacriticalsext' => 206, - 'diacriticalsforsymbols' => 207, - 'diacriticalssup' => 208, - 'diak' => 209, - 'digit' => 1165, - 'dingbats' => 210, - 'dogr' => 211, - 'domino' => 212, - 'dsrt' => 213, - 'dt=can' => 214, - 'dt=com' => 215, - 'dt=enc' => 216, - 'dt=fin' => 217, - 'dt=font' => 218, - 'dt=fra' => 219, - 'dt=init' => 220, - 'dt=iso' => 221, - 'dt=med' => 222, - 'dt=nar' => 223, - 'dt=nb' => 224, - 'dt=noncanon' => 225, - 'dt=none' => 226, - 'dt=sml' => 227, - 'dt=sqr' => 228, - 'dt=sub' => 229, - 'dt=sup' => 230, - 'dt=vert' => 231, - 'dupl' => 232, - 'ea=a' => 234, - 'ea=f' => 235, - 'ea=h' => 236, - 'ea=n' => 237, - 'ea=na' => 238, - 'ea=w' => 239, - 'earlydynasticcuneiform' => 233, - 'ebase' => 240, - 'ecomp' => 241, - 'egyp' => 242, - 'egyptianhieroglyphformatcontrols' => 243, - 'elba' => 244, - 'elym' => 245, - 'emod' => 246, - 'emoji' => 247, - 'emoticons' => 248, - 'enclosedalphanum' => 249, - 'enclosedalphanumsup' => 250, - 'enclosedcjk' => 251, - 'enclosedideographicsup' => 252, - 'epres' => 253, - 'ethi' => 254, - 'ethiopicext' => 255, - 'ethiopicexta' => 256, - 'ethiopicsup' => 257, - 'ext' => 258, - 'extpict' => 259, - 'gcb=cn' => 260, - 'gcb=ex' => 261, - 'gcb=l' => 262, - 'gcb=pp' => 263, - 'gcb=sm' => 264, - 'gcb=t' => 265, - 'gcb=v' => 266, - 'gcb=xx' => 267, - 'geometricshapes' => 268, - 'geometricshapesext' => 269, - 'geor' => 270, - 'georgianext' => 271, - 'georgiansup' => 272, - 'glag' => 273, - 'glagoliticsup' => 274, - 'gong' => 275, - 'gonm' => 276, - 'goth' => 277, - 'gran' => 278, - 'graph' => 1166, - 'grbase' => 279, - 'greekext' => 280, - 'grek' => 281, - 'grext' => 282, - 'gujr' => 283, - 'guru' => 284, - 'halfandfullforms' => 285, - 'halfmarks' => 286, - 'han' => 287, - 'hang' => 288, - 'hano' => 289, - 'hatr' => 290, - 'hebr' => 291, - 'hex' => 1173, - 'hexdigit' => 1173, - 'highpusurrogates' => 292, - 'highsurrogates' => 293, - 'hira' => 294, - 'hluw' => 295, - 'hmng' => 296, - 'hmnp' => 297, - 'horizspace' => 1163, - 'hst=na' => 298, - 'hung' => 299, - 'hyphen_perl_aux' => 300, - 'idc' => 301, - 'identifierstatus=allowed' => 302, - 'identifierstatus=restricted' => 303, - 'identifiertype=defaultignorable' => 304, - 'identifiertype=exclusion' => 305, - 'identifiertype=inclusion' => 306, - 'identifiertype=limiteduse' => 307, - 'identifiertype=notcharacter' => 308, - 'identifiertype=notnfkc' => 309, - 'identifiertype=notxid' => 310, - 'identifiertype=obsolete' => 311, - 'identifiertype=recommended' => 312, - 'identifiertype=technical' => 313, - 'identifiertype=uncommonuse' => 314, - 'ideo' => 315, - 'ideographicsymbols' => 316, - 'ids' => 317, - 'idsb' => 318, - 'idst' => 319, - 'in=1.1' => 517, - 'in=10' => 512, - 'in=11' => 513, - 'in=12' => 514, - 'in=12.1' => 515, - 'in=13' => 516, - 'in=2' => 518, - 'in=2.1' => 519, - 'in=3' => 520, - 'in=3.1' => 521, - 'in=3.2' => 522, - 'in=4' => 523, - 'in=4.1' => 524, - 'in=5' => 525, - 'in=5.1' => 526, - 'in=5.2' => 527, - 'in=6' => 528, - 'in=6.1' => 529, - 'in=6.2' => 530, - 'in=6.3' => 531, - 'in=7' => 532, - 'in=8' => 533, - 'in=9' => 534, - 'inadlam' => 320, - 'inahom' => 321, - 'inanatolianhieroglyphs' => 322, - 'inarabic' => 323, - 'inarmenian' => 324, - 'inavestan' => 325, - 'inbalinese' => 326, - 'inbamum' => 327, - 'inbassavah' => 328, - 'inbatak' => 329, - 'inbengali' => 330, - 'inbhaiksuki' => 331, - 'inbopomofo' => 332, - 'inbrahmi' => 333, - 'inbuginese' => 334, - 'inbuhid' => 335, - 'incarian' => 336, - 'incaucasianalbanian' => 337, - 'inchakma' => 338, - 'incham' => 339, - 'incherokee' => 340, - 'inchorasmian' => 341, - 'incoptic' => 342, - 'incuneiform' => 343, - 'incyrillic' => 344, - 'indevanagari' => 345, - 'indicnumberforms' => 346, - 'indicsiyaqnumbers' => 347, - 'indivesakuru' => 348, - 'indogra' => 349, - 'induployan' => 350, - 'inegyptianhieroglyphs' => 351, - 'inelbasan' => 352, - 'inelymaic' => 353, - 'inethiopic' => 354, - 'ingeorgian' => 355, - 'inglagolitic' => 356, - 'ingothic' => 357, - 'ingrantha' => 358, - 'ingreek' => 359, - 'ingujarati' => 360, - 'ingunjalagondi' => 361, - 'ingurmukhi' => 362, - 'inhangul' => 363, - 'inhanifirohingya' => 364, - 'inhanunoo' => 365, - 'inhatran' => 366, - 'inhebrew' => 367, - 'inhiragana' => 368, - 'inidc' => 369, - 'inimperialaramaic' => 370, - 'ininscriptionalpahlavi' => 371, - 'ininscriptionalparthian' => 372, - 'injavanese' => 373, - 'inkaithi' => 374, - 'inkannada' => 375, - 'inkatakana' => 376, - 'inkharoshthi' => 377, - 'inkhitansmallscript' => 378, - 'inkhmer' => 379, - 'inkhojki' => 380, - 'inkhudawadi' => 381, - 'inlao' => 382, - 'inlepcha' => 383, - 'inlimbu' => 384, - 'inlineara' => 385, - 'inlisu' => 386, - 'inlycian' => 387, - 'inlydian' => 388, - 'inmahajani' => 389, - 'inmakasar' => 390, - 'inmalayalam' => 391, - 'inmandaic' => 392, - 'inmanichaean' => 393, - 'inmarchen' => 394, - 'inmasaramgondi' => 395, - 'inmedefaidrin' => 396, - 'inmeeteimayek' => 397, - 'inmendekikakui' => 398, - 'inmeroiticcursive' => 399, - 'inmiao' => 400, - 'inmodi' => 401, - 'inmongolian' => 402, - 'inmro' => 403, - 'inmultani' => 404, - 'inmyanmar' => 405, - 'innabataean' => 406, - 'innandinagari' => 407, - 'innewa' => 408, - 'innewtailue' => 409, - 'innko' => 410, - 'innushu' => 411, - 'innyiakengpuachuehmong' => 412, - 'inogham' => 413, - 'inoldhungarian' => 414, - 'inolditalic' => 415, - 'inoldpermic' => 416, - 'inoldpersian' => 417, - 'inoldsogdian' => 418, - 'inoldturkic' => 419, - 'inoriya' => 420, - 'inosage' => 421, - 'inosmanya' => 422, - 'inpahawhhmong' => 423, - 'inpaucinhau' => 424, - 'inpc=bottom' => 425, - 'inpc=bottomandleft' => 426, - 'inpc=bottomandright' => 427, - 'inpc=left' => 428, - 'inpc=leftandright' => 429, - 'inpc=na' => 430, - 'inpc=overstruck' => 431, - 'inpc=right' => 432, - 'inpc=top' => 433, - 'inpc=topandbottom' => 434, - 'inpc=topandbottomandleft' => 435, - 'inpc=topandbottomandright' => 436, - 'inpc=topandleft' => 437, - 'inpc=topandleftandright' => 438, - 'inpc=topandright' => 439, - 'inphagspa' => 440, - 'inphoenician' => 441, - 'inpsalterpahlavi' => 442, - 'inpunctuation' => 443, - 'inrejang' => 444, - 'inrunic' => 445, - 'insamaritan' => 446, - 'insaurashtra' => 447, - 'insc=avagraha' => 448, - 'insc=bindu' => 449, - 'insc=brahmijoiningnumber' => 450, - 'insc=cantillationmark' => 451, - 'insc=consonant' => 452, - 'insc=consonantdead' => 453, - 'insc=consonantfinal' => 454, - 'insc=consonantheadletter' => 455, - 'insc=consonantinitialpostfixed' => 456, - 'insc=consonantkiller' => 457, - 'insc=consonantmedial' => 458, - 'insc=consonantplaceholder' => 459, - 'insc=consonantprecedingrepha' => 460, - 'insc=consonantprefixed' => 461, - 'insc=consonantsubjoined' => 462, - 'insc=consonantsucceedingrepha' => 463, - 'insc=consonantwithstacker' => 464, - 'insc=geminationmark' => 465, - 'insc=invisiblestacker' => 466, - 'insc=modifyingletter' => 467, - 'insc=nonjoiner' => 468, - 'insc=nukta' => 469, - 'insc=number' => 470, - 'insc=numberjoiner' => 471, - 'insc=other' => 472, - 'insc=purekiller' => 473, - 'insc=registershifter' => 474, - 'insc=syllablemodifier' => 475, - 'insc=toneletter' => 476, - 'insc=tonemark' => 477, - 'insc=virama' => 478, - 'insc=visarga' => 479, - 'insc=vowel' => 480, - 'insc=voweldependent' => 481, - 'insc=vowelindependent' => 482, - 'insiddham' => 483, - 'insinhala' => 484, - 'insogdian' => 485, - 'insorasompeng' => 486, - 'insoyombo' => 487, - 'insundanese' => 488, - 'insylotinagri' => 489, - 'insyriac' => 490, - 'intagalog' => 491, - 'intagbanwa' => 492, - 'intaile' => 493, - 'intaitham' => 494, - 'intaiviet' => 495, - 'intakri' => 496, - 'intamil' => 497, - 'intangut' => 498, - 'intelugu' => 499, - 'inthaana' => 500, - 'inthai' => 501, - 'intibetan' => 502, - 'intifinagh' => 503, - 'intirhuta' => 504, - 'inugaritic' => 505, - 'invai' => 506, - 'invs' => 507, - 'inwancho' => 508, - 'inwarangciti' => 509, - 'inyezidi' => 510, - 'inzanabazarsquare' => 511, - 'ipaext' => 535, - 'ital' => 536, - 'jamo' => 537, - 'jamoexta' => 538, - 'jamoextb' => 539, - 'java' => 540, - 'jg=africanfeh' => 541, - 'jg=africannoon' => 542, - 'jg=africanqaf' => 543, - 'jg=ain' => 544, - 'jg=alaph' => 545, - 'jg=alef' => 546, - 'jg=beh' => 547, - 'jg=beth' => 548, - 'jg=burushaskiyehbarree' => 549, - 'jg=dal' => 550, - 'jg=dalathrish' => 551, - 'jg=e' => 552, - 'jg=farsiyeh' => 553, - 'jg=fe' => 554, - 'jg=feh' => 555, - 'jg=finalsemkath' => 556, - 'jg=gaf' => 557, - 'jg=gamal' => 558, - 'jg=hah' => 559, - 'jg=hamzaonhehgoal' => 560, - 'jg=hanifirohingyakinnaya' => 561, - 'jg=hanifirohingyapa' => 562, - 'jg=he' => 563, - 'jg=heh' => 564, - 'jg=hehgoal' => 565, - 'jg=heth' => 566, - 'jg=kaf' => 567, - 'jg=kaph' => 568, - 'jg=khaph' => 569, - 'jg=knottedheh' => 570, - 'jg=lam' => 571, - 'jg=lamadh' => 572, - 'jg=malayalambha' => 573, - 'jg=malayalamja' => 574, - 'jg=malayalamlla' => 575, - 'jg=malayalamllla' => 576, - 'jg=malayalamnga' => 577, - 'jg=malayalamnna' => 578, - 'jg=malayalamnnna' => 579, - 'jg=malayalamnya' => 580, - 'jg=malayalamra' => 581, - 'jg=malayalamssa' => 582, - 'jg=malayalamtta' => 583, - 'jg=manichaeanaleph' => 584, - 'jg=manichaeanayin' => 585, - 'jg=manichaeanbeth' => 586, - 'jg=manichaeandaleth' => 587, - 'jg=manichaeandhamedh' => 588, - 'jg=manichaeanfive' => 589, - 'jg=manichaeangimel' => 590, - 'jg=manichaeanheth' => 591, - 'jg=manichaeanhundred' => 592, - 'jg=manichaeankaph' => 593, - 'jg=manichaeanlamedh' => 594, - 'jg=manichaeanmem' => 595, - 'jg=manichaeannun' => 596, - 'jg=manichaeanone' => 597, - 'jg=manichaeanpe' => 598, - 'jg=manichaeanqoph' => 599, - 'jg=manichaeanresh' => 600, - 'jg=manichaeansadhe' => 601, - 'jg=manichaeansamekh' => 602, - 'jg=manichaeantaw' => 603, - 'jg=manichaeanten' => 604, - 'jg=manichaeanteth' => 605, - 'jg=manichaeanthamedh' => 606, - 'jg=manichaeantwenty' => 607, - 'jg=manichaeanwaw' => 608, - 'jg=manichaeanyodh' => 609, - 'jg=manichaeanzayin' => 610, - 'jg=meem' => 611, - 'jg=mim' => 612, - 'jg=nojoininggroup' => 613, - 'jg=noon' => 614, - 'jg=nun' => 615, - 'jg=nya' => 616, - 'jg=pe' => 617, - 'jg=qaf' => 618, - 'jg=qaph' => 619, - 'jg=reh' => 620, - 'jg=reversedpe' => 621, - 'jg=rohingyayeh' => 622, - 'jg=sad' => 623, - 'jg=sadhe' => 624, - 'jg=seen' => 625, - 'jg=semkath' => 626, - 'jg=shin' => 627, - 'jg=straightwaw' => 628, - 'jg=swashkaf' => 629, - 'jg=syriacwaw' => 630, - 'jg=tah' => 631, - 'jg=taw' => 632, - 'jg=tehmarbuta' => 633, - 'jg=teth' => 634, - 'jg=waw' => 635, - 'jg=yeh' => 636, - 'jg=yehbarree' => 637, - 'jg=yehwithtail' => 638, - 'jg=yudh' => 639, - 'jg=yudhhe' => 640, - 'jg=zain' => 641, - 'jg=zhain' => 642, - 'joinc' => 643, - 'jt=c' => 644, - 'jt=d' => 645, - 'jt=l' => 646, - 'jt=r' => 647, - 'jt=t' => 648, - 'jt=u' => 649, - 'kali' => 650, - 'kana' => 651, - 'kanaexta' => 652, - 'kanasup' => 653, - 'kanbun' => 654, - 'kangxi' => 655, - 'katakanaext' => 656, - 'khar' => 657, - 'khmersymbols' => 658, - 'khmr' => 659, - 'khoj' => 660, - 'kits' => 661, - 'knda' => 662, - 'kthi' => 663, - 'l' => 664, - 'l_' => 96, - 'l_amp_' => 96, - 'lana' => 665, - 'lao' => 666, - 'latin1' => 667, - 'latinexta' => 668, - 'latinextadditional' => 669, - 'latinextb' => 670, - 'latinextc' => 671, - 'latinextd' => 672, - 'latinexte' => 673, - 'latn' => 674, - 'lb=ai' => 675, - 'lb=al' => 676, - 'lb=b2' => 677, - 'lb=ba' => 678, - 'lb=bb' => 679, - 'lb=bk' => 680, - 'lb=cb' => 681, - 'lb=cj' => 682, - 'lb=cl' => 683, - 'lb=cm' => 684, - 'lb=cp' => 685, - 'lb=cr' => 686, - 'lb=ex' => 687, - 'lb=gl' => 688, - 'lb=h2' => 689, - 'lb=h3' => 690, - 'lb=hl' => 691, - 'lb=hy' => 692, - 'lb=id' => 693, - 'lb=in' => 694, - 'lb=is' => 695, - 'lb=lf' => 696, - 'lb=nl' => 697, - 'lb=ns' => 698, - 'lb=nu' => 699, - 'lb=op' => 700, - 'lb=po' => 701, - 'lb=pr' => 702, - 'lb=qu' => 703, - 'lb=sa' => 704, - 'lb=sg_perl_aux' => 705, - 'lb=sp' => 706, - 'lb=sy' => 707, - 'lb=wj' => 708, - 'lb=xx' => 709, - 'lb=zw' => 710, - 'lb=zwj' => 711, - 'lc' => 96, - 'lepc' => 712, - 'letterlikesymbols' => 713, - 'limb' => 714, - 'lina' => 715, - 'linb' => 716, - 'linearbideograms' => 717, - 'linearbsyllabary' => 718, - 'lisu' => 719, - 'lisusup' => 720, - 'll' => 724, - 'lm' => 721, - 'lo' => 722, - 'loe' => 723, - 'lower' => 1167, - 'lowercase' => 1167, - 'lowercaseletter' => 724, - 'lowsurrogates' => 725, - 'lt' => 1124, - 'lu' => 1130, - 'lyci' => 726, - 'lydi' => 727, - 'm' => 728, - 'mahj' => 729, - 'mahjong' => 730, - 'maka' => 731, - 'mand' => 732, - 'mani' => 733, - 'marc' => 734, - 'math' => 735, - 'mathalphanum' => 736, - 'mathoperators' => 737, - 'mayannumerals' => 738, - 'mc' => 739, - 'me' => 740, - 'medf' => 741, - 'meeteimayekext' => 742, - 'mend' => 743, - 'merc' => 744, - 'mero' => 745, - 'miao' => 746, - 'miscarrows' => 747, - 'miscmathsymbolsa' => 748, - 'miscmathsymbolsb' => 749, - 'miscpictographs' => 750, - 'miscsymbols' => 751, - 'misctechnical' => 752, - 'mlym' => 753, - 'mn' => 754, - 'modi' => 755, - 'modifierletters' => 756, - 'modifiertoneletters' => 757, - 'mong' => 758, - 'mongoliansup' => 759, - 'mro' => 760, - 'mtei' => 761, - 'mult' => 762, - 'music' => 763, - 'myanmarexta' => 764, - 'myanmarextb' => 765, - 'mymr' => 766, - 'n' => 767, - 'nand' => 768, - 'narb' => 769, - 'nb' => 770, - 'nbat' => 771, - 'nd' => 1165, - 'newa' => 772, - 'nfcqc=m' => 773, - 'nfcqc=y' => 774, - 'nfdqc=y' => 775, - 'nfkcqc=n' => 776, - 'nfkcqc=y' => 777, - 'nfkdqc=n' => 778, - 'nko' => 779, - 'nl' => 780, - 'no' => 781, - 'nshu' => 782, - 'nt=di' => 783, - 'nt=nu' => 784, - 'numberforms' => 785, - 'nv=0' => 786, - 'nv=1' => 787, - 'nv=1/10' => 812, - 'nv=1/12' => 813, - 'nv=1/16' => 814, - 'nv=1/160' => 815, - 'nv=1/2' => 816, - 'nv=1/20' => 817, - 'nv=1/3' => 818, - 'nv=1/32' => 819, - 'nv=1/320' => 820, - 'nv=1/4' => 821, - 'nv=1/40' => 822, - 'nv=1/5' => 823, - 'nv=1/6' => 824, - 'nv=1/64' => 825, - 'nv=1/7' => 826, - 'nv=1/8' => 827, - 'nv=1/80' => 828, - 'nv=1/9' => 829, - 'nv=10' => 788, - 'nv=100' => 789, - 'nv=1000' => 790, - 'nv=10000' => 791, - 'nv=100000' => 792, - 'nv=1000000' => 793, - 'nv=10000000' => 794, - 'nv=100000000' => 795, - 'nv=10000000000' => 796, - 'nv=1000000000000' => 797, - 'nv=11' => 798, - 'nv=11/12' => 799, - 'nv=11/2' => 800, - 'nv=12' => 801, - 'nv=13' => 802, - 'nv=13/2' => 803, - 'nv=14' => 804, - 'nv=15' => 805, - 'nv=15/2' => 806, - 'nv=16' => 807, - 'nv=17' => 808, - 'nv=17/2' => 809, - 'nv=18' => 810, - 'nv=19' => 811, - 'nv=2' => 830, - 'nv=2/3' => 847, - 'nv=2/5' => 848, - 'nv=20' => 831, - 'nv=200' => 832, - 'nv=2000' => 833, - 'nv=20000' => 834, - 'nv=200000' => 835, - 'nv=20000000' => 836, - 'nv=21' => 837, - 'nv=216000' => 838, - 'nv=22' => 839, - 'nv=23' => 840, - 'nv=24' => 841, - 'nv=25' => 842, - 'nv=26' => 843, - 'nv=27' => 844, - 'nv=28' => 845, - 'nv=29' => 846, - 'nv=3' => 849, - 'nv=3/16' => 864, - 'nv=3/2' => 865, - 'nv=3/20' => 866, - 'nv=3/4' => 867, - 'nv=3/5' => 868, - 'nv=3/64' => 869, - 'nv=3/8' => 870, - 'nv=3/80' => 871, - 'nv=30' => 850, - 'nv=300' => 851, - 'nv=3000' => 852, - 'nv=30000' => 853, - 'nv=300000' => 854, - 'nv=31' => 855, - 'nv=32' => 856, - 'nv=33' => 857, - 'nv=34' => 858, - 'nv=35' => 859, - 'nv=36' => 860, - 'nv=37' => 861, - 'nv=38' => 862, - 'nv=39' => 863, - 'nv=4' => 872, - 'nv=4/5' => 888, - 'nv=40' => 873, - 'nv=400' => 874, - 'nv=4000' => 875, - 'nv=40000' => 876, - 'nv=400000' => 877, - 'nv=41' => 878, - 'nv=42' => 879, - 'nv=43' => 880, - 'nv=432000' => 881, - 'nv=44' => 882, - 'nv=45' => 883, - 'nv=46' => 884, - 'nv=47' => 885, - 'nv=48' => 886, - 'nv=49' => 887, - 'nv=5' => 889, - 'nv=5/12' => 895, - 'nv=5/2' => 896, - 'nv=5/6' => 897, - 'nv=5/8' => 898, - 'nv=50' => 890, - 'nv=500' => 891, - 'nv=5000' => 892, - 'nv=50000' => 893, - 'nv=500000' => 894, - 'nv=6' => 899, - 'nv=60' => 900, - 'nv=600' => 901, - 'nv=6000' => 902, - 'nv=60000' => 903, - 'nv=600000' => 904, - 'nv=7' => 905, - 'nv=7/12' => 911, - 'nv=7/2' => 912, - 'nv=7/8' => 913, - 'nv=70' => 906, - 'nv=700' => 907, - 'nv=7000' => 908, - 'nv=70000' => 909, - 'nv=700000' => 910, - 'nv=8' => 914, - 'nv=80' => 915, - 'nv=800' => 916, - 'nv=8000' => 917, - 'nv=80000' => 918, - 'nv=800000' => 919, - 'nv=9' => 920, - 'nv=9/2' => 926, - 'nv=90' => 921, - 'nv=900' => 922, - 'nv=9000' => 923, - 'nv=90000' => 924, - 'nv=900000' => 925, - 'nv=_minus_1/2' => 928, - 'nv=nan' => 927, - 'ocr' => 929, - 'ogam' => 930, - 'olck' => 931, - 'orkh' => 932, - 'ornamentaldingbats' => 933, - 'orya' => 934, - 'osge' => 935, - 'osma' => 936, - 'ottomansiyaqnumbers' => 937, - 'p' => 938, - 'palm' => 939, - 'patsyn' => 940, - 'pauc' => 941, - 'pc' => 942, - 'pcm' => 943, - 'pd' => 944, - 'pe' => 945, - 'perlspace' => 967, - 'perlword' => 969, - 'perm' => 946, - 'pf' => 947, - 'phag' => 948, - 'phaistos' => 949, - 'phli' => 950, - 'phlp' => 951, - 'phnx' => 952, - 'phoneticext' => 953, - 'phoneticextsup' => 954, - 'pi' => 955, - 'playingcards' => 956, - 'po' => 957, - 'posixalnum' => 958, - 'posixalpha' => 959, - 'posixblank' => 960, - 'posixcntrl' => 961, - 'posixdigit' => 962, - 'posixgraph' => 963, - 'posixlower' => 964, - 'posixprint' => 965, - 'posixpunct' => 966, - 'posixspace' => 967, - 'posixupper' => 968, - 'posixword' => 969, - 'posixxdigit' => 970, - 'print' => 1168, - 'prti' => 971, - 'ps' => 972, - 'pua' => 973, - 'qaai' => 974, - 'qmark' => 975, - 'radical' => 976, - 'ri' => 977, - 'rjng' => 978, - 'rohg' => 979, - 'rumi' => 980, - 'runr' => 981, - 's' => 982, - 'samr' => 983, - 'sarb' => 984, - 'saur' => 985, - 'sb=at' => 986, - 'sb=cl' => 987, - 'sb=ex' => 988, - 'sb=fo' => 989, - 'sb=le' => 990, - 'sb=lo' => 991, - 'sb=nu' => 992, - 'sb=sc' => 993, - 'sb=se' => 994, - 'sb=sp' => 995, - 'sb=st' => 996, - 'sb=up' => 997, - 'sb=xx' => 998, - 'sc' => 999, - 'sc=adlm' => 1000, - 'sc=arab' => 1001, - 'sc=beng' => 1002, - 'sc=bopo' => 1003, - 'sc=bugi' => 1004, - 'sc=buhd' => 1005, - 'sc=cakm' => 1006, - 'sc=copt' => 1007, - 'sc=cprt' => 1008, - 'sc=cyrl' => 1009, - 'sc=deva' => 1010, - 'sc=dogr' => 1011, - 'sc=dupl' => 1012, - 'sc=geor' => 1013, - 'sc=glag' => 1014, - 'sc=gong' => 1015, - 'sc=gonm' => 1016, - 'sc=gran' => 1017, - 'sc=grek' => 1018, - 'sc=gujr' => 1019, - 'sc=guru' => 1020, - 'sc=han' => 1021, - 'sc=hang' => 1022, - 'sc=hano' => 1023, - 'sc=hira' => 1024, - 'sc=java' => 1025, - 'sc=kali' => 1026, - 'sc=kana' => 1027, - 'sc=khoj' => 1028, - 'sc=knda' => 1029, - 'sc=kthi' => 1030, - 'sc=latn' => 1031, - 'sc=limb' => 1032, - 'sc=lina' => 1033, - 'sc=linb' => 1034, - 'sc=mahj' => 1035, - 'sc=mand' => 1036, - 'sc=mani' => 1037, - 'sc=mlym' => 1038, - 'sc=modi' => 1039, - 'sc=mong' => 1040, - 'sc=mult' => 1041, - 'sc=mymr' => 1042, - 'sc=nand' => 1043, - 'sc=orya' => 1044, - 'sc=perm' => 1045, - 'sc=phag' => 1046, - 'sc=phlp' => 1047, - 'sc=qaai' => 1048, - 'sc=rohg' => 1049, - 'sc=shrd' => 1050, - 'sc=sind' => 1051, - 'sc=sinh' => 1052, - 'sc=sogd' => 1053, - 'sc=sylo' => 1054, - 'sc=syrc' => 1055, - 'sc=tagb' => 1056, - 'sc=takr' => 1057, - 'sc=tale' => 1058, - 'sc=taml' => 1059, - 'sc=telu' => 1060, - 'sc=tglg' => 1061, - 'sc=thaa' => 1062, - 'sc=tirh' => 1063, - 'sc=yezi' => 1064, - 'sc=yi' => 1065, - 'sc=zyyy' => 1066, - 'sd' => 1067, - 'sgnw' => 1068, - 'shaw' => 1069, - 'shorthandformatcontrols' => 1070, - 'shrd' => 1071, - 'sidd' => 1072, - 'sind' => 1073, - 'sinh' => 1074, - 'sinhalaarchaicnumbers' => 1075, - 'sk' => 1076, - 'sm' => 1077, - 'smallforms' => 1078, - 'smallkanaext' => 1079, - 'so' => 1080, - 'sogd' => 1081, - 'sogo' => 1082, - 'sora' => 1083, - 'soyo' => 1084, - 'space' => 1170, - 'spaceperl' => 1170, - 'specials' => 1085, - 'sterm' => 1086, - 'sund' => 1087, - 'sundanesesup' => 1088, - 'suparrowsa' => 1089, - 'suparrowsb' => 1090, - 'suparrowsc' => 1091, - 'superandsub' => 1092, - 'supmathoperators' => 1093, - 'suppuaa' => 1094, - 'suppuab' => 1095, - 'suppunctuation' => 1096, - 'supsymbolsandpictographs' => 1097, - 'suttonsignwriting' => 1098, - 'sylo' => 1099, - 'symbolsandpictographsexta' => 1100, - 'symbolsforlegacycomputing' => 1101, - 'syrc' => 1102, - 'syriacsup' => 1103, - 'tagb' => 1104, - 'tags' => 1105, - 'taixuanjing' => 1106, - 'takr' => 1107, - 'tale' => 1108, - 'talu' => 1109, - 'tamilsup' => 1110, - 'taml' => 1111, - 'tang' => 1112, - 'tangutcomponents' => 1113, - 'tangutsup' => 1114, - 'tavt' => 1115, - 'telu' => 1116, - 'term' => 1117, - 'tfng' => 1118, - 'tglg' => 1119, - 'thaa' => 1120, - 'thai' => 1121, - 'tibt' => 1122, - 'tirh' => 1123, - 'title' => 1124, - 'titlecase' => 1124, - 'titlecaseletter' => 1124, - 'transportandmap' => 1125, - 'ucas' => 1126, - 'ucasext' => 1127, - 'ugar' => 1128, - 'uideo' => 1129, - 'upper' => 1171, - 'uppercase' => 1171, - 'uppercaseletter' => 1130, - 'vai' => 1131, - 'vedicext' => 1132, - 'verticalforms' => 1133, - 'vertspace' => 1134, - 'vo=r' => 1135, - 'vo=tr' => 1136, - 'vo=tu' => 1137, - 'vo=u' => 1138, - 'vs' => 1139, - 'vssup' => 1140, - 'wara' => 1141, - 'wb=dq' => 1142, - 'wb=eb' => 1143, - 'wb=ex' => 1144, - 'wb=extend' => 1145, - 'wb=fo' => 1146, - 'wb=ka' => 1147, - 'wb=le' => 1148, - 'wb=mb' => 1149, - 'wb=ml' => 1150, - 'wb=mn' => 1151, - 'wb=nl' => 1152, - 'wb=nu' => 1153, - 'wb=sq' => 1154, - 'wb=wsegspace' => 1155, - 'wb=xx' => 1156, - 'wcho' => 1157, - 'whitespace' => 1170, - 'word' => 1172, - 'wspace' => 1170, - 'xdigit' => 1173, - 'xidc' => 1158, - 'xids' => 1159, - 'xpeo' => 1160, - 'xperlspace' => 1170, - 'xposixalnum' => 1161, - 'xposixalpha' => 1162, - 'xposixblank' => 1163, - 'xposixcntrl' => 1164, - 'xposixdigit' => 1165, - 'xposixgraph' => 1166, - 'xposixlower' => 1167, - 'xposixprint' => 1168, - 'xposixpunct' => 1169, - 'xposixspace' => 1170, - 'xposixupper' => 1171, - 'xposixword' => 1172, - 'xposixxdigit' => 1173, - 'xsux' => 1174, - 'yezi' => 1175, - 'yi' => 1176, - 'yijing' => 1177, - 'yiradicals' => 1178, - 'yisyllables' => 1179, - 'z' => 1180, - 'zanb' => 1181, - 'zl' => 1182, - 'zp' => 1183, - 'zs' => 1184, - 'zyyy' => 1185, - 'zzzz' => 1186, + 'age=14' => 8, + 'age=2' => 9, + 'age=2.1' => 10, + 'age=3' => 11, + 'age=3.1' => 12, + 'age=3.2' => 13, + 'age=4' => 14, + 'age=4.1' => 15, + 'age=5' => 16, + 'age=5.1' => 17, + 'age=5.2' => 18, + 'age=6' => 19, + 'age=6.1' => 20, + 'age=6.2' => 21, + 'age=6.3' => 22, + 'age=7' => 23, + 'age=8' => 24, + 'age=9' => 25, + 'age=na' => 26, + 'aghb' => 27, + 'ahex' => 986, + 'ahom' => 28, + 'alchemical' => 29, + 'all' => 30, + 'alnum' => 1184, + 'alpha' => 1185, + 'alphabetic' => 1185, + 'alphabeticpf' => 31, + 'ancientgreekmusic' => 32, + 'ancientgreeknumbers' => 33, + 'ancientsymbols' => 34, + 'any' => 35, + 'arab' => 36, + 'arabicexta' => 37, + 'arabicextb' => 38, + 'arabicmath' => 39, + 'arabicpfa' => 40, + 'arabicpfb' => 41, + 'arabicsup' => 42, + 'armi' => 43, + 'armn' => 44, + 'arrows' => 45, + 'ascii' => 46, + 'asciihexdigit' => 986, + 'assigned' => 47, + 'avst' => 48, + 'bali' => 49, + 'bamu' => 50, + 'bamumsup' => 51, + 'basiclatin' => 46, + 'bass' => 52, + 'batk' => 53, + 'bc=al' => 54, + 'bc=an' => 55, + 'bc=b' => 56, + 'bc=bn' => 57, + 'bc=cs' => 58, + 'bc=en' => 59, + 'bc=es' => 60, + 'bc=et' => 61, + 'bc=fsi' => 62, + 'bc=l' => 63, + 'bc=lre' => 64, + 'bc=lri' => 65, + 'bc=lro' => 66, + 'bc=nsm' => 67, + 'bc=on' => 68, + 'bc=pdf' => 69, + 'bc=pdi' => 70, + 'bc=r' => 71, + 'bc=rle' => 72, + 'bc=rli' => 73, + 'bc=rlo' => 74, + 'bc=s' => 75, + 'bc=ws' => 76, + 'beng' => 77, + 'bhks' => 78, + 'bidic' => 79, + 'bidim' => 80, + 'blank' => 1186, + 'blockelements' => 81, + 'bopo' => 82, + 'bopomofoext' => 83, + 'boxdrawing' => 84, + 'bpt=c' => 85, + 'bpt=n' => 86, + 'bpt=o' => 87, + 'brah' => 88, + 'brai' => 89, + 'bugi' => 90, + 'buhd' => 91, + 'byzantinemusic' => 92, + 'c' => 93, + 'cakm' => 94, + 'cans' => 95, + 'cari' => 96, + 'cased' => 97, + 'casedletter' => 98, + 'cc' => 1187, + 'ccc=0' => 99, + 'ccc=1' => 100, + 'ccc=10' => 101, + 'ccc=103' => 102, + 'ccc=107' => 103, + 'ccc=11' => 104, + 'ccc=118' => 105, + 'ccc=12' => 106, + 'ccc=122' => 107, + 'ccc=129' => 108, + 'ccc=13' => 109, + 'ccc=130' => 110, + 'ccc=132' => 111, + 'ccc=14' => 112, + 'ccc=15' => 113, + 'ccc=16' => 114, + 'ccc=17' => 115, + 'ccc=18' => 116, + 'ccc=19' => 117, + 'ccc=20' => 118, + 'ccc=202' => 119, + 'ccc=21' => 120, + 'ccc=214' => 121, + 'ccc=216' => 122, + 'ccc=22' => 123, + 'ccc=23' => 124, + 'ccc=24' => 125, + 'ccc=25' => 126, + 'ccc=26' => 127, + 'ccc=27' => 128, + 'ccc=28' => 129, + 'ccc=29' => 130, + 'ccc=30' => 131, + 'ccc=31' => 132, + 'ccc=32' => 133, + 'ccc=33' => 134, + 'ccc=34' => 135, + 'ccc=35' => 136, + 'ccc=36' => 137, + 'ccc=6' => 138, + 'ccc=7' => 139, + 'ccc=8' => 140, + 'ccc=84' => 141, + 'ccc=9' => 142, + 'ccc=91' => 143, + 'ccc=a' => 144, + 'ccc=al' => 145, + 'ccc=ar' => 146, + 'ccc=b' => 147, + 'ccc=bl' => 148, + 'ccc=br' => 149, + 'ccc=da' => 150, + 'ccc=db' => 151, + 'ccc=is' => 152, + 'ccc=l' => 153, + 'ccc=r' => 154, + 'ce' => 155, + 'cf' => 156, + 'cham' => 157, + 'cher' => 158, + 'cherokeesup' => 159, + 'chesssymbols' => 160, + 'chrs' => 161, + 'ci' => 162, + 'cjk' => 163, + 'cjkcompat' => 164, + 'cjkcompatforms' => 165, + 'cjkcompatideographs' => 166, + 'cjkcompatideographssup' => 167, + 'cjkexta' => 168, + 'cjkextb' => 169, + 'cjkextc' => 170, + 'cjkextd' => 171, + 'cjkexte' => 172, + 'cjkextf' => 173, + 'cjkextg' => 174, + 'cjkradicalssup' => 175, + 'cjkstrokes' => 176, + 'cjksymbols' => 177, + 'cn' => 178, + 'cntrl' => 1187, + 'co' => 179, + 'compatjamo' => 180, + 'compex' => 181, + 'control' => 1187, + 'controlpictures' => 182, + 'copt' => 183, + 'copticepactnumbers' => 184, + 'countingrod' => 185, + 'cpmn' => 186, + 'cprt' => 187, + 'cuneiformnumbers' => 188, + 'currencysymbols' => 189, + 'cwcf' => 190, + 'cwcm' => 191, + 'cwkcf' => 192, + 'cwl' => 193, + 'cwt' => 194, + 'cwu' => 195, + 'cypriotsyllabary' => 196, + 'cyrillicexta' => 197, + 'cyrillicextb' => 198, + 'cyrillicextc' => 199, + 'cyrillicsup' => 200, + 'cyrl' => 201, + 'dash' => 202, + 'decimalnumber' => 1188, + 'dep' => 203, + 'deva' => 204, + 'devanagariext' => 205, + 'di' => 206, + 'dia' => 207, + 'diacriticals' => 208, + 'diacriticalsext' => 209, + 'diacriticalsforsymbols' => 210, + 'diacriticalssup' => 211, + 'diak' => 212, + 'digit' => 1188, + 'dingbats' => 213, + 'dogr' => 214, + 'domino' => 215, + 'dsrt' => 216, + 'dt=can' => 217, + 'dt=com' => 218, + 'dt=enc' => 219, + 'dt=fin' => 220, + 'dt=font' => 221, + 'dt=fra' => 222, + 'dt=init' => 223, + 'dt=iso' => 224, + 'dt=med' => 225, + 'dt=nar' => 226, + 'dt=nb' => 227, + 'dt=noncanon' => 228, + 'dt=none' => 229, + 'dt=sml' => 230, + 'dt=sqr' => 231, + 'dt=sub' => 232, + 'dt=sup' => 233, + 'dt=vert' => 234, + 'dupl' => 235, + 'ea=a' => 237, + 'ea=f' => 238, + 'ea=h' => 239, + 'ea=n' => 240, + 'ea=na' => 241, + 'ea=w' => 242, + 'earlydynasticcuneiform' => 236, + 'ebase' => 243, + 'ecomp' => 244, + 'egyp' => 245, + 'egyptianhieroglyphformatcontrols' => 246, + 'elba' => 247, + 'elym' => 248, + 'emod' => 249, + 'emoji' => 250, + 'emoticons' => 251, + 'enclosedalphanum' => 252, + 'enclosedalphanumsup' => 253, + 'enclosedcjk' => 254, + 'enclosedideographicsup' => 255, + 'epres' => 256, + 'ethi' => 257, + 'ethiopicext' => 258, + 'ethiopicexta' => 259, + 'ethiopicextb' => 260, + 'ethiopicsup' => 261, + 'ext' => 262, + 'extpict' => 263, + 'gcb=cn' => 264, + 'gcb=ex' => 265, + 'gcb=l' => 266, + 'gcb=pp' => 267, + 'gcb=sm' => 268, + 'gcb=t' => 269, + 'gcb=v' => 270, + 'gcb=xx' => 271, + 'geometricshapes' => 272, + 'geometricshapesext' => 273, + 'geor' => 274, + 'georgianext' => 275, + 'georgiansup' => 276, + 'glag' => 277, + 'glagoliticsup' => 278, + 'gong' => 279, + 'gonm' => 280, + 'goth' => 281, + 'gran' => 282, + 'graph' => 1189, + 'grbase' => 283, + 'greekext' => 284, + 'grek' => 285, + 'grext' => 286, + 'gujr' => 287, + 'guru' => 288, + 'halfandfullforms' => 289, + 'halfmarks' => 290, + 'han' => 291, + 'hang' => 292, + 'hano' => 293, + 'hatr' => 294, + 'hebr' => 295, + 'hex' => 1196, + 'hexdigit' => 1196, + 'highpusurrogates' => 296, + 'highsurrogates' => 297, + 'hira' => 298, + 'hluw' => 299, + 'hmng' => 300, + 'hmnp' => 301, + 'horizspace' => 1186, + 'hst=na' => 302, + 'hung' => 303, + 'hyphen_perl_aux' => 304, + 'idc' => 305, + 'identifierstatus=allowed' => 306, + 'identifierstatus=restricted' => 307, + 'identifiertype=defaultignorable' => 308, + 'identifiertype=exclusion' => 309, + 'identifiertype=inclusion' => 310, + 'identifiertype=limiteduse' => 311, + 'identifiertype=notcharacter' => 312, + 'identifiertype=notnfkc' => 313, + 'identifiertype=notxid' => 314, + 'identifiertype=obsolete' => 315, + 'identifiertype=recommended' => 316, + 'identifiertype=technical' => 317, + 'identifiertype=uncommonuse' => 318, + 'ideo' => 319, + 'ideographicsymbols' => 320, + 'ids' => 321, + 'idsb' => 322, + 'idst' => 323, + 'in=1.1' => 527, + 'in=10' => 521, + 'in=11' => 522, + 'in=12' => 523, + 'in=12.1' => 524, + 'in=13' => 525, + 'in=14' => 526, + 'in=2' => 528, + 'in=2.1' => 529, + 'in=3' => 530, + 'in=3.1' => 531, + 'in=3.2' => 532, + 'in=4' => 533, + 'in=4.1' => 534, + 'in=5' => 535, + 'in=5.1' => 536, + 'in=5.2' => 537, + 'in=6' => 538, + 'in=6.1' => 539, + 'in=6.2' => 540, + 'in=6.3' => 541, + 'in=7' => 542, + 'in=8' => 543, + 'in=9' => 544, + 'inadlam' => 324, + 'inahom' => 325, + 'inanatolianhieroglyphs' => 326, + 'inarabic' => 327, + 'inarmenian' => 328, + 'inavestan' => 329, + 'inbalinese' => 330, + 'inbamum' => 331, + 'inbassavah' => 332, + 'inbatak' => 333, + 'inbengali' => 334, + 'inbhaiksuki' => 335, + 'inbopomofo' => 336, + 'inbrahmi' => 337, + 'inbuginese' => 338, + 'inbuhid' => 339, + 'incarian' => 340, + 'incaucasianalbanian' => 341, + 'inchakma' => 342, + 'incham' => 343, + 'incherokee' => 344, + 'inchorasmian' => 345, + 'incoptic' => 346, + 'incuneiform' => 347, + 'incyprominoan' => 348, + 'incyrillic' => 349, + 'indevanagari' => 350, + 'indicnumberforms' => 351, + 'indicsiyaqnumbers' => 352, + 'indivesakuru' => 353, + 'indogra' => 354, + 'induployan' => 355, + 'inegyptianhieroglyphs' => 356, + 'inelbasan' => 357, + 'inelymaic' => 358, + 'inethiopic' => 359, + 'ingeorgian' => 360, + 'inglagolitic' => 361, + 'ingothic' => 362, + 'ingrantha' => 363, + 'ingreek' => 364, + 'ingujarati' => 365, + 'ingunjalagondi' => 366, + 'ingurmukhi' => 367, + 'inhangul' => 368, + 'inhanifirohingya' => 369, + 'inhanunoo' => 370, + 'inhatran' => 371, + 'inhebrew' => 372, + 'inhiragana' => 373, + 'inidc' => 374, + 'inimperialaramaic' => 375, + 'ininscriptionalpahlavi' => 376, + 'ininscriptionalparthian' => 377, + 'injavanese' => 378, + 'inkaithi' => 379, + 'inkannada' => 380, + 'inkatakana' => 381, + 'inkharoshthi' => 382, + 'inkhitansmallscript' => 383, + 'inkhmer' => 384, + 'inkhojki' => 385, + 'inkhudawadi' => 386, + 'inlao' => 387, + 'inlepcha' => 388, + 'inlimbu' => 389, + 'inlineara' => 390, + 'inlisu' => 391, + 'inlycian' => 392, + 'inlydian' => 393, + 'inmahajani' => 394, + 'inmakasar' => 395, + 'inmalayalam' => 396, + 'inmandaic' => 397, + 'inmanichaean' => 398, + 'inmarchen' => 399, + 'inmasaramgondi' => 400, + 'inmedefaidrin' => 401, + 'inmeeteimayek' => 402, + 'inmendekikakui' => 403, + 'inmeroiticcursive' => 404, + 'inmiao' => 405, + 'inmodi' => 406, + 'inmongolian' => 407, + 'inmro' => 408, + 'inmultani' => 409, + 'inmyanmar' => 410, + 'innabataean' => 411, + 'innandinagari' => 412, + 'innewa' => 413, + 'innewtailue' => 414, + 'innko' => 415, + 'innushu' => 416, + 'innyiakengpuachuehmong' => 417, + 'inogham' => 418, + 'inoldhungarian' => 419, + 'inolditalic' => 420, + 'inoldpermic' => 421, + 'inoldpersian' => 422, + 'inoldsogdian' => 423, + 'inoldturkic' => 424, + 'inolduyghur' => 425, + 'inoriya' => 426, + 'inosage' => 427, + 'inosmanya' => 428, + 'inpahawhhmong' => 429, + 'inpaucinhau' => 430, + 'inpc=bottom' => 431, + 'inpc=bottomandleft' => 432, + 'inpc=bottomandright' => 433, + 'inpc=left' => 434, + 'inpc=leftandright' => 435, + 'inpc=na' => 436, + 'inpc=overstruck' => 437, + 'inpc=right' => 438, + 'inpc=top' => 439, + 'inpc=topandbottom' => 440, + 'inpc=topandbottomandleft' => 441, + 'inpc=topandbottomandright' => 442, + 'inpc=topandleft' => 443, + 'inpc=topandleftandright' => 444, + 'inpc=topandright' => 445, + 'inphagspa' => 446, + 'inphoenician' => 447, + 'inpsalterpahlavi' => 448, + 'inpunctuation' => 449, + 'inrejang' => 450, + 'inrunic' => 451, + 'insamaritan' => 452, + 'insaurashtra' => 453, + 'insc=avagraha' => 454, + 'insc=bindu' => 455, + 'insc=brahmijoiningnumber' => 456, + 'insc=cantillationmark' => 457, + 'insc=consonant' => 458, + 'insc=consonantdead' => 459, + 'insc=consonantfinal' => 460, + 'insc=consonantheadletter' => 461, + 'insc=consonantinitialpostfixed' => 462, + 'insc=consonantkiller' => 463, + 'insc=consonantmedial' => 464, + 'insc=consonantplaceholder' => 465, + 'insc=consonantprecedingrepha' => 466, + 'insc=consonantprefixed' => 467, + 'insc=consonantsubjoined' => 468, + 'insc=consonantsucceedingrepha' => 469, + 'insc=consonantwithstacker' => 470, + 'insc=geminationmark' => 471, + 'insc=invisiblestacker' => 472, + 'insc=modifyingletter' => 473, + 'insc=nonjoiner' => 474, + 'insc=nukta' => 475, + 'insc=number' => 476, + 'insc=numberjoiner' => 477, + 'insc=other' => 478, + 'insc=purekiller' => 479, + 'insc=registershifter' => 480, + 'insc=syllablemodifier' => 481, + 'insc=toneletter' => 482, + 'insc=tonemark' => 483, + 'insc=virama' => 484, + 'insc=visarga' => 485, + 'insc=vowel' => 486, + 'insc=voweldependent' => 487, + 'insc=vowelindependent' => 488, + 'insiddham' => 489, + 'insinhala' => 490, + 'insogdian' => 491, + 'insorasompeng' => 492, + 'insoyombo' => 493, + 'insundanese' => 494, + 'insylotinagri' => 495, + 'insyriac' => 496, + 'intagalog' => 497, + 'intagbanwa' => 498, + 'intaile' => 499, + 'intaitham' => 500, + 'intaiviet' => 501, + 'intakri' => 502, + 'intamil' => 503, + 'intangsa' => 504, + 'intangut' => 505, + 'intelugu' => 506, + 'inthaana' => 507, + 'inthai' => 508, + 'intibetan' => 509, + 'intifinagh' => 510, + 'intirhuta' => 511, + 'intoto' => 512, + 'inugaritic' => 513, + 'invai' => 514, + 'invithkuqi' => 515, + 'invs' => 516, + 'inwancho' => 517, + 'inwarangciti' => 518, + 'inyezidi' => 519, + 'inzanabazarsquare' => 520, + 'ipaext' => 545, + 'ital' => 546, + 'jamo' => 547, + 'jamoexta' => 548, + 'jamoextb' => 549, + 'java' => 550, + 'jg=africanfeh' => 551, + 'jg=africannoon' => 552, + 'jg=africanqaf' => 553, + 'jg=ain' => 554, + 'jg=alaph' => 555, + 'jg=alef' => 556, + 'jg=beh' => 557, + 'jg=beth' => 558, + 'jg=burushaskiyehbarree' => 559, + 'jg=dal' => 560, + 'jg=dalathrish' => 561, + 'jg=e' => 562, + 'jg=farsiyeh' => 563, + 'jg=fe' => 564, + 'jg=feh' => 565, + 'jg=finalsemkath' => 566, + 'jg=gaf' => 567, + 'jg=gamal' => 568, + 'jg=hah' => 569, + 'jg=hamzaonhehgoal' => 570, + 'jg=hanifirohingyakinnaya' => 571, + 'jg=hanifirohingyapa' => 572, + 'jg=he' => 573, + 'jg=heh' => 574, + 'jg=hehgoal' => 575, + 'jg=heth' => 576, + 'jg=kaf' => 577, + 'jg=kaph' => 578, + 'jg=khaph' => 579, + 'jg=knottedheh' => 580, + 'jg=lam' => 581, + 'jg=lamadh' => 582, + 'jg=malayalambha' => 583, + 'jg=malayalamja' => 584, + 'jg=malayalamlla' => 585, + 'jg=malayalamllla' => 586, + 'jg=malayalamnga' => 587, + 'jg=malayalamnna' => 588, + 'jg=malayalamnnna' => 589, + 'jg=malayalamnya' => 590, + 'jg=malayalamra' => 591, + 'jg=malayalamssa' => 592, + 'jg=malayalamtta' => 593, + 'jg=manichaeanaleph' => 594, + 'jg=manichaeanayin' => 595, + 'jg=manichaeanbeth' => 596, + 'jg=manichaeandaleth' => 597, + 'jg=manichaeandhamedh' => 598, + 'jg=manichaeanfive' => 599, + 'jg=manichaeangimel' => 600, + 'jg=manichaeanheth' => 601, + 'jg=manichaeanhundred' => 602, + 'jg=manichaeankaph' => 603, + 'jg=manichaeanlamedh' => 604, + 'jg=manichaeanmem' => 605, + 'jg=manichaeannun' => 606, + 'jg=manichaeanone' => 607, + 'jg=manichaeanpe' => 608, + 'jg=manichaeanqoph' => 609, + 'jg=manichaeanresh' => 610, + 'jg=manichaeansadhe' => 611, + 'jg=manichaeansamekh' => 612, + 'jg=manichaeantaw' => 613, + 'jg=manichaeanten' => 614, + 'jg=manichaeanteth' => 615, + 'jg=manichaeanthamedh' => 616, + 'jg=manichaeantwenty' => 617, + 'jg=manichaeanwaw' => 618, + 'jg=manichaeanyodh' => 619, + 'jg=manichaeanzayin' => 620, + 'jg=meem' => 621, + 'jg=mim' => 622, + 'jg=nojoininggroup' => 623, + 'jg=noon' => 624, + 'jg=nun' => 625, + 'jg=nya' => 626, + 'jg=pe' => 627, + 'jg=qaf' => 628, + 'jg=qaph' => 629, + 'jg=reh' => 630, + 'jg=reversedpe' => 631, + 'jg=rohingyayeh' => 632, + 'jg=sad' => 633, + 'jg=sadhe' => 634, + 'jg=seen' => 635, + 'jg=semkath' => 636, + 'jg=shin' => 637, + 'jg=straightwaw' => 638, + 'jg=swashkaf' => 639, + 'jg=syriacwaw' => 640, + 'jg=tah' => 641, + 'jg=taw' => 642, + 'jg=tehmarbuta' => 643, + 'jg=teth' => 644, + 'jg=thinyeh' => 645, + 'jg=verticaltail' => 646, + 'jg=waw' => 647, + 'jg=yeh' => 648, + 'jg=yehbarree' => 649, + 'jg=yehwithtail' => 650, + 'jg=yudh' => 651, + 'jg=yudhhe' => 652, + 'jg=zain' => 653, + 'jg=zhain' => 654, + 'joinc' => 655, + 'jt=c' => 656, + 'jt=d' => 657, + 'jt=l' => 658, + 'jt=r' => 659, + 'jt=t' => 660, + 'jt=u' => 661, + 'kali' => 662, + 'kana' => 663, + 'kanaexta' => 664, + 'kanaextb' => 665, + 'kanasup' => 666, + 'kanbun' => 667, + 'kangxi' => 668, + 'katakanaext' => 669, + 'khar' => 670, + 'khmersymbols' => 671, + 'khmr' => 672, + 'khoj' => 673, + 'kits' => 674, + 'knda' => 675, + 'kthi' => 676, + 'l' => 677, + 'l_' => 98, + 'l_amp_' => 98, + 'lana' => 678, + 'lao' => 679, + 'latin1' => 680, + 'latinexta' => 681, + 'latinextadditional' => 682, + 'latinextb' => 683, + 'latinextc' => 684, + 'latinextd' => 685, + 'latinexte' => 686, + 'latinextf' => 687, + 'latinextg' => 688, + 'latn' => 689, + 'lb=ai' => 690, + 'lb=al' => 691, + 'lb=b2' => 692, + 'lb=ba' => 693, + 'lb=bb' => 694, + 'lb=bk' => 695, + 'lb=cb' => 696, + 'lb=cj' => 697, + 'lb=cl' => 698, + 'lb=cm' => 699, + 'lb=cp' => 700, + 'lb=cr' => 701, + 'lb=ex' => 702, + 'lb=gl' => 703, + 'lb=h2' => 704, + 'lb=h3' => 705, + 'lb=hl' => 706, + 'lb=hy' => 707, + 'lb=id' => 708, + 'lb=in' => 709, + 'lb=is' => 710, + 'lb=lf' => 711, + 'lb=nl' => 712, + 'lb=ns' => 713, + 'lb=nu' => 714, + 'lb=op' => 715, + 'lb=po' => 716, + 'lb=pr' => 717, + 'lb=qu' => 718, + 'lb=sa' => 719, + 'lb=sg_perl_aux' => 720, + 'lb=sp' => 721, + 'lb=sy' => 722, + 'lb=wj' => 723, + 'lb=xx' => 724, + 'lb=zw' => 725, + 'lb=zwj' => 726, + 'lc' => 98, + 'lepc' => 727, + 'letterlikesymbols' => 728, + 'limb' => 729, + 'lina' => 730, + 'linb' => 731, + 'linearbideograms' => 732, + 'linearbsyllabary' => 733, + 'lisu' => 734, + 'lisusup' => 735, + 'll' => 739, + 'lm' => 736, + 'lo' => 737, + 'loe' => 738, + 'lower' => 1190, + 'lowercase' => 1190, + 'lowercaseletter' => 739, + 'lowsurrogates' => 740, + 'lt' => 1143, + 'lu' => 1152, + 'lyci' => 741, + 'lydi' => 742, + 'm' => 743, + 'mahj' => 744, + 'mahjong' => 745, + 'maka' => 746, + 'mand' => 747, + 'mani' => 748, + 'marc' => 749, + 'math' => 750, + 'mathalphanum' => 751, + 'mathoperators' => 752, + 'mayannumerals' => 753, + 'mc' => 754, + 'me' => 755, + 'medf' => 756, + 'meeteimayekext' => 757, + 'mend' => 758, + 'merc' => 759, + 'mero' => 760, + 'miao' => 761, + 'miscarrows' => 762, + 'miscmathsymbolsa' => 763, + 'miscmathsymbolsb' => 764, + 'miscpictographs' => 765, + 'miscsymbols' => 766, + 'misctechnical' => 767, + 'mlym' => 768, + 'mn' => 769, + 'modi' => 770, + 'modifierletters' => 771, + 'modifiertoneletters' => 772, + 'mong' => 773, + 'mongoliansup' => 774, + 'mro' => 775, + 'mtei' => 776, + 'mult' => 777, + 'music' => 778, + 'myanmarexta' => 779, + 'myanmarextb' => 780, + 'mymr' => 781, + 'n' => 782, + 'nand' => 783, + 'narb' => 784, + 'nb' => 785, + 'nbat' => 786, + 'nd' => 1188, + 'newa' => 787, + 'nfcqc=m' => 788, + 'nfcqc=y' => 789, + 'nfdqc=y' => 790, + 'nfkcqc=n' => 791, + 'nfkcqc=y' => 792, + 'nfkdqc=n' => 793, + 'nko' => 794, + 'nl' => 795, + 'no' => 796, + 'nshu' => 797, + 'nt=di' => 798, + 'nt=nu' => 799, + 'numberforms' => 800, + 'nv=0' => 801, + 'nv=1' => 802, + 'nv=1/10' => 827, + 'nv=1/12' => 828, + 'nv=1/16' => 829, + 'nv=1/160' => 830, + 'nv=1/2' => 831, + 'nv=1/20' => 832, + 'nv=1/3' => 833, + 'nv=1/32' => 834, + 'nv=1/320' => 835, + 'nv=1/4' => 836, + 'nv=1/40' => 837, + 'nv=1/5' => 838, + 'nv=1/6' => 839, + 'nv=1/64' => 840, + 'nv=1/7' => 841, + 'nv=1/8' => 842, + 'nv=1/80' => 843, + 'nv=1/9' => 844, + 'nv=10' => 803, + 'nv=100' => 804, + 'nv=1000' => 805, + 'nv=10000' => 806, + 'nv=100000' => 807, + 'nv=1000000' => 808, + 'nv=10000000' => 809, + 'nv=100000000' => 810, + 'nv=10000000000' => 811, + 'nv=1000000000000' => 812, + 'nv=11' => 813, + 'nv=11/12' => 814, + 'nv=11/2' => 815, + 'nv=12' => 816, + 'nv=13' => 817, + 'nv=13/2' => 818, + 'nv=14' => 819, + 'nv=15' => 820, + 'nv=15/2' => 821, + 'nv=16' => 822, + 'nv=17' => 823, + 'nv=17/2' => 824, + 'nv=18' => 825, + 'nv=19' => 826, + 'nv=2' => 845, + 'nv=2/3' => 862, + 'nv=2/5' => 863, + 'nv=20' => 846, + 'nv=200' => 847, + 'nv=2000' => 848, + 'nv=20000' => 849, + 'nv=200000' => 850, + 'nv=20000000' => 851, + 'nv=21' => 852, + 'nv=216000' => 853, + 'nv=22' => 854, + 'nv=23' => 855, + 'nv=24' => 856, + 'nv=25' => 857, + 'nv=26' => 858, + 'nv=27' => 859, + 'nv=28' => 860, + 'nv=29' => 861, + 'nv=3' => 864, + 'nv=3/16' => 879, + 'nv=3/2' => 880, + 'nv=3/20' => 881, + 'nv=3/4' => 882, + 'nv=3/5' => 883, + 'nv=3/64' => 884, + 'nv=3/8' => 885, + 'nv=3/80' => 886, + 'nv=30' => 865, + 'nv=300' => 866, + 'nv=3000' => 867, + 'nv=30000' => 868, + 'nv=300000' => 869, + 'nv=31' => 870, + 'nv=32' => 871, + 'nv=33' => 872, + 'nv=34' => 873, + 'nv=35' => 874, + 'nv=36' => 875, + 'nv=37' => 876, + 'nv=38' => 877, + 'nv=39' => 878, + 'nv=4' => 887, + 'nv=4/5' => 903, + 'nv=40' => 888, + 'nv=400' => 889, + 'nv=4000' => 890, + 'nv=40000' => 891, + 'nv=400000' => 892, + 'nv=41' => 893, + 'nv=42' => 894, + 'nv=43' => 895, + 'nv=432000' => 896, + 'nv=44' => 897, + 'nv=45' => 898, + 'nv=46' => 899, + 'nv=47' => 900, + 'nv=48' => 901, + 'nv=49' => 902, + 'nv=5' => 904, + 'nv=5/12' => 910, + 'nv=5/2' => 911, + 'nv=5/6' => 912, + 'nv=5/8' => 913, + 'nv=50' => 905, + 'nv=500' => 906, + 'nv=5000' => 907, + 'nv=50000' => 908, + 'nv=500000' => 909, + 'nv=6' => 914, + 'nv=60' => 915, + 'nv=600' => 916, + 'nv=6000' => 917, + 'nv=60000' => 918, + 'nv=600000' => 919, + 'nv=7' => 920, + 'nv=7/12' => 926, + 'nv=7/2' => 927, + 'nv=7/8' => 928, + 'nv=70' => 921, + 'nv=700' => 922, + 'nv=7000' => 923, + 'nv=70000' => 924, + 'nv=700000' => 925, + 'nv=8' => 929, + 'nv=80' => 930, + 'nv=800' => 931, + 'nv=8000' => 932, + 'nv=80000' => 933, + 'nv=800000' => 934, + 'nv=9' => 935, + 'nv=9/2' => 941, + 'nv=90' => 936, + 'nv=900' => 937, + 'nv=9000' => 938, + 'nv=90000' => 939, + 'nv=900000' => 940, + 'nv=_minus_1/2' => 943, + 'nv=nan' => 942, + 'ocr' => 944, + 'ogam' => 945, + 'olck' => 946, + 'orkh' => 947, + 'ornamentaldingbats' => 948, + 'orya' => 949, + 'osge' => 950, + 'osma' => 951, + 'ottomansiyaqnumbers' => 952, + 'ougr' => 953, + 'p' => 954, + 'palm' => 955, + 'patsyn' => 956, + 'pauc' => 957, + 'pc' => 958, + 'pcm' => 959, + 'pd' => 960, + 'pe' => 961, + 'perlspace' => 983, + 'perlword' => 985, + 'perm' => 962, + 'pf' => 963, + 'phag' => 964, + 'phaistos' => 965, + 'phli' => 966, + 'phlp' => 967, + 'phnx' => 968, + 'phoneticext' => 969, + 'phoneticextsup' => 970, + 'pi' => 971, + 'playingcards' => 972, + 'po' => 973, + 'posixalnum' => 974, + 'posixalpha' => 975, + 'posixblank' => 976, + 'posixcntrl' => 977, + 'posixdigit' => 978, + 'posixgraph' => 979, + 'posixlower' => 980, + 'posixprint' => 981, + 'posixpunct' => 982, + 'posixspace' => 983, + 'posixupper' => 984, + 'posixword' => 985, + 'posixxdigit' => 986, + 'print' => 1191, + 'prti' => 987, + 'ps' => 988, + 'pua' => 989, + 'qaai' => 990, + 'qmark' => 991, + 'radical' => 992, + 'ri' => 993, + 'rjng' => 994, + 'rohg' => 995, + 'rumi' => 996, + 'runr' => 997, + 's' => 998, + 'samr' => 999, + 'sarb' => 1000, + 'saur' => 1001, + 'sb=at' => 1002, + 'sb=cl' => 1003, + 'sb=ex' => 1004, + 'sb=fo' => 1005, + 'sb=le' => 1006, + 'sb=lo' => 1007, + 'sb=nu' => 1008, + 'sb=sc' => 1009, + 'sb=se' => 1010, + 'sb=sp' => 1011, + 'sb=st' => 1012, + 'sb=up' => 1013, + 'sb=xx' => 1014, + 'sc' => 1015, + 'sc=adlm' => 1016, + 'sc=arab' => 1017, + 'sc=beng' => 1018, + 'sc=bopo' => 1019, + 'sc=bugi' => 1020, + 'sc=buhd' => 1021, + 'sc=cakm' => 1022, + 'sc=copt' => 1023, + 'sc=cpmn' => 1024, + 'sc=cprt' => 1025, + 'sc=cyrl' => 1026, + 'sc=deva' => 1027, + 'sc=dogr' => 1028, + 'sc=dupl' => 1029, + 'sc=geor' => 1030, + 'sc=glag' => 1031, + 'sc=gong' => 1032, + 'sc=gonm' => 1033, + 'sc=gran' => 1034, + 'sc=grek' => 1035, + 'sc=gujr' => 1036, + 'sc=guru' => 1037, + 'sc=han' => 1038, + 'sc=hang' => 1039, + 'sc=hano' => 1040, + 'sc=hira' => 1041, + 'sc=java' => 1042, + 'sc=kali' => 1043, + 'sc=kana' => 1044, + 'sc=khoj' => 1045, + 'sc=knda' => 1046, + 'sc=kthi' => 1047, + 'sc=latn' => 1048, + 'sc=limb' => 1049, + 'sc=lina' => 1050, + 'sc=linb' => 1051, + 'sc=mahj' => 1052, + 'sc=mand' => 1053, + 'sc=mani' => 1054, + 'sc=mlym' => 1055, + 'sc=modi' => 1056, + 'sc=mong' => 1057, + 'sc=mult' => 1058, + 'sc=mymr' => 1059, + 'sc=nand' => 1060, + 'sc=nko' => 1061, + 'sc=orya' => 1062, + 'sc=ougr' => 1063, + 'sc=perm' => 1064, + 'sc=phag' => 1065, + 'sc=phlp' => 1066, + 'sc=qaai' => 1067, + 'sc=rohg' => 1068, + 'sc=shrd' => 1069, + 'sc=sind' => 1070, + 'sc=sinh' => 1071, + 'sc=sogd' => 1072, + 'sc=sylo' => 1073, + 'sc=syrc' => 1074, + 'sc=tagb' => 1075, + 'sc=takr' => 1076, + 'sc=tale' => 1077, + 'sc=taml' => 1078, + 'sc=telu' => 1079, + 'sc=tglg' => 1080, + 'sc=thaa' => 1081, + 'sc=tirh' => 1082, + 'sc=yezi' => 1083, + 'sc=yi' => 1084, + 'sc=zyyy' => 1085, + 'sd' => 1086, + 'sgnw' => 1087, + 'shaw' => 1088, + 'shorthandformatcontrols' => 1089, + 'shrd' => 1090, + 'sidd' => 1091, + 'sind' => 1092, + 'sinh' => 1093, + 'sinhalaarchaicnumbers' => 1094, + 'sk' => 1095, + 'sm' => 1096, + 'smallforms' => 1097, + 'smallkanaext' => 1098, + 'so' => 1099, + 'sogd' => 1100, + 'sogo' => 1101, + 'sora' => 1102, + 'soyo' => 1103, + 'space' => 1193, + 'spaceperl' => 1193, + 'specials' => 1104, + 'sterm' => 1105, + 'sund' => 1106, + 'sundanesesup' => 1107, + 'suparrowsa' => 1108, + 'suparrowsb' => 1109, + 'suparrowsc' => 1110, + 'superandsub' => 1111, + 'supmathoperators' => 1112, + 'suppuaa' => 1113, + 'suppuab' => 1114, + 'suppunctuation' => 1115, + 'supsymbolsandpictographs' => 1116, + 'suttonsignwriting' => 1117, + 'sylo' => 1118, + 'symbolsandpictographsexta' => 1119, + 'symbolsforlegacycomputing' => 1120, + 'syrc' => 1121, + 'syriacsup' => 1122, + 'tagb' => 1123, + 'tags' => 1124, + 'taixuanjing' => 1125, + 'takr' => 1126, + 'tale' => 1127, + 'talu' => 1128, + 'tamilsup' => 1129, + 'taml' => 1130, + 'tang' => 1131, + 'tangutcomponents' => 1132, + 'tangutsup' => 1133, + 'tavt' => 1134, + 'telu' => 1135, + 'term' => 1136, + 'tfng' => 1137, + 'tglg' => 1138, + 'thaa' => 1139, + 'thai' => 1140, + 'tibt' => 1141, + 'tirh' => 1142, + 'title' => 1143, + 'titlecase' => 1143, + 'titlecaseletter' => 1143, + 'tnsa' => 1144, + 'toto' => 1145, + 'transportandmap' => 1146, + 'ucas' => 1147, + 'ucasext' => 1148, + 'ucasexta' => 1149, + 'ugar' => 1150, + 'uideo' => 1151, + 'upper' => 1194, + 'uppercase' => 1194, + 'uppercaseletter' => 1152, + 'vai' => 1153, + 'vedicext' => 1154, + 'verticalforms' => 1155, + 'vertspace' => 1156, + 'vith' => 1157, + 'vo=r' => 1158, + 'vo=tr' => 1159, + 'vo=tu' => 1160, + 'vo=u' => 1161, + 'vs' => 1162, + 'vssup' => 1163, + 'wara' => 1164, + 'wb=dq' => 1165, + 'wb=eb' => 1166, + 'wb=ex' => 1167, + 'wb=extend' => 1168, + 'wb=fo' => 1169, + 'wb=ka' => 1170, + 'wb=le' => 1171, + 'wb=mb' => 1172, + 'wb=ml' => 1173, + 'wb=mn' => 1174, + 'wb=nl' => 1175, + 'wb=nu' => 1176, + 'wb=sq' => 1177, + 'wb=wsegspace' => 1178, + 'wb=xx' => 1179, + 'wcho' => 1180, + 'whitespace' => 1193, + 'word' => 1195, + 'wspace' => 1193, + 'xdigit' => 1196, + 'xidc' => 1181, + 'xids' => 1182, + 'xpeo' => 1183, + 'xperlspace' => 1193, + 'xposixalnum' => 1184, + 'xposixalpha' => 1185, + 'xposixblank' => 1186, + 'xposixcntrl' => 1187, + 'xposixdigit' => 1188, + 'xposixgraph' => 1189, + 'xposixlower' => 1190, + 'xposixprint' => 1191, + 'xposixpunct' => 1192, + 'xposixspace' => 1193, + 'xposixupper' => 1194, + 'xposixword' => 1195, + 'xposixxdigit' => 1196, + 'xsux' => 1197, + 'yezi' => 1198, + 'yi' => 1199, + 'yijing' => 1200, + 'yiradicals' => 1201, + 'yisyllables' => 1202, + 'z' => 1203, + 'zanb' => 1204, + 'zl' => 1205, + 'znamennymusic' => 1206, + 'zp' => 1207, + 'zs' => 1208, + 'zyyy' => 1209, + 'zzzz' => 1210, ); 1; # Generated from: # 688d673ec947f7ccf898b4eae9848139d4d33676b688dee54f449f8bf9d3bbd2 lib/Unicode/UCD.pm -# ce96627d4fc91b4fd886c409caeb9b76cf7bd345e12f05c6701add7f233f6437 lib/unicore/ArabicShaping.txt -# 0e69eef3da722cc104522d8372e86d5b86bb7afcc761b0c991e39e832294946d lib/unicore/BidiBrackets.txt -# a00d9d21585106a52113fb7b1d3d0373a5835be72e76862fb559ebddd474d70e lib/unicore/BidiMirroring.txt -# 81a82b6a9fcf1a9c12f588d7a1decd73a9afdc4cac95b0eb7e576e7942d6c19f lib/unicore/Blocks.txt -# 99d231d7c91688bbe8ca8ccebcc2f46b5b222f844babe4827295bae11e2abe5f lib/unicore/CaseFolding.txt -# 38badafd818d8405324fe298c0676be0c95186368c84b5368375fd871a645144 lib/unicore/CompositionExclusions.txt -# e779a443d3aa2a3166a15becaa2b737c922480e32c0453d5956093633555078f lib/unicore/DAge.txt -# a5d45f59b39deaab3c72ce8c1a2e212a5e086dff11b1f9d5bb0e352642e82248 lib/unicore/DCoreProperties.txt -# 3ac44e11c84bdaf6b207d2c2c20eed857ae17052393fc7f71b0fe951186ba906 lib/unicore/DNormalizationProps.txt -# 4f822ec7a9ebbb3138ad29bade8b9688d25b39c7a3c0b7431f01e7229e4fcb6e lib/unicore/EastAsianWidth.txt -# fc535aa1047a70105ab9a22c2b4c3f363a2ff02fe48ebbc5eeb9873b2752ff0b lib/unicore/EquivalentUnifiedIdeograph.txt -# b9c5158ce944d2fec57e0e4ecb716bdabfc3bdde73525f1772fe03f61a30d473 lib/unicore/HangulSyllableType.txt -# 36c1b2a626ff1fb23b8b21e6ea8712698f8ce668dded1cb48b8ddf6a6a1b04e9 lib/unicore/IdStatus.txt -# 4857c4ffa3898e6128b2d46b0a02e499a663fb91464a69ef3611096f01293acc lib/unicore/IdType.txt -# 69197b019fa5f2fb0d8c6ed1ed8acb9f2e8b5b8f45a947953ffa652f3bf54983 lib/unicore/IndicPositionalCategory.txt -# 6604e2f0fde7428675364aa0006bc686b79488dcc60ae8cb29800af2be3352e8 lib/unicore/IndicSyllabicCategory.txt -# 84ead63924aaa74b988b2eaf254a8733276ed108633ce2ef77a9ee1de7818162 lib/unicore/Jamo.txt -# d5abcd8f54c8a2aa912924c485ccf7f968ad98feaa303d8e9a29ad89172f1faf lib/unicore/LineBreak.txt -# 985128e8c8b2540233331d9b27d897d2c23bd5bcf1d05da960befce6efc59542 lib/unicore/NameAliases.txt -# 27282b8aa01d4d0c44aef436cb74195ae8639ffa187aeee4e6247af76febea76 lib/unicore/NamedSequences.txt -# 485b5a3ed25dbf1f94dfa5a9b69d8b4550ffd0c33045ccc55ccfd7c80b2a40cf lib/unicore/PropList.txt -# 6b3902e9268cd843fe65cbdea992108c9528343ec0679f800b96f356bb553e5a lib/unicore/PropValueAliases.txt -# 2bd5777847e3d6add3c7e5c0d1393ddcab89e5a0ac3ff498cb0c53041f0b86e4 lib/unicore/PropertyAliases.txt -# 03a61dc89422e44cc2b73e8e893321007880ab69e2a4d281c0f1bc29c602b9d0 lib/unicore/ScriptExtensions.txt -# 9a5ed1ec9b5f0d7147e9371ad792ab39203611af7637cff2aa4a5c663b172cde lib/unicore/Scripts.txt -# 6424312f1dc39b22e0ff9c0ffb13dfad424d9b03e6a6dc6bca941f6bf5ef1ffd lib/unicore/SpecialCasing.txt -# bdbffbbfc8ad4d3a6d01b5891510458f3d36f7170422af4ea2bed3211a73e8bb lib/unicore/UnicodeData.txt -# 160f41816234addb511901d5f21febd69574578dd93de6ef8153e35693325575 lib/unicore/VerticalOrientation.txt -# 32dfb37d21db530529a6ec3dc13d96f21f8e7c7faf7ff3db8a9760cd76cec81d lib/unicore/auxiliary/GCBTest.txt -# 2bd3c5e2d62701ff81fb3ec318e179a4618cabb1493b1e0dd2b4e7e56c5437c4 lib/unicore/auxiliary/GraphemeBreakProperty.txt -# c51fbebfa82a0f36473b44bfd71d5ef6cb6a1f81fb313375dc9a1910d79bb2b6 lib/unicore/auxiliary/LBTest.txt -# 80b0107750818d8f370bd120b6fe56b6855b60581f72affe8b60409a469b4b65 lib/unicore/auxiliary/SBTest.txt -# 09e3166ebab166ac630a227f77f4e794ebd433271abd5588f5a67e7f199c71ee lib/unicore/auxiliary/SentenceBreakProperty.txt -# bf5373ce28a5df06796c93dc159dd15a997bb2950c92704b40ae8190cfc3716d lib/unicore/auxiliary/WBTest.txt -# a2b7373cf2fe3fa3b26dbb53405ca849985f771ff47f1c61743978003ff80499 lib/unicore/auxiliary/WordBreakProperty.txt -# d2686f400a638c80775d7c662556fb8fa8dd3bbe4aa548d9d31624264c6e1bb1 lib/unicore/emoji/emoji.txt -# b827ae5da8c2b08947cc9a120a7b7fd2f1676fb160b508df78075381635b127c lib/unicore/extracted/DBidiClass.txt -# 6fdc5b5ef40444a8f0c772e6b67c00498d4216fe0c0fdf76744ce338f2ad3810 lib/unicore/extracted/DBinaryProperties.txt -# e14928a5bf6ad5958a80332bd42e96e14420080a95c660e5da29384e496755d0 lib/unicore/extracted/DCombiningClass.txt -# 579a03281fbe87b78d5d9a8523de4d255edd7e4ca6eab0e4c7729de97e9b89b1 lib/unicore/extracted/DDecompositionType.txt -# ad83c59b257e9d480ffd3001d4ac240c5fed7cb1919453e1c4e8877035256bcd lib/unicore/extracted/DEastAsianWidth.txt -# 4502f0969e4e6558c4b4c6ca4c23dad70b863d61dd3d5eed1a62a6c3c99fd570 lib/unicore/extracted/DGeneralCategory.txt -# 00bb88b89e2adb646f3177f9444e2d3192386b81a5de9556104b338274b253e1 lib/unicore/extracted/DJoinGroup.txt -# ac835b6e11a60c9820d3cf2d1cb0558dd68efb8f53f404a51632e4726690a6d7 lib/unicore/extracted/DJoinType.txt -# baba9dfc133e3cb770a89aaf0973b1341fa61c2da6c176baf6428898b3b568d8 lib/unicore/extracted/DLineBreak.txt -# 6d4a8c945dd7db83ed617cbb7d937de7f4ecf016ff22970d846e996a7c9a2a5d lib/unicore/extracted/DNumType.txt -# 5b7c14380d5cceeaffcfbc18db1ed936391d2af2d51f5a41f1a17b692c77e59b lib/unicore/extracted/DNumValues.txt -# 4e169849b96b76987a8fc443ef421b44d2dcebbd981bb457f6a13e8af77cdbe2 lib/unicore/mktables -# 50b85a67451145545a65cea370dab8d3444fbfe07e9c34cef560c5b7da9d3eef lib/unicore/version +# c7698811e9adb6cc98fb996a7de4be2b6532f2ac67e76055cc8afdbf6ee18af3 lib/unicore/ArabicShaping.txt +# 24a74555f918bbe99f5b3f1b83cf36fc0e205bb8a600a6a3aa539c710a3dcf27 lib/unicore/BidiBrackets.txt +# 7a5c74cedc1616a9af0a9d22e108ae592d86fe93649c144ae6ba49f193a44122 lib/unicore/BidiMirroring.txt +# 598870dddef7b34b5a972916528c456aff2765b79cd4f9647fb58ceb767e7f17 lib/unicore/Blocks.txt +# a566cd48687b2cd897e02501118b2413c14ae86d318f9abbbba97feb84189f0f lib/unicore/CaseFolding.txt +# 3360762fc3295cea54ab251c31df621d05ba4b94d46c60eaac29aa16d70ad1e0 lib/unicore/CompositionExclusions.txt +# 7e058dec02147098bc9c28d86209f0f251bba0538f3b5a705ad02ea3bb709fe0 lib/unicore/DAge.txt +# e3eddd7d469cd1b0feed7528defad1a1cc7c6a9ceb0ae4446a6d10921ed2e7bc lib/unicore/DCoreProperties.txt +# b2c444c20730b097787fdf50bd7d6dd3fc5256ab8084f5b35b11c8776eca674c lib/unicore/DNormalizationProps.txt +# f901ac011aa32a09224d6555da71e2532c59c1d3381322829de0e3b880507250 lib/unicore/EastAsianWidth.txt +# 5995522f01633073911dad1edb74d13aa832f42862c0392a79627b85d52f2391 lib/unicore/EquivalentUnifiedIdeograph.txt +# cd1c9367cba438afa965fcb5edc6ed3ec6e685fd5dd21c0cc20c026f04beb0e5 lib/unicore/HangulSyllableType.txt +# 3f3f368fccdb37f350ecedc20b37fa71ab31c04e847884c77780d34283539f73 lib/unicore/IdStatus.txt +# 45a150c23961b58d7784704af6c4daccd6517d97b6489e53d13bbdbf9e4f065f lib/unicore/IdType.txt +# d8704c8725568813a947ff2ef38bcf1f05e2a6fbea6876ba384890f187a8bf61 lib/unicore/IndicPositionalCategory.txt +# c7b969b653dc278fb66ab4136223d320e30ad19367eb791ae60dcc6d92071b16 lib/unicore/IndicSyllabicCategory.txt +# 39ff89e0a329e1ccce6d54fad8cf82e90926901928c0ca9b9a2ad5681f330dd9 lib/unicore/Jamo.txt +# 9e06e9f35c6959fb91dcc7993f90d58523c3079bc62c6b25f828b4cdebc5d70c lib/unicore/LineBreak.txt +# 14b3b677d33f95c51423dce6eef4a6a28b4b160451ecedee4b91edb6745cf4a3 lib/unicore/NameAliases.txt +# db5745688affcdc0c3927a1ee0667018a96a7b24513f866d5235e98fef6c2436 lib/unicore/NamedSequences.txt +# 6bddfdb850417a5bee6deff19290fd1b138589909afb50f5a049f343bf2c6722 lib/unicore/PropList.txt +# eb755757e20b72b330b2948df3cf2ff7adb0e31bb060140dc09dafb132ace2cd lib/unicore/PropValueAliases.txt +# 859d7225f2d2a460b3ccb1d61a7945f8cc219acdf5aa53b66b7a1e4bf6ebfc87 lib/unicore/PropertyAliases.txt +# d37eedf63ff9c48bac863d5f76862373d6cf5269fd21253d499e2430d638c01d lib/unicore/ScriptExtensions.txt +# 52db475c4ec445e73b0b16915448c357614946ad7062843c563e00d7535c6510 lib/unicore/Scripts.txt +# c667b45908fd269af25fd55d2fc5bbc157fb1b77675936e25c513ce32e080334 lib/unicore/SpecialCasing.txt +# 36018e68657fdcb3485f636630ffe8c8532e01c977703d2803f5b89d6c5feafb lib/unicore/UnicodeData.txt +# 869ff43dd012f924d03c89fc268c88f0e7eea72f0228b91ca30455afdb84f8fd lib/unicore/VerticalOrientation.txt +# ddc7d4d1f3838573b94fc5d83ff7217e63c47b22ae1cd40c5fe1a54efc15589b lib/unicore/auxiliary/GCBTest.txt +# 97e79f1f8d9cd76d120f2420381a01abc00a7c78a2aa583fa3f9627264a99742 lib/unicore/auxiliary/GraphemeBreakProperty.txt +# 488dbb6a7e1d0070d4aa7c175352c818ff6425172850d1b40c6177726658cb05 lib/unicore/auxiliary/LBTest.txt +# 7e42dd749dbb94aa44b13faf9df6319d9a16ce2ea09a3a094fcfbb5962168040 lib/unicore/auxiliary/SBTest.txt +# 7092ca4117cec891c25c7724132efc519e1dece01ae9fd6068035a9db04d526e lib/unicore/auxiliary/SentenceBreakProperty.txt +# 8094b544ec1580c7e41ac0187805cc1aeb330a90301ec7505563e1a59318284e lib/unicore/auxiliary/WBTest.txt +# 7716752aad296d4ab23ff4ed0a2746fc5328750ff84e9e7d6f3828ee9eaef742 lib/unicore/auxiliary/WordBreakProperty.txt +# b597836124298b8f7fa076273802840cfc3271a25f5c397a082e120954b82c3c lib/unicore/emoji/emoji.txt +# e5fe51acc74e3e83b4fb4c7b25f3c34491d6eb8095c9955d0712dafbca7b3c2b lib/unicore/extracted/DBidiClass.txt +# cd0a14176d93bf440b77a582a0d678190fc0688b15442d4cfb250bf2e27956af lib/unicore/extracted/DBinaryProperties.txt +# 12b0c3af9b600b49488d66545a3e7844ea980809627201bf9afeebe1c9f16f4e lib/unicore/extracted/DCombiningClass.txt +# f76064b298cfbd715ba542e7894f7a507d32da2f011070d1d01df95cad9817d6 lib/unicore/extracted/DDecompositionType.txt +# f9bef074cc916db57fece99d54a4505f8e7c7b17481619e3f0005211f7717d4b lib/unicore/extracted/DEastAsianWidth.txt +# cde679c8461976ed40d7edf61ae98cbb947540831f06f5bc7da7decbf91a1420 lib/unicore/extracted/DGeneralCategory.txt +# 9bb891831328713603a486a4a03df7f7987c3e1e8144a6d1ac71fd061ef3f732 lib/unicore/extracted/DJoinGroup.txt +# e97c65bbea0a69d2fae6ec4182b09e519e13232e20bd804b3004edc0f36bb0d4 lib/unicore/extracted/DJoinType.txt +# 43f6df50e4878f501b417e366b0ee097ae5ccb2d4ce942026bed3d62d78e7887 lib/unicore/extracted/DLineBreak.txt +# a04502ebb36a45d83cbe48a7d8132ea8143edb7b3d34d0aa6afe4a9685049741 lib/unicore/extracted/DNumType.txt +# 11075771b112e8e7ccf6ffa637c4c91eadc3ef3db0517b24e605df8fd3624239 lib/unicore/extracted/DNumValues.txt +# 24b7b7bda1a2ab4684ba53355d82ad227c1624b337b37c3b96f2e4b902eea1f2 lib/unicore/mktables +# c72bbdeda99714db1c8024d3311da4aef3c0db3b9b9f11455a7cfe10d5e9aba3 lib/unicore/version # 0a6b5ab33bb1026531f816efe81aea1a8ffcd34a27cbea37dd6a70a63d73c844 regen/charset_translations.pl # 5f8520d3a17ade6317fc0c423f5091470924b1ef425bca0c41ce8e4a9f8460fe regen/mk_PL_charclass.pl -# 04a5294218c412e5ee2e0d9f8d22af1d95bbfd2cafae3935cbb6b5871e9f9704 regen/mk_invlists.pl +# 6defb8383a69034f8279fea4ff66e09bf58049c4cbecf2331b9b245c45d4f2d5 regen/mk_invlists.pl # ex: set ro: diff --git a/lib/unicore/version b/lib/unicore/version index 02161ca86e..4b964e9654 100644 --- a/lib/unicore/version +++ b/lib/unicore/version @@ -1 +1 @@ -13.0.0 +14.0.0 |