From 826fc8c9bd0b7dabb58e0b278b52c5d9f7a7efd9 Mon Sep 17 00:00:00 2001 From: Ievgenii Meshcheriakov Date: Mon, 4 Oct 2021 15:06:52 +0200 Subject: Update UCD to Revision 28 This corresponds to Unicode version 14.0.0. Added the following scripts: * CyproMinoan * OldUyghur * Tangsa * Toto * Vithkuqi Full support of these scripts requires harfbuzz version 3.0.0, this version adds support for Unicode 14.0: https://github.com/harfbuzz/harfbuzz/releases/tag/3.0.0 With this release 10 test cases in tst_qurluts46 were fixed, one additional test case is failing in tst_qtextboundaryfinder and is commented out. In total 62 line break test cases and 44 word break test cases are failing. A comment in src/corelib/text/qt_attribution.json was updated to include the URL of the page containing UCD version number. Fixes: QTBUG-94359 Change-Id: Iefc9ff13f3df279f91cbdb1246d56f75b20ecb35 Reviewed-by: Edward Welbourne --- util/unicode/data/ArabicShaping.txt | 80 ++- util/unicode/data/BidiMirroring.txt | 26 +- util/unicode/data/Blocks.txt | 22 +- util/unicode/data/CaseFolding.txt | 46 +- util/unicode/data/DerivedAge.txt | 95 ++- util/unicode/data/DerivedNormalizationProps.txt | 144 +++- util/unicode/data/GraphemeBreakProperty.txt | 33 +- util/unicode/data/IdnaMappingTable.txt | 307 +++++++-- util/unicode/data/LineBreak.txt | 169 +++-- util/unicode/data/NormalizationCorrections.txt | 6 +- util/unicode/data/Scripts.txt | 213 ++++-- util/unicode/data/SentenceBreakProperty.txt | 130 +++- util/unicode/data/SpecialCasing.txt | 6 +- util/unicode/data/UnicodeData.txt | 837 +++++++++++++++++++++++- util/unicode/data/WordBreakProperty.txt | 96 ++- util/unicode/data/emoji-data.txt | 96 ++- util/unicode/main.cpp | 12 +- 17 files changed, 1999 insertions(+), 319 deletions(-) (limited to 'util/unicode') diff --git a/util/unicode/data/ArabicShaping.txt b/util/unicode/data/ArabicShaping.txt index 9a93adc12f..bfb6b47a55 100644 --- a/util/unicode/data/ArabicShaping.txt +++ b/util/unicode/data/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/util/unicode/data/BidiMirroring.txt b/util/unicode/data/BidiMirroring.txt index 34e42ae8dc..bd8e2c5d00 100644 --- a/util/unicode/data/BidiMirroring.txt +++ b/util/unicode/data/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/util/unicode/data/Blocks.txt b/util/unicode/data/Blocks.txt index 56877db10f..cc5d61988b 100644 --- a/util/unicode/data/Blocks.txt +++ b/util/unicode/data/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/util/unicode/data/CaseFolding.txt b/util/unicode/data/CaseFolding.txt index 033788b253..932ace29e6 100644 --- a/util/unicode/data/CaseFolding.txt +++ b/util/unicode/data/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/util/unicode/data/DerivedAge.txt b/util/unicode/data/DerivedAge.txt index 0d2bd10f8d..c8ee531b8a 100644 --- a/util/unicode/data/DerivedAge.txt +++ b/util/unicode/data/DerivedAge.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/util/unicode/data/DerivedNormalizationProps.txt b/util/unicode/data/DerivedNormalizationProps.txt index 00a25f0e7e..b344567fd3 100644 --- a/util/unicode/data/DerivedNormalizationProps.txt +++ b/util/unicode/data/DerivedNormalizationProps.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; @@ -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] ...... -# Total code points: 10329 +# Total code points: 10429 # ================================================ @@ -9164,6 +9275,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] ...... 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] .... -# Total code points: 10329 +# Total code points: 10429 # EOF diff --git a/util/unicode/data/GraphemeBreakProperty.txt b/util/unicode/data/GraphemeBreakProperty.txt index 6ee92f6eec..dd2569064a 100644 --- a/util/unicode/data/GraphemeBreakProperty.txt +++ b/util/unicode/data/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] .. 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] .. 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] .. 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] .. 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] .. 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] .. 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/util/unicode/data/IdnaMappingTable.txt b/util/unicode/data/IdnaMappingTable.txt index 5995088466..8f6bf539e6 100644 --- a/util/unicode/data/IdnaMappingTable.txt +++ b/util/unicode/data/IdnaMappingTable.txt @@ -1,11 +1,11 @@ # IdnaMappingTable.txt -# Date: 2019-11-07, 13:44:35 GMT -# © 2019 Unicode®, Inc. +# Date: 2021-07-10, 00:49:51 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 IDNA Compatible Preprocessing for UTS #46 -# Version: 13.0.0 +# Version: 14.0.0 # # For documentation and usage, see http://www.unicode.org/reports/tr46 # @@ -906,7 +906,7 @@ 0616..061A ; valid # 5.1 ARABIC SMALL HIGH LIGATURE ALEF WITH LAM WITH YEH..ARABIC SMALL KASRA 061B ; valid ; ; NV8 # 1.1 ARABIC SEMICOLON 061C ; disallowed # 6.3 ARABIC LETTER MARK -061D ; disallowed # NA +061D ; valid ; ; NV8 # 14.0 ARABIC END OF TEXT MARK 061E ; valid ; ; NV8 # 4.1 ARABIC TRIPLE DOT PUNCTUATION MARK 061F ; valid ; ; NV8 # 1.1 ARABIC QUESTION MARK 0620 ; valid # 6.0 ARABIC LETTER KASHMIRI YEH @@ -971,16 +971,23 @@ 085E ; valid ; ; NV8 # 6.0 MANDAIC PUNCTUATION 085F ; disallowed # NA 0860..086A ; valid # 10.0 SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -086B..089F ; disallowed # NA .. +086B..086F ; disallowed # NA .. +0870..0887 ; valid # 14.0 ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; valid ; ; NV8 # 14.0 ARABIC RAISED ROUND DOT +0889..088E ; valid # 14.0 ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +088F ; disallowed # NA +0890..0891 ; disallowed # 14.0 ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0892..0897 ; disallowed # NA .. +0898..089F ; valid # 14.0 ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA 08A0 ; valid # 6.1 ARABIC LETTER BEH WITH SMALL V BELOW 08A1 ; valid # 7.0 ARABIC LETTER BEH WITH HAMZA ABOVE 08A2..08AC ; valid # 6.1 ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH 08AD..08B2 ; valid # 7.0 ARABIC LETTER LOW ALEF..ARABIC LETTER ZAIN WITH INVERTED V ABOVE 08B3..08B4 ; valid # 8.0 ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B5 ; disallowed # NA +08B5 ; valid # 14.0 ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE 08B6..08BD ; valid # 9.0 ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 08BE..08C7 ; valid # 13.0 ARABIC LETTER PEH WITH SMALL V..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08C8..08D2 ; disallowed # NA .. +08C8..08D2 ; valid # 14.0 ARABIC LETTER GRAF..ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW 08D3 ; valid # 11.0 ARABIC SMALL LOW WAW 08D4..08E1 ; valid # 9.0 ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; disallowed # 9.0 ARABIC DISPUTED END OF AYAH @@ -1216,7 +1223,8 @@ 0C2A..0C33 ; valid # 1.1 TELUGU LETTER PA..TELUGU LETTER LLA 0C34 ; valid # 7.0 TELUGU LETTER LLLA 0C35..0C39 ; valid # 1.1 TELUGU LETTER VA..TELUGU LETTER HA -0C3A..0C3C ; disallowed # NA .. +0C3A..0C3B ; disallowed # NA .. +0C3C ; valid # 14.0 TELUGU SIGN NUKTA 0C3D ; valid # 5.1 TELUGU SIGN AVAGRAHA 0C3E..0C44 ; valid # 1.1 TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN VOCALIC RR 0C45 ; disallowed # NA @@ -1228,7 +1236,9 @@ 0C57 ; disallowed # NA 0C58..0C59 ; valid # 5.1 TELUGU LETTER TSA..TELUGU LETTER DZA 0C5A ; valid # 8.0 TELUGU LETTER RRRA -0C5B..0C5F ; disallowed # NA .. +0C5B..0C5C ; disallowed # NA .. +0C5D ; valid # 14.0 TELUGU LETTER NAKAARA POLLU +0C5E..0C5F ; disallowed # NA .. 0C60..0C61 ; valid # 1.1 TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; valid # 5.1 TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C64..0C65 ; disallowed # NA .. @@ -1258,7 +1268,8 @@ 0CCA..0CCD ; valid # 1.1 KANNADA VOWEL SIGN O..KANNADA SIGN VIRAMA 0CCE..0CD4 ; disallowed # NA .. 0CD5..0CD6 ; valid # 1.1 KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CD7..0CDD ; disallowed # NA .. +0CD7..0CDC ; disallowed # NA .. +0CDD ; valid # 14.0 KANNADA LETTER NAKAARA POLLU 0CDE ; valid # 1.1 KANNADA LETTER FA 0CDF ; disallowed # NA 0CE0..0CE1 ; valid # 1.1 KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL @@ -1577,9 +1588,11 @@ 16F1..16F8 ; valid # 7.0 RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC 16F9..16FF ; disallowed # NA .. 1700..170C ; valid # 3.2 TAGALOG LETTER A..TAGALOG LETTER YA -170D ; disallowed # NA +170D ; valid # 14.0 TAGALOG LETTER RA 170E..1714 ; valid # 3.2 TAGALOG LETTER LA..TAGALOG SIGN VIRAMA -1715..171F ; disallowed # NA .. +1715 ; valid # 14.0 TAGALOG SIGN PAMUDPOD +1716..171E ; disallowed # NA .. +171F ; valid # 14.0 TAGALOG LETTER ARCHAIC RA 1720..1734 ; valid # 3.2 HANUNOO LETTER A..HANUNOO SIGN PAMUDPOD 1735..1736 ; valid ; ; NV8 # 3.2 PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1737..173F ; disallowed # NA .. @@ -1609,7 +1622,7 @@ 1807..180A ; valid ; ; NV8 # 3.0 MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU 180B..180D ; ignored # 3.0 MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; disallowed # 3.0 MONGOLIAN VOWEL SEPARATOR -180F ; disallowed # NA +180F ; ignored # 14.0 MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; valid # 3.0 MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 181A..181F ; disallowed # NA .. 1820..1877 ; valid # 3.0 MONGOLIAN LETTER A..MONGOLIAN LETTER MANCHU ZHA @@ -1662,14 +1675,17 @@ 1AB0..1ABD ; valid # 7.0 COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; valid ; ; NV8 # 7.0 COMBINING PARENTHESES OVERLAY 1ABF..1AC0 ; valid # 13.0 COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW -1AC1..1AFF ; disallowed # NA .. +1AC1..1ACE ; valid # 14.0 COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING LATIN SMALL LETTER INSULAR T +1ACF..1AFF ; disallowed # NA .. 1B00..1B4B ; valid # 5.0 BALINESE SIGN ULU RICEM..BALINESE LETTER ASYURA SASAK -1B4C..1B4F ; disallowed # NA .. +1B4C ; valid # 14.0 BALINESE LETTER ARCHAIC JNYA +1B4D..1B4F ; disallowed # NA .. 1B50..1B59 ; valid # 5.0 BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B6A ; valid ; ; NV8 # 5.0 BALINESE PANTI..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73 ; valid # 5.0 BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C ; valid ; ; NV8 # 5.0 BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING -1B7D..1B7F ; disallowed # NA .. +1B7D..1B7E ; valid ; ; NV8 # 14.0 BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG +1B7F ; disallowed # NA 1B80..1BAA ; valid # 5.1 SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PAMAAEH 1BAB..1BAD ; valid # 6.1 SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA 1BAE..1BB9 ; valid # 5.1 SUNDANESE LETTER KHA..SUNDANESE DIGIT NINE @@ -1860,7 +1876,7 @@ 1DCB..1DE6 ; valid # 5.1 COMBINING BREVE-MACRON..COMBINING LATIN SMALL LETTER Z 1DE7..1DF5 ; valid # 7.0 COMBINING LATIN SMALL LETTER ALPHA..COMBINING UP TACK ABOVE 1DF6..1DF9 ; valid # 10.0 COMBINING KAVYKA ABOVE RIGHT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFA ; disallowed # NA +1DFA ; valid # 14.0 COMBINING DOT BELOW LEFT 1DFB ; valid # 9.0 COMBINING DELETION MARK 1DFC ; valid # 6.0 COMBINING DOUBLE INVERTED BREVE BELOW 1DFD ; valid # 5.2 COMBINING ALMOST EQUAL TO BELOW @@ -2410,7 +2426,8 @@ 20BB..20BD ; valid ; ; NV8 # 7.0 NORDIC MARK SIGN..RUBLE SIGN 20BE ; valid ; ; NV8 # 8.0 LARI SIGN 20BF ; valid ; ; NV8 # 10.0 BITCOIN SIGN -20C0..20CF ; disallowed # NA .. +20C0 ; valid ; ; NV8 # 14.0 SOM SIGN +20C1..20CF ; disallowed # NA .. 20D0..20E1 ; valid ; ; NV8 # 1.1 COMBINING LEFT HARPOON ABOVE..COMBINING LEFT RIGHT ARROW ABOVE 20E2..20E3 ; valid ; ; NV8 # 3.0 COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING KEYCAP 20E4..20EA ; valid ; ; NV8 # 3.2 COMBINING ENCLOSING UPWARD POINTING TRIANGLE..COMBINING LEFTWARDS ARROW OVERLAY @@ -2844,9 +2861,9 @@ 2C2C ; mapped ; 2C5C # 4.1 GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D ; mapped ; 2C5D # 4.1 GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E ; mapped ; 2C5E # 4.1 GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C2F ; disallowed # NA +2C2F ; mapped ; 2C5F # 14.0 GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C30..2C5E ; valid # 4.1 GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C5F ; disallowed # NA +2C5F ; valid # 14.0 GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60 ; mapped ; 2C61 # 5.0 LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C61 ; valid # 5.0 LATIN SMALL LETTER L WITH DOUBLE BAR 2C62 ; mapped ; 026B # 5.0 LATIN CAPITAL LETTER L WITH MIDDLE TILDE @@ -3029,7 +3046,8 @@ 2E4A..2E4E ; valid ; ; NV8 # 11.0 DOTTED SOLIDUS..PUNCTUS ELEVATUS MARK 2E4F ; valid ; ; NV8 # 12.0 CORNISH VERSE DIVIDER 2E50..2E52 ; valid ; ; NV8 # 13.0 CROSS PATTY WITH RIGHT CROSSBAR..TIRONIAN SIGN CAPITAL ET -2E53..2E7F ; disallowed # NA .. +2E53..2E5D ; valid ; ; NV8 # 14.0 MEDIEVAL EXCLAMATION MARK..OBLIQUE HYPHEN +2E5E..2E7F ; disallowed # NA .. 2E80..2E99 ; valid ; ; NV8 # 3.0 CJK RADICAL REPEAT..CJK RADICAL RAP 2E9A ; disallowed # NA 2E9B..2E9E ; valid ; ; NV8 # 3.0 CJK RADICAL CHOKE..CJK RADICAL DEATH @@ -3924,7 +3942,7 @@ 9FD6..9FEA ; valid # 10.0 CJK UNIFIED IDEOGRAPH-9FD6..CJK UNIFIED IDEOGRAPH-9FEA 9FEB..9FEF ; valid # 11.0 CJK UNIFIED IDEOGRAPH-9FEB..CJK UNIFIED IDEOGRAPH-9FEF 9FF0..9FFC ; valid # 13.0 CJK UNIFIED IDEOGRAPH-9FF0..CJK UNIFIED IDEOGRAPH-9FFC -9FFD..9FFF ; disallowed # NA .. +9FFD..9FFF ; valid # 14.0 CJK UNIFIED IDEOGRAPH-9FFD..CJK UNIFIED IDEOGRAPH-9FFF A000..A48C ; valid # 3.0 YI SYLLABLE IT..YI SYLLABLE YYR A48D..A48F ; disallowed # NA .. A490..A4A1 ; valid ; ; NV8 # 3.0 YI RADICAL QOT..YI RADICAL GA @@ -4181,7 +4199,8 @@ A7BC ; mapped ; A7BD # 12.0 LATIN CAPITAL LETT A7BD ; valid # 12.0 LATIN SMALL LETTER GLOTTAL I A7BE ; mapped ; A7BF # 12.0 LATIN CAPITAL LETTER GLOTTAL U A7BF ; valid # 12.0 LATIN SMALL LETTER GLOTTAL U -A7C0..A7C1 ; disallowed # NA .. +A7C0 ; mapped ; A7C1 # 14.0 LATIN CAPITAL LETTER OLD POLISH O +A7C1 ; valid # 14.0 LATIN SMALL LETTER OLD POLISH O A7C2 ; mapped ; A7C3 # 12.0 LATIN CAPITAL LETTER ANGLICANA W A7C3 ; valid # 12.0 LATIN SMALL LETTER ANGLICANA W A7C4 ; mapped ; A794 # 12.0 LATIN CAPITAL LETTER C WITH PALATAL HOOK @@ -4191,7 +4210,21 @@ A7C7 ; mapped ; A7C8 # 13.0 LATIN CAPITAL LETT A7C8 ; valid # 13.0 LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; mapped ; A7CA # 13.0 LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CA ; valid # 13.0 LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY -A7CB..A7F4 ; disallowed # NA .. +A7CB..A7CF ; disallowed # NA .. +A7D0 ; mapped ; A7D1 # 14.0 LATIN CAPITAL LETTER CLOSED INSULAR G +A7D1 ; valid # 14.0 LATIN SMALL LETTER CLOSED INSULAR G +A7D2 ; disallowed # NA +A7D3 ; valid # 14.0 LATIN SMALL LETTER DOUBLE THORN +A7D4 ; disallowed # NA +A7D5 ; valid # 14.0 LATIN SMALL LETTER DOUBLE WYNN +A7D6 ; mapped ; A7D7 # 14.0 LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D7 ; valid # 14.0 LATIN SMALL LETTER MIDDLE SCOTS S +A7D8 ; mapped ; A7D9 # 14.0 LATIN CAPITAL LETTER SIGMOID S +A7D9 ; valid # 14.0 LATIN SMALL LETTER SIGMOID S +A7DA..A7F1 ; disallowed # NA .. +A7F2 ; mapped ; 0063 # 14.0 MODIFIER LETTER CAPITAL C +A7F3 ; mapped ; 0066 # 14.0 MODIFIER LETTER CAPITAL F +A7F4 ; mapped ; 0071 # 14.0 MODIFIER LETTER CAPITAL Q A7F5 ; mapped ; A7F6 # 13.0 LATIN CAPITAL LETTER REVERSED HALF H A7F6 ; valid # 13.0 LATIN SMALL LETTER REVERSED HALF H A7F7 ; valid # 7.0 LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -4933,7 +4966,8 @@ FBAA..FBAD ; mapped ; 06BE # 1.1 ARABIC LETTER HEH FBAE..FBAF ; mapped ; 06D2 # 1.1 ARABIC LETTER YEH BARREE ISOLATED FORM..ARABIC LETTER YEH BARREE FINAL FORM FBB0..FBB1 ; mapped ; 06D3 # 1.1 ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC1 ; valid ; ; NV8 # 6.0 ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW -FBC2..FBD2 ; disallowed # NA .. +FBC2 ; valid ; ; NV8 # 14.0 ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; disallowed # NA .. FBD3..FBD6 ; mapped ; 06AD # 1.1 ARABIC LETTER NG ISOLATED FORM..ARABIC LETTER NG MEDIAL FORM FBD7..FBD8 ; mapped ; 06C7 # 1.1 ARABIC LETTER U ISOLATED FORM..ARABIC LETTER U FINAL FORM FBD9..FBDA ; mapped ; 06C6 # 1.1 ARABIC LETTER OE ISOLATED FORM..ARABIC LETTER OE FINAL FORM @@ -5271,7 +5305,7 @@ FD3A ; mapped ; 0637 0645 # 1.1 ARABIC LIGATURE TA FD3B ; mapped ; 0638 0645 # 1.1 ARABIC LIGATURE ZAH WITH MEEM MEDIAL FORM FD3C..FD3D ; mapped ; 0627 064B # 1.1 ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E..FD3F ; valid ; ; NV8 # 1.1 ORNATE LEFT PARENTHESIS..ORNATE RIGHT PARENTHESIS -FD40..FD4F ; disallowed # NA .. +FD40..FD4F ; valid ; ; NV8 # 14.0 ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50 ; mapped ; 062A 062C 0645 #1.1 ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM FD51..FD52 ; mapped ; 062A 062D 062C #1.1 ARABIC LIGATURE TEH WITH HAH WITH JEEM FINAL FORM..ARABIC LIGATURE TEH WITH HAH WITH JEEM INITIAL FORM FD53 ; mapped ; 062A 062D 0645 #1.1 ARABIC LIGATURE TEH WITH HAH WITH MEEM INITIAL FORM @@ -5374,7 +5408,8 @@ FDC4 ; mapped ; 0639 062C 0645 #1.1 ARABIC LIGATURE AI FDC5 ; mapped ; 0635 0645 0645 #1.1 ARABIC LIGATURE SAD WITH MEEM WITH MEEM INITIAL FORM FDC6 ; mapped ; 0633 062E 064A #1.1 ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM FDC7 ; mapped ; 0646 062C 064A #1.1 ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDC8..FDCF ; disallowed # NA .. +FDC8..FDCE ; disallowed # NA .. +FDCF ; valid ; ; NV8 # 14.0 ARABIC LIGATURE SALAAMUHU ALAYNAA FDD0..FDEF ; disallowed # 3.1 .. FDF0 ; mapped ; 0635 0644 06D2 #1.1 ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM FDF1 ; mapped ; 0642 0644 06D2 #1.1 ARABIC LIGATURE QALA USED AS KORANIC STOP SIGN ISOLATED FORM @@ -5390,7 +5425,7 @@ FDFA ; disallowed_STD3_mapped ; 0635 0644 0649 0020 0627 0644 0644 0647 FDFB ; disallowed_STD3_mapped ; 062C 0644 0020 062C 0644 0627 0644 0647 #1.1 ARABIC LIGATURE JALLAJALALOUHOU FDFC ; mapped ; 0631 06CC 0627 0644 #3.2 RIAL SIGN FDFD ; valid ; ; NV8 # 4.0 ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM -FDFE..FDFF ; disallowed # NA .. +FDFE..FDFF ; valid ; ; NV8 # 14.0 ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGATURE AZZA WA JALL FE00..FE0F ; ignored # 3.2 VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE10 ; disallowed_STD3_mapped ; 002C # 4.1 PRESENTATION FORM FOR VERTICAL COMMA FE11 ; mapped ; 3001 # 4.1 PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA @@ -5903,13 +5938,119 @@ FFFE..FFFF ; disallowed # 1.1 .. 1056F ; valid ; ; NV8 # 7.0 CAUCASIAN ALBANIAN CITATION MARK -10570..105FF ; disallowed # NA .. +10570 ; mapped ; 10597 # 14.0 VITHKUQI CAPITAL LETTER A +10571 ; mapped ; 10598 # 14.0 VITHKUQI CAPITAL LETTER BBE +10572 ; mapped ; 10599 # 14.0 VITHKUQI CAPITAL LETTER BE +10573 ; mapped ; 1059A # 14.0 VITHKUQI CAPITAL LETTER CE +10574 ; mapped ; 1059B # 14.0 VITHKUQI CAPITAL LETTER CHE +10575 ; mapped ; 1059C # 14.0 VITHKUQI CAPITAL LETTER DE +10576 ; mapped ; 1059D # 14.0 VITHKUQI CAPITAL LETTER DHE +10577 ; mapped ; 1059E # 14.0 VITHKUQI CAPITAL LETTER EI +10578 ; mapped ; 1059F # 14.0 VITHKUQI CAPITAL LETTER E +10579 ; mapped ; 105A0 # 14.0 VITHKUQI CAPITAL LETTER FE +1057A ; mapped ; 105A1 # 14.0 VITHKUQI CAPITAL LETTER GA +1057B ; disallowed # NA +1057C ; mapped ; 105A3 # 14.0 VITHKUQI CAPITAL LETTER HA +1057D ; mapped ; 105A4 # 14.0 VITHKUQI CAPITAL LETTER HHA +1057E ; mapped ; 105A5 # 14.0 VITHKUQI CAPITAL LETTER I +1057F ; mapped ; 105A6 # 14.0 VITHKUQI CAPITAL LETTER IJE +10580 ; mapped ; 105A7 # 14.0 VITHKUQI CAPITAL LETTER JE +10581 ; mapped ; 105A8 # 14.0 VITHKUQI CAPITAL LETTER KA +10582 ; mapped ; 105A9 # 14.0 VITHKUQI CAPITAL LETTER LA +10583 ; mapped ; 105AA # 14.0 VITHKUQI CAPITAL LETTER LLA +10584 ; mapped ; 105AB # 14.0 VITHKUQI CAPITAL LETTER ME +10585 ; mapped ; 105AC # 14.0 VITHKUQI CAPITAL LETTER NE +10586 ; mapped ; 105AD # 14.0 VITHKUQI CAPITAL LETTER NJE +10587 ; mapped ; 105AE # 14.0 VITHKUQI CAPITAL LETTER O +10588 ; mapped ; 105AF # 14.0 VITHKUQI CAPITAL LETTER PE +10589 ; mapped ; 105B0 # 14.0 VITHKUQI CAPITAL LETTER QA +1058A ; mapped ; 105B1 # 14.0 VITHKUQI CAPITAL LETTER RE +1058B ; disallowed # NA +1058C ; mapped ; 105B3 # 14.0 VITHKUQI CAPITAL LETTER SE +1058D ; mapped ; 105B4 # 14.0 VITHKUQI CAPITAL LETTER SHE +1058E ; mapped ; 105B5 # 14.0 VITHKUQI CAPITAL LETTER TE +1058F ; mapped ; 105B6 # 14.0 VITHKUQI CAPITAL LETTER THE +10590 ; mapped ; 105B7 # 14.0 VITHKUQI CAPITAL LETTER U +10591 ; mapped ; 105B8 # 14.0 VITHKUQI CAPITAL LETTER VE +10592 ; mapped ; 105B9 # 14.0 VITHKUQI CAPITAL LETTER XE +10593 ; disallowed # NA +10594 ; mapped ; 105BB # 14.0 VITHKUQI CAPITAL LETTER Y +10595 ; mapped ; 105BC # 14.0 VITHKUQI CAPITAL LETTER ZE +10596 ; disallowed # NA +10597..105A1 ; valid # 14.0 VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A2 ; disallowed # NA +105A3..105B1 ; valid # 14.0 VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B2 ; disallowed # NA +105B3..105B9 ; valid # 14.0 VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BA ; disallowed # NA +105BB..105BC ; valid # 14.0 VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105BD..105FF ; disallowed # NA .. 10600..10736 ; valid # 7.0 LINEAR A SIGN AB001..LINEAR A SIGN A664 10737..1073F ; disallowed # NA .. 10740..10755 ; valid # 7.0 LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10756..1075F ; disallowed # NA .. 10760..10767 ; valid # 7.0 LINEAR A SIGN A800..LINEAR A SIGN A807 -10768..107FF ; disallowed # NA .. +10768..1077F ; disallowed # NA .. +10780 ; valid # 14.0 MODIFIER LETTER SMALL CAPITAL AA +10781 ; mapped ; 02D0 # 14.0 MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON +10782 ; mapped ; 02D1 # 14.0 MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON +10783 ; mapped ; 00E6 # 14.0 MODIFIER LETTER SMALL AE +10784 ; mapped ; 0299 # 14.0 MODIFIER LETTER SMALL CAPITAL B +10785 ; mapped ; 0253 # 14.0 MODIFIER LETTER SMALL B WITH HOOK +10786 ; disallowed # NA +10787 ; mapped ; 02A3 # 14.0 MODIFIER LETTER SMALL DZ DIGRAPH +10788 ; mapped ; AB66 # 14.0 MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK +10789 ; mapped ; 02A5 # 14.0 MODIFIER LETTER SMALL DZ DIGRAPH WITH CURL +1078A ; mapped ; 02A4 # 14.0 MODIFIER LETTER SMALL DEZH DIGRAPH +1078B ; mapped ; 0256 # 14.0 MODIFIER LETTER SMALL D WITH TAIL +1078C ; mapped ; 0257 # 14.0 MODIFIER LETTER SMALL D WITH HOOK +1078D ; mapped ; 1D91 # 14.0 MODIFIER LETTER SMALL D WITH HOOK AND TAIL +1078E ; mapped ; 0258 # 14.0 MODIFIER LETTER SMALL REVERSED E +1078F ; mapped ; 025E # 14.0 MODIFIER LETTER SMALL CLOSED REVERSED OPEN E +10790 ; mapped ; 02A9 # 14.0 MODIFIER LETTER SMALL FENG DIGRAPH +10791 ; mapped ; 0264 # 14.0 MODIFIER LETTER SMALL RAMS HORN +10792 ; mapped ; 0262 # 14.0 MODIFIER LETTER SMALL CAPITAL G +10793 ; mapped ; 0260 # 14.0 MODIFIER LETTER SMALL G WITH HOOK +10794 ; mapped ; 029B # 14.0 MODIFIER LETTER SMALL CAPITAL G WITH HOOK +10795 ; mapped ; 0127 # 14.0 MODIFIER LETTER SMALL H WITH STROKE +10796 ; mapped ; 029C # 14.0 MODIFIER LETTER SMALL CAPITAL H +10797 ; mapped ; 0267 # 14.0 MODIFIER LETTER SMALL HENG WITH HOOK +10798 ; mapped ; 0284 # 14.0 MODIFIER LETTER SMALL DOTLESS J WITH STROKE AND HOOK +10799 ; mapped ; 02AA # 14.0 MODIFIER LETTER SMALL LS DIGRAPH +1079A ; mapped ; 02AB # 14.0 MODIFIER LETTER SMALL LZ DIGRAPH +1079B ; mapped ; 026C # 14.0 MODIFIER LETTER SMALL L WITH BELT +1079C ; mapped ; 1DF04 # 14.0 MODIFIER LETTER SMALL CAPITAL L WITH BELT +1079D ; mapped ; A78E # 14.0 MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT +1079E ; mapped ; 026E # 14.0 MODIFIER LETTER SMALL LEZH +1079F ; mapped ; 1DF05 # 14.0 MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK +107A0 ; mapped ; 028E # 14.0 MODIFIER LETTER SMALL TURNED Y +107A1 ; mapped ; 1DF06 # 14.0 MODIFIER LETTER SMALL TURNED Y WITH BELT +107A2 ; mapped ; 00F8 # 14.0 MODIFIER LETTER SMALL O WITH STROKE +107A3 ; mapped ; 0276 # 14.0 MODIFIER LETTER SMALL CAPITAL OE +107A4 ; mapped ; 0277 # 14.0 MODIFIER LETTER SMALL CLOSED OMEGA +107A5 ; mapped ; 0071 # 14.0 MODIFIER LETTER SMALL Q +107A6 ; mapped ; 027A # 14.0 MODIFIER LETTER SMALL TURNED R WITH LONG LEG +107A7 ; mapped ; 1DF08 # 14.0 MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK +107A8 ; mapped ; 027D # 14.0 MODIFIER LETTER SMALL R WITH TAIL +107A9 ; mapped ; 027E # 14.0 MODIFIER LETTER SMALL R WITH FISHHOOK +107AA ; mapped ; 0280 # 14.0 MODIFIER LETTER SMALL CAPITAL R +107AB ; mapped ; 02A8 # 14.0 MODIFIER LETTER SMALL TC DIGRAPH WITH CURL +107AC ; mapped ; 02A6 # 14.0 MODIFIER LETTER SMALL TS DIGRAPH +107AD ; mapped ; AB67 # 14.0 MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK +107AE ; mapped ; 02A7 # 14.0 MODIFIER LETTER SMALL TESH DIGRAPH +107AF ; mapped ; 0288 # 14.0 MODIFIER LETTER SMALL T WITH RETROFLEX HOOK +107B0 ; mapped ; 2C71 # 14.0 MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B1 ; disallowed # NA +107B2 ; mapped ; 028F # 14.0 MODIFIER LETTER SMALL CAPITAL Y +107B3 ; mapped ; 02A1 # 14.0 MODIFIER LETTER GLOTTAL STOP WITH STROKE +107B4 ; mapped ; 02A2 # 14.0 MODIFIER LETTER REVERSED GLOTTAL STOP WITH STROKE +107B5 ; mapped ; 0298 # 14.0 MODIFIER LETTER BILABIAL CLICK +107B6 ; mapped ; 01C0 # 14.0 MODIFIER LETTER DENTAL CLICK +107B7 ; mapped ; 01C1 # 14.0 MODIFIER LETTER LATERAL CLICK +107B8 ; mapped ; 01C2 # 14.0 MODIFIER LETTER ALVEOLAR CLICK +107B9 ; mapped ; 1DF0A # 14.0 MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +107BA ; mapped ; 1DF1E # 14.0 MODIFIER LETTER SMALL S WITH CURL +107BB..107FF ; disallowed # NA .. 10800..10805 ; valid # 4.0 CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10806..10807 ; disallowed # NA .. 10808 ; valid # 4.0 CYPRIOT SYLLABLE JO @@ -6072,7 +6213,10 @@ FFFE..FFFF ; disallowed # 1.1 .. 10F30..10F50 ; valid # 11.0 SOGDIAN LETTER ALEPH..SOGDIAN COMBINING STROKE BELOW 10F51..10F59 ; valid ; ; NV8 # 11.0 SOGDIAN NUMBER ONE..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT -10F5A..10FAF ; disallowed # NA .. +10F5A..10F6F ; disallowed # NA .. +10F70..10F85 ; valid # 14.0 OLD UYGHUR LETTER ALEPH..OLD UYGHUR COMBINING TWO DOTS BELOW +10F86..10F89 ; valid ; ; NV8 # 14.0 OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS +10F8A..10FAF ; disallowed # NA .. 10FB0..10FC4 ; valid # 13.0 CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; valid ; ; NV8 # 13.0 CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FCC..10FDF ; disallowed # NA .. @@ -6083,13 +6227,15 @@ FFFE..FFFF ; disallowed # 1.1 .. 11052..11065 ; valid ; ; NV8 # 6.0 BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; valid # 6.0 BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE -11070..1107E ; disallowed # NA .. +11070..11075 ; valid # 14.0 BRAHMI SIGN OLD TAMIL VIRAMA..BRAHMI LETTER OLD TAMIL LLA +11076..1107E ; disallowed # NA .. 1107F ; valid # 7.0 BRAHMI NUMBER JOINER 11080..110BA ; valid # 5.2 KAITHI SIGN CANDRABINDU..KAITHI SIGN NUKTA 110BB..110BC ; valid ; ; NV8 # 5.2 KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BD ; disallowed # 5.2 KAITHI NUMBER SIGN 110BE..110C1 ; valid ; ; NV8 # 5.2 KAITHI SECTION MARK..KAITHI DOUBLE DANDA -110C2..110CC ; disallowed # NA .. +110C2 ; valid # 14.0 KAITHI VOWEL SIGN VOCALIC R +110C3..110CC ; disallowed # NA .. 110CD ; disallowed # 11.0 KAITHI NUMBER SIGN ABOVE 110CE..110CF ; disallowed # NA .. 110D0..110E8 ; valid # 6.1 SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE @@ -6207,7 +6353,8 @@ FFFE..FFFF ; disallowed # 1.1 .. 11680..116B7 ; valid # 6.1 TAKRI LETTER A..TAKRI SIGN NUKTA 116B8 ; valid # 12.0 TAKRI LETTER ARCHAIC KHA -116B9..116BF ; disallowed # NA .. +116B9 ; valid ; ; NV8 # 14.0 TAKRI ABBREVIATION SIGN +116BA..116BF ; disallowed # NA .. 116C0..116C9 ; valid # 6.1 TAKRI DIGIT ZERO..TAKRI DIGIT NINE 116CA..116FF ; disallowed # NA .. 11700..11719 ; valid # 8.0 AHOM LETTER KA..AHOM LETTER JHA @@ -6217,7 +6364,8 @@ FFFE..FFFF ; disallowed # 1.1 .. 11730..11739 ; valid # 8.0 AHOM DIGIT ZERO..AHOM DIGIT NINE 1173A..1173F ; valid ; ; NV8 # 8.0 AHOM NUMBER TEN..AHOM SYMBOL VI -11740..117FF ; disallowed # NA .. +11740..11746 ; valid # 14.0 AHOM LETTER CA..AHOM LETTER LLA +11747..117FF ; disallowed # NA .. 11800..1183A ; valid # 11.0 DOGRA LETTER A..DOGRA SIGN NUKTA 1183B ; valid ; ; NV8 # 11.0 DOGRA ABBREVIATION SIGN 1183C..1189F ; disallowed # NA .. @@ -6292,7 +6440,8 @@ FFFE..FFFF ; disallowed # 1.1 .. +11AA3..11AAF ; disallowed # NA .. +11AB0..11ABF ; valid # 14.0 CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11AC0..11AF8 ; valid # 7.0 PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11AF9..11BFF ; disallowed # NA .. 11C00..11C08 ; valid # 9.0 BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L @@ -6357,7 +6506,10 @@ FFFE..FFFF ; disallowed # 1.1 .. 12480..12543 ; valid # 8.0 CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -12544..12FFF ; disallowed # NA .. +12544..12F8F ; disallowed # NA .. +12F90..12FF0 ; valid # 14.0 CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; valid ; ; NV8 # 14.0 CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 +12FF3..12FFF ; disallowed # NA .. 13000..1342E ; valid # 5.2 EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 1342F ; disallowed # NA 13430..13438 ; disallowed # 12.0 EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT @@ -6371,7 +6523,10 @@ FFFE..FFFF ; disallowed # 1.1 .. 16A6E..16A6F ; valid ; ; NV8 # 7.0 MRO DANDA..MRO DOUBLE DANDA -16A70..16ACF ; disallowed # NA .. +16A70..16ABE ; valid # 14.0 TANGSA LETTER OZ..TANGSA LETTER ZA +16ABF ; disallowed # NA +16AC0..16AC9 ; valid # 14.0 TANGSA DIGIT ZERO..TANGSA DIGIT NINE +16ACA..16ACF ; disallowed # NA .. 16AD0..16AED ; valid # 7.0 BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AEE..16AEF ; disallowed # NA .. 16AF0..16AF4 ; valid # 7.0 BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE @@ -6450,10 +6605,17 @@ FFFE..FFFF ; disallowed # 1.1 .. 18D00..18D08 ; valid # 13.0 TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -18D09..1AFFF ; disallowed # NA .. +18D09..1AFEF ; disallowed # NA .. +1AFF0..1AFF3 ; valid # 14.0 KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF4 ; disallowed # NA +1AFF5..1AFFB ; valid # 14.0 KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFC ; disallowed # NA +1AFFD..1AFFE ; valid # 14.0 KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1AFFF ; disallowed # NA 1B000..1B001 ; valid # 6.0 KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE 1B002..1B11E ; valid # 10.0 HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2 -1B11F..1B14F ; disallowed # NA .. +1B11F..1B122 ; valid # 14.0 HIRAGANA LETTER ARCHAIC WU..KATAKANA LETTER ARCHAIC WU +1B123..1B14F ; disallowed # NA .. 1B150..1B152 ; valid # 12.0 HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B153..1B163 ; disallowed # NA .. 1B164..1B167 ; valid # 12.0 KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N @@ -6472,7 +6634,13 @@ FFFE..FFFF ; disallowed # 1.1 .. +1BCA4..1CEFF ; disallowed # NA .. +1CF00..1CF2D ; valid # 14.0 ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF2E..1CF2F ; disallowed # NA .. +1CF30..1CF46 ; valid # 14.0 ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1CF47..1CF4F ; disallowed # NA .. +1CF50..1CFC3 ; valid ; ; NV8 # 14.0 ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK +1CFC4..1CFFF ; disallowed # NA .. 1D000..1D0F5 ; valid ; ; NV8 # 3.1 BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D0F6..1D0FF ; disallowed # NA .. 1D100..1D126 ; valid ; ; NV8 # 3.1 MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -6497,7 +6665,8 @@ FFFE..FFFF ; disallowed # 1.1 .. +1D1E9..1D1EA ; valid ; ; NV8 # 14.0 MUSICAL SYMBOL SORI..MUSICAL SYMBOL KORON +1D1EB..1D1FF ; disallowed # NA .. 1D200..1D245 ; valid ; ; NV8 # 4.1 GREEK VOCAL NOTATION SYMBOL-1..GREEK MUSICAL LEIMMA 1D246..1D2DF ; disallowed # NA .. 1D2E0..1D2F3 ; valid ; ; NV8 # 11.0 MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN @@ -7530,7 +7699,9 @@ FFFE..FFFF ; disallowed # 1.1 1DAA1..1DAAF ; valid # 8.0 SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 -1DAB0..1DFFF ; disallowed # NA .. +1DAB0..1DEFF ; disallowed # NA .. +1DF00..1DF1E ; valid # 14.0 LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL +1DF1F..1DFFF ; disallowed # NA .. 1E000..1E006 ; valid # 9.0 COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E007 ; disallowed # NA 1E008..1E018 ; valid # 9.0 COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU @@ -7549,11 +7720,21 @@ FFFE..FFFF ; disallowed # 1.1 .. 1E14E ; valid # 12.0 NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; valid ; ; NV8 # 12.0 NYIAKENG PUACHUE HMONG CIRCLED CA -1E150..1E2BF ; disallowed # NA .. +1E150..1E28F ; disallowed # NA .. +1E290..1E2AE ; valid # 14.0 TOTO LETTER PA..TOTO SIGN RISING TONE +1E2AF..1E2BF ; disallowed # NA .. 1E2C0..1E2F9 ; valid # 12.0 WANCHO LETTER AA..WANCHO DIGIT NINE 1E2FA..1E2FE ; disallowed # NA .. 1E2FF ; valid ; ; NV8 # 12.0 WANCHO NGUN SIGN -1E300..1E7FF ; disallowed # NA .. +1E300..1E7DF ; disallowed # NA .. +1E7E0..1E7E6 ; valid # 14.0 ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E7 ; disallowed # NA +1E7E8..1E7EB ; valid # 14.0 ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7EC ; disallowed # NA +1E7ED..1E7EE ; valid # 14.0 ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7EF ; disallowed # NA +1E7F0..1E7FE ; valid # 14.0 ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE +1E7FF ; disallowed # NA 1E800..1E8C4 ; valid # 7.0 MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C5..1E8C6 ; disallowed # NA .. 1E8C7..1E8CF ; valid ; ; NV8 # 7.0 MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE @@ -8032,7 +8213,8 @@ FFFE..FFFF ; disallowed # 1.1 .. +1F6D8..1F6DC ; disallowed # NA .. +1F6DD..1F6DF ; valid ; ; NV8 # 14.0 PLAYGROUND SLIDE..RING BUOY 1F6E0..1F6EC ; valid ; ; NV8 # 7.0 HAMMER AND WRENCH..AIRPLANE ARRIVING 1F6ED..1F6EF ; disallowed # NA .. 1F6F0..1F6F3 ; valid ; ; NV8 # 7.0 SATELLITE..PASSENGER SHIP @@ -8048,7 +8230,9 @@ FFFE..FFFF ; disallowed # 1.1 .. 1F7E0..1F7EB ; valid ; ; NV8 # 12.0 LARGE ORANGE CIRCLE..LARGE BROWN SQUARE -1F7EC..1F7FF ; disallowed # NA .. +1F7EC..1F7EF ; disallowed # NA .. +1F7F0 ; valid ; ; NV8 # 14.0 HEAVY EQUALS SIGN +1F7F1..1F7FF ; disallowed # NA .. 1F800..1F80B ; valid ; ; NV8 # 7.0 LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F80C..1F80F ; disallowed # NA .. 1F810..1F847 ; valid ; ; NV8 # 7.0 LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW @@ -8083,7 +8267,7 @@ FFFE..FFFF ; disallowed # 1.1 +1F979 ; valid ; ; NV8 # 14.0 FACE HOLDING BACK TEARS 1F97A ; valid ; ; NV8 # 11.0 FACE WITH PLEADING EYES 1F97B ; valid ; ; NV8 # 12.0 SARI 1F97C..1F97F ; valid ; ; NV8 # 11.0 LAB COAT..FLAT SHOE @@ -8101,7 +8285,7 @@ FFFE..FFFF ; disallowed # 1.1 +1F9CC ; valid ; ; NV8 # 14.0 TROLL 1F9CD..1F9CF ; valid ; ; NV8 # 12.0 STANDING PERSON..DEAF PERSON 1F9D0..1F9E6 ; valid ; ; NV8 # 10.0 FACE WITH MONOCLE..SOCKS 1F9E7..1F9FF ; valid ; ; NV8 # 11.0 RED GIFT ENVELOPE..NAZAR AMULET @@ -8113,19 +8297,28 @@ FFFE..FFFF ; disallowed # 1.1 .. 1FA78..1FA7A ; valid ; ; NV8 # 12.0 DROP OF BLOOD..STETHOSCOPE -1FA7B..1FA7F ; disallowed # NA .. +1FA7B..1FA7C ; valid ; ; NV8 # 14.0 X-RAY..CRUTCH +1FA7D..1FA7F ; disallowed # NA .. 1FA80..1FA82 ; valid ; ; NV8 # 12.0 YO-YO..PARACHUTE 1FA83..1FA86 ; valid ; ; NV8 # 13.0 BOOMERANG..NESTING DOLLS 1FA87..1FA8F ; disallowed # NA .. 1FA90..1FA95 ; valid ; ; NV8 # 12.0 RINGED PLANET..BANJO 1FA96..1FAA8 ; valid ; ; NV8 # 13.0 MILITARY HELMET..ROCK -1FAA9..1FAAF ; disallowed # NA .. +1FAA9..1FAAC ; valid ; ; NV8 # 14.0 MIRROR BALL..HAMSA +1FAAD..1FAAF ; disallowed # NA .. 1FAB0..1FAB6 ; valid ; ; NV8 # 13.0 FLY..FEATHER -1FAB7..1FABF ; disallowed # NA .. +1FAB7..1FABA ; valid ; ; NV8 # 14.0 LOTUS..NEST WITH EGGS +1FABB..1FABF ; disallowed # NA .. 1FAC0..1FAC2 ; valid ; ; NV8 # 13.0 ANATOMICAL HEART..PEOPLE HUGGING -1FAC3..1FACF ; disallowed # NA .. +1FAC3..1FAC5 ; valid ; ; NV8 # 14.0 PREGNANT MAN..PERSON WITH CROWN +1FAC6..1FACF ; disallowed # NA .. 1FAD0..1FAD6 ; valid ; ; NV8 # 13.0 BLUEBERRIES..TEAPOT -1FAD7..1FAFF ; disallowed # NA .. +1FAD7..1FAD9 ; valid ; ; NV8 # 14.0 POURING LIQUID..JAR +1FADA..1FADF ; disallowed # NA .. +1FAE0..1FAE7 ; valid ; ; NV8 # 14.0 MELTING FACE..BUBBLES +1FAE8..1FAEF ; disallowed # NA .. +1FAF0..1FAF6 ; valid ; ; NV8 # 14.0 HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS +1FAF7..1FAFF ; disallowed # NA .. 1FB00..1FB92 ; valid ; ; NV8 # 13.0 BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB93 ; disallowed # NA 1FB94..1FBCA ; valid ; ; NV8 # 13.0 LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON @@ -8144,9 +8337,11 @@ FFFE..FFFF ; disallowed # 1.1 .. 20000..2A6D6 ; valid # 3.1 CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6DD ; valid # 13.0 CJK UNIFIED IDEOGRAPH-2A6D7..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF ; disallowed # NA .. +2A6DE..2A6DF ; valid # 14.0 CJK UNIFIED IDEOGRAPH-2A6DE..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF ; disallowed # NA .. 2A700..2B734 ; valid # 5.2 CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F ; disallowed # NA .. +2B735..2B738 ; valid # 14.0 CJK UNIFIED IDEOGRAPH-2B735..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F ; disallowed # NA .. 2B740..2B81D ; valid # 6.0 CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; disallowed # NA .. 2B820..2CEA1 ; valid # 8.0 CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 diff --git a/util/unicode/data/LineBreak.txt b/util/unicode/data/LineBreak.txt index 22abddcd90..aa5985b8f0 100644 --- a/util/unicode/data/LineBreak.txt +++ b/util/unicode/data/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] .. @@ -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] .. +20C0;PO # Sc SOM SIGN +20C1..20CF;PR # Cn [15] .. 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] .. +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] .. -1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6D8..1F6DC;ID # Cn [5] .. +1F6DD..1F6EC;ID # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6ED..1F6EF;ID # Cn [3] .. 1F6F0..1F6FC;ID # So [13] SATELLITE..ROLLER SKATE 1F6FD..1F6FF;ID # Cn [3] .. @@ -3400,7 +3465,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F7D5..1F7D8;ID # So [4] CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7D9..1F7DF;ID # Cn [7] .. 1F7E0..1F7EB;ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE -1F7EC..1F7FF;ID # Cn [20] .. +1F7EC..1F7EF;ID # Cn [4] .. +1F7F0;ID # So HEAVY EQUALS SIGN +1F7F1..1F7FF;ID # Cn [15] .. 1F800..1F80B;AL # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F80C..1F80F;ID # Cn [4] .. 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 -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 +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] .. 1FA70..1FA74;ID # So [5] BALLET SHOES..THONG SANDAL 1FA75..1FA77;ID # Cn [3] .. -1FA78..1FA7A;ID # So [3] DROP OF BLOOD..STETHOSCOPE -1FA7B..1FA7F;ID # Cn [5] .. +1FA78..1FA7C;ID # So [5] DROP OF BLOOD..CRUTCH +1FA7D..1FA7F;ID # Cn [3] .. 1FA80..1FA86;ID # So [7] YO-YO..NESTING DOLLS 1FA87..1FA8F;ID # Cn [9] .. -1FA90..1FAA8;ID # So [25] RINGED PLANET..ROCK -1FAA9..1FAAF;ID # Cn [7] .. -1FAB0..1FAB6;ID # So [7] FLY..FEATHER -1FAB7..1FABF;ID # Cn [9] .. +1FA90..1FAAC;ID # So [29] RINGED PLANET..HAMSA +1FAAD..1FAAF;ID # Cn [3] .. +1FAB0..1FABA;ID # So [11] FLY..NEST WITH EGGS +1FABB..1FABF;ID # Cn [5] .. 1FAC0..1FAC2;ID # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAC3..1FACF;ID # Cn [13] .. -1FAD0..1FAD6;ID # So [7] BLUEBERRIES..TEAPOT -1FAD7..1FAFF;ID # Cn [41] .. +1FAC3..1FAC5;EB # So [3] PREGNANT MAN..PERSON WITH CROWN +1FAC6..1FACF;ID # Cn [10] .. +1FAD0..1FAD9;ID # So [10] BLUEBERRIES..JAR +1FADA..1FADF;ID # Cn [6] .. +1FAE0..1FAE7;ID # So [8] MELTING FACE..BUBBLES +1FAE8..1FAEF;ID # Cn [8] .. +1FAF0..1FAF6;EB # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS +1FAF7..1FAFF;ID # Cn [9] .. 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] .. -20000..2A6DD;ID # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A6DE..2A6FF;ID # Cn [34] .. -2A700..2B734;ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 -2B735..2B73F;ID # Cn [11] .. +20000..2A6DF;ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A6E0..2A6FF;ID # Cn [32] .. +2A700..2B738;ID # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B739..2B73F;ID # Cn [7] .. 2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F;ID # Cn [2] .. 2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 diff --git a/util/unicode/data/NormalizationCorrections.txt b/util/unicode/data/NormalizationCorrections.txt index 7144fb8935..a1a34d6bb6 100644 --- a/util/unicode/data/NormalizationCorrections.txt +++ b/util/unicode/data/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/util/unicode/data/Scripts.txt b/util/unicode/data/Scripts.txt index e0363f54d1..a138373011 100644 --- a/util/unicode/data/Scripts.txt +++ b/util/unicode/data/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/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt index 432385b269..4b12b85492 100644 --- a/util/unicode/data/SentenceBreakProperty.txt +++ b/util/unicode/data/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/util/unicode/data/SpecialCasing.txt b/util/unicode/data/SpecialCasing.txt index 2a1a5a1d6b..1c2e968a8c 100644 --- a/util/unicode/data/SpecialCasing.txt +++ b/util/unicode/data/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/util/unicode/data/UnicodeData.txt b/util/unicode/data/UnicodeData.txt index e22f967bba..b5abef7ed4 100644 --- a/util/unicode/data/UnicodeData.txt +++ b/util/unicode/data/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;;Lo;0;L;;;;;N;;;;; -9FFC;;Lo;0;L;;;;;N;;;;; +9FFF;;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; 0043;;;;N;;;;; +A7F3;MODIFIER LETTER CAPITAL F;Lm;0;L; 0046;;;;N;;;;; +A7F4;MODIFIER LETTER CAPITAL Q;Lm;0;L; 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; 06AD;;;;N;;;;; FBD4;ARABIC LETTER NG FINAL FORM;Lo;0;AL; 06AD;;;;N;;;;; FBD5;ARABIC LETTER NG INITIAL FORM;Lo;0;AL; 06AD;;;;N;;;;; @@ -16159,6 +16266,22 @@ FD3C;ARABIC LIGATURE ALEF WITH FATHATAN FINAL FORM;Lo;0;AL; 0627 064B;;;; FD3D;ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM;Lo;0;AL; 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; 062A 062C 0645;;;;N;;;;; FD51;ARABIC LIGATURE TEH WITH HAH WITH JEEM FINAL FORM;Lo;0;AL; 062A 062D 062C;;;;N;;;;; FD52;ARABIC LIGATURE TEH WITH HAH WITH JEEM INITIAL FORM;Lo;0;AL; 062A 062D 062C;;;;N;;;;; @@ -16277,6 +16400,7 @@ FDC4;ARABIC LIGATURE AIN WITH JEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0639 FDC5;ARABIC LIGATURE SAD WITH MEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0635 0645 0645;;;;N;;;;; FDC6;ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM;Lo;0;AL; 0633 062E 064A;;;;N;;;;; FDC7;ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM;Lo;0;AL; 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; 0635 0644 06D2;;;;N;;;;; FDF1;ARABIC LIGATURE QALA USED AS KORANIC STOP SIGN ISOLATED FORM;Lo;0;AL; 0642 0644 06D2;;;;N;;;;; FDF2;ARABIC LIGATURE ALLAH ISOLATED FORM;Lo;0;AL; 0627 0644 0644 0647;;;;N;;;;; @@ -16291,6 +16415,8 @@ FDFA;ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM;Lo;0;AL; 0635 0644 06 FDFB;ARABIC LIGATURE JALLAJALALOUHOU;Lo;0;AL; 062C 0644 0020 062C 0644 0627 0644 0647;;;;N;ARABIC LETTER JALLAJALALOUHOU;;;; FDFC;RIAL SIGN;Sc;0;AL; 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; 02D0;;;;N;;;;; +10782;MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON;Lm;0;L; 02D1;;;;N;;;;; +10783;MODIFIER LETTER SMALL AE;Lm;0;L; 00E6;;;;N;;;;; +10784;MODIFIER LETTER SMALL CAPITAL B;Lm;0;L; 0299;;;;N;;;;; +10785;MODIFIER LETTER SMALL B WITH HOOK;Lm;0;L; 0253;;;;N;;;;; +10787;MODIFIER LETTER SMALL DZ DIGRAPH;Lm;0;L; 02A3;;;;N;;;;; +10788;MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK;Lm;0;L; AB66;;;;N;;;;; +10789;MODIFIER LETTER SMALL DZ DIGRAPH WITH CURL;Lm;0;L; 02A5;;;;N;;;;; +1078A;MODIFIER LETTER SMALL DEZH DIGRAPH;Lm;0;L; 02A4;;;;N;;;;; +1078B;MODIFIER LETTER SMALL D WITH TAIL;Lm;0;L; 0256;;;;N;;;;; +1078C;MODIFIER LETTER SMALL D WITH HOOK;Lm;0;L; 0257;;;;N;;;;; +1078D;MODIFIER LETTER SMALL D WITH HOOK AND TAIL;Lm;0;L; 1D91;;;;N;;;;; +1078E;MODIFIER LETTER SMALL REVERSED E;Lm;0;L; 0258;;;;N;;;;; +1078F;MODIFIER LETTER SMALL CLOSED REVERSED OPEN E;Lm;0;L; 025E;;;;N;;;;; +10790;MODIFIER LETTER SMALL FENG DIGRAPH;Lm;0;L; 02A9;;;;N;;;;; +10791;MODIFIER LETTER SMALL RAMS HORN;Lm;0;L; 0264;;;;N;;;;; +10792;MODIFIER LETTER SMALL CAPITAL G;Lm;0;L; 0262;;;;N;;;;; +10793;MODIFIER LETTER SMALL G WITH HOOK;Lm;0;L; 0260;;;;N;;;;; +10794;MODIFIER LETTER SMALL CAPITAL G WITH HOOK;Lm;0;L; 029B;;;;N;;;;; +10795;MODIFIER LETTER SMALL H WITH STROKE;Lm;0;L; 0127;;;;N;;;;; +10796;MODIFIER LETTER SMALL CAPITAL H;Lm;0;L; 029C;;;;N;;;;; +10797;MODIFIER LETTER SMALL HENG WITH HOOK;Lm;0;L; 0267;;;;N;;;;; +10798;MODIFIER LETTER SMALL DOTLESS J WITH STROKE AND HOOK;Lm;0;L; 0284;;;;N;;;;; +10799;MODIFIER LETTER SMALL LS DIGRAPH;Lm;0;L; 02AA;;;;N;;;;; +1079A;MODIFIER LETTER SMALL LZ DIGRAPH;Lm;0;L; 02AB;;;;N;;;;; +1079B;MODIFIER LETTER SMALL L WITH BELT;Lm;0;L; 026C;;;;N;;;;; +1079C;MODIFIER LETTER SMALL CAPITAL L WITH BELT;Lm;0;L; 1DF04;;;;N;;;;; +1079D;MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT;Lm;0;L; A78E;;;;N;;;;; +1079E;MODIFIER LETTER SMALL LEZH;Lm;0;L; 026E;;;;N;;;;; +1079F;MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK;Lm;0;L; 1DF05;;;;N;;;;; +107A0;MODIFIER LETTER SMALL TURNED Y;Lm;0;L; 028E;;;;N;;;;; +107A1;MODIFIER LETTER SMALL TURNED Y WITH BELT;Lm;0;L; 1DF06;;;;N;;;;; +107A2;MODIFIER LETTER SMALL O WITH STROKE;Lm;0;L; 00F8;;;;N;;;;; +107A3;MODIFIER LETTER SMALL CAPITAL OE;Lm;0;L; 0276;;;;N;;;;; +107A4;MODIFIER LETTER SMALL CLOSED OMEGA;Lm;0;L; 0277;;;;N;;;;; +107A5;MODIFIER LETTER SMALL Q;Lm;0;L; 0071;;;;N;;;;; +107A6;MODIFIER LETTER SMALL TURNED R WITH LONG LEG;Lm;0;L; 027A;;;;N;;;;; +107A7;MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK;Lm;0;L; 1DF08;;;;N;;;;; +107A8;MODIFIER LETTER SMALL R WITH TAIL;Lm;0;L; 027D;;;;N;;;;; +107A9;MODIFIER LETTER SMALL R WITH FISHHOOK;Lm;0;L; 027E;;;;N;;;;; +107AA;MODIFIER LETTER SMALL CAPITAL R;Lm;0;L; 0280;;;;N;;;;; +107AB;MODIFIER LETTER SMALL TC DIGRAPH WITH CURL;Lm;0;L; 02A8;;;;N;;;;; +107AC;MODIFIER LETTER SMALL TS DIGRAPH;Lm;0;L; 02A6;;;;N;;;;; +107AD;MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK;Lm;0;L; AB67;;;;N;;;;; +107AE;MODIFIER LETTER SMALL TESH DIGRAPH;Lm;0;L; 02A7;;;;N;;;;; +107AF;MODIFIER LETTER SMALL T WITH RETROFLEX HOOK;Lm;0;L; 0288;;;;N;;;;; +107B0;MODIFIER LETTER SMALL V WITH RIGHT HOOK;Lm;0;L; 2C71;;;;N;;;;; +107B2;MODIFIER LETTER SMALL CAPITAL Y;Lm;0;L; 028F;;;;N;;;;; +107B3;MODIFIER LETTER GLOTTAL STOP WITH STROKE;Lm;0;L; 02A1;;;;N;;;;; +107B4;MODIFIER LETTER REVERSED GLOTTAL STOP WITH STROKE;Lm;0;L; 02A2;;;;N;;;;; +107B5;MODIFIER LETTER BILABIAL CLICK;Lm;0;L; 0298;;;;N;;;;; +107B6;MODIFIER LETTER DENTAL CLICK;Lm;0;L; 01C0;;;;N;;;;; +107B7;MODIFIER LETTER LATERAL CLICK;Lm;0;L; 01C1;;;;N;;;;; +107B8;MODIFIER LETTER ALVEOLAR CLICK;Lm;0;L; 01C2;;;;N;;;;; +107B9;MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK;Lm;0;L; 1DF0A;;;;N;;;;; +107BA;MODIFIER LETTER SMALL S WITH CURL;Lm;0;L; 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;;Lo;0;L;;;;;N;;;;; 18D08;;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; 0038;8;8;8;N;;;;; 1FBF9;SEGMENTED DIGIT NINE;Nd;0;EN; 0039;9;9;9;N;;;;; 20000;;Lo;0;L;;;;;N;;;;; -2A6DD;;Lo;0;L;;;;;N;;;;; +2A6DF;;Lo;0;L;;;;;N;;;;; 2A700;;Lo;0;L;;;;;N;;;;; -2B734;;Lo;0;L;;;;;N;;;;; +2B738;;Lo;0;L;;;;;N;;;;; 2B740;;Lo;0;L;;;;;N;;;;; 2B81D;;Lo;0;L;;;;;N;;;;; 2B820;;Lo;0;L;;;;;N;;;;; diff --git a/util/unicode/data/WordBreakProperty.txt b/util/unicode/data/WordBreakProperty.txt index 36d1438c26..73cd069dcb 100644 --- a/util/unicode/data/WordBreakProperty.txt +++ b/util/unicode/data/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/util/unicode/data/emoji-data.txt b/util/unicode/data/emoji-data.txt index 5d7dc1b156..7806c7ab53 100644 --- a/util/unicode/data/emoji-data.txt +++ b/util/unicode/data/emoji-data.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] (🛘..🛟) .. +1F6D8..1F6DC ; Extended_Pictographic# E0.0 [5] (🛘..🛜) .. +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] (🝴..🝿) .. 1F7D5..1F7DF ; Extended_Pictographic# E0.0 [11] (🟕..🟟) CIRCLED TRIANGLE.. 1F7E0..1F7EB ; Extended_Pictographic# E12.0 [12] (🟠..🟫) orange circle..brown square -1F7EC..1F7FF ; Extended_Pictographic# E0.0 [20] (🟬..🟿) .. +1F7EC..1F7EF ; Extended_Pictographic# E0.0 [4] (🟬..🟯) .. +1F7F0 ; Extended_Pictographic# E14.0 [1] (🟰) heavy equals sign +1F7F1..1F7FF ; Extended_Pictographic# E0.0 [15] (🟱..🟿) .. 1F80C..1F80F ; Extended_Pictographic# E0.0 [4] (🠌..🠏) .. 1F848..1F84F ; Extended_Pictographic# E0.0 [8] (🡈..🡏) .. 1F85A..1F85F ; Extended_Pictographic# E0.0 [6] (🡚..🡟) .. @@ -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] (🥹) +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] (🧌) +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] (🩵..🩷) .. 1FA78..1FA7A ; Extended_Pictographic# E12.0 [3] (🩸..🩺) drop of blood..stethoscope -1FA7B..1FA7F ; Extended_Pictographic# E0.0 [5] (🩻..🩿) .. +1FA7B..1FA7C ; Extended_Pictographic# E14.0 [2] (🩻..🩼) x-ray..crutch +1FA7D..1FA7F ; Extended_Pictographic# E0.0 [3] (🩽..🩿) .. 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] (🪇..🪏) .. 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] (🪩..🪯) .. +1FAA9..1FAAC ; Extended_Pictographic# E14.0 [4] (🪩..🪬) mirror ball..hamsa +1FAAD..1FAAF ; Extended_Pictographic# E0.0 [3] (🪭..🪯) .. 1FAB0..1FAB6 ; Extended_Pictographic# E13.0 [7] (🪰..🪶) fly..feather -1FAB7..1FABF ; Extended_Pictographic# E0.0 [9] (🪷..🪿) .. +1FAB7..1FABA ; Extended_Pictographic# E14.0 [4] (🪷..🪺) lotus..nest with eggs +1FABB..1FABF ; Extended_Pictographic# E0.0 [5] (🪻..🪿) .. 1FAC0..1FAC2 ; Extended_Pictographic# E13.0 [3] (🫀..🫂) anatomical heart..people hugging -1FAC3..1FACF ; Extended_Pictographic# E0.0 [13] (🫃..🫏) .. +1FAC3..1FAC5 ; Extended_Pictographic# E14.0 [3] (🫃..🫅) pregnant man..person with crown +1FAC6..1FACF ; Extended_Pictographic# E0.0 [10] (🫆..🫏) .. 1FAD0..1FAD6 ; Extended_Pictographic# E13.0 [7] (🫐..🫖) blueberries..teapot -1FAD7..1FAFF ; Extended_Pictographic# E0.0 [41] (🫗..🫿) .. +1FAD7..1FAD9 ; Extended_Pictographic# E14.0 [3] (🫗..🫙) pouring liquid..jar +1FADA..1FADF ; Extended_Pictographic# E0.0 [6] (🫚..🫟) .. +1FAE0..1FAE7 ; Extended_Pictographic# E14.0 [8] (🫠..🫧) melting face..bubbles +1FAE8..1FAEF ; Extended_Pictographic# E0.0 [8] (🫨..🫯) .. +1FAF0..1FAF6 ; Extended_Pictographic# E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands +1FAF7..1FAFF ; Extended_Pictographic# E0.0 [9] (🫷..🫿) .. 1FC00..1FFFD ; Extended_Pictographic# E0.0[1022] (🰀..🿽) .. # Total elements: 3537 diff --git a/util/unicode/main.cpp b/util/unicode/main.cpp index 91015411a0..71ab4c5d55 100644 --- a/util/unicode/main.cpp +++ b/util/unicode/main.cpp @@ -39,8 +39,8 @@ #include #endif -#define DATA_VERSION_S "13.0" -#define DATA_VERSION_STR "QChar::Unicode_13_0" +#define DATA_VERSION_S "14.0" +#define DATA_VERSION_STR "QChar::Unicode_14_0" static QHash age_map; @@ -74,6 +74,7 @@ static void initAgeMap() { QChar::Unicode_12_0, "12.0" }, { QChar::Unicode_12_1, "12.1" }, // UCD Revision 24 { QChar::Unicode_13_0, "13.0" }, // UCD Revision 26 + { QChar::Unicode_14_0, "14.0" }, // UCD Revision 28 { QChar::Unicode_Unassigned, 0 } }; AgeMap *d = ageMap; @@ -797,6 +798,13 @@ static void initScriptMap() { QChar::Script_KhitanSmallScript, "KhitanSmallScript" }, { QChar::Script_Yezidi, "Yezidi" }, + // 14.0 + { QChar::Script_CyproMinoan, "CyproMinoan"}, + { QChar::Script_OldUyghur, "OldUyghur"}, + { QChar::Script_Tangsa, "Tangsa"}, + { QChar::Script_Toto, "Toto"}, + { QChar::Script_Vithkuqi, "Vithkuqi"}, + // unhandled { QChar::Script_Unknown, 0 } }; -- cgit v1.2.3