From 71ed0fde2140d8607fb0f170c59154a8596b2872 Mon Sep 17 00:00:00 2001 From: Rod S Date: Thu, 11 Aug 2022 21:50:15 -0700 Subject: [PATCH 1/2] 15.0 update --- third_party/ucd/BidiMirroring.txt | 26 +- third_party/ucd/Blocks.txt | 37 +- third_party/ucd/DerivedAge.txt | 140 +- third_party/ucd/DerivedCoreProperties.txt | 897 ++++-- third_party/ucd/IndicPositionalCategory.txt | 52 +- third_party/ucd/IndicSyllabicCategory.txt | 73 +- third_party/ucd/NameAliases.txt | 19 +- third_party/ucd/NamesList.txt | 2393 ++++++++++++++++- third_party/ucd/PropertyValueAliases.txt | 44 +- third_party/ucd/ScriptExtensions.txt | 84 +- third_party/ucd/Scripts.txt | 281 +- third_party/ucd/StandardizedVariants.txt | 177 +- third_party/ucd/UnicodeData.txt | 1135 +++++++- third_party/ucd/emoji-data.txt | 85 +- third_party/ucd/emoji-sequences.txt | 34 +- third_party/ucd/emoji-test.txt | 115 +- third_party/ucd/emoji-variation-sequences.txt | 12 +- third_party/ucd/emoji-zwj-sequences.txt | 13 +- 18 files changed, 5041 insertions(+), 576 deletions(-) diff --git a/third_party/ucd/BidiMirroring.txt b/third_party/ucd/BidiMirroring.txt index 34e42ae8..5861d6e7 100644 --- a/third_party/ucd/BidiMirroring.txt +++ b/third_party/ucd/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-15.0.0.txt +# Date: 2022-05-03, 18:47:00 GMT [KW, RP] +# © 2022 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 15.0.0. # # 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/third_party/ucd/Blocks.txt b/third_party/ucd/Blocks.txt index 56877db1..12684594 100644 --- a/third_party/ucd/Blocks.txt +++ b/third_party/ucd/Blocks.txt @@ -1,10 +1,10 @@ -# Blocks-13.0.0.txt -# Date: 2019-07-10, 19:06:00 GMT [KW] -# © 2019 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# Blocks-15.0.0.txt +# Date: 2022-01-28, 20:58:00 GMT [KW] +# © 2022 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/ # # Format: # Start Code..End Code; Block Name @@ -15,7 +15,7 @@ # and underbars are ignored. # For example, "Latin Extended-A" and "latin extended a" are equivalent. # For more information on the comparison of property values, -# see UAX #44: http://www.unicode.org/reports/tr44/ +# see UAX #44: https://www.unicode.org/reports/tr44/ # # All block ranges start with a value where (cp MOD 16) = 0, # and end with a value where (cp MOD 16) = 15. In other words, @@ -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 @@ -238,8 +241,10 @@ FFF0..FFFF; Specials 10D00..10D3F; Hanifi Rohingya 10E60..10E7F; Rumi Numeral Symbols 10E80..10EBF; Yezidi +10EC0..10EFF; Arabic Extended-C 10F00..10F2F; Old Sogdian 10F30..10F6F; Sogdian +10F70..10FAF; Old Uyghur 10FB0..10FDF; Chorasmian 10FE0..10FFF; Elymaic 11000..1107F; Brahmi @@ -259,29 +264,34 @@ 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 +11B00..11B5F; Devanagari Extended-A 11C00..11C6F; Bhaiksuki 11C70..11CBF; Marchen 11D00..11D5F; Masaram Gondi 11D60..11DAF; Gunjala Gondi 11EE0..11EFF; Makasar +11F00..11F5F; Kawi 11FB0..11FBF; Lisu Supplement 11FC0..11FFF; Tamil Supplement 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 +13430..1345F; 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 @@ -290,24 +300,32 @@ 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 +1D2C0..1D2DF; Kaktovik Numerals 1D2E0..1D2FF; Mayan Numerals 1D300..1D35F; Tai Xuan Jing Symbols 1D360..1D37F; Counting Rod Numerals 1D400..1D7FF; Mathematical Alphanumeric Symbols 1D800..1DAAF; Sutton SignWriting +1DF00..1DFFF; Latin Extended-G 1E000..1E02F; Glagolitic Supplement +1E030..1E08F; Cyrillic Extended-D 1E100..1E14F; Nyiakeng Puachue Hmong +1E290..1E2BF; Toto 1E2C0..1E2FF; Wancho +1E4D0..1E4FF; Nag Mundari +1E7E0..1E7FF; Ethiopic Extended-B 1E800..1E8DF; Mende Kikakui 1E900..1E95F; Adlam 1EC70..1ECBF; Indic Siyaq Numbers @@ -336,6 +354,7 @@ FFF0..FFFF; Specials 2CEB0..2EBEF; CJK Unified Ideographs Extension F 2F800..2FA1F; CJK Compatibility Ideographs Supplement 30000..3134F; CJK Unified Ideographs Extension G +31350..323AF; CJK Unified Ideographs Extension H E0000..E007F; Tags E0100..E01EF; Variation Selectors Supplement F0000..FFFFF; Supplementary Private Use Area-A diff --git a/third_party/ucd/DerivedAge.txt b/third_party/ucd/DerivedAge.txt index 0d2bd10f..603ab387 100644 --- a/third_party/ucd/DerivedAge.txt +++ b/third_party/ucd/DerivedAge.txt @@ -1,11 +1,11 @@ -# DerivedAge-13.0.0.txt -# Date: 2019-09-08, 23:30:59 GMT -# © 2019 Unicode®, Inc. +# DerivedAge-15.0.0.txt +# Date: 2022-08-02, 18:14:00 GMT [KW] +# © 2022 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/ # # Unicode Character Database: Derived Property Data # This file shows when various code points were first assigned in Unicode. @@ -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 +1862,132 @@ 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 + +# ================================================ + +# Age=V15_0 + +# Newly assigned in Unicode 15.0.0 (September, 2022) + +0CF3 ; 15.0 # KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT +0ECE ; 15.0 # LAO YAMAKKAN +10EFD..10EFF ; 15.0 # [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA +1123F..11241 ; 15.0 # [3] KHOJKI LETTER QA..KHOJKI VOWEL SIGN VOCALIC R +11B00..11B09 ; 15.0 # [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU +11F00..11F10 ; 15.0 # [17] KAWI SIGN CANDRABINDU..KAWI LETTER O +11F12..11F3A ; 15.0 # [41] KAWI LETTER KA..KAWI VOWEL SIGN VOCALIC R +11F3E..11F59 ; 15.0 # [28] KAWI VOWEL SIGN E..KAWI DIGIT NINE +1342F ; 15.0 # EGYPTIAN HIEROGLYPH V011D +13439..13455 ; 15.0 # [29] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +1B132 ; 15.0 # HIRAGANA LETTER SMALL KO +1B155 ; 15.0 # KATAKANA LETTER SMALL KO +1D2C0..1D2D3 ; 15.0 # [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN +1DF25..1DF2A ; 15.0 # [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; 15.0 # [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; 15.0 # COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E4D0..1E4F9 ; 15.0 # [42] NAG MUNDARI LETTER O..NAG MUNDARI DIGIT NINE +1F6DC ; 15.0 # WIRELESS +1F774..1F776 ; 15.0 # [3] LOT OF FORTUNE..LUNAR ECLIPSE +1F77B..1F77F ; 15.0 # [5] HAUMEA..ORCUS +1F7D9 ; 15.0 # NINE POINTED WHITE STAR +1FA75..1FA77 ; 15.0 # [3] LIGHT BLUE HEART..PINK HEART +1FA87..1FA88 ; 15.0 # [2] MARACAS..FLUTE +1FAAD..1FAAF ; 15.0 # [3] FOLDING HAND FAN..KHANDA +1FABB..1FABD ; 15.0 # [3] HYACINTH..WING +1FABF ; 15.0 # GOOSE +1FACE..1FACF ; 15.0 # [2] MOOSE..DONKEY +1FADA..1FADB ; 15.0 # [2] GINGER ROOT..PEA POD +1FAE8 ; 15.0 # SHAKING FACE +1FAF7..1FAF8 ; 15.0 # [2] LEFTWARDS PUSHING HAND..RIGHTWARDS PUSHING HAND +2B739 ; 15.0 # CJK UNIFIED IDEOGRAPH-2B739 +31350..323AF ; 15.0 # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF + +# Total code points: 4489 + # EOF diff --git a/third_party/ucd/DerivedCoreProperties.txt b/third_party/ucd/DerivedCoreProperties.txt index bc97e217..8b482b5c 100644 --- a/third_party/ucd/DerivedCoreProperties.txt +++ b/third_party/ucd/DerivedCoreProperties.txt @@ -1,11 +1,11 @@ -# DerivedCoreProperties-13.0.0.txt -# Date: 2020-01-22, 00:07:19 GMT -# © 2020 Unicode®, Inc. +# DerivedCoreProperties-15.0.0.txt +# Date: 2022-08-05, 22:17:05 GMT +# © 2022 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/ # ================================================ @@ -341,8 +341,10 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0829..082C ; Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN 0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; Alphabetic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; Alphabetic # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Alphabetic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Alphabetic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Alphabetic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; Alphabetic # Lm ARABIC SMALL FARSI YEH 08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA 08E3..08E9 ; Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN 08F0..0902 ; Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA @@ -460,6 +462,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0BD7 ; Alphabetic # Mc TAMIL AU LENGTH MARK 0C00 ; Alphabetic # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Alphabetic # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C04 ; Alphabetic # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE 0C05..0C0C ; Alphabetic # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L 0C0E..0C10 ; Alphabetic # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; Alphabetic # Lo [23] TELUGU LETTER O..TELUGU LETTER NA @@ -471,6 +474,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0C4A..0C4C ; Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C55..0C56 ; Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Alphabetic # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Alphabetic # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Alphabetic # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C80 ; Alphabetic # Lo KANNADA SIGN SPACING CANDRABINDU @@ -490,10 +494,11 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CCA..0CCB ; Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; Alphabetic # Lo KANNADA LETTER FA +0CDD..0CDE ; Alphabetic # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0CF3 ; Alphabetic # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D04..0D0C ; Alphabetic # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -549,7 +554,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0F49..0F6C ; Alphabetic # Lo [36] TIBETAN LETTER NYA..TIBETAN LETTER RRA 0F71..0F7E ; Alphabetic # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO 0F7F ; Alphabetic # Mc TIBETAN SIGN RNAM BCAD -0F80..0F81 ; Alphabetic # Mn [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II +0F80..0F83 ; Alphabetic # Mn [4] TIBETAN VOWEL SIGN REVERSED I..TIBETAN SIGN SNA LDAN 0F88..0F8C ; Alphabetic # Lo [5] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN INVERTED MCHU CAN 0F8D..0F97 ; Alphabetic # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA 0F99..0FBC ; Alphabetic # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA @@ -614,10 +619,9 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 16A0..16EA ; Alphabetic # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; Alphabetic # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Alphabetic # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Alphabetic # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; Alphabetic # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1713 ; Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U -1720..1731 ; Alphabetic # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +171F..1731 ; Alphabetic # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1732..1733 ; Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1740..1751 ; Alphabetic # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -670,6 +674,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1A73..1A74 ; Alphabetic # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG 1AA7 ; Alphabetic # Lm TAI THAM SIGN MAI YAMOK 1ABF..1AC0 ; Alphabetic # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ACC..1ACE ; Alphabetic # Mn [3] COMBINING LATIN SMALL LETTER INSULAR G..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Alphabetic # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Alphabetic # Mc BALINESE SIGN BISAH 1B05..1B33 ; Alphabetic # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -680,7 +685,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1B3D..1B41 ; Alphabetic # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; Alphabetic # Mn BALINESE VOWEL SIGN PEPET 1B43 ; Alphabetic # Mc BALINESE VOWEL SIGN PEPET TEDUNG -1B45..1B4B ; Alphabetic # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Alphabetic # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B80..1B81 ; Alphabetic # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; Alphabetic # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; Alphabetic # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -760,9 +765,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 2183..2184 ; Alphabetic # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; Alphabetic # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND 24B6..24E9 ; Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Alphabetic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Alphabetic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Alphabetic # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Alphabetic # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Alphabetic # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Alphabetic # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; Alphabetic # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -802,8 +805,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 31A0..31BF ; Alphabetic # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; Alphabetic # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Alphabetic # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Alphabetic # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; Alphabetic # Lm YI SYLLABLE WU A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Alphabetic # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -828,8 +830,11 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; Alphabetic # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Alphabetic # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Alphabetic # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Alphabetic # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Alphabetic # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -985,9 +990,20 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 104D8..104FB ; Alphabetic # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; Alphabetic # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Alphabetic # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; Alphabetic # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Alphabetic # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Alphabetic # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Alphabetic # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Alphabetic # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Alphabetic # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Alphabetic # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Alphabetic # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; Alphabetic # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Alphabetic # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Alphabetic # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; Alphabetic # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Alphabetic # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Alphabetic # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; Alphabetic # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Alphabetic # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Alphabetic # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1028,6 +1044,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; Alphabetic # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; Alphabetic # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; Alphabetic # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; Alphabetic # Mc BRAHMI SIGN CANDRABINDU @@ -1035,11 +1052,16 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11002 ; Alphabetic # Mc BRAHMI SIGN VISARGA 11003..11037 ; Alphabetic # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11045 ; Alphabetic # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU +11071..11072 ; Alphabetic # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; Alphabetic # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; Alphabetic # Lo BRAHMI LETTER OLD TAMIL LLA +11080..11081 ; Alphabetic # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA 11082 ; Alphabetic # Mc KAITHI SIGN VISARGA 11083..110AF ; Alphabetic # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110C2 ; Alphabetic # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; Alphabetic # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11100..11102 ; Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11103..11126 ; Alphabetic # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -1070,6 +1092,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11234 ; Alphabetic # Mn KHOJKI SIGN ANUSVARA 11237 ; Alphabetic # Mn KHOJKI SIGN SHADDA 1123E ; Alphabetic # Mn KHOJKI SIGN SUKUN +1123F..11240 ; Alphabetic # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I +11241 ; Alphabetic # Mn KHOJKI VOWEL SIGN VOCALIC R 11280..11286 ; Alphabetic # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; Alphabetic # Lo MULTANI LETTER GHA 1128A..1128D ; Alphabetic # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1144,6 +1168,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11722..11725 ; Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Alphabetic # Mc AHOM VOWEL SIGN E 11727..1172A ; Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11740..11746 ; Alphabetic # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Alphabetic # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; Alphabetic # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; Alphabetic # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -1185,7 +1210,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA 11A9D ; Alphabetic # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; Alphabetic # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA @@ -1223,14 +1248,26 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11EE0..11EF2 ; Alphabetic # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; Alphabetic # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F02 ; Alphabetic # Lo KAWI SIGN REPHA +11F03 ; Alphabetic # Mc KAWI SIGN VISARGA +11F04..11F10 ; Alphabetic # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; Alphabetic # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11F34..11F35 ; Alphabetic # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; Alphabetic # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; Alphabetic # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; Alphabetic # Mn KAWI VOWEL SIGN EU 11FB0 ; Alphabetic # Lo LISU LETTER YHA 12000..12399 ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; Alphabetic # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; Alphabetic # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; Alphabetic # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; Alphabetic # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; Alphabetic # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Alphabetic # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Alphabetic # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; Alphabetic # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; Alphabetic # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; Alphabetic # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; Alphabetic # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -1249,8 +1286,13 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 17000..187F7 ; Alphabetic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Alphabetic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Alphabetic # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; Alphabetic # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; Alphabetic # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; Alphabetic # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; Alphabetic # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Alphabetic # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -1288,15 +1330,28 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1D78A..1D7A8 ; Alphabetic # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Alphabetic # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Alphabetic # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Alphabetic # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; Alphabetic # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; Alphabetic # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Alphabetic # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E000..1E006 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; Alphabetic # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; Alphabetic # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E100..1E12C ; Alphabetic # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Alphabetic # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; Alphabetic # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; Alphabetic # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Alphabetic # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; Alphabetic # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; Alphabetic # Lm NAG MUNDARI SIGN OJOD +1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Alphabetic # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Alphabetic # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; Alphabetic # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E947 ; Alphabetic # Mn ADLAM HAMZA @@ -1337,15 +1392,16 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1F130..1F149 ; Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -20000..2A6DD ; Alphabetic # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Alphabetic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Alphabetic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B739 ; Alphabetic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132875 +# Total code points: 137765 # ================================================ @@ -1630,6 +1686,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 052F ; Lowercase # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0560..0588 ; Lowercase # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 10D0..10FA ; Lowercase # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FC ; Lowercase # Lm MODIFIER LETTER GEORGIAN NAR 10FD..10FF ; Lowercase # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13F8..13FD ; Lowercase # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Lowercase # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK @@ -1798,7 +1855,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 2170..217F ; Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Lowercase # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Lowercase # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Lowercase # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Lowercase # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Lowercase # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Lowercase # L& LATIN SMALL LETTER H WITH DESCENDER @@ -1970,21 +2027,37 @@ A7B9 ; Lowercase # L& LATIN SMALL LETTER U WITH STROKE A7BB ; Lowercase # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Lowercase # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Lowercase # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Lowercase # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Lowercase # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lowercase # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lowercase # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Lowercase # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Lowercase # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Lowercase # L& LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Lowercase # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F6 ; Lowercase # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Lowercase # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG AB5C..AB5F ; Lowercase # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB60..AB68 ; Lowercase # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE +AB69 ; Lowercase # Lm MODIFIER LETTER SMALL TURNED W AB70..ABBF ; Lowercase # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Lowercase # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Lowercase # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lowercase # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Lowercase # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Lowercase # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Lowercase # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Lowercase # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Lowercase # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10CC0..10CF2 ; Lowercase # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lowercase # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y @@ -2016,9 +2089,13 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7AA..1D7C2 ; Lowercase # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Lowercase # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Lowercase # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Lowercase # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Lowercase # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2344 +# Total code points: 2544 # ================================================ @@ -2458,7 +2535,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 2160..216F ; Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Uppercase # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Uppercase # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Uppercase # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Uppercase # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Uppercase # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Uppercase # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -2623,13 +2700,21 @@ A7B8 ; Uppercase # L& LATIN CAPITAL LETTER U WITH STROKE A7BA ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Uppercase # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Uppercase # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Uppercase # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Uppercase # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Uppercase # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Uppercase # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Uppercase # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Uppercase # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Uppercase # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Uppercase # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Uppercase # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Uppercase # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -2669,7 +2754,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1911 +# Total code points: 1951 # ================================================ @@ -2710,6 +2795,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 10C7 ; Cased # L& GEORGIAN CAPITAL LETTER YN 10CD ; Cased # L& GEORGIAN CAPITAL LETTER AEN 10D0..10FA ; Cased # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FC ; Cased # Lm MODIFIER LETTER GEORGIAN NAR 10FD..10FF ; Cased # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13A0..13F5 ; Cased # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV 13F8..13FD ; Cased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV @@ -2761,9 +2847,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 2160..217F ; Cased # Nl [32] ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2183..2184 ; Cased # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 24B6..24E9 ; Cased # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Cased # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Cased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Cased # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Cased # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Cased # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Cased # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; Cased # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -2778,14 +2862,18 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7BF ; Cased # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Cased # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Cased # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Cased # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Cased # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG AB5C..AB5F ; Cased # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB60..AB68 ; Cased # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE +AB69 ; Cased # Lm MODIFIER LETTER SMALL TURNED W AB70..ABBF ; Cased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Cased # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Cased # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH @@ -2794,6 +2882,18 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10400..1044F ; Cased # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 104B0..104D3 ; Cased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 104D8..104FB ; Cased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10570..1057A ; Cased # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Cased # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Cased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Cased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Cased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Cased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Cased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Cased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Cased # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Cased # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Cased # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Cased # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10C80..10CB2 ; Cased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Cased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Cased # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -2828,12 +2928,16 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D78A..1D7A8 ; Cased # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Cased # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Cased # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Cased # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Cased # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Cased # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; Cased # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E900..1E943 ; Cased # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1F130..1F149 ; Cased # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4286 +# Total code points: 4526 # ================================================ @@ -2908,7 +3012,11 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0828 ; Case_Ignorable # Lm SAMARITAN MODIFIER LETTER I 0829..082D ; Case_Ignorable # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Case_Ignorable # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Case_Ignorable # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0888 ; Case_Ignorable # Sk ARABIC RAISED ROUND DOT +0890..0891 ; Case_Ignorable # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; Case_Ignorable # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08C9 ; Case_Ignorable # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; Case_Ignorable # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; Case_Ignorable # Cf ARABIC DISPUTED END OF AYAH 08E3..0902 ; Case_Ignorable # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Case_Ignorable # Mn DEVANAGARI VOWEL SIGN OE @@ -2951,6 +3059,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0BCD ; Case_Ignorable # Mn TAMIL SIGN VIRAMA 0C00 ; Case_Ignorable # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Case_Ignorable # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Case_Ignorable # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Case_Ignorable # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Case_Ignorable # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Case_Ignorable # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -2978,7 +3087,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0EB1 ; Case_Ignorable # Mn LAO VOWEL SIGN MAI KAN 0EB4..0EBC ; Case_Ignorable # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO 0EC6 ; Case_Ignorable # Lm LAO KO LA -0EC8..0ECD ; Case_Ignorable # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; Case_Ignorable # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0F18..0F19 ; Case_Ignorable # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS 0F35 ; Case_Ignorable # Mn TIBETAN MARK NGAS BZUNG NYI ZLA 0F37 ; Case_Ignorable # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS @@ -3003,7 +3112,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10FC ; Case_Ignorable # Lm MODIFIER LETTER GEORGIAN NAR 135D..135F ; Case_Ignorable # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Case_Ignorable # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Case_Ignorable # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Case_Ignorable # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Case_Ignorable # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Case_Ignorable # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Case_Ignorable # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -3014,6 +3123,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 17DD ; Case_Ignorable # Mn KHMER SIGN ATTHACAN 180B..180D ; Case_Ignorable # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Case_Ignorable # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Case_Ignorable # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1843 ; Case_Ignorable # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1885..1886 ; Case_Ignorable # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Case_Ignorable # Mn MONGOLIAN LETTER ALI GALI DAGALGA @@ -3033,7 +3143,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Case_Ignorable # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Case_Ignorable # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3060,8 +3170,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D2C..1D6A ; Case_Ignorable # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D78 ; Case_Ignorable # Lm MODIFIER LETTER CYRILLIC EN 1D9B..1DBF ; Case_Ignorable # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; Case_Ignorable # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Case_Ignorable # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Case_Ignorable # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Case_Ignorable # Sk GREEK KORONIS 1FBF..1FC1 ; Case_Ignorable # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI 1FCD..1FCF ; Case_Ignorable # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -3114,6 +3223,7 @@ A720..A721 ; Case_Ignorable # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE.. A770 ; Case_Ignorable # Lm MODIFIER LETTER US A788 ; Case_Ignorable # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Case_Ignorable # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN +A7F2..A7F4 ; Case_Ignorable # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Case_Ignorable # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A802 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN HASANTA @@ -3156,7 +3266,7 @@ ABE5 ; Case_Ignorable # Mn MEETEI MAYEK VOWEL SIGN ANAP ABE8 ; Case_Ignorable # Mn MEETEI MAYEK VOWEL SIGN UNAP ABED ; Case_Ignorable # Mn MEETEI MAYEK APUN IYEK FB1E ; Case_Ignorable # Mn HEBREW POINT JUDEO-SPANISH VARIKA -FBB2..FBC1 ; Case_Ignorable # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Case_Ignorable # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FE00..FE0F ; Case_Ignorable # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE13 ; Case_Ignorable # Po PRESENTATION FORM FOR VERTICAL COLON FE20..FE2F ; Case_Ignorable # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF @@ -3175,6 +3285,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 101FD ; Case_Ignorable # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE 102E0 ; Case_Ignorable # Mn COPTIC EPACT THOUSANDS MARK 10376..1037A ; Case_Ignorable # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10780..10785 ; Case_Ignorable # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Case_Ignorable # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Case_Ignorable # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10A01..10A03 ; Case_Ignorable # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R 10A05..10A06 ; Case_Ignorable # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0F ; Case_Ignorable # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA @@ -3183,13 +3296,18 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10AE5..10AE6 ; Case_Ignorable # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Case_Ignorable # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFD..10EFF ; Case_Ignorable # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Case_Ignorable # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Case_Ignorable # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Case_Ignorable # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Case_Ignorable # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Case_Ignorable # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Case_Ignorable # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA 110BD ; Case_Ignorable # Cf KAITHI NUMBER SIGN +110C2 ; Case_Ignorable # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; Case_Ignorable # Cf KAITHI NUMBER SIGN ABOVE 11100..11102 ; Case_Ignorable # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Case_Ignorable # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU @@ -3203,6 +3321,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11234 ; Case_Ignorable # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Case_Ignorable # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; Case_Ignorable # Mn KHOJKI SIGN SUKUN +11241 ; Case_Ignorable # Mn KHOJKI VOWEL SIGN VOCALIC R 112DF ; Case_Ignorable # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Case_Ignorable # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Case_Ignorable # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -3264,7 +3383,13 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11D95 ; Case_Ignorable # Mn GUNJALA GONDI SIGN ANUSVARA 11D97 ; Case_Ignorable # Mn GUNJALA GONDI VIRAMA 11EF3..11EF4 ; Case_Ignorable # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U -13430..13438 ; Case_Ignorable # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +11F00..11F01 ; Case_Ignorable # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; Case_Ignorable # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; Case_Ignorable # Mn KAWI VOWEL SIGN EU +11F42 ; Case_Ignorable # Mn KAWI CONJOINER +13430..1343F ; Case_Ignorable # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; Case_Ignorable # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; Case_Ignorable # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -3274,8 +3399,13 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Case_Ignorable # Lm OLD CHINESE ITERATION MARK 16FE4 ; Case_Ignorable # Mn KHITAN SMALL SCRIPT FILLER +1AFF0..1AFF3 ; Case_Ignorable # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Case_Ignorable # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Case_Ignorable # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1BC9D..1BC9E ; Case_Ignorable # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BCA0..1BCA3 ; Case_Ignorable # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; Case_Ignorable # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Case_Ignorable # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Case_Ignorable # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D173..1D17A ; Case_Ignorable # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D17B..1D182 ; Case_Ignorable # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE @@ -3293,9 +3423,14 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E01B..1E021 ; Case_Ignorable # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Case_Ignorable # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Case_Ignorable # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; Case_Ignorable # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; Case_Ignorable # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E130..1E136 ; Case_Ignorable # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; Case_Ignorable # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E2AE ; Case_Ignorable # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Case_Ignorable # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EB ; Case_Ignorable # Lm NAG MUNDARI SIGN OJOD +1E4EC..1E4EF ; Case_Ignorable # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; Case_Ignorable # Lm ADLAM NASALIZATION MARK @@ -3304,7 +3439,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2413 +# Total code points: 2707 # ================================================ @@ -3738,7 +3873,7 @@ E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELEC 2160..216F ; Changes_When_Lowercased # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Changes_When_Lowercased # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Changes_When_Lowercased # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Changes_When_Lowercased # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_Lowercased # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_Lowercased # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -3903,19 +4038,27 @@ A7B8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER U WITH S A7BA ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Lowercased # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_Lowercased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_Lowercased # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Lowercased # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Lowercased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Lowercased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Lowercased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Lowercased # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1393 +# Total code points: 1433 # ================================================ @@ -4363,7 +4506,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 2170..217F ; Changes_When_Uppercased # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Changes_When_Uppercased # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Changes_When_Uppercased # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Changes_When_Uppercased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Changes_When_Uppercased # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Changes_When_Uppercased # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Changes_When_Uppercased # L& LATIN SMALL LETTER H WITH DESCENDER @@ -4528,9 +4671,13 @@ A7B9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER U WITH STR A7BB ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Changes_When_Uppercased # L& LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Uppercased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -4539,12 +4686,16 @@ FB13..FB17 ; Changes_When_Uppercased # L& [5] ARMENIAN SMALL LIGATURE MEN N FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Uppercased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Changes_When_Uppercased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Changes_When_Uppercased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Uppercased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Uppercased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Uppercased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Uppercased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Uppercased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1485 +# Total code points: 1525 # ================================================ @@ -4991,7 +5142,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 2170..217F ; Changes_When_Titlecased # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Changes_When_Titlecased # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Changes_When_Titlecased # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Changes_When_Titlecased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Changes_When_Titlecased # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Changes_When_Titlecased # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Changes_When_Titlecased # L& LATIN SMALL LETTER H WITH DESCENDER @@ -5156,9 +5307,13 @@ A7B9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER U WITH STR A7BB ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Changes_When_Titlecased # L& LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Titlecased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5167,12 +5322,16 @@ FB13..FB17 ; Changes_When_Titlecased # L& [5] ARMENIAN SMALL LIGATURE MEN N FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Titlecased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Changes_When_Titlecased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Changes_When_Titlecased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Titlecased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Titlecased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Titlecased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Titlecased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Titlecased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1412 +# Total code points: 1452 # ================================================ @@ -5616,7 +5775,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 2160..216F ; Changes_When_Casefolded # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Changes_When_Casefolded # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Changes_When_Casefolded # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Changes_When_Casefolded # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_Casefolded # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_Casefolded # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -5781,9 +5940,13 @@ A7B8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER U WITH S A7BA ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H AB70..ABBF ; Changes_When_Casefolded # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Changes_When_Casefolded # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST @@ -5791,12 +5954,16 @@ FB13..FB17 ; Changes_When_Casefolded # L& [5] ARMENIAN SMALL LIGATURE MEN N FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_Casefolded # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Casefolded # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Casefolded # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Casefolded # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1466 +# Total code points: 1506 # ================================================ @@ -5893,9 +6060,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 2160..217F ; Changes_When_Casemapped # Nl [32] ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2183..2184 ; Changes_When_Casemapped # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 24B6..24E9 ; Changes_When_Casemapped # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Changes_When_Casemapped # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Changes_When_Casemapped # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C70 ; Changes_When_Casemapped # L& [17] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN CAPITAL LETTER TURNED ALPHA +2C00..2C70 ; Changes_When_Casemapped # L& [113] GLAGOLITIC CAPITAL LETTER AZU..LATIN CAPITAL LETTER TURNED ALPHA 2C72..2C73 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER W WITH HOOK..LATIN SMALL LETTER W WITH HOOK 2C75..2C76 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER HALF H..LATIN SMALL LETTER HALF H 2C7E..2CE3 ; Changes_When_Casemapped # L& [102] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SMALL LETTER OLD NUBIAN WAU @@ -5912,8 +6077,9 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7BF ; Changes_When_Casemapped # L& [16] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Changes_When_Casemapped # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7B0..A7CA ; Changes_When_Casemapped # L& [27] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D6..A7D9 ; Changes_When_Casemapped # L& [4] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN SMALL LETTER SIGMOID S A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5924,13 +6090,21 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 10400..1044F ; Changes_When_Casemapped # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 104B0..104D3 ; Changes_When_Casemapped # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 104D8..104FB ; Changes_When_Casemapped # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10570..1057A ; Changes_When_Casemapped # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Casemapped # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Casemapped # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Casemapped # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Changes_When_Casemapped # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Casemapped # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Casemapped # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Casemapped # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10C80..10CB2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Changes_When_Casemapped # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2847 +# Total code points: 2927 # ================================================ @@ -6003,8 +6177,10 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0828 ; ID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; ID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; ID_Start # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; ID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; ID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ID_Start # Lo DEVANAGARI OM @@ -6070,6 +6246,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0C2A..0C39 ; ID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ID_Start # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -6078,7 +6255,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0CAA..0CB3 ; ID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ID_Start # Lo KANNADA SIGN AVAGRAHA -0CDE ; ID_Start # Lo KANNADA LETTER FA +0CDD..0CDE ; ID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -6153,9 +6330,8 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 16A0..16EA ; ID_Start # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ID_Start # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ID_Start # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ID_Start # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ID_Start # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; ID_Start # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; ID_Start # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; ID_Start # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; ID_Start # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; ID_Start # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; ID_Start # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -6179,7 +6355,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 1A20..1A54 ; ID_Start # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; ID_Start # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; ID_Start # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; ID_Start # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ID_Start # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; ID_Start # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; ID_Start # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; ID_Start # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -6242,9 +6418,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 2160..2182 ; ID_Start # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; ID_Start # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ID_Start # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; ID_Start # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ID_Start # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ID_Start # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ID_Start # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ID_Start # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ID_Start # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ID_Start # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -6283,8 +6457,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 31A0..31BF ; ID_Start # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; ID_Start # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID_Start # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID_Start # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; ID_Start # Lm YI SYLLABLE WU A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; ID_Start # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -6307,8 +6480,11 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ID_Start # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ID_Start # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6418,9 +6594,20 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 104D8..104FB ; ID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ID_Start # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ID_Start # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ID_Start # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ID_Start # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ID_Start # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -6456,9 +6643,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; ID_Start # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; ID_Start # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ID_Start # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; ID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; ID_Start # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; ID_Start # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; ID_Start # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; ID_Start # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; ID_Start # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -6472,6 +6662,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 111DC ; ID_Start # Lo SHARADA HEADSTROKE 11200..11211 ; ID_Start # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA 11213..1122B ; ID_Start # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1123F..11240 ; ID_Start # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I 11280..11286 ; ID_Start # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; ID_Start # Lo MULTANI LETTER GHA 1128A..1128D ; ID_Start # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -6500,6 +6691,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; ID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; ID_Start # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; ID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; ID_Start # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; ID_Start # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; ID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF..11906 ; ID_Start # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E @@ -6519,7 +6711,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; ID_Start # Lo SOYOMBO LETTER A 11A5C..11A89 ; ID_Start # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; ID_Start # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ID_Start # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; ID_Start # Lo BHAIKSUKI SIGN AVAGRAHA @@ -6533,14 +6725,20 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11D6A..11D89 ; ID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; ID_Start # Lo GUNJALA GONDI OM 11EE0..11EF2 ; ID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11F02 ; ID_Start # Lo KAWI SIGN REPHA +11F04..11F10 ; ID_Start # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; ID_Start # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 11FB0 ; ID_Start # Lo LISU LETTER YHA 12000..12399 ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; ID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; ID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; ID_Start # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; ID_Start # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; ID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; ID_Start # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; ID_Start # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; ID_Start # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; ID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -6555,8 +6753,13 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17000..187F7 ; ID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; ID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; ID_Start # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; ID_Start # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; ID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; ID_Start # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; ID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -6593,10 +6796,22 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78A..1D7A8 ; ID_Start # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; ID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; ID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; ID_Start # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; ID_Start # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; ID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; ID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; ID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; ID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; ID_Start # Lm NAG MUNDARI SIGN OJOD +1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ID_Start # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; ID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; ID_Start # Lm ADLAM NASALIZATION MARK @@ -6633,15 +6848,16 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1EEA1..1EEA3 ; ID_Start # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; ID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; ID_Start # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; ID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; ID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B739 ; ID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 131482 +# Total code points: 136345 # ================================================ @@ -6746,9 +6962,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0840..0858 ; ID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; ID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; ID_Continue # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; ID_Continue # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; ID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0898..089F ; ID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; ID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ID_Continue # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; ID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; ID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; ID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; ID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -6886,6 +7105,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C0E..0C10 ; ID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; ID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; ID_Continue # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; ID_Continue # Mn TELUGU SIGN NUKTA 0C3D ; ID_Continue # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; ID_Continue # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; ID_Continue # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -6893,6 +7113,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C4A..0C4D ; ID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; ID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; ID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ID_Continue # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; ID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; ID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -6914,11 +7135,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CCA..0CCB ; ID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; ID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; ID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; ID_Continue # Lo KANNADA LETTER FA +0CDD..0CDE ; ID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; ID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0CF3 ; ID_Continue # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; ID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; ID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D04..0D0C ; ID_Continue # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -6972,7 +7194,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0EBD ; ID_Continue # Lo LAO SEMIVOWEL SIGN NYO 0EC0..0EC4 ; ID_Continue # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI 0EC6 ; ID_Continue # Lm LAO KO LA -0EC8..0ECD ; ID_Continue # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; ID_Continue # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0ED0..0ED9 ; ID_Continue # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE 0EDC..0EDF ; ID_Continue # Lo [4] LAO HO NO..LAO LETTER KHMU NYO 0F00 ; ID_Continue # Lo TIBETAN SYLLABLE OM @@ -7058,11 +7280,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16A0..16EA ; ID_Continue # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ID_Continue # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ID_Continue # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ID_Continue # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ID_Continue # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; ID_Continue # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; ID_Continue # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; ID_Continue # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; ID_Continue # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; ID_Continue # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; ID_Continue # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; ID_Continue # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; ID_Continue # Mc HANUNOO SIGN PAMUDPOD 1740..1751 ; ID_Continue # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; ID_Continue # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1760..176C ; ID_Continue # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -7081,6 +7304,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17DD ; ID_Continue # Mn KHMER SIGN ATTHACAN 17E0..17E9 ; ID_Continue # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 180B..180D ; ID_Continue # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; ID_Continue # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; ID_Continue # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; ID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -7128,7 +7352,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; ID_Continue # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; ID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -7140,7 +7364,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1B3D..1B41 ; ID_Continue # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; ID_Continue # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; ID_Continue # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; ID_Continue # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ID_Continue # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; ID_Continue # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B6B..1B73 ; ID_Continue # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1B81 ; ID_Continue # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR @@ -7194,8 +7418,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78 ; ID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; ID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; ID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; ID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; ID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; ID_Continue # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; ID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; ID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; ID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -7243,9 +7466,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2160..2182 ; ID_Continue # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; ID_Continue # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ID_Continue # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; ID_Continue # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ID_Continue # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ID_Continue # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ID_Continue # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ID_Continue # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ID_Continue # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ID_Continue # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -7290,8 +7511,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 31A0..31BF ; ID_Continue # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; ID_Continue # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID_Continue # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID_Continue # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; ID_Continue # Lm YI SYLLABLE WU A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; ID_Continue # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -7319,8 +7539,11 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ID_Continue # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ID_Continue # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -7499,9 +7722,20 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 104D8..104FB ; ID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ID_Continue # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ID_Continue # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ID_Continue # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ID_Continue # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ID_Continue # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -7543,10 +7777,13 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10E80..10EA9 ; ID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; ID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EFD..10EFF ; ID_Continue # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F46..10F50 ; ID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F70..10F81 ; ID_Continue # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; ID_Continue # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; ID_Continue # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ID_Continue # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; ID_Continue # Mc BRAHMI SIGN CANDRABINDU @@ -7555,6 +7792,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11003..11037 ; ID_Continue # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11046 ; ID_Continue # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11066..1106F ; ID_Continue # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; ID_Continue # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; ID_Continue # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; ID_Continue # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; ID_Continue # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; ID_Continue # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; ID_Continue # Mc KAITHI SIGN VISARGA 11083..110AF ; ID_Continue # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -7562,6 +7803,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 110B3..110B6 ; ID_Continue # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; ID_Continue # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; ID_Continue # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; ID_Continue # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; ID_Continue # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; ID_Continue # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11100..11102 ; ID_Continue # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -7598,6 +7840,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11235 ; ID_Continue # Mc KHOJKI SIGN VIRAMA 11236..11237 ; ID_Continue # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; ID_Continue # Mn KHOJKI SIGN SUKUN +1123F..11240 ; ID_Continue # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I +11241 ; ID_Continue # Mn KHOJKI VOWEL SIGN VOCALIC R 11280..11286 ; ID_Continue # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; ID_Continue # Lo MULTANI LETTER GHA 1128A..1128D ; ID_Continue # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -7687,6 +7931,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11726 ; ID_Continue # Mc AHOM VOWEL SIGN E 11727..1172B ; ID_Continue # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 11730..11739 ; ID_Continue # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; ID_Continue # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; ID_Continue # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; ID_Continue # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; ID_Continue # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -7737,7 +7982,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; ID_Continue # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; ID_Continue # Mc BHAIKSUKI VOWEL SIGN AA @@ -7779,15 +8024,33 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11EE0..11EF2 ; ID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; ID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; ID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; ID_Continue # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F02 ; ID_Continue # Lo KAWI SIGN REPHA +11F03 ; ID_Continue # Mc KAWI SIGN VISARGA +11F04..11F10 ; ID_Continue # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; ID_Continue # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11F34..11F35 ; ID_Continue # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; ID_Continue # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; ID_Continue # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; ID_Continue # Mn KAWI VOWEL SIGN EU +11F41 ; ID_Continue # Mc KAWI SIGN KILLER +11F42 ; ID_Continue # Mn KAWI CONJOINER +11F50..11F59 ; ID_Continue # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 11FB0 ; ID_Continue # Lo LISU LETTER YHA 12000..12399 ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; ID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; ID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; ID_Continue # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13440 ; ID_Continue # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13441..13446 ; ID_Continue # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN +13447..13455 ; ID_Continue # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 14400..14646 ; ID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; ID_Continue # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A70..16ABE ; ID_Continue # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; ID_Continue # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; ID_Continue # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; ID_Continue # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B2F ; ID_Continue # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -7810,8 +8073,13 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 17000..187F7 ; ID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; ID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; ID_Continue # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; ID_Continue # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; ID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; ID_Continue # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; ID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -7819,6 +8087,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1BC80..1BC88 ; ID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; ID_Continue # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9D..1BC9E ; ID_Continue # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; ID_Continue # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; ID_Continue # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; ID_Continue # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; ID_Continue # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; ID_Continue # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -7863,19 +8133,35 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DA84 ; ID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; ID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; ID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; ID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; ID_Continue # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E000..1E006 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; ID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; ID_Continue # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; ID_Continue # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; ID_Continue # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; ID_Continue # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E100..1E12C ; ID_Continue # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E130..1E136 ; ID_Continue # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; ID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; ID_Continue # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; ID_Continue # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ID_Continue # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; ID_Continue # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; ID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; ID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; ID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E4D0..1E4EA ; ID_Continue # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; ID_Continue # Lm NAG MUNDARI SIGN OJOD +1E4EC..1E4EF ; ID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E4F0..1E4F9 ; ID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ID_Continue # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; ID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E900..1E943 ; ID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -7916,16 +8202,17 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1EEA5..1EEA9 ; ID_Continue # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; ID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; ID_Continue # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; ID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; ID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B739 ; ID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 134434 +# Total code points: 139482 # ================================================ @@ -7995,8 +8282,10 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0828 ; XID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; XID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; XID_Start # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; XID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; XID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; XID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; XID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; XID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; XID_Start # Lo DEVANAGARI OM @@ -8062,6 +8351,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0C2A..0C39 ; XID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; XID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; XID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; XID_Start # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; XID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; XID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -8070,7 +8360,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0CAA..0CB3 ; XID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; XID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; XID_Start # Lo KANNADA SIGN AVAGRAHA -0CDE ; XID_Start # Lo KANNADA LETTER FA +0CDD..0CDE ; XID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; XID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; XID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; XID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -8145,9 +8435,8 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 16A0..16EA ; XID_Start # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; XID_Start # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; XID_Start # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; XID_Start # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; XID_Start # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; XID_Start # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; XID_Start # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; XID_Start # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; XID_Start # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; XID_Start # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; XID_Start # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -8171,7 +8460,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 1A20..1A54 ; XID_Start # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; XID_Start # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; XID_Start # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; XID_Start # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; XID_Start # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; XID_Start # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; XID_Start # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; XID_Start # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -8234,9 +8523,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 2160..2182 ; XID_Start # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; XID_Start # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; XID_Start # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; XID_Start # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; XID_Start # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; XID_Start # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; XID_Start # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; XID_Start # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; XID_Start # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; XID_Start # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -8274,8 +8561,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 31A0..31BF ; XID_Start # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; XID_Start # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; XID_Start # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; XID_Start # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; XID_Start # Lm YI SYLLABLE WU A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; XID_Start # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -8298,8 +8584,11 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; XID_Start # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; XID_Start # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; XID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; XID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; XID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -8414,9 +8703,20 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 104D8..104FB ; XID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; XID_Start # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; XID_Start # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; XID_Start # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; XID_Start # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; XID_Start # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; XID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; XID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; XID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; XID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; XID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; XID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; XID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; XID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -8452,9 +8752,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; XID_Start # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; XID_Start # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; XID_Start # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; XID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; XID_Start # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; XID_Start # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; XID_Start # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; XID_Start # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; XID_Start # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -8468,6 +8771,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 111DC ; XID_Start # Lo SHARADA HEADSTROKE 11200..11211 ; XID_Start # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA 11213..1122B ; XID_Start # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1123F..11240 ; XID_Start # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I 11280..11286 ; XID_Start # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; XID_Start # Lo MULTANI LETTER GHA 1128A..1128D ; XID_Start # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -8496,6 +8800,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11680..116AA ; XID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; XID_Start # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; XID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; XID_Start # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; XID_Start # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; XID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF..11906 ; XID_Start # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E @@ -8515,7 +8820,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11A50 ; XID_Start # Lo SOYOMBO LETTER A 11A5C..11A89 ; XID_Start # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; XID_Start # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; XID_Start # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; XID_Start # Lo BHAIKSUKI SIGN AVAGRAHA @@ -8529,14 +8834,20 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11D6A..11D89 ; XID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; XID_Start # Lo GUNJALA GONDI OM 11EE0..11EF2 ; XID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11F02 ; XID_Start # Lo KAWI SIGN REPHA +11F04..11F10 ; XID_Start # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; XID_Start # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA 11FB0 ; XID_Start # Lo LISU LETTER YHA 12000..12399 ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; XID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; XID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; XID_Start # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; XID_Start # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; XID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; XID_Start # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; XID_Start # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; XID_Start # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; XID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -8551,8 +8862,13 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 17000..187F7 ; XID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; XID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; XID_Start # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; XID_Start # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; XID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; XID_Start # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; XID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -8589,10 +8905,22 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78A..1D7A8 ; XID_Start # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; XID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; XID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; XID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; XID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; XID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; XID_Start # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; XID_Start # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; XID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; XID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; XID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; XID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; XID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; XID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; XID_Start # Lm NAG MUNDARI SIGN OJOD +1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; XID_Start # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; XID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; XID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; XID_Start # Lm ADLAM NASALIZATION MARK @@ -8629,15 +8957,16 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1EEA1..1EEA3 ; XID_Start # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; XID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; XID_Start # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; XID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; XID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B739 ; XID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 131459 +# Total code points: 136322 # ================================================ @@ -8738,9 +9067,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0840..0858 ; XID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; XID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; XID_Continue # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; XID_Continue # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; XID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; XID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0898..089F ; XID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; XID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; XID_Continue # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; XID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; XID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; XID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; XID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -8878,6 +9210,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C0E..0C10 ; XID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; XID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; XID_Continue # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; XID_Continue # Mn TELUGU SIGN NUKTA 0C3D ; XID_Continue # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; XID_Continue # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; XID_Continue # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -8885,6 +9218,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C4A..0C4D ; XID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; XID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; XID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; XID_Continue # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; XID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; XID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -8906,11 +9240,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CCA..0CCB ; XID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; XID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; XID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; XID_Continue # Lo KANNADA LETTER FA +0CDD..0CDE ; XID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; XID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; XID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0CF3 ; XID_Continue # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; XID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; XID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D04..0D0C ; XID_Continue # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -8964,7 +9299,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0EBD ; XID_Continue # Lo LAO SEMIVOWEL SIGN NYO 0EC0..0EC4 ; XID_Continue # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI 0EC6 ; XID_Continue # Lm LAO KO LA -0EC8..0ECD ; XID_Continue # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; XID_Continue # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0ED0..0ED9 ; XID_Continue # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE 0EDC..0EDF ; XID_Continue # Lo [4] LAO HO NO..LAO LETTER KHMU NYO 0F00 ; XID_Continue # Lo TIBETAN SYLLABLE OM @@ -9050,11 +9385,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16A0..16EA ; XID_Continue # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; XID_Continue # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; XID_Continue # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; XID_Continue # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; XID_Continue # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; XID_Continue # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; XID_Continue # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; XID_Continue # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; XID_Continue # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; XID_Continue # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; XID_Continue # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; XID_Continue # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; XID_Continue # Mc HANUNOO SIGN PAMUDPOD 1740..1751 ; XID_Continue # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; XID_Continue # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1760..176C ; XID_Continue # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -9073,6 +9409,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 17DD ; XID_Continue # Mn KHMER SIGN ATTHACAN 17E0..17E9 ; XID_Continue # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 180B..180D ; XID_Continue # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; XID_Continue # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; XID_Continue # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; XID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; XID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -9120,7 +9457,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; XID_Continue # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; XID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -9132,7 +9469,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1B3D..1B41 ; XID_Continue # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; XID_Continue # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; XID_Continue # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; XID_Continue # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; XID_Continue # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; XID_Continue # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B6B..1B73 ; XID_Continue # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1B81 ; XID_Continue # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR @@ -9186,8 +9523,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78 ; XID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; XID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; XID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; XID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; XID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; XID_Continue # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; XID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; XID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; XID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -9235,9 +9571,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 2160..2182 ; XID_Continue # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; XID_Continue # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; XID_Continue # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; XID_Continue # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; XID_Continue # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; XID_Continue # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; XID_Continue # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; XID_Continue # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; XID_Continue # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; XID_Continue # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -9281,8 +9615,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 31A0..31BF ; XID_Continue # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; XID_Continue # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; XID_Continue # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; XID_Continue # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; XID_Continue # Lm YI SYLLABLE WU A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; XID_Continue # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -9310,8 +9643,11 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; XID_Continue # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; XID_Continue # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; XID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; XID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; XID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -9496,9 +9832,20 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 104D8..104FB ; XID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; XID_Continue # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; XID_Continue # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; XID_Continue # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; XID_Continue # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; XID_Continue # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; XID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; XID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; XID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; XID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; XID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; XID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; XID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; XID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -9540,10 +9887,13 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10E80..10EA9 ; XID_Continue # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EAB..10EAC ; XID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EFD..10EFF ; XID_Continue # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F46..10F50 ; XID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F70..10F81 ; XID_Continue # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; XID_Continue # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; XID_Continue # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; XID_Continue # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; XID_Continue # Mc BRAHMI SIGN CANDRABINDU @@ -9552,6 +9902,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11003..11037 ; XID_Continue # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11046 ; XID_Continue # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11066..1106F ; XID_Continue # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; XID_Continue # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; XID_Continue # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; XID_Continue # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; XID_Continue # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; XID_Continue # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; XID_Continue # Mc KAITHI SIGN VISARGA 11083..110AF ; XID_Continue # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -9559,6 +9913,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 110B3..110B6 ; XID_Continue # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; XID_Continue # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; XID_Continue # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; XID_Continue # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; XID_Continue # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; XID_Continue # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11100..11102 ; XID_Continue # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -9595,6 +9950,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11235 ; XID_Continue # Mc KHOJKI SIGN VIRAMA 11236..11237 ; XID_Continue # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; XID_Continue # Mn KHOJKI SIGN SUKUN +1123F..11240 ; XID_Continue # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I +11241 ; XID_Continue # Mn KHOJKI VOWEL SIGN VOCALIC R 11280..11286 ; XID_Continue # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; XID_Continue # Lo MULTANI LETTER GHA 1128A..1128D ; XID_Continue # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -9684,6 +10041,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11726 ; XID_Continue # Mc AHOM VOWEL SIGN E 11727..1172B ; XID_Continue # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 11730..11739 ; XID_Continue # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; XID_Continue # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; XID_Continue # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; XID_Continue # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; XID_Continue # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -9734,7 +10092,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; XID_Continue # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; XID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; XID_Continue # Mc BHAIKSUKI VOWEL SIGN AA @@ -9776,15 +10134,33 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11EE0..11EF2 ; XID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; XID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; XID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; XID_Continue # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F02 ; XID_Continue # Lo KAWI SIGN REPHA +11F03 ; XID_Continue # Mc KAWI SIGN VISARGA +11F04..11F10 ; XID_Continue # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; XID_Continue # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11F34..11F35 ; XID_Continue # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; XID_Continue # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; XID_Continue # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; XID_Continue # Mn KAWI VOWEL SIGN EU +11F41 ; XID_Continue # Mc KAWI SIGN KILLER +11F42 ; XID_Continue # Mn KAWI CONJOINER +11F50..11F59 ; XID_Continue # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 11FB0 ; XID_Continue # Lo LISU LETTER YHA 12000..12399 ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; XID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; XID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; XID_Continue # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13440 ; XID_Continue # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13441..13446 ; XID_Continue # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN +13447..13455 ; XID_Continue # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 14400..14646 ; XID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; XID_Continue # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A70..16ABE ; XID_Continue # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; XID_Continue # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; XID_Continue # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; XID_Continue # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B2F ; XID_Continue # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -9807,8 +10183,13 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 17000..187F7 ; XID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; XID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; XID_Continue # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; XID_Continue # Lo HIRAGANA LETTER SMALL KO 1B150..1B152 ; XID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; XID_Continue # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; XID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M @@ -9816,6 +10197,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1BC80..1BC88 ; XID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; XID_Continue # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9D..1BC9E ; XID_Continue # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; XID_Continue # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; XID_Continue # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; XID_Continue # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; XID_Continue # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; XID_Continue # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -9860,19 +10243,35 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DA84 ; XID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; XID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; XID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; XID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; XID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; XID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; XID_Continue # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E000..1E006 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; XID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; XID_Continue # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; XID_Continue # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E030..1E06D ; XID_Continue # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E08F ; XID_Continue # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E100..1E12C ; XID_Continue # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E130..1E136 ; XID_Continue # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; XID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; XID_Continue # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; XID_Continue # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; XID_Continue # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; XID_Continue # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; XID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; XID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; XID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E4D0..1E4EA ; XID_Continue # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; XID_Continue # Lm NAG MUNDARI SIGN OJOD +1E4EC..1E4EF ; XID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E4F0..1E4F9 ; XID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; XID_Continue # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; XID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; XID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E900..1E943 ; XID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -9913,16 +10312,17 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1EEA5..1EEA9 ; XID_Continue # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; XID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; XID_Continue # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; XID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; XID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B739 ; XID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 134415 +# Total code points: 139463 # ================================================ @@ -9933,7 +10333,7 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO # + Variation_Selector # - White_Space # - FFF9..FFFB (Interlinear annotation format characters) -# - 13430..13438 (Egyptian hieroglyph format characters) +# - 13430..13440 (Egyptian hieroglyph format characters) # - Prepended_Concatenation_Mark (Exceptional format characters that should be visible) 00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN @@ -9943,6 +10343,7 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO 17B4..17B5 ; Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Default_Ignorable_Code_Point # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Default_Ignorable_Code_Point # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 200B..200F ; Default_Ignorable_Code_Point # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK 202A..202E ; Default_Ignorable_Code_Point # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Default_Ignorable_Code_Point # Cf [5] WORD JOINER..INVISIBLE PLUS @@ -9963,7 +10364,7 @@ E0080..E00FF ; Default_Ignorable_Code_Point # Cn [128] .... -# Total code points: 4173 +# Total code points: 4174 # ================================================ @@ -9997,7 +10398,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .............. @@ -475,30 +586,42 @@ x (figure space - 2007) x (narrow no-break space - 202F) x (word joiner - 2060) + x (shouldered open box - 237D) x (zero width no-break space - FEFF) # 0020 00A1 INVERTED EXCLAMATION MARK * Spanish, Asturian, Galician + * used in extended IPA to represent sublaminal lower alveolar percussive x (exclamation mark - 0021) + x (modifier letter raised inverted exclamation mark - A71E) 00A2 CENT SIGN + x (latin small letter c with stroke - 023C) + x (mill sign - 20A5) + x (cedi sign - 20B5) + x (musical symbol cut time - 1D135) 00A3 POUND SIGN - = pound sterling, Irish punt, Italian lira, Turkish lira, etc. + = pound sterling, Irish punt, lira, etc. + * glyph may have one or two crossbars, in distinction from 20A4 x (lira sign - 20A4) x (turkish lira sign - 20BA) x (roman semuncia sign - 10192) 00A4 CURRENCY SIGN - * other currency symbol characters: 20A0-20BF + * generic or unknown currency + * other currency symbol characters start at 20A0 x (dollar sign - 0024) 00A5 YEN SIGN - = yuan sign + = yuan sign (renminbi) * glyph may have one or two crossbars, but the official symbol in Japan and China has two + * in native context, specific ideographs may be used for units of these currencies x 5143 x 5186 00A6 BROKEN BAR = broken vertical bar (1.0) = parted rule (in typography) + x (vertical line - 007C) 00A7 SECTION SIGN - * paragraph sign in some European usage + * used in referencing numbered sections or paragraphs + x (top half section sign - 2E39) 00A8 DIAERESIS * this is a spacing character x (combining diaeresis - 0308) @@ -510,6 +633,7 @@ x (mask work symbol - 1F1AD) 00AA FEMININE ORDINAL INDICATOR * Spanish + x (modifier letter small a - 1D43) # 0061 00AB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK = left guillemet @@ -520,26 +644,37 @@ 00AC NOT SIGN = angled dash (in typography) x (reversed not sign - 2310) + x (turned not sign - 2319) 00AD SOFT HYPHEN = discretionary hyphen * commonly abbreviated as SHY + * an invisible format character indicating a possible hyphenation location 00AE REGISTERED SIGN = registered trade mark sign (1.0) + x (trade mark sign - 2122) x (circled latin capital letter r - 24C7) + x (raised md sign - 1F16B) + x (raised mr sign - 1F16C) 00AF MACRON = overline, APL overbar * this is a spacing character + * unlike 203E, adjacent instances of this character do not join x (modifier letter macron - 02C9) x (combining macron - 0304) x (combining overline - 0305) + x (overline - 203E) + x (combining conjoining macron - FE26) # 0020 0304 00B0 DEGREE SIGN * this is a spacing character x (ring above - 02DA) x (combining ring above - 030A) x (superscript zero - 2070) + x (degree celsius - 2103) + x (degree fahrenheit - 2109) x (ring operator - 2218) 00B1 PLUS-MINUS SIGN + = biquintile (astrological aspect: 144°) x (minus-or-plus sign - 2213) 00B2 SUPERSCRIPT TWO = squared @@ -555,6 +690,8 @@ x (modifier letter prime - 02B9) x (modifier letter acute accent - 02CA) x (combining acute accent - 0301) + x (greek tonos - 0384) + x (greek oxia - 1FFD) x (prime - 2032) # 0020 0301 00B5 MICRO SIGN @@ -570,6 +707,8 @@ = Georgian comma = Greek middle dot (ano teleia) * also used as a raised decimal point or to denote multiplication; for multiplication 22C5 is preferred + x (full stop - 002E) + x (dot above - 02D9) x (greek ano teleia - 0387) x (runic single punctuation - 16EB) x (bullet - 2022) @@ -589,9 +728,12 @@ 00B9 SUPERSCRIPT ONE x (superscript two - 00B2) x (superscript three - 00B3) + x (superscript zero - 2070) # 0031 00BA MASCULINE ORDINAL INDICATOR * Spanish + x (modifier letter small o - 1D52) + x (numero sign - 2116) # 006F 00BB RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK = right guillemet @@ -650,6 +792,7 @@ * lowercase is 00F0 x (latin capital letter d with stroke - 0110) x (latin capital letter african d - 0189) + x (latin capital letter d with short stroke overlay - A7C7) 00D1 LATIN CAPITAL LETTER N WITH TILDE : 004E 0303 00D2 LATIN CAPITAL LETTER O WITH GRAVE @@ -665,9 +808,14 @@ @ Mathematical operator 00D7 MULTIPLICATION SIGN = z notation Cartesian product + x (latin small letter x - 0078) + x (saltire - 2613) x (multiplication x - 2715) + x (heavy ballot x - 2718) x (cross mark - 274C) x (vector or cross product - 2A2F) + x (cancellation x - 1F5D9) + x (light saltire - 1F7A9) @ Letters 00D8 LATIN CAPITAL LETTER O WITH STROKE = o slash @@ -687,9 +835,12 @@ = Eszett * German * not used in Swiss High German - * uppercase is "SS" or 1E9E + * uppercase is "SS" (standard case mapping), alternatively 1E9E * typographically the glyph for this character can be based on a ligature of 017F with either 0073 or with an old-style glyph for 007A (the latter similar in appearance to 0292). Both forms exist interchangeably today. + x (latin small letter long s - 017F) + x (latin small letter ezh - 0292) x (greek small letter beta - 03B2) + x (latin capital letter sharp s - 1E9E) 00E0 LATIN SMALL LETTER A WITH GRAVE : 0061 0300 00E1 LATIN SMALL LETTER A WITH ACUTE @@ -732,6 +883,7 @@ 00F0 LATIN SMALL LETTER ETH * Icelandic, Faroese, Old English, IPA * uppercase is 00D0 + x (latin small letter d with stroke - 0111) x (greek small letter delta - 03B4) x (partial differential - 2202) 00F1 LATIN SMALL LETTER N WITH TILDE @@ -750,7 +902,7 @@ @ Mathematical operator 00F7 DIVISION SIGN = obelus - * occasionally used as an alternate, more visually distinct version of 2212 or 2011 in some contexts + * occasionally used as an alternate, more visually distinct shape for a hyphen in some contexts * historically used as a punctuation mark to denote questionable passages in manuscripts x (syriac harklean obelus - 070B) x (commercial minus sign - 2052) @@ -759,6 +911,8 @@ x (divides - 2223) x (ratio - 2236) x (heavy division sign - 2797) + x (long division - 27CC) + x (dotted obelos - 2E13) @ Letters 00F8 LATIN SMALL LETTER O WITH STROKE = o slash @@ -1530,7 +1684,7 @@ : 00D8 0301 01FF LATIN SMALL LETTER O WITH STROKE AND ACUTE : 00F8 0301 -@ Additions for Slovenian and Croatian +@ Additions for Slovenian 0200 LATIN CAPITAL LETTER A WITH DOUBLE GRAVE : 0041 030F 0201 LATIN SMALL LETTER A WITH DOUBLE GRAVE @@ -2077,7 +2231,7 @@ # 0079 @ Miscellaneous phonetic modifiers 02B9 MODIFIER LETTER PRIME - * primary stress, emphasis + * stress, emphasis * transliteration of mjagkij znak (Cyrillic soft sign: palatalization) * transliteration of Hebrew geresh x (apostrophe - 0027) @@ -2418,6 +2572,7 @@ 031F COMBINING PLUS SIGN BELOW * IPA: advanced or fronted articulation x (modifier letter plus sign - 02D6) + x (combining plus sign above - 1AC8) 0320 COMBINING MINUS SIGN BELOW * IPA: retracted or backed articulation * glyph may have small end-serifs @@ -2464,6 +2619,7 @@ 032B COMBINING INVERTED DOUBLE ARCH BELOW * IPA: labialization x (modifier letter small w - 02B7) + x (combining inverted double arch above - 1AC7) 032C COMBINING CARON BELOW * IPA: voiced 032D COMBINING CIRCUMFLEX ACCENT BELOW @@ -2948,6 +3104,7 @@ 0416 CYRILLIC CAPITAL LETTER ZHE 0417 CYRILLIC CAPITAL LETTER ZE 0418 CYRILLIC CAPITAL LETTER I +@+ This letter is also used to represent electrolarynx phonation in the Voice Quality Symbols for extended IPA. 0419 CYRILLIC CAPITAL LETTER SHORT I : 0418 0306 041A CYRILLIC CAPITAL LETTER KA @@ -3352,6 +3509,7 @@ 04FF CYRILLIC SMALL LETTER HA WITH STROKE @@ 0500 Cyrillic Supplement 052F @ Komi letters +@+ These letters are for the obsolete Molodtsov alphabet, used in the 1920s. 0500 CYRILLIC CAPITAL LETTER KOMI DE 0501 CYRILLIC SMALL LETTER KOMI DE 0502 CYRILLIC CAPITAL LETTER KOMI DJE @@ -3414,9 +3572,10 @@ 0528 CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK 0529 CYRILLIC SMALL LETTER EN WITH LEFT HOOK @ Komi letters +@+ These are obsolete letters attested in a 19th century grammar of Komi. 052A CYRILLIC CAPITAL LETTER DZZHE 052B CYRILLIC SMALL LETTER DZZHE - * also used for Ossetian + * also used for Ossetian until 1924 052C CYRILLIC CAPITAL LETTER DCHE 052D CYRILLIC SMALL LETTER DCHE @ Khanty letters @@ -3728,15 +3887,18 @@ * represents sallallahu alayhe wasallam "may God's peace and blessings be upon him" 0611 ARABIC SIGN ALAYHE ASSALLAM * represents alayhe assalam "upon him be peace" + x (arabic ligature alayhi as-salaam - FD47) 0612 ARABIC SIGN RAHMATULLAH ALAYHE * represents rahmatullah alayhe "may God have mercy upon him" + x (arabic ligature rahimahu allaah - FD40) 0613 ARABIC SIGN RADI ALLAHOU ANHU * represents radi allahu 'anhu "may God be pleased with him" + x (arabic ligature radi allaahu anh - FD41) 0614 ARABIC SIGN TAKHALLUS * sign placed over the name or nom-de-plume of a poet, or in some writings used to mark all proper names @ Quranic annotation sign 0615 ARABIC SMALL HIGH TAH - * marks a recommended pause position in some Korans published in Iran and Pakistan + * marks a recommended pause position in some Qurans published in Iran and Pakistan * should not be confused with the small TAH sign used as a diacritic for some letters such as 0679 @ Extended Arabic mark 0616 ARABIC SMALL HIGH LIGATURE ALEF WITH LAM WITH YEH @@ -3760,6 +3922,7 @@ * commonly abbreviated ALM x (right-to-left mark - 200F) @ Punctuation +061D ARABIC END OF TEXT MARK 061E ARABIC TRIPLE DOT PUNCTUATION MARK 061F ARABIC QUESTION MARK * also used with Thaana and Syriac in modern text @@ -3780,6 +3943,7 @@ 0625 ARABIC LETTER ALEF WITH HAMZA BELOW : 0627 0655 0626 ARABIC LETTER YEH WITH HAMZA ABOVE + * in Kyrgyz the hamza is consistently positioned to the top right in isolate and final forms : 064A 0654 0627 ARABIC LETTER ALEF 0628 ARABIC LETTER BEH @@ -3820,6 +3984,7 @@ 0643 ARABIC LETTER KAF 0644 ARABIC LETTER LAM 0645 ARABIC LETTER MEEM + * Sindhi uses a shape with a short tail 0646 ARABIC LETTER NOON 0647 ARABIC LETTER HEH 0648 ARABIC LETTER WAW @@ -3842,11 +4007,15 @@ 0651 ARABIC SHADDA 0652 ARABIC SUKUN * marks absence of a vowel after the base consonant - * used in some Korans to mark a long vowel as ignored + * used in some Qurans to mark a long vowel as ignored * can have a variety of shapes, including a circular one and a shape that looks like '06E1' x (arabic small high dotless head of khah - 06E1) @ Combining maddah and hamza 0653 ARABIC MADDAH ABOVE + * used for madd jaa'iz in South Asian and Indonesian orthographies + x (arabic madda waajib - 089C) + x (arabic doubled madda - 089E) + x (arabic half madda over madda - 089F) 0654 ARABIC HAMZA ABOVE * restricted to hamza and ezafe semantics * is not used as a diacritic to form new letters @@ -3912,22 +4081,25 @@ * Kashmiri * this character is deprecated and its use is strongly discouraged * use the sequence 0627 065F instead -@ Extended Arabic letters +@ High hamza 0674 ARABIC LETTER HIGH HAMZA - * Kazakh + * Kazakh, Jawi * forms digraphs +@ Digraphic letters for Kazakh +@+ Use of these characters is discouraged. They were encoded for Kazakh digraphs, but their decompositions do not reflect the preferred order of representation. Accordingly, the representation of these Kazakh digraphs should instead use the preferred two-character spellings with the correct order of elements. 0675 ARABIC LETTER HIGH HAMZA ALEF - * Kazakh + * preferred spelling is 0674 0627 # 0627 0674 0676 ARABIC LETTER HIGH HAMZA WAW - * Kazakh + * preferred spelling is 0674 0648 # 0648 0674 0677 ARABIC LETTER U WITH HAMZA ABOVE - * Kazakh + * preferred spelling is 0674 06C7 # 06C7 0674 0678 ARABIC LETTER HIGH HAMZA YEH - * Kazakh + * preferred spelling is 0674 0649 # 064A 0674 +@ Extended Arabic letters 0679 ARABIC LETTER TTEH * Urdu 067A ARABIC LETTER TTEHEH @@ -4026,7 +4198,7 @@ 06A6 ARABIC LETTER PEHEH * Sindhi 06A7 ARABIC LETTER QAF WITH DOT ABOVE - * Maghrib Arabic, Uighur + * Maghrib Arabic, Uyghur 06A8 ARABIC LETTER QAF WITH THREE DOTS ABOVE * Tunisian Arabic 06A9 ARABIC LETTER KEHEH @@ -4041,9 +4213,10 @@ * use for the Jawi gaf is not recommended, although it may be found in some existing text data; recommended character for Jawi gaf is 0762 x (arabic letter keheh with dot above - 0762) 06AD ARABIC LETTER NG - * Uighur, Kazakh, Moroccan Arabic, early Jawi, early Persian, ... + * Uyghur, Kazakh, Moroccan Arabic, early Jawi, early Persian, ... 06AE ARABIC LETTER KAF WITH THREE DOTS BELOW * Berber, early Persian + * Pegon alternative for 068A 06AF ARABIC LETTER GAF * Persian, Urdu, ... 06B0 ARABIC LETTER GAF WITH RING @@ -4075,7 +4248,7 @@ * Jawi 06BE ARABIC LETTER HEH DOACHASHMEE * forms aspirate digraphs in Urdu and other languages of South Asia - * represents the glottal fricative /h/ in Uighur + * represents the glottal fricative /h/ in Uyghur 06BF ARABIC LETTER TCHEH WITH DOT ABOVE 06C0 ARABIC LETTER HEH WITH YEH ABOVE = arabic letter hamzah on ha (1.0) @@ -4093,19 +4266,20 @@ 06C4 ARABIC LETTER WAW WITH RING * Kashmiri 06C5 ARABIC LETTER KIRGHIZ OE - * Kirghiz + * Kyrgyz + * a glyph variant occurs which replaces the looped tail with a horizontal bar through the tail 06C6 ARABIC LETTER OE - * Uighur, Kurdish, Kazakh, Azerbaijani, Bosnian + * Uyghur, Kurdish, Kazakh, Azerbaijani, Bosnian 06C7 ARABIC LETTER U - * Kirghiz, Azerbaijani + * Azerbaijani, Kazakh, Kyrgyz, Uyghur 06C8 ARABIC LETTER YU - * Uighur + * Uyghur 06C9 ARABIC LETTER KIRGHIZ YU - * Kazakh, Kirghiz, Bosnian + * Kazakh, Kyrgyz, Bosnian 06CA ARABIC LETTER WAW WITH TWO DOTS ABOVE * Kurdish 06CB ARABIC LETTER VE - * Uighur, Kazakh + * Uyghur, Kazakh 06CC ARABIC LETTER FARSI YEH * Arabic, Persian, Urdu, Kashmiri, ... * initial and medial forms of this letter have dots @@ -4117,7 +4291,7 @@ * Kurdish 06CF ARABIC LETTER WAW WITH DOT ABOVE 06D0 ARABIC LETTER E - * Pashto, Uighur + * Pashto, Uyghur * used as the letter bbeh in Sindhi 06D1 ARABIC LETTER YEH WITH THREE DOTS BELOW * Mende languages, Hausa @@ -4132,7 +4306,7 @@ * Urdu @ Extended Arabic letter 06D5 ARABIC LETTER AE - * Uighur, Kazakh, Kirghiz + * Uyghur, Kazakh, Kyrgyz @ Quranic annotation signs 06D6 ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA 06D7 ARABIC SMALL HIGH LIGATURE QAF WITH LAM WITH ALEF MAKSURA @@ -4146,10 +4320,11 @@ 06DF ARABIC SMALL HIGH ROUNDED ZERO * smaller than the typical circular shape used for 0652 06E0 ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO + * the term "rectangular zero" is a translation of the Arabic name of this sign 06E1 ARABIC SMALL HIGH DOTLESS HEAD OF KHAH = Arabic jazm * presentation form of 0652, using font technology to select the variant is preferred - * used in some Korans to mark absence of a vowel + * used in some Qurans to mark absence of a vowel x (arabic sukun - 0652) 06E2 ARABIC SMALL HIGH MEEM ISOLATED FORM 06E3 ARABIC SMALL LOW SEEN @@ -4295,6 +4470,7 @@ @ Syriac marks 0740 SYRIAC FEMININE DOT * feminine marker used with the Taw feminine suffix + x (combining dot above left - 1DF8) 0741 SYRIAC QUSHSHAYA * indicates a plosive pronunciation 0742 SYRIAC RUKKAKHA @@ -4688,6 +4864,63 @@ x (malayalam letter llla - 0D34) 086A SYRIAC LETTER MALAYALAM SSA x (malayalam letter ssa - 0D37) +@@ 0870 Arabic Extended-B 089F +@ Additions for Quranic orthographies +0870 ARABIC LETTER ALEF WITH ATTACHED FATHA +0871 ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA +0872 ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE +0873 ARABIC LETTER ALEF WITH LEFT MIDDLE STROKE +0874 ARABIC LETTER ALEF WITH ATTACHED KASRA +0875 ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA +0876 ARABIC LETTER ALEF WITH ATTACHED ROUND DOT ABOVE +0877 ARABIC LETTER ALEF WITH ATTACHED RIGHT ROUND DOT +0878 ARABIC LETTER ALEF WITH ATTACHED LEFT ROUND DOT +0879 ARABIC LETTER ALEF WITH ATTACHED ROUND DOT BELOW +087A ARABIC LETTER ALEF WITH DOT ABOVE +087B ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA AND DOT ABOVE +087C ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE AND DOT ABOVE +087D ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND DOT ABOVE +087E ARABIC LETTER ALEF WITH ATTACHED TOP RIGHT FATHA AND LEFT RING +087F ARABIC LETTER ALEF WITH RIGHT MIDDLE STROKE AND LEFT RING +0880 ARABIC LETTER ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND LEFT RING +0881 ARABIC LETTER ALEF WITH ATTACHED RIGHT HAMZA +0882 ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +0883 ARABIC TATWEEL WITH OVERSTRUCK HAMZA +0884 ARABIC TATWEEL WITH OVERSTRUCK WAW +0885 ARABIC TATWEEL WITH TWO DOTS BELOW +0886 ARABIC LETTER THIN YEH + * no final or isolated forms are attested +0887 ARABIC BASELINE ROUND DOT +0888 ARABIC RAISED ROUND DOT +@ Additions for Bosnian orthographies +0889 ARABIC LETTER NOON WITH INVERTED SMALL V +088A ARABIC LETTER HAH WITH INVERTED SMALL V BELOW +@ Additions for Pegon orthographies +088B ARABIC LETTER TAH WITH DOT BELOW + * Pegon, Malagasy +088C ARABIC LETTER TAH WITH THREE DOTS BELOW + * Pegon alternative for 088B +088D ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW + * Sundanese Pegon +@ Abbreviation mark +088E ARABIC VERTICAL TAIL + * mark used to indicate abbreviations in early movable type texts from Iran + * only attested in final form +@ Supertending currency symbols +0890 ARABIC POUND MARK ABOVE + * Egyptian pound +0891 ARABIC PIASTRE MARK ABOVE + * Egyptian piastre +@ Additions for Quranic orthographies +0898 ARABIC SMALL HIGH WORD AL-JUZ +0899 ARABIC SMALL LOW WORD ISHMAAM +089A ARABIC SMALL LOW WORD IMAALA +089B ARABIC SMALL LOW WORD TASHEEL +089C ARABIC MADDA WAAJIB + x (arabic maddah above - 0653) +089D ARABIC SUPERSCRIPT ALEF MOKHASSAS +089E ARABIC DOUBLED MADDA +089F ARABIC HALF MADDA OVER MADDA @@ 08A0 Arabic Extended-A 08FF @ Arabic letters for African languages 08A0 ARABIC LETTER BEH WITH SMALL V BELOW @@ -4733,6 +4966,8 @@ @ Arabic letters for Arwi 08B3 ARABIC LETTER AIN WITH THREE DOTS BELOW 08B4 ARABIC LETTER KAF WITH DOT BELOW +@ Early Arabic letter +08B5 ARABIC LETTER QAF WITH DOT BELOW AND NO DOTS ABOVE @ Arabic letters for Bravanese 08B6 ARABIC LETTER BEH WITH SMALL MEEM ABOVE 08B7 ARABIC LETTER PEH WITH SMALL MEEM ABOVE @@ -4769,6 +5004,20 @@ 08C6 ARABIC LETTER JEEM WITH THREE DOTS BELOW @ Arabic letter for Punjabi 08C7 ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +@ Arabic letter for Balti +08C8 ARABIC LETTER GRAF +@ Additions for Quranic orthographies +08C9 ARABIC SMALL FARSI YEH +08CA ARABIC SMALL HIGH FARSI YEH +08CB ARABIC SMALL HIGH YEH BARREE WITH TWO DOTS BELOW +08CC ARABIC SMALL HIGH WORD SAH + = sign of waqf +08CD ARABIC SMALL HIGH ZAH +08CE ARABIC LARGE ROUND DOT ABOVE +08CF ARABIC LARGE ROUND DOT BELOW +08D0 ARABIC SUKUN BELOW +08D1 ARABIC LARGE CIRCLE BELOW +08D2 ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW @ Quranic annotation signs 08D3 ARABIC SMALL LOW WAW 08D4 ARABIC SMALL HIGH WORD AR-RUB @@ -4781,6 +5030,7 @@ 08DB ARABIC SMALL HIGH WORD AS-SAJDA 08DC ARABIC SMALL HIGH WORD AN-NISF 08DD ARABIC SMALL HIGH WORD SAKTA + x (arabic small low word sakta - 10EFD) 08DE ARABIC SMALL HIGH WORD QIF 08DF ARABIC SMALL HIGH WORD WAQFA 08E0 ARABIC SMALL HIGH FOOTNOTE MARKER @@ -4821,8 +5071,8 @@ 08F9 ARABIC LEFT ARROWHEAD BELOW 08FA ARABIC RIGHT ARROWHEAD BELOW 08FB ARABIC DOUBLE RIGHT ARROWHEAD ABOVE -08FC ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT * also used in Quranic text in African and other orthographies to represent dammatan +08FC ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT 08FD ARABIC RIGHT ARROWHEAD ABOVE WITH DOT @ Extended vowel signs 08FE ARABIC DAMMA WITH DOT @@ -5779,6 +6029,10 @@ 0C37 TELUGU LETTER SSA 0C38 TELUGU LETTER SA 0C39 TELUGU LETTER HA +@ Sign +0C3C TELUGU SIGN NUKTA + * used for Tamil transliteration and Perso-Arabic phonemes + * can also appear as a large dot, should be placed sufficiently below the baseline of a consonant to avoid confusion/collision with the aspiration marker @ Addition for Sanskrit 0C3D TELUGU SIGN AVAGRAHA @ Dependent vowel signs @@ -5807,6 +6061,11 @@ 0C59 TELUGU LETTER DZA 0C5A TELUGU LETTER RRRA * letter for an alveolar consonant whose exact phonetic value is not known +@ Consonant +0C5D TELUGU LETTER NAKAARA POLLU + * vowelless form of na + x (kannada letter nakaara pollu - 0CDD) + x (malayalam letter chillu n - 0D7B) @ Additional vowels for Sanskrit 0C60 TELUGU LETTER VOCALIC RR 0C61 TELUGU LETTER VOCALIC LL @@ -5850,6 +6109,7 @@ 0C80 KANNADA SIGN SPACING CANDRABINDU 0C81 KANNADA SIGN CANDRABINDU 0C82 KANNADA SIGN ANUSVARA + * used in Konkani, Havyaka Kannada (Havigannada) and Awadhi texts to indicate regular anusvara 0C83 KANNADA SIGN VISARGA 0C84 KANNADA SIGN SIDDHAM = siddhirastu @@ -5936,6 +6196,10 @@ 0CD5 KANNADA LENGTH MARK 0CD6 KANNADA AI LENGTH MARK @ Additional consonants +0CDD KANNADA LETTER NAKAARA POLLU + * vowelless form of na + x (telugu letter nakaara pollu - 0C5D) + x (malayalam letter chillu n - 0D7B) 0CDE KANNADA LETTER FA % KANNADA LETTER LLLA * obsolete historic letter @@ -5968,6 +6232,8 @@ x (vedic sign jihvamuliya - 1CF5) 0CF2 KANNADA SIGN UPADHMANIYA x (vedic sign upadhmaniya - 1CF6) +0CF3 KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT + * used in Konkani, Havyaka Kannada (Havigannada) and Awadhi texts to indicate anunāsikā @@ 0D00 Malayalam 0D7F @ Various signs 0D00 MALAYALAM SIGN COMBINING ANUSVARA ABOVE @@ -6474,6 +6740,7 @@ = nikkhahit * final nasal 0E4E THAI CHARACTER YAMAKKAN + x (lao yamakkan - 0ECE) 0E4F THAI CHARACTER FONGMAN * used as a bullet x (khmer sign phnaek muan - 17D9) @@ -6617,6 +6884,9 @@ 0ECC LAO CANCELLATION MARK 0ECD LAO NIGGAHITA * final nasal or long o vowel +0ECE LAO YAMAKKAN + * marks a consonant that is simultaneously a part of two consonant clusters in Pali text + x (thai character yamakkan - 0E4E) @ Digits 0ED0 LAO DIGIT ZERO 0ED1 LAO DIGIT ONE @@ -7746,9 +8016,12 @@ 1247 ETHIOPIC SYLLABLE QOA 1248 ETHIOPIC SYLLABLE QWA 124A ETHIOPIC SYLLABLE QWI + x (ethiopic syllable gurage qwi - 1E7F0) 124B ETHIOPIC SYLLABLE QWAA 124C ETHIOPIC SYLLABLE QWEE + x (ethiopic syllable gurage qwee - 1E7F1) 124D ETHIOPIC SYLLABLE QWE + x (ethiopic syllable gurage qwe - 1E7F2) 1250 ETHIOPIC SYLLABLE QHA 1251 ETHIOPIC SYLLABLE QHU 1252 ETHIOPIC SYLLABLE QHI @@ -7840,9 +8113,12 @@ 12AF ETHIOPIC SYLLABLE KOA 12B0 ETHIOPIC SYLLABLE KWA 12B2 ETHIOPIC SYLLABLE KWI + x (ethiopic syllable gurage kwi - 1E7F5) 12B3 ETHIOPIC SYLLABLE KWAA 12B4 ETHIOPIC SYLLABLE KWEE + x (ethiopic syllable gurage kwee - 1E7F6) 12B5 ETHIOPIC SYLLABLE KWE + x (ethiopic syllable gurage kwe - 1E7F7) 12B8 ETHIOPIC SYLLABLE KXA 12B9 ETHIOPIC SYLLABLE KXU 12BA ETHIOPIC SYLLABLE KXI @@ -7851,10 +8127,14 @@ 12BD ETHIOPIC SYLLABLE KXE 12BE ETHIOPIC SYLLABLE KXO 12C0 ETHIOPIC SYLLABLE KXWA + x (ethiopic syllable gurage hhwa - 1E7E8) 12C2 ETHIOPIC SYLLABLE KXWI + x (ethiopic syllable hhwi - 1E7E9) 12C3 ETHIOPIC SYLLABLE KXWAA 12C4 ETHIOPIC SYLLABLE KXWEE + x (ethiopic syllable hhwee - 1E7EA) 12C5 ETHIOPIC SYLLABLE KXWE + x (ethiopic syllable hhwe - 1E7EB) 12C8 ETHIOPIC SYLLABLE WA 12C9 ETHIOPIC SYLLABLE WU 12CA ETHIOPIC SYLLABLE WI @@ -7928,9 +8208,12 @@ 130F ETHIOPIC SYLLABLE GOA 1310 ETHIOPIC SYLLABLE GWA 1312 ETHIOPIC SYLLABLE GWI + x (ethiopic syllable gurage gwi - 1E7F8) 1313 ETHIOPIC SYLLABLE GWAA 1314 ETHIOPIC SYLLABLE GWEE + x (ethiopic syllable gurage gwee - 1E7F9) 1315 ETHIOPIC SYLLABLE GWE + x (ethiopic syllable gurage gwe - 1E7FA) 1318 ETHIOPIC SYLLABLE GGA 1319 ETHIOPIC SYLLABLE GGU 131A ETHIOPIC SYLLABLE GGI @@ -8037,22 +8320,30 @@ 137B ETHIOPIC NUMBER HUNDRED 137C ETHIOPIC NUMBER TEN THOUSAND @@ 1380 Ethiopic Supplement 139F -@ Syllables for Sebatbeit +@ Syllables for Gurage 1380 ETHIOPIC SYLLABLE SEBATBEIT MWA 1381 ETHIOPIC SYLLABLE MWI + x (ethiopic syllable gurage mwi - 1E7ED) 1382 ETHIOPIC SYLLABLE MWEE + x (ethiopic syllable gurage mwee - 1E7EE) 1383 ETHIOPIC SYLLABLE MWE 1384 ETHIOPIC SYLLABLE SEBATBEIT BWA 1385 ETHIOPIC SYLLABLE BWI + x (ethiopic syllable gurage bwi - 1E7F3) 1386 ETHIOPIC SYLLABLE BWEE + x (ethiopic syllable gurage bwee - 1E7F4) 1387 ETHIOPIC SYLLABLE BWE 1388 ETHIOPIC SYLLABLE SEBATBEIT FWA 1389 ETHIOPIC SYLLABLE FWI + x (ethiopic syllable gurage fwi - 1E7FB) 138A ETHIOPIC SYLLABLE FWEE + x (ethiopic syllable gurage fwee - 1E7FC) 138B ETHIOPIC SYLLABLE FWE 138C ETHIOPIC SYLLABLE SEBATBEIT PWA 138D ETHIOPIC SYLLABLE PWI + x (ethiopic syllable gurage pwi - 1E7FD) 138E ETHIOPIC SYLLABLE PWEE + x (ethiopic syllable gurage pwee - 1E7FE) 138F ETHIOPIC SYLLABLE PWE @ Tonal marks @+ Intended for use with a multiline scored layout @@ -8732,6 +9023,7 @@ 15C2 CANADIAN SYLLABICS SAYISI HO * Sayisi (HU) 15C3 CANADIAN SYLLABICS SAYISI HA +@ Syllables for Carrier 15C4 CANADIAN SYLLABICS CARRIER GHU 15C5 CANADIAN SYLLABICS CARRIER GHO 15C6 CANADIAN SYLLABICS CARRIER GHE @@ -9088,6 +9380,8 @@ 170A TAGALOG LETTER BA 170B TAGALOG LETTER MA 170C TAGALOG LETTER YA +170D TAGALOG LETTER RA + * modern adaptation, not found in Old Tagalog 170E TAGALOG LETTER LA 170F TAGALOG LETTER WA 1710 TAGALOG LETTER SA @@ -9095,8 +9389,14 @@ @ Dependent vowel signs 1712 TAGALOG VOWEL SIGN I 1713 TAGALOG VOWEL SIGN U -@ Virama +@ Viramas 1714 TAGALOG SIGN VIRAMA +1715 TAGALOG SIGN PAMUDPOD + x (hanunoo sign pamudpod - 1734) +@ Archaic letter +171F TAGALOG LETTER ARCHAIC RA + = Zambales ra + * modern adaptation, not found in Old Tagalog @@ 1720 Hanunoo 173F @ Independent vowels 1720 HANUNOO LETTER A @@ -9123,6 +9423,7 @@ 1733 HANUNOO VOWEL SIGN U @ Virama 1734 HANUNOO SIGN PAMUDPOD + x (tagalog sign pamudpod - 1715) @ Generic punctuation for Philippine scripts 1735 PHILIPPINE SINGLE PUNCTUATION x (devanagari danda - 0964) @@ -9411,6 +9712,8 @@ * abbreviated FVS3 180E MONGOLIAN VOWEL SEPARATOR * abbreviated MVS +180F MONGOLIAN FREE VARIATION SELECTOR FOUR + * abbreviated FVS4 @ Digits 1810 MONGOLIAN DIGIT ZERO 1811 MONGOLIAN DIGIT ONE @@ -10137,7 +10440,8 @@ * used in combinations with other punctuation marks at ends of sections 1AAD TAI THAM SIGN CAANG @@ 1AB0 Combining Diacritical Marks Extended 1AFF -@ Used for German dialectology +@+ This block contains many specialized combining marks, often derived from European dialectology transcriptional conventions. +@ Used in German dialectology 1AB0 COMBINING DOUBLED CIRCUMFLEX ACCENT 1AB1 COMBINING DIAERESIS-RING 1AB2 COMBINING INFINITY @@ -10151,6 +10455,8 @@ 1AB8 COMBINING DOUBLE OPEN MARK BELOW 1AB9 COMBINING LIGHT CENTRALIZATION STROKE BELOW 1ABA COMBINING STRONG CENTRALIZATION STROKE BELOW +@ Marks surrounding other diacritics or letters +@+ These marks are often intended to indicate partial or uncertain applicability of another diacritic. 1ABB COMBINING PARENTHESES ABOVE * intended to surround a diacritic above 1ABC COMBINING DOUBLE PARENTHESES ABOVE @@ -10159,11 +10465,39 @@ 1ABE COMBINING PARENTHESES OVERLAY * intended to surround a base letter * exact placement is font dependent -@ Used for Scots dialectology +@ Used in Scots dialectology 1ABF COMBINING LATIN SMALL LETTER W BELOW * indicates voiced labialization + x (modifier letter small w - 02B7) 1AC0 COMBINING LATIN SMALL LETTER TURNED W BELOW * indicates voiceless labialization +@ Marks next to or surrounding other diacritics +@+ The left or right parentheses marks are used in extended IPA in combination with voicing or devoicing diacritics to indicate initial or final partial applicability. +1AC1 COMBINING LEFT PARENTHESIS ABOVE LEFT +1AC2 COMBINING RIGHT PARENTHESIS ABOVE RIGHT +1AC3 COMBINING LEFT PARENTHESIS BELOW LEFT +1AC4 COMBINING RIGHT PARENTHESIS BELOW RIGHT +1AC5 COMBINING SQUARE BRACKETS ABOVE + * intended to surround a diacritic above + * used to indicate cancellation of an accent in Japanese transliteration +@ Phonetic sign +1AC6 COMBINING NUMBER SIGN ABOVE + = superscript octothorp + * used extensively in J.P. Harrington's transcriptional notation +@ Used in extended IPA +1AC7 COMBINING INVERTED DOUBLE ARCH ABOVE + x (combining inverted double arch below - 032B) + x (combining latin small letter w - 1DF1) +1AC8 COMBINING PLUS SIGN ABOVE + x (combining plus sign below - 031F) +1AC9 COMBINING DOUBLE PLUS SIGN ABOVE +1ACA COMBINING DOUBLE PLUS SIGN BELOW +@ Used in Middle English Ormulum +1ACB COMBINING TRIPLE ACUTE ACCENT + x (combining double acute accent - 030B) +1ACC COMBINING LATIN SMALL LETTER INSULAR G +1ACD COMBINING LATIN SMALL LETTER INSULAR R +1ACE COMBINING LATIN SMALL LETTER INSULAR T @@ 1B00 Balinese 1B7F @ Various signs 1B00 BALINESE SIGN ULU RICEM @@ -10173,7 +10507,9 @@ 1B02 BALINESE SIGN CECEK = anusvara 1B03 BALINESE SIGN SURANG - = repha + = final r + * also used for repha in transliteration of Kawi + x (javanese sign layar - A982) 1B04 BALINESE SIGN BISAH = visarga @ Independent vowels @@ -10310,6 +10646,9 @@ 1B49 BALINESE LETTER VE SASAK 1B4A BALINESE LETTER ZAL SASAK 1B4B BALINESE LETTER ASYURA SASAK +1B4C BALINESE LETTER ARCHAIC JNYA + * used in older texts in place of the ja + nya conjunct + x (javanese letter nya murda - A998) @ Digits 1B50 BALINESE DIGIT ZERO 1B51 BALINESE DIGIT ONE @@ -10369,12 +10708,17 @@ 1B7A BALINESE MUSICAL SYMBOL LEFT-HAND CLOSED PLAK 1B7B BALINESE MUSICAL SYMBOL LEFT-HAND CLOSED PLUK 1B7C BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +@ Punctuation +1B7D BALINESE PANTI LANTANG + = end of text +1B7E BALINESE PAMADA LANTANG + = end of text @@ 1B80 Sundanese 1BBF @ Various signs 1B80 SUNDANESE SIGN PANYECEK = anusvara 1B81 SUNDANESE SIGN PANGLAYAR - = repha + = final r 1B82 SUNDANESE SIGN PANGWISAD = visarga @ Vowels @@ -10456,14 +10800,19 @@ 1BB9 SUNDANESE DIGIT NINE @ Sign 1BBA SUNDANESE AVAGRAHA + = gemination mark @ Historic letters 1BBB SUNDANESE LETTER REU * vocalic r 1BBC SUNDANESE LETTER LEU * vocalic l 1BBD SUNDANESE LETTER BHA + % SUNDANESE LETTER ARCHAIC I + * character was originally misidentified, so its name is a misnomer 1BBE SUNDANESE LETTER FINAL K 1BBF SUNDANESE LETTER FINAL M + * used in a 21st century document + * for actual final m, use the sequence 1B99 1BAA @@ 1BC0 Batak 1BFF @ Letters @+ Annotations for letters indicate different usage among the various alphabets sharing the Batak script. @@ -10969,9 +11318,11 @@ 1D33 MODIFIER LETTER CAPITAL G # 0047 1D34 MODIFIER LETTER CAPITAL H + # 0048 +@+ A typographical distinction between a capital form and a small capital form is not distinctive for this character in IPA usage. + * voiceless epiglottalized release (extended IPA) x (latin letter small capital h - 029C) x (modifier letter cyrillic en - 1D78) - # 0048 1D35 MODIFIER LETTER CAPITAL I # 0049 1D36 MODIFIER LETTER CAPITAL J @@ -11104,6 +11455,7 @@ * Georgian transcription x (georgian letter turned gan - 10F9) 1D78 MODIFIER LETTER CYRILLIC EN + * sometimes substituted for 1D34 in extended IPA x (modifier letter capital h - 1D34) # 043D @ Other phonetic symbols @@ -11114,6 +11466,7 @@ x (latin small letter yogh - 021D) x (latin small letter script g - 0261) x (latin small letter gamma - 0263) + x (latin small letter closed insular g - A7D1) 1D7A LATIN SMALL LETTER TH WITH STRIKETHROUGH * American dictionary usage x (greek small letter theta - 03B8) @@ -11332,6 +11685,8 @@ 1DEF COMBINING LATIN SMALL LETTER ESH 1DF0 COMBINING LATIN SMALL LETTER U WITH LIGHT CENTRALIZATION STROKE 1DF1 COMBINING LATIN SMALL LETTER W + x (combining latin small letter w below - 1ABF) + x (combining inverted double arch above - 1AC7) 1DF2 COMBINING LATIN SMALL LETTER A WITH DIAERESIS 1DF3 COMBINING LATIN SMALL LETTER O WITH DIAERESIS 1DF4 COMBINING LATIN SMALL LETTER U WITH DIAERESIS @@ -11346,9 +11701,12 @@ * used in Syriac as a disambiguation dot * used in Typicon Cyrillic, where the dot may have a square appearance x (combining dot above right - 0358) + x (syriac feminine dot - 0740) 1DF9 COMBINING WIDE INVERTED BRIDGE BELOW * used as a Typicon mark x (combining inverted bridge below - 033A) +1DFA COMBINING DOT BELOW LEFT + * used in Syriac as a disambiguation dot 1DFB COMBINING DELETION MARK * used for "mhusaa" in Newa scribal tradition @ Double diacritic mark for UPA @@ -12620,7 +12978,7 @@ = Japanese kome = Urdu paragraph separator x (tibetan ku ru kha bzhi mig can - 0FBF) - x (cjk unified ideograph-200AD - 200AD) + x 200AD @ Double punctuation for vertical text 203C DOUBLE EXCLAMATION MARK x (exclamation mark - 0021) @@ -12654,6 +13012,7 @@ @ Brackets 2045 LEFT SQUARE BRACKET WITH QUILL x (left vertical bar with quill - 2E20) + x (left square bracket with stroke - 2E55) 2046 RIGHT SQUARE BRACKET WITH QUILL @ Double punctuation for vertical text 2047 DOUBLE QUESTION MARK @@ -12882,10 +13241,10 @@ x (thai currency symbol baht - 0E3F) x (khmer currency symbol riel - 17DB) x (script capital m - 2133) - x (cjk unified ideograph-5143 - 5143) - x (cjk unified ideograph-5186 - 5186) - x (cjk unified ideograph-5706 - 5706) - x (cjk unified ideograph-5713 - 5713) + x 5143 + x 5186 + x 5706 + x 5713 x (rial sign - FDFC) x (wancho ngun sign - 1E2FF) 20A0 EURO-CURRENCY SIGN @@ -12978,6 +13337,8 @@ * Georgia 20BF BITCOIN SIGN * a cryptocurrency +20C0 SOM SIGN + * Kyrgyzstan @@ 20D0 Combining Diacritical Marks for Symbols 20FF @ Combining diacritical marks for symbols 20D0 COMBINING LEFT HARPOON ABOVE @@ -13030,6 +13391,9 @@ 20E6 COMBINING DOUBLE VERTICAL STROKE OVERLAY = z notation finite function diacritic x (double vertical line - 2016) + x (rightwards arrow with double vertical stroke - 21FB) + x (rightwards two-headed arrow with double vertical stroke - 2901) + x (rightwards arrow with tail with double vertical stroke - 2915) 20E7 COMBINING ANNUITY SYMBOL = actuarial bend x (right ceiling - 2309) @@ -13080,6 +13444,8 @@ # 0067 latin small letter g 210B SCRIPT CAPITAL H = Hamiltonian operator + ~ 210B FE00 chancery style + ~ 210B FE01 roundhand style # 0048 latin capital letter h 210C BLACK-LETTER CAPITAL H = Hilbert space @@ -13095,12 +13461,16 @@ x (cyrillic small letter tshe - 045B) # 0127 latin small letter h with stroke 2110 SCRIPT CAPITAL I + ~ 2110 FE00 chancery style + ~ 2110 FE01 roundhand style # 0049 latin capital letter i 2111 BLACK-LETTER CAPITAL I = imaginary part # 0049 latin capital letter i 2112 SCRIPT CAPITAL L = Laplace transform + ~ 2112 FE00 chancery style + ~ 2112 FE01 roundhand style # 004C latin capital letter l 2113 SCRIPT SMALL L = mathematical symbol 'ell' @@ -13135,6 +13505,8 @@ # 0051 latin capital letter q 211B SCRIPT CAPITAL R = Riemann Integral + ~ 211B FE00 chancery style + ~ 211B FE01 roundhand style # 0052 latin capital letter r 211C BLACK-LETTER CAPITAL R = real part @@ -13189,6 +13561,8 @@ : 00C5 latin capital letter a with ring above 212C SCRIPT CAPITAL B = Bernoulli function + ~ 212C FE00 chancery style + ~ 212C FE01 roundhand style # 0042 latin capital letter b 212D BLACK-LETTER CAPITAL C # 0043 latin capital letter c @@ -13201,9 +13575,13 @@ # 0065 latin small letter e 2130 SCRIPT CAPITAL E = emf (electromotive force) + ~ 2130 FE00 chancery style + ~ 2130 FE01 roundhand style # 0045 latin capital letter e 2131 SCRIPT CAPITAL F = Fourier transform + ~ 2131 FE00 chancery style + ~ 2131 FE01 roundhand style # 0046 latin capital letter f 2132 TURNED CAPITAL F = Claudian digamma inversum @@ -13215,6 +13593,8 @@ = German Mark currency symbol, before WWII * when used for the Mark symbol, the range of glyph variation is restricted x (nordic mark sign - 20BB) + ~ 2133 FE00 chancery style + ~ 2133 FE01 roundhand style # 004D latin capital letter m 2134 SCRIPT SMALL O = order, of inferior order to @@ -13298,6 +13678,7 @@ x (greek small letter digamma - 03DD) @ Biblical editorial symbol 214F SYMBOL FOR SAMARITAN SOURCE +@~ Standardized Variation Sequences @@ 2150 Number Forms 218F @ Fractions @+ Other fraction number forms are found in the Latin-1 Supplement block. @@ -13877,7 +14258,9 @@ : 2261 0338 2263 STRICTLY EQUIVALENT TO 2264 LESS-THAN OR EQUAL TO + x (less-than sign - 003C) 2265 GREATER-THAN OR EQUAL TO + x (greater-than sign - 003E) 2266 LESS-THAN OVER EQUAL TO 2267 GREATER-THAN OVER EQUAL TO 2268 LESS-THAN BUT NOT EQUAL TO @@ -13984,6 +14367,7 @@ x (circled crossing lanes - 26D2) x (n-ary circled times operator - 2A02) x (circled x - 2BBE) + x (lot of fortune - 1F774) ~ 2297 FE00 with white rim 2298 CIRCLED DIVISION SLASH 2299 CIRCLED DOT OPERATOR @@ -14097,6 +14481,9 @@ x (black star - 2605) x (white medium star - 2B50) 22C7 DIVISION TIMES + x (multiplication sign - 00D7) + x (division sign - 00F7) + x (multiplication x - 2715) @ Relation 22C8 BOWTIE x (ocr bow tie - 2445) @@ -14258,7 +14645,7 @@ 231B HOURGLASS = alchemical symbol for hour @ Quine corners -@+ These form a set of four quine corners, for quincuncial arrangement. They are also used in upper and lower pairs in mathematic, or more rarely in editorial usage as alternatives to half brackets. +@+ These form a set of four quine corners, for quincuncial arrangement. They are also used in upper and lower pairs in mathematics, or more rarely in editorial usage as alternatives to half brackets. 231C TOP LEFT CORNER x (right angle substitution marker - 2E00) x (top left half bracket - 2E22) @@ -15527,7 +15914,9 @@ x (alchemical symbol for purify - 1F763) 260C CONJUNCTION = alchemical symbol for day + x (occultation - 1F775) 260D OPPOSITION + x (lunar eclipse - 1F776) @ Miscellaneous symbols 260E BLACK TELEPHONE x (telephone sign - 2121) @@ -15613,6 +16002,7 @@ 262C ADI SHAKTI = khanda * Sikh religious symbol + x (khanda - 1FAAF) 262D HAMMER AND SICKLE 262E PEACE SYMBOL 262F YIN YANG @@ -15891,7 +16281,7 @@ = heterosexuality 26A5 MALE AND FEMALE SIGN = intersex, androgynous - = hermaphrodite (in entomology) + = hermaphroditic (in botany) 26A6 MALE WITH STROKE SIGN = transgender = alchemical symbol for iron or crocus of iron @@ -18262,6 +18652,8 @@ 2C2C GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI +@+ This is used as an alternative to Glagolitic letter chrivi, combined with 0303 combining tilde or with 0483 combining Cyrillic titlo as an et cetera sign. @ Small letters 2C30 GLAGOLITIC SMALL LETTER AZU 2C31 GLAGOLITIC SMALL LETTER BUKY @@ -18311,6 +18703,7 @@ 2C5C GLAGOLITIC SMALL LETTER SHTAPIC 2C5D GLAGOLITIC SMALL LETTER TROKUTASTI A 2C5E GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C5F GLAGOLITIC SMALL LETTER CAUDATE CHRIVI @@ 2C60 Latin Extended-C 2C7F @ Orthographic Latin additions 2C60 LATIN CAPITAL LETTER L WITH DOUBLE BAR @@ -18325,7 +18718,7 @@ * uppercase is 023A 2C66 LATIN SMALL LETTER T WITH DIAGONAL STROKE * uppercase is 023E -@ Additions for Uighur +@ Additions for Uyghur 2C67 LATIN CAPITAL LETTER H WITH DESCENDER 2C68 LATIN SMALL LETTER H WITH DESCENDER 2C69 LATIN CAPITAL LETTER K WITH DESCENDER @@ -18692,7 +19085,7 @@ 2DBC ETHIOPIC SYLLABLE CCHEE 2DBD ETHIOPIC SYLLABLE CCHE 2DBE ETHIOPIC SYLLABLE CCHO -@ Syllables for Sebatbeit +@ Syllables for Gurage 2DC0 ETHIOPIC SYLLABLE QYA 2DC1 ETHIOPIC SYLLABLE QYU 2DC2 ETHIOPIC SYLLABLE QYI @@ -18708,12 +19101,19 @@ 2DCD ETHIOPIC SYLLABLE KYE 2DCE ETHIOPIC SYLLABLE KYO 2DD0 ETHIOPIC SYLLABLE XYA + x (ethiopic syllable hhya - 1E7E0) 2DD1 ETHIOPIC SYLLABLE XYU + x (ethiopic syllable hhyu - 1E7E1) 2DD2 ETHIOPIC SYLLABLE XYI + x (ethiopic syllable hhyi - 1E7E2) 2DD3 ETHIOPIC SYLLABLE XYAA + x (ethiopic syllable hhyaa - 1E7E3) 2DD4 ETHIOPIC SYLLABLE XYEE + x (ethiopic syllable hhyee - 1E7E4) 2DD5 ETHIOPIC SYLLABLE XYE + x (ethiopic syllable hhye - 1E7E5) 2DD6 ETHIOPIC SYLLABLE XYO + x (ethiopic syllable hhyo - 1E7E6) 2DD8 ETHIOPIC SYLLABLE GYA 2DD9 ETHIOPIC SYLLABLE GYU 2DDA ETHIOPIC SYLLABLE GYI @@ -18808,6 +19208,7 @@ x (equals sign - 003D) x (hyphen - 2010) x (double hyphen - 2E40) + x (oblique hyphen - 2E5D) @ General punctuation 2E18 INVERTED INTERROBANG = gnaborretni @@ -18965,13 +19366,37 @@ x (paragraphos - 2E0F) x (capitulum - 2E3F) 2E4E PUNCTUS ELEVATUS MARK - * indicates a major medial pause where the sense is complete but the meaning is not +@+ This mark indicates a major intermediate pause where the sensus is complete but the sentence is not; this is similar in some regards to the modern use of a semicolon. 2E4F CORNISH VERSE DIVIDER 2E50 CROSS PATTY WITH RIGHT CROSSBAR x (maltese cross - 2720) + x (latin capital letter half h - 2C75) 2E51 CROSS PATTY WITH LEFT CROSSBAR + x (latin capital letter reversed half h - A7F5) 2E52 TIRONIAN SIGN CAPITAL ET x (tironian sign et - 204A) +2E53 MEDIEVAL EXCLAMATION MARK +2E54 MEDIEVAL QUESTION MARK +@ Brackets +@+ These brackets indicate ellipsis in certain conventions for Japanese transliteration. +2E55 LEFT SQUARE BRACKET WITH STROKE + * optional ellipsis + x (left square bracket with quill - 2045) +2E56 RIGHT SQUARE BRACKET WITH STROKE +2E57 LEFT SQUARE BRACKET WITH DOUBLE STROKE + * obligatory ellipsis +2E58 RIGHT SQUARE BRACKET WITH DOUBLE STROKE +@ Parentheses top and bottom halves +@+ These are used in pairs in extended IPA to indicate dubious phonemes or questionable presence of a sound. +2E59 TOP HALF LEFT PARENTHESIS +2E5A TOP HALF RIGHT PARENTHESIS +2E5B BOTTOM HALF LEFT PARENTHESIS +2E5C BOTTOM HALF RIGHT PARENTHESIS +@ Oblique hyphen +@+ The oblique hyphen is historic punctuation seen in some medieval and Renaissance manuscripts. In some modern lexicography an oblique hyphen is used distinctly to indicate hyphenation which is retained when a word is not broken at a line boundary. +2E5D OBLIQUE HYPHEN + x (hyphen - 2010) + x (double oblique hyphen - 2E17) @@ 2E80 CJK Radicals Supplement 2EFF @+ For the characters in this block whose representative glyph takes up only a portion of the em-box, the placement relative to the em-box is either centered or respects prototypical usage. The placement of the representative glyph is for informational purposes only, and should not be considered a recommendation for implementations. @ CJK radicals supplement @@ -19030,7 +19455,9 @@ 2E94 CJK RADICAL SNOUT ONE x 5F51 2E95 CJK RADICAL SNOUT TWO + * actually a form of the radical for hand, despite its resemblance in shape to the radical for snout x 5F50 + x 2B739 2E96 CJK RADICAL HEART ONE * form used on left side x 5FC4 @@ -19077,6 +19504,7 @@ x 4E2C 2EA7 CJK RADICAL COW x 725B + x 20092 2EA8 CJK RADICAL DOG * form used on left side x 72AD @@ -19777,6 +20205,7 @@ * substitute for ideograph not in font * editorial convention to represent ideographic lacuna x (white square - 25A1) + x (heavy equals sign - 1F7F0) @ CJK brackets 3014 LEFT TORTOISE SHELL BRACKET 3015 RIGHT TORTOISE SHELL BRACKET @@ -21681,6 +22110,7 @@ 33D6 SQUARE MOL # 006D 006F 006C 33D7 SQUARE PH + * casing inconsistency in the compatibility decomposition is a known anomaly dating from glyph presentations in very early versions of the standard # 0050 0048 33D8 SQUARE PM # 0070 002E 006D 002E @@ -21831,7 +22261,7 @@ 4DFD HEXAGRAM FOR SMALL PREPONDERANCE 4DFE HEXAGRAM FOR AFTER COMPLETION 4DFF HEXAGRAM FOR BEFORE COMPLETION -@@ 4E00 CJK Unified Ideographs 9FFC +@@ 4E00 CJK Unified Ideographs 9FFF @@ A000 Yi Syllables A48F @@+ @ Syllables @@ -23778,6 +24208,7 @@ A72F LATIN SMALL LETTER CUATRILLO WITH COMMA A730 LATIN LETTER SMALL CAPITAL F A731 LATIN LETTER SMALL CAPITAL S A732 LATIN CAPITAL LETTER AA + x (modifier letter small capital aa - 10780) A733 LATIN SMALL LETTER AA A734 LATIN CAPITAL LETTER AO A735 LATIN SMALL LETTER AO @@ -23963,6 +24394,7 @@ A7AE LATIN CAPITAL LETTER SMALL CAPITAL I @ Letter for Japanese phonemic transcription A7AF LATIN LETTER SMALL CAPITAL Q * used to represent gemination + x (modifier letter capital q - A7F4) @ Letters for Americanist orthographies A7B0 LATIN CAPITAL LETTER TURNED K * lowercase is 029E @@ -23983,7 +24415,7 @@ A7B5 LATIN SMALL LETTER BETA A7B6 LATIN CAPITAL LETTER OMEGA A7B7 LATIN SMALL LETTER OMEGA x (greek small letter omega - 03C9) -@ Letters for Mazahua (Mexico) +@ Letters for Mazahua (México) A7B8 LATIN CAPITAL LETTER U WITH STROKE A7B9 LATIN SMALL LETTER U WITH STROKE @ Letters for Ugaritic and Egyptological transliteration @@ -23997,7 +24429,11 @@ A7BD LATIN SMALL LETTER GLOTTAL I x (latin small letter egyptological ain - A725) A7BE LATIN CAPITAL LETTER GLOTTAL U A7BF LATIN SMALL LETTER GLOTTAL U -@ Additional letters +@ Additional medieval letters +A7C0 LATIN CAPITAL LETTER OLD POLISH O +A7C1 LATIN SMALL LETTER OLD POLISH O + * used in Old Polish as a nasal vowel + x (latin small letter o with stroke - 00F8) A7C2 LATIN CAPITAL LETTER ANGLICANA W A7C3 LATIN SMALL LETTER ANGLICANA W * used in medieval English and Cornish @@ -24015,6 +24451,31 @@ A7C8 LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY * indicates a dental affricate A7C9 LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CA LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +@ Letters used in the Middle English Ormulum +A7D0 LATIN CAPITAL LETTER CLOSED INSULAR G +A7D1 LATIN SMALL LETTER CLOSED INSULAR G + x (latin small letter insular g - 1D79) +A7D3 LATIN SMALL LETTER DOUBLE THORN + x (latin small letter thorn - 00FE) +A7D5 LATIN SMALL LETTER DOUBLE WYNN + x (latin letter wynn - 01BF) +@ Letters used in medieval palaeography +A7D6 LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D7 LATIN SMALL LETTER MIDDLE SCOTS S + * used in Middle Scots for s, ss, ser, sir, is, sis, etc. + x (latin small letter sharp s - 00DF) +A7D8 LATIN CAPITAL LETTER SIGMOID S +A7D9 LATIN SMALL LETTER SIGMOID S + * used in Middle Cornish, Middle English, and Middle Scots +@ Modifier letters for Chatino (México) +A7F2 MODIFIER LETTER CAPITAL C + # 0043 +A7F3 MODIFIER LETTER CAPITAL F + # 0046 +@ Modifier letter for Japanese phonemic transcription +A7F4 MODIFIER LETTER CAPITAL Q + x (latin letter small capital q - A7AF) + # 0051 @ Ancient Gaulish and Celtic epigraphic letters A7F5 LATIN CAPITAL LETTER REVERSED HALF H = H dimidié @@ -24026,7 +24487,7 @@ A7F7 LATIN EPIGRAPHIC LETTER SIDEWAYS I @ Additions for Extended IPA A7F8 MODIFIER LETTER CAPITAL H WITH STROKE # 0126 -@+ A typographical distinction between a capital form and a small capital form is not distinctive for this IPA usage. +@+ A typographical distinction between a capital form and a small capital form is not distinctive for this character in IPA usage. * faucalized x (latin letter small capital h - 029C) A7F9 MODIFIER LETTER SMALL LIGATURE OE @@ -24116,7 +24577,7 @@ A838 NORTH INDIC RUPEE MARK A839 NORTH INDIC QUANTITY MARK * a unit mark for various weights and measures @@ A840 Phags-pa A87F -@+ Phags-pa letters are used for Mongolian, Chinese, Uighur, Tibetan, and Sanskrit unless annotated with a more restricted list of languages. +@+ Phags-pa letters are used for Mongolian, Chinese, Uyghur, Tibetan, and Sanskrit unless annotated with a more restricted list of languages. @ Consonants A840 PHAGS-PA LETTER KA * Mongolian, Chinese, Tibetan, Sanskrit @@ -24132,10 +24593,10 @@ A844 PHAGS-PA LETTER CA * Chinese, Tibetan x (tibetan letter ca - 0F45) A845 PHAGS-PA LETTER CHA - * Mongolian, Chinese, Uighur, Tibetan + * Mongolian, Chinese, Uyghur, Tibetan x (tibetan letter cha - 0F46) A846 PHAGS-PA LETTER JA - * Mongolian, Chinese, Uighur, Tibetan + * Mongolian, Chinese, Uyghur, Tibetan x (tibetan letter ja - 0F47) A847 PHAGS-PA LETTER NYA * Chinese, Tibetan, Sanskrit @@ -24182,7 +24643,7 @@ A856 PHAGS-PA LETTER SMALL A A857 PHAGS-PA LETTER YA x (tibetan letter ya - 0F61) A858 PHAGS-PA LETTER RA - * Mongolian, Uighur, Tibetan, Sanskrit + * Mongolian, Uyghur, Tibetan, Sanskrit x (tibetan letter ra - 0F62) A859 PHAGS-PA LETTER LA x (tibetan letter la - 0F63) @@ -24210,18 +24671,18 @@ A861 PHAGS-PA LETTER O x (tibetan vowel sign o - 0F7C) @ Consonants A862 PHAGS-PA LETTER QA - * Mongolian, Uighur + * Mongolian, Uyghur A863 PHAGS-PA LETTER XA * Mongolian, Chinese A864 PHAGS-PA LETTER FA - * Chinese, Uighur + * Chinese, Uyghur x (phags-pa letter ha - A85C) A865 PHAGS-PA LETTER GGA * language usage unknown * created by reversal of A862 @ Vowel A866 PHAGS-PA LETTER EE - * Mongolian, Chinese, Uighur + * Mongolian, Chinese, Uyghur @ Subjoined consonants A867 PHAGS-PA SUBJOINED LETTER WA * Chinese, Tibetan, Sanskrit @@ -24497,11 +24958,13 @@ A91E KAYAH LI LETTER THA A91F KAYAH LI LETTER HA A920 KAYAH LI LETTER VA A921 KAYAH LI LETTER CA +@ Vowels A922 KAYAH LI LETTER A + * serves as a vowel carrier for vowels indicated with combining marks A923 KAYAH LI LETTER OE + * also serves as a vowel carrier A924 KAYAH LI LETTER I A925 KAYAH LI LETTER OO -@ Vowels A926 KAYAH LI VOWEL UE A927 KAYAH LI VOWEL E A928 KAYAH LI VOWEL U @@ -24607,7 +25070,9 @@ A980 JAVANESE SIGN PANYANGGA A981 JAVANESE SIGN CECAK = anusvara A982 JAVANESE SIGN LAYAR - = repha + = final r + * also used for repha in transliteration of Kawi + x (balinese sign surang - 1B03) A983 JAVANESE SIGN WIGNYAN = visarga @ Letters @@ -24643,6 +25108,7 @@ A996 JAVANESE LETTER CA MURDA A997 JAVANESE LETTER JA A998 JAVANESE LETTER NYA MURDA = jnya + x (balinese letter archaic jnya - 1B4C) A999 JAVANESE LETTER JA MAHAPRANA = jha A99A JAVANESE LETTER NYA @@ -24902,6 +25368,7 @@ AA6C MYANMAR LETTER KHAMTI SA ~ AA6C FE00 dotted form AA6D MYANMAR LETTER KHAMTI HA AA6E MYANMAR LETTER KHAMTI HHA + % MYANMAR LETTER KHAMTI LLA AA6F MYANMAR LETTER KHAMTI FA ~ AA6F FE00 dotted form AA70 MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION @@ -25573,7 +26040,7 @@ F92B CJK COMPATIBILITY IDEOGRAPH-F92B : 72FC F92C CJK COMPATIBILITY IDEOGRAPH-F92C * a mapping change removed the original K0 source - x (cjk unified ideograph-90DE - 90DE) + x 90DE x (cjk compatibility ideograph-FA2E - FA2E) : 90CE F92D CJK COMPATIBILITY IDEOGRAPH-F92D @@ -25856,7 +26323,7 @@ F9B7 CJK COMPATIBILITY IDEOGRAPH-F9B7 : 91B4 F9B8 CJK COMPATIBILITY IDEOGRAPH-F9B8 * a mapping change removed the original K0 source - x (cjk unified ideograph-96B7 - 96B7) + x 96B7 x (cjk compatibility ideograph-FA2F - FA2F) : 96B8 F9B9 CJK COMPATIBILITY IDEOGRAPH-F9B9 @@ -26792,6 +27259,8 @@ FBC0 ARABIC SYMBOL SMALL TAH ABOVE * Urdu FBC1 ARABIC SYMBOL SMALL TAH BELOW * Urdu +FBC2 ARABIC SYMBOL WASLA ABOVE + x (arabic letter alef wasla - 0671) @ Glyphs for contextual forms of letters for Central Asian languages FBD3 ARABIC LETTER NG ISOLATED FORM # 06AD @@ -27525,6 +27994,29 @@ FD3D ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM @+ These parentheses also do not have compatibility decompositions and should not be considered presentation forms. FD3E ORNATE LEFT PARENTHESIS FD3F ORNATE RIGHT PARENTHESIS +@ Honorific word ligatures +FD40 ARABIC LIGATURE RAHIMAHU ALLAAH + x (arabic sign rahmatullah alayhe - 0612) +FD41 ARABIC LIGATURE RADI ALLAAHU ANH + x (arabic sign radi allahou anhu - 0613) +FD42 ARABIC LIGATURE RADI ALLAAHU ANHAA +FD43 ARABIC LIGATURE RADI ALLAAHU ANHUM +FD44 ARABIC LIGATURE RADI ALLAAHU ANHUMAA +FD45 ARABIC LIGATURE RADI ALLAAHU ANHUNNA +FD46 ARABIC LIGATURE SALLALLAAHU ALAYHI WA-AALIH + x (arabic ligature sallallahou alayhe wasallam - FDFA) +FD47 ARABIC LIGATURE ALAYHI AS-SALAAM + x (arabic sign alayhe assallam - 0611) +FD48 ARABIC LIGATURE ALAYHIM AS-SALAAM +FD49 ARABIC LIGATURE ALAYHIMAA AS-SALAAM +FD4A ARABIC LIGATURE ALAYHI AS-SALAATU WAS-SALAAM +FD4B ARABIC LIGATURE QUDDISA SIRRAH +FD4C ARABIC LIGATURE SALLALLAHU ALAYHI WAAALIHEE WA-SALLAM + x (arabic ligature sallallahou alayhe wasallam - FDFA) + x (arabic ligature sallallaahu alayhi wa-aalih - FD46) +FD4D ARABIC LIGATURE ALAYHAA AS-SALAAM +FD4E ARABIC LIGATURE TABAARAKA WA-TAAALAA +FD4F ARABIC LIGATURE RAHIMAHUM ALLAAH @ Ligatures (three elements) FD50 ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM # 062A 062C 0645 @@ -27762,6 +28254,10 @@ FDC6 ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM # 0633 062E 064A FDC7 ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM # 0646 062C 064A +@ Honorific word ligature +FDCF ARABIC LIGATURE SALAAMUHU ALAYNAA + * his blessing on us + * used in Christian texts @ Noncharacters @+ These codes are intended for process-internal uses. FDD0 @@ -27826,9 +28322,11 @@ FDFB ARABIC LIGATURE JALLAJALALOUHOU @ Currency symbol FDFC RIAL SIGN # 0631 06CC 0627 0644 -@ Symbol -@+ The bismillah is treated as an atomic symbol, rather than as a word ligature. It has no decomposition. +@ Honorific word ligatures +@+ These word ligatures have no decompositions. FDFD ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFE ARABIC LIGATURE SUBHAANAHU WA TAAALAA +FDFF ARABIC LIGATURE AZZA WA JALL @@ FE00 Variation Selectors FE0F @ Variation selectors @+ These are combining characters; in conjunction with the preceding character they indicate a predetermined choice of variant glyph. @@ -30023,6 +30521,83 @@ FFFF 10563 CAUCASIAN ALBANIAN LETTER KIW @ Punctuation 1056F CAUCASIAN ALBANIAN CITATION MARK +@@ 10570 Vithkuqi 105BF +@ Capital letters +10570 VITHKUQI CAPITAL LETTER A +10571 VITHKUQI CAPITAL LETTER BBE +10572 VITHKUQI CAPITAL LETTER BE +10573 VITHKUQI CAPITAL LETTER CE +10574 VITHKUQI CAPITAL LETTER CHE +10575 VITHKUQI CAPITAL LETTER DE +10576 VITHKUQI CAPITAL LETTER DHE +10577 VITHKUQI CAPITAL LETTER EI +10578 VITHKUQI CAPITAL LETTER E +10579 VITHKUQI CAPITAL LETTER FE +1057A VITHKUQI CAPITAL LETTER GA +1057C VITHKUQI CAPITAL LETTER HA +1057D VITHKUQI CAPITAL LETTER HHA + * used in 19th-century orthography +1057E VITHKUQI CAPITAL LETTER I +1057F VITHKUQI CAPITAL LETTER IJE + * used in 19th-century orthography +10580 VITHKUQI CAPITAL LETTER JE +10581 VITHKUQI CAPITAL LETTER KA +10582 VITHKUQI CAPITAL LETTER LA +10583 VITHKUQI CAPITAL LETTER LLA +10584 VITHKUQI CAPITAL LETTER ME +10585 VITHKUQI CAPITAL LETTER NE +10586 VITHKUQI CAPITAL LETTER NJE +10587 VITHKUQI CAPITAL LETTER O +10588 VITHKUQI CAPITAL LETTER PE +10589 VITHKUQI CAPITAL LETTER QA +1058A VITHKUQI CAPITAL LETTER RE +1058C VITHKUQI CAPITAL LETTER SE +1058D VITHKUQI CAPITAL LETTER SHE +1058E VITHKUQI CAPITAL LETTER TE +1058F VITHKUQI CAPITAL LETTER THE +10590 VITHKUQI CAPITAL LETTER U +10591 VITHKUQI CAPITAL LETTER VE +10592 VITHKUQI CAPITAL LETTER XE +10594 VITHKUQI CAPITAL LETTER Y +10595 VITHKUQI CAPITAL LETTER ZE +@ Small letters +10597 VITHKUQI SMALL LETTER A +10598 VITHKUQI SMALL LETTER BBE +10599 VITHKUQI SMALL LETTER BE +1059A VITHKUQI SMALL LETTER CE +1059B VITHKUQI SMALL LETTER CHE +1059C VITHKUQI SMALL LETTER DE +1059D VITHKUQI SMALL LETTER DHE +1059E VITHKUQI SMALL LETTER EI +1059F VITHKUQI SMALL LETTER E +105A0 VITHKUQI SMALL LETTER FE +105A1 VITHKUQI SMALL LETTER GA +105A3 VITHKUQI SMALL LETTER HA +105A4 VITHKUQI SMALL LETTER HHA + * used in 19th-century orthography +105A5 VITHKUQI SMALL LETTER I +105A6 VITHKUQI SMALL LETTER IJE + * used in 19th-century orthography +105A7 VITHKUQI SMALL LETTER JE +105A8 VITHKUQI SMALL LETTER KA +105A9 VITHKUQI SMALL LETTER LA +105AA VITHKUQI SMALL LETTER LLA +105AB VITHKUQI SMALL LETTER ME +105AC VITHKUQI SMALL LETTER NE +105AD VITHKUQI SMALL LETTER NJE +105AE VITHKUQI SMALL LETTER O +105AF VITHKUQI SMALL LETTER PE +105B0 VITHKUQI SMALL LETTER QA +105B1 VITHKUQI SMALL LETTER RE +105B3 VITHKUQI SMALL LETTER SE +105B4 VITHKUQI SMALL LETTER SHE +105B5 VITHKUQI SMALL LETTER TE +105B6 VITHKUQI SMALL LETTER THE +105B7 VITHKUQI SMALL LETTER U +105B8 VITHKUQI SMALL LETTER VE +105B9 VITHKUQI SMALL LETTER XE +105BB VITHKUQI SMALL LETTER Y +105BC VITHKUQI SMALL LETTER ZE @@ 10600 Linear A 1077F @ Simple signs 10600 LINEAR A SIGN AB001 @@ -30574,6 +31149,124 @@ FFFF * 10668 a316, 10601 ab002 10767 LINEAR A SIGN A807 * 10668 a316, 10742 a703 d +@@ 10780 Latin Extended-F 107BF +@ Modifier letter for VoQS +10780 MODIFIER LETTER SMALL CAPITAL AA + * actually a small capital in VoQS (voice quality symbol) usage, with no semantic distinction from a full capital + x (latin capital letter aa - A732) +@ Modifier letters for IPA +10781 MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON + # 02D0 +10782 MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON + # 02D1 +10783 MODIFIER LETTER SMALL AE + # 00E6 +10784 MODIFIER LETTER SMALL CAPITAL B + # 0299 +10785 MODIFIER LETTER SMALL B WITH HOOK + # 0253 +10787 MODIFIER LETTER SMALL DZ DIGRAPH + # 02A3 +10788 MODIFIER LETTER SMALL DZ DIGRAPH WITH RETROFLEX HOOK + # AB66 +10789 MODIFIER LETTER SMALL DZ DIGRAPH WITH CURL + # 02A5 +1078A MODIFIER LETTER SMALL DEZH DIGRAPH + # 02A4 +1078B MODIFIER LETTER SMALL D WITH TAIL + # 0256 +1078C MODIFIER LETTER SMALL D WITH HOOK + # 0257 +1078D MODIFIER LETTER SMALL D WITH HOOK AND TAIL + # 1D91 +1078E MODIFIER LETTER SMALL REVERSED E + # 0258 +1078F MODIFIER LETTER SMALL CLOSED REVERSED OPEN E + # 025E +10790 MODIFIER LETTER SMALL FENG DIGRAPH + # 02A9 +10791 MODIFIER LETTER SMALL RAMS HORN + # 0264 +10792 MODIFIER LETTER SMALL CAPITAL G + # 0262 +10793 MODIFIER LETTER SMALL G WITH HOOK + # 0260 +10794 MODIFIER LETTER SMALL CAPITAL G WITH HOOK + # 029B +10795 MODIFIER LETTER SMALL H WITH STROKE + # 0127 +10796 MODIFIER LETTER SMALL CAPITAL H + # 029C +10797 MODIFIER LETTER SMALL HENG WITH HOOK + # 0267 +10798 MODIFIER LETTER SMALL DOTLESS J WITH STROKE AND HOOK + # 0284 +10799 MODIFIER LETTER SMALL LS DIGRAPH + # 02AA +1079A MODIFIER LETTER SMALL LZ DIGRAPH + # 02AB +1079B MODIFIER LETTER SMALL L WITH BELT + # 026C +1079C MODIFIER LETTER SMALL CAPITAL L WITH BELT + # 1DF04 +1079D MODIFIER LETTER SMALL L WITH RETROFLEX HOOK AND BELT + # A78E +1079E MODIFIER LETTER SMALL LEZH + # 026E +1079F MODIFIER LETTER SMALL LEZH WITH RETROFLEX HOOK + # 1DF05 +107A0 MODIFIER LETTER SMALL TURNED Y + # 028E +107A1 MODIFIER LETTER SMALL TURNED Y WITH BELT + # 1DF06 +107A2 MODIFIER LETTER SMALL O WITH STROKE + # 00F8 +107A3 MODIFIER LETTER SMALL CAPITAL OE + # 0276 +107A4 MODIFIER LETTER SMALL CLOSED OMEGA + # 0277 +107A5 MODIFIER LETTER SMALL Q + # 0071 +107A6 MODIFIER LETTER SMALL TURNED R WITH LONG LEG + # 027A +107A7 MODIFIER LETTER SMALL TURNED R WITH LONG LEG AND RETROFLEX HOOK + # 1DF08 +107A8 MODIFIER LETTER SMALL R WITH TAIL + # 027D +107A9 MODIFIER LETTER SMALL R WITH FISHHOOK + # 027E +107AA MODIFIER LETTER SMALL CAPITAL R + # 0280 +107AB MODIFIER LETTER SMALL TC DIGRAPH WITH CURL + # 02A8 +107AC MODIFIER LETTER SMALL TS DIGRAPH + # 02A6 +107AD MODIFIER LETTER SMALL TS DIGRAPH WITH RETROFLEX HOOK + # AB67 +107AE MODIFIER LETTER SMALL TESH DIGRAPH + # 02A7 +107AF MODIFIER LETTER SMALL T WITH RETROFLEX HOOK + # 0288 +107B0 MODIFIER LETTER SMALL V WITH RIGHT HOOK + # 2C71 +107B2 MODIFIER LETTER SMALL CAPITAL Y + # 028F +107B3 MODIFIER LETTER GLOTTAL STOP WITH STROKE + # 02A1 +107B4 MODIFIER LETTER REVERSED GLOTTAL STOP WITH STROKE + # 02A2 +107B5 MODIFIER LETTER BILABIAL CLICK + # 0298 +107B6 MODIFIER LETTER DENTAL CLICK + # 01C0 +107B7 MODIFIER LETTER LATERAL CLICK + # 01C1 +107B8 MODIFIER LETTER ALVEOLAR CLICK + # 01C2 +107B9 MODIFIER LETTER RETROFLEX CLICK WITH RETROFLEX HOOK + # 1DF0A +107BA MODIFIER LETTER SMALL S WITH CURL + # 1DF1E @@ 10800 Cypriot Syllabary 1083F @ Syllables 10800 CYPRIOT SYLLABLE A @@ -31653,6 +32346,7 @@ FFFF 10C47 OLD TURKIC LETTER ORKHON OT 10C48 OLD TURKIC LETTER ORKHON BASH @@ 10C80 Old Hungarian 10CFF +@+ This script has contemporary usage in Hungary, where users often prefer the name Szekely-Hungarian Rovas. @ Uppercase letters @+ The use of uppercase letters is a modern innovation. 10C80 OLD HUNGARIAN CAPITAL LETTER A @@ -31840,6 +32534,7 @@ FFFF * in earlier literature called "tprus" (later recognized as an abbreviation for "temperius") 10CF2 OLD HUNGARIAN SMALL LETTER US @ Numbers +@+ The numbers for one, five, and ten have a clear relationship to Roman numerals. 10CFA OLD HUNGARIAN NUMBER ONE 10CFB OLD HUNGARIAN NUMBER FIVE 10CFC OLD HUNGARIAN NUMBER TEN @@ -32005,6 +32700,12 @@ FFFF @ Historical letters with diacritics 10EB0 YEZIDI LETTER LAM WITH DOT ABOVE 10EB1 YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +@@ 10EC0 Arabic Extended-C 10EFF +@ Quranic marks used in Turkey +10EFD ARABIC SMALL LOW WORD SAKTA + x (arabic small high word sakta - 08DD) +10EFE ARABIC SMALL LOW WORD QASR +10EFF ARABIC SMALL LOW WORD MADDA @@ 10F00 Old Sogdian 10F2F @+ This block unifies the scripts used in the Ancient Letters and the Kultobe and Upper Indus inscriptions. @ Letters @@ -32107,6 +32808,37 @@ FFFF 10F57 SOGDIAN PUNCTUATION CIRCLE WITH DOT 10F58 SOGDIAN PUNCTUATION TWO CIRCLES WITH DOTS 10F59 SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +@@ 10F70 Old Uyghur 10FAF +@ Letters +10F70 OLD UYGHUR LETTER ALEPH +10F71 OLD UYGHUR LETTER BETH +10F72 OLD UYGHUR LETTER GIMEL-HETH +10F73 OLD UYGHUR LETTER WAW +10F74 OLD UYGHUR LETTER ZAYIN +10F75 OLD UYGHUR LETTER FINAL HETH +10F76 OLD UYGHUR LETTER YODH +10F77 OLD UYGHUR LETTER KAPH +10F78 OLD UYGHUR LETTER LAMEDH +10F79 OLD UYGHUR LETTER MEM +10F7A OLD UYGHUR LETTER NUN +10F7B OLD UYGHUR LETTER SAMEKH +10F7C OLD UYGHUR LETTER PE +10F7D OLD UYGHUR LETTER SADHE +10F7E OLD UYGHUR LETTER RESH +10F7F OLD UYGHUR LETTER SHIN +10F80 OLD UYGHUR LETTER TAW +10F81 OLD UYGHUR LETTER LESH + = hooked resh +@ Combining signs +10F82 OLD UYGHUR COMBINING DOT ABOVE +10F83 OLD UYGHUR COMBINING DOT BELOW +10F84 OLD UYGHUR COMBINING TWO DOTS ABOVE +10F85 OLD UYGHUR COMBINING TWO DOTS BELOW +@ Punctuation +10F86 OLD UYGHUR PUNCTUATION BAR +10F87 OLD UYGHUR PUNCTUATION TWO BARS +10F88 OLD UYGHUR PUNCTUATION TWO DOTS +10F89 OLD UYGHUR PUNCTUATION FOUR DOTS @@ 10FB0 Chorasmian 10FDF @+ This script is also known as 'Khwarezmian', from its classical Persian name xvārazm. @ Letters @@ -32283,6 +33015,17 @@ FFFF 1106D BRAHMI DIGIT SEVEN 1106E BRAHMI DIGIT EIGHT 1106F BRAHMI DIGIT NINE +@ Virama +@+ The Old Tamil virama and the other Old Tamil characters below are extensions used in Brahmi when writing Old Tamil. +11070 BRAHMI SIGN OLD TAMIL VIRAMA +@ Independent vowels +11071 BRAHMI LETTER OLD TAMIL SHORT E +11072 BRAHMI LETTER OLD TAMIL SHORT O +@ Dependent vowel signs +11073 BRAHMI VOWEL SIGN OLD TAMIL SHORT E +11074 BRAHMI VOWEL SIGN OLD TAMIL SHORT O +@ Consonant +11075 BRAHMI LETTER OLD TAMIL LLA @ Number joiner 1107F BRAHMI NUMBER JOINER * a virama used to form ligatures between Brahmi numbers signifying multiplication @@ -32369,6 +33112,8 @@ FFFF x (khojki double section mark - 1123C) 110C0 KAITHI DANDA 110C1 KAITHI DOUBLE DANDA +@ Vowel sign +110C2 KAITHI VOWEL SIGN VOCALIC R @ Sign 110CD KAITHI NUMBER SIGN ABOVE * used to indicate a number in an itemized list @@ -32774,6 +33519,12 @@ FFFF @ Sign 1123E KHOJKI SIGN SUKUN * used for Arabic transliteration +@ Consonant +1123F KHOJKI LETTER QA +@ Independent vowel +11240 KHOJKI LETTER SHORT I +@ Dependent vowel sign +11241 KHOJKI VOWEL SIGN VOCALIC R @@ 11280 Multani 112AF @ Vowels 11280 MULTANI LETTER A @@ -33531,6 +34282,10 @@ FFFF @ Consonant 116B8 TAKRI LETTER ARCHAIC KHA * used in earlier writings to denote kha +@ Punctuation +116B9 TAKRI ABBREVIATION SIGN + x (gurmukhi abbreviation sign - 0A76) + x (sharada abbreviation sign - 111C7) @ Digits 116C0 TAKRI DIGIT ZERO 116C1 TAKRI DIGIT ONE @@ -33542,7 +34297,7 @@ FFFF 116C7 TAKRI DIGIT SEVEN 116C8 TAKRI DIGIT EIGHT 116C9 TAKRI DIGIT NINE -@@ 11700 Ahom 1173F +@@ 11700 Ahom 1174F @ Consonants 11700 AHOM LETTER KA 11701 AHOM LETTER KHA @@ -33607,6 +34362,14 @@ FFFF 1173D AHOM SIGN SECTION 1173E AHOM SIGN RULAI 1173F AHOM SYMBOL VI +@ Additional consonants +11740 AHOM LETTER CA +11741 AHOM LETTER TTA +11742 AHOM LETTER TTHA +11743 AHOM LETTER DDA +11744 AHOM LETTER DDHA +11745 AHOM LETTER NNA +11746 AHOM LETTER LLA @@ 11800 Dogra 1184F @ Independent vowels 11800 DOGRA LETTER A @@ -34168,6 +34931,29 @@ FFFF 11AA1 SOYOMBO TERMINAL MARK-1 11AA2 SOYOMBO TERMINAL MARK-2 = cintamani, candamani +@@ 11AB0 Unified Canadian Aboriginal Syllabics Extended-A 11ABF +@ Syllables for Nattilik +11AB0 CANADIAN SYLLABICS NATTILIK HI +11AB1 CANADIAN SYLLABICS NATTILIK HII +11AB2 CANADIAN SYLLABICS NATTILIK HO + * Nattilik (HU) +11AB3 CANADIAN SYLLABICS NATTILIK HOO + * Nattilik (HUU) +11AB4 CANADIAN SYLLABICS NATTILIK HA +11AB5 CANADIAN SYLLABICS NATTILIK HAA +11AB6 CANADIAN SYLLABICS NATTILIK SHRI +11AB7 CANADIAN SYLLABICS NATTILIK SHRII +11AB8 CANADIAN SYLLABICS NATTILIK SHRO + * Nattilik (SHRU) +11AB9 CANADIAN SYLLABICS NATTILIK SHROO + * Nattilik (SHRUU) +11ABA CANADIAN SYLLABICS NATTILIK SHRA +11ABB CANADIAN SYLLABICS NATTILIK SHRAA +@ Historic syllables for Cree and Ojibway +11ABC CANADIAN SYLLABICS SPE +11ABD CANADIAN SYLLABICS SPI +11ABE CANADIAN SYLLABICS SPO +11ABF CANADIAN SYLLABICS SPA @@ 11AC0 Pau Cin Hau 11AFF @ Consonants 11AC0 PAU CIN HAU LETTER PA @@ -34230,6 +35016,22 @@ FFFF 11AF6 PAU CIN HAU LOW-FALLING TONE LONG FINAL 11AF7 PAU CIN HAU LOW-FALLING TONE FINAL 11AF8 PAU CIN HAU GLOTTAL STOP FINAL +@@ 11B00 Devanagari Extended-A 11B5F +@ Head marks +11B00 DEVANAGARI HEAD MARK + x (devanagari double danda - 0965) +11B01 DEVANAGARI HEAD MARK WITH HEADSTROKE +@ Auspicious signs +@+ These are used for representing bhale mīndu signs. +11B02 DEVANAGARI SIGN BHALE +11B03 DEVANAGARI SIGN BHALE WITH HOOK +11B04 DEVANAGARI SIGN EXTENDED BHALE +11B05 DEVANAGARI SIGN EXTENDED BHALE WITH HOOK +11B06 DEVANAGARI SIGN WESTERN FIVE-LIKE BHALE +11B07 DEVANAGARI SIGN WESTERN NINE-LIKE BHALE +11B08 DEVANAGARI SIGN REVERSED NINE-LIKE BHALE +11B09 DEVANAGARI SIGN MINDU + x (devanagari digit zero - 0966) @@ 11C00 Bhaiksuki 11C6F @ Independent vowels 11C00 BHAIKSUKI LETTER A @@ -34604,6 +35406,106 @@ FFFF @ Punctuation 11EF7 MAKASAR PASSIMBANG 11EF8 MAKASAR END OF SECTION +@@ 11F00 Kawi 11F5F +@ Signs +11F00 KAWI SIGN CANDRABINDU +11F01 KAWI SIGN ANUSVARA +11F02 KAWI SIGN REPHA + * cluster-initial form of 11F2C + * also used as final r +11F03 KAWI SIGN VISARGA +@ Independent vowels +11F04 KAWI LETTER A +11F05 KAWI LETTER AA +11F06 KAWI LETTER I +11F07 KAWI LETTER II +11F08 KAWI LETTER U +11F09 KAWI LETTER UU +11F0A KAWI LETTER VOCALIC R +11F0B KAWI LETTER VOCALIC RR +11F0C KAWI LETTER VOCALIC L +11F0D KAWI LETTER VOCALIC LL +11F0E KAWI LETTER E +11F0F KAWI LETTER AI +11F10 KAWI LETTER O +@ Consonants +11F12 KAWI LETTER KA +11F13 KAWI LETTER KHA +11F14 KAWI LETTER GA +11F15 KAWI LETTER GHA +11F16 KAWI LETTER NGA +11F17 KAWI LETTER CA +11F18 KAWI LETTER CHA +11F19 KAWI LETTER JA +11F1A KAWI LETTER JHA +11F1B KAWI LETTER NYA +11F1C KAWI LETTER TTA +11F1D KAWI LETTER TTHA +11F1E KAWI LETTER DDA +11F1F KAWI LETTER DDHA +11F20 KAWI LETTER NNA +11F21 KAWI LETTER TA +11F22 KAWI LETTER THA +11F23 KAWI LETTER DA +11F24 KAWI LETTER DHA +11F25 KAWI LETTER NA +11F26 KAWI LETTER PA +11F27 KAWI LETTER PHA +11F28 KAWI LETTER BA +11F29 KAWI LETTER BHA +11F2A KAWI LETTER MA +11F2B KAWI LETTER YA +11F2C KAWI LETTER RA +11F2D KAWI LETTER LA +11F2E KAWI LETTER WA +11F2F KAWI LETTER SHA +11F30 KAWI LETTER SSA +11F31 KAWI LETTER SA +11F32 KAWI LETTER HA +11F33 KAWI LETTER JNYA +@ Dependent vowel signs +11F34 KAWI VOWEL SIGN AA +11F35 KAWI VOWEL SIGN ALTERNATE AA +11F36 KAWI VOWEL SIGN I +11F37 KAWI VOWEL SIGN II +11F38 KAWI VOWEL SIGN U +11F39 KAWI VOWEL SIGN UU +11F3A KAWI VOWEL SIGN VOCALIC R +11F3E KAWI VOWEL SIGN E +11F3F KAWI VOWEL SIGN AI +11F40 KAWI VOWEL SIGN EU + * represents schwa [ǝ] +@ Viramas +11F41 KAWI SIGN KILLER + * vowel killer, always rendered visibly +11F42 KAWI CONJOINER + * used for producing below-base and post-base conjunct forms +@ Punctuation +11F43 KAWI DANDA +11F44 KAWI DOUBLE DANDA +11F45 KAWI PUNCTUATION SECTION MARKER +11F46 KAWI PUNCTUATION ALTERNATE SECTION MARKER +11F47 KAWI PUNCTUATION FLOWER +11F48 KAWI PUNCTUATION SPACE FILLER +11F49 KAWI PUNCTUATION DOT +11F4A KAWI PUNCTUATION DOUBLE DOT +11F4B KAWI PUNCTUATION TRIPLE DOT +11F4C KAWI PUNCTUATION CIRCLE +11F4D KAWI PUNCTUATION FILLED CIRCLE +11F4E KAWI PUNCTUATION SPIRAL +11F4F KAWI PUNCTUATION CLOSING SPIRAL +@ Digits +11F50 KAWI DIGIT ZERO +11F51 KAWI DIGIT ONE +11F52 KAWI DIGIT TWO + * also used as letter ro +11F53 KAWI DIGIT THREE +11F54 KAWI DIGIT FOUR +11F55 KAWI DIGIT FIVE +11F56 KAWI DIGIT SIX +11F57 KAWI DIGIT SEVEN +11F58 KAWI DIGIT EIGHT +11F59 KAWI DIGIT NINE @@ 11FB0 Lisu Supplement 11FBF @ Letter 11FB0 LISU LETTER YHA @@ -35992,6 +36894,108 @@ FFFF 12541 CUNEIFORM SIGN ZA7 12542 CUNEIFORM SIGN ZU OVER ZU PLUS SAR 12543 CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +@@ 12F90 Cypro-Minoan 12FFF +@ Signs +12F90 CYPRO-MINOAN SIGN CM001 +12F91 CYPRO-MINOAN SIGN CM002 +12F92 CYPRO-MINOAN SIGN CM004 +12F93 CYPRO-MINOAN SIGN CM005 +12F94 CYPRO-MINOAN SIGN CM006 +12F95 CYPRO-MINOAN SIGN CM007 +12F96 CYPRO-MINOAN SIGN CM008 +12F97 CYPRO-MINOAN SIGN CM009 +12F98 CYPRO-MINOAN SIGN CM010 +12F99 CYPRO-MINOAN SIGN CM011 +12F9A CYPRO-MINOAN SIGN CM012 +12F9B CYPRO-MINOAN SIGN CM012B +12F9C CYPRO-MINOAN SIGN CM013 +12F9D CYPRO-MINOAN SIGN CM015 +12F9E CYPRO-MINOAN SIGN CM017 +12F9F CYPRO-MINOAN SIGN CM019 +12FA0 CYPRO-MINOAN SIGN CM021 +12FA1 CYPRO-MINOAN SIGN CM023 +12FA2 CYPRO-MINOAN SIGN CM024 +12FA3 CYPRO-MINOAN SIGN CM025 +12FA4 CYPRO-MINOAN SIGN CM026 +12FA5 CYPRO-MINOAN SIGN CM027 +12FA6 CYPRO-MINOAN SIGN CM028 +12FA7 CYPRO-MINOAN SIGN CM029 +12FA8 CYPRO-MINOAN SIGN CM030 +12FA9 CYPRO-MINOAN SIGN CM033 +12FAA CYPRO-MINOAN SIGN CM034 +12FAB CYPRO-MINOAN SIGN CM035 +12FAC CYPRO-MINOAN SIGN CM036 +12FAD CYPRO-MINOAN SIGN CM037 +12FAE CYPRO-MINOAN SIGN CM038 +12FAF CYPRO-MINOAN SIGN CM039 +12FB0 CYPRO-MINOAN SIGN CM040 +12FB1 CYPRO-MINOAN SIGN CM041 +12FB2 CYPRO-MINOAN SIGN CM044 +12FB3 CYPRO-MINOAN SIGN CM046 +12FB4 CYPRO-MINOAN SIGN CM047 +12FB5 CYPRO-MINOAN SIGN CM049 +12FB6 CYPRO-MINOAN SIGN CM050 +12FB7 CYPRO-MINOAN SIGN CM051 +12FB8 CYPRO-MINOAN SIGN CM052 +12FB9 CYPRO-MINOAN SIGN CM053 +12FBA CYPRO-MINOAN SIGN CM054 +12FBB CYPRO-MINOAN SIGN CM055 +12FBC CYPRO-MINOAN SIGN CM056 +12FBD CYPRO-MINOAN SIGN CM058 +12FBE CYPRO-MINOAN SIGN CM059 +12FBF CYPRO-MINOAN SIGN CM060 +12FC0 CYPRO-MINOAN SIGN CM061 +12FC1 CYPRO-MINOAN SIGN CM062 +12FC2 CYPRO-MINOAN SIGN CM063 +12FC3 CYPRO-MINOAN SIGN CM064 +12FC4 CYPRO-MINOAN SIGN CM066 +12FC5 CYPRO-MINOAN SIGN CM067 +12FC6 CYPRO-MINOAN SIGN CM068 +12FC7 CYPRO-MINOAN SIGN CM069 +12FC8 CYPRO-MINOAN SIGN CM070 +12FC9 CYPRO-MINOAN SIGN CM071 +12FCA CYPRO-MINOAN SIGN CM072 +12FCB CYPRO-MINOAN SIGN CM073 +12FCC CYPRO-MINOAN SIGN CM074 +12FCD CYPRO-MINOAN SIGN CM075 +12FCE CYPRO-MINOAN SIGN CM075B +12FCF CYPRO-MINOAN SIGN CM076 +12FD0 CYPRO-MINOAN SIGN CM078 +12FD1 CYPRO-MINOAN SIGN CM079 +12FD2 CYPRO-MINOAN SIGN CM080 +12FD3 CYPRO-MINOAN SIGN CM081 +12FD4 CYPRO-MINOAN SIGN CM082 +12FD5 CYPRO-MINOAN SIGN CM083 +12FD6 CYPRO-MINOAN SIGN CM084 +12FD7 CYPRO-MINOAN SIGN CM085 +12FD8 CYPRO-MINOAN SIGN CM086 +12FD9 CYPRO-MINOAN SIGN CM087 +12FDA CYPRO-MINOAN SIGN CM088 +12FDB CYPRO-MINOAN SIGN CM089 +12FDC CYPRO-MINOAN SIGN CM090 +12FDD CYPRO-MINOAN SIGN CM091 +12FDE CYPRO-MINOAN SIGN CM092 +12FDF CYPRO-MINOAN SIGN CM094 +12FE0 CYPRO-MINOAN SIGN CM095 +12FE1 CYPRO-MINOAN SIGN CM096 +12FE2 CYPRO-MINOAN SIGN CM097 +12FE3 CYPRO-MINOAN SIGN CM098 +12FE4 CYPRO-MINOAN SIGN CM099 +12FE5 CYPRO-MINOAN SIGN CM100 +12FE6 CYPRO-MINOAN SIGN CM101 +12FE7 CYPRO-MINOAN SIGN CM102 +12FE8 CYPRO-MINOAN SIGN CM103 +12FE9 CYPRO-MINOAN SIGN CM104 +12FEA CYPRO-MINOAN SIGN CM105 +12FEB CYPRO-MINOAN SIGN CM107 +12FEC CYPRO-MINOAN SIGN CM108 +12FED CYPRO-MINOAN SIGN CM109 +12FEE CYPRO-MINOAN SIGN CM110 +12FEF CYPRO-MINOAN SIGN CM112 +12FF0 CYPRO-MINOAN SIGN CM114 +@ Punctuation +12FF1 CYPRO-MINOAN SIGN CM301 +12FF2 CYPRO-MINOAN SIGN CM302 @@ 13000 Egyptian Hieroglyphs 1342F @+ The characters in this block are taken primarily from Alan Gardiner's works on Middle Egyptian. @ A. Man and his occupations @@ -36091,7 +37095,9 @@ FFFF 1305B EGYPTIAN HIEROGLYPH C002 1305C EGYPTIAN HIEROGLYPH C002A 1305D EGYPTIAN HIEROGLYPH C002B + * mirrored version of 1305C 1305E EGYPTIAN HIEROGLYPH C002C + * mirrored version of 1305B 1305F EGYPTIAN HIEROGLYPH C003 13060 EGYPTIAN HIEROGLYPH C004 13061 EGYPTIAN HIEROGLYPH C005 @@ -36105,8 +37111,10 @@ FFFF * 1,000,000 13069 EGYPTIAN HIEROGLYPH C012 1306A EGYPTIAN HIEROGLYPH C013 + * mirrored version of 13069 1306B EGYPTIAN HIEROGLYPH C014 1306C EGYPTIAN HIEROGLYPH C015 + * mirrored version of 1306B 1306D EGYPTIAN HIEROGLYPH C016 1306E EGYPTIAN HIEROGLYPH C017 1306F EGYPTIAN HIEROGLYPH C018 @@ -36131,6 +37139,8 @@ FFFF 13081 EGYPTIAN HIEROGLYPH D011 * 1/2 13082 EGYPTIAN HIEROGLYPH D012 + * pupil of the eye + * not to be confused with 131F3 or 133F8 * 1/4 13083 EGYPTIAN HIEROGLYPH D013 * 1/8 @@ -36145,6 +37155,8 @@ FFFF 13089 EGYPTIAN HIEROGLYPH D019 1308A EGYPTIAN HIEROGLYPH D020 1308B EGYPTIAN HIEROGLYPH D021 + * mouth + * not to be confused with 133AB * transliterated as r 1308C EGYPTIAN HIEROGLYPH D022 1308D EGYPTIAN HIEROGLYPH D023 @@ -36152,8 +37164,11 @@ FFFF 1308F EGYPTIAN HIEROGLYPH D025 13090 EGYPTIAN HIEROGLYPH D026 13091 EGYPTIAN HIEROGLYPH D027 + ~ 13091 FE00 rotated 90 degrees 13092 EGYPTIAN HIEROGLYPH D027A + ~ 13092 FE00 rotated 90 degrees 13093 EGYPTIAN HIEROGLYPH D028 + ~ 13093 FE01 rotated 180 degrees 13094 EGYPTIAN HIEROGLYPH D029 13095 EGYPTIAN HIEROGLYPH D030 13096 EGYPTIAN HIEROGLYPH D031 @@ -36180,10 +37195,13 @@ FFFF * transliterated as d 130A8 EGYPTIAN HIEROGLYPH D046A 130A9 EGYPTIAN HIEROGLYPH D047 + ~ 130A9 FE01 rotated 180 degrees 130AA EGYPTIAN HIEROGLYPH D048 130AB EGYPTIAN HIEROGLYPH D048A 130AC EGYPTIAN HIEROGLYPH D049 130AD EGYPTIAN HIEROGLYPH D050 + * classifier 'accurate, finger' + * not to be confused with 130B7 * 10,000 130AE EGYPTIAN HIEROGLYPH D050A * 20,000 @@ -36204,12 +37222,16 @@ FFFF 130B6 EGYPTIAN HIEROGLYPH D050I * 50,000 130B7 EGYPTIAN HIEROGLYPH D051 + * classifier 'measure, nail, scratching, taking' + * not to be confused with 130AD 130B8 EGYPTIAN HIEROGLYPH D052 130B9 EGYPTIAN HIEROGLYPH D052A 130BA EGYPTIAN HIEROGLYPH D053 130BB EGYPTIAN HIEROGLYPH D054 + * (forward) motion 130BC EGYPTIAN HIEROGLYPH D054A 130BD EGYPTIAN HIEROGLYPH D055 + * backward motion 130BE EGYPTIAN HIEROGLYPH D056 130BF EGYPTIAN HIEROGLYPH D057 130C0 EGYPTIAN HIEROGLYPH D058 @@ -36224,6 +37246,7 @@ FFFF 130C8 EGYPTIAN HIEROGLYPH D066 130C9 EGYPTIAN HIEROGLYPH D067 * 1 heqat measure + * not to be confused with 13212 130CA EGYPTIAN HIEROGLYPH D067A * 2 heqat measures 130CB EGYPTIAN HIEROGLYPH D067B @@ -36242,7 +37265,10 @@ FFFF * 9 heqat measures @ E. Mammals 130D2 EGYPTIAN HIEROGLYPH E001 + * bull, classifier 'cattle' + * not to be confused with 130FD 130D3 EGYPTIAN HIEROGLYPH E002 + * aggressive bull 130D4 EGYPTIAN HIEROGLYPH E003 130D5 EGYPTIAN HIEROGLYPH E004 130D6 EGYPTIAN HIEROGLYPH E005 @@ -36282,9 +37308,12 @@ FFFF 130F8 EGYPTIAN HIEROGLYPH E033 130F9 EGYPTIAN HIEROGLYPH E034 130FA EGYPTIAN HIEROGLYPH E034A + * stylistic variant, use of 130F9 is preferred 130FB EGYPTIAN HIEROGLYPH E036 130FC EGYPTIAN HIEROGLYPH E037 130FD EGYPTIAN HIEROGLYPH E038 + * cow + * not to be confused with 130D2 @ F. Parts of mammals 130FE EGYPTIAN HIEROGLYPH F001 130FF EGYPTIAN HIEROGLYPH F001A @@ -36301,34 +37330,43 @@ FFFF 1310A EGYPTIAN HIEROGLYPH F012 1310B EGYPTIAN HIEROGLYPH F013 1310C EGYPTIAN HIEROGLYPH F013A + * stylistic variant, use of 1310B is preferred 1310D EGYPTIAN HIEROGLYPH F014 1310E EGYPTIAN HIEROGLYPH F015 1310F EGYPTIAN HIEROGLYPH F016 + ~ 1310F FE00 rotated 90 degrees 13110 EGYPTIAN HIEROGLYPH F017 13111 EGYPTIAN HIEROGLYPH F018 13112 EGYPTIAN HIEROGLYPH F019 13113 EGYPTIAN HIEROGLYPH F020 13114 EGYPTIAN HIEROGLYPH F021 13115 EGYPTIAN HIEROGLYPH F021A + * from hieratic 13116 EGYPTIAN HIEROGLYPH F022 13117 EGYPTIAN HIEROGLYPH F023 + ~ 13117 FE02 rotated 270 degrees 13118 EGYPTIAN HIEROGLYPH F024 + * mirrored version of 13117 13119 EGYPTIAN HIEROGLYPH F025 1311A EGYPTIAN HIEROGLYPH F026 1311B EGYPTIAN HIEROGLYPH F027 1311C EGYPTIAN HIEROGLYPH F028 + ~ 1311C FE00 rotated 90 degrees 1311D EGYPTIAN HIEROGLYPH F029 1311E EGYPTIAN HIEROGLYPH F030 1311F EGYPTIAN HIEROGLYPH F031 13120 EGYPTIAN HIEROGLYPH F031A + * cursive variant of 1311F 13121 EGYPTIAN HIEROGLYPH F032 * transliterated as 1E96 + ~ 13121 FE00 rotated 90 degrees 13122 EGYPTIAN HIEROGLYPH F033 13123 EGYPTIAN HIEROGLYPH F034 13124 EGYPTIAN HIEROGLYPH F035 13125 EGYPTIAN HIEROGLYPH F036 13126 EGYPTIAN HIEROGLYPH F037 13127 EGYPTIAN HIEROGLYPH F037A + ~ 13127 FE00 rotated 90 degrees 13128 EGYPTIAN HIEROGLYPH F038 13129 EGYPTIAN HIEROGLYPH F038A 1312A EGYPTIAN HIEROGLYPH F039 @@ -36341,25 +37379,37 @@ FFFF 13131 EGYPTIAN HIEROGLYPH F045A 13132 EGYPTIAN HIEROGLYPH F046 13133 EGYPTIAN HIEROGLYPH F046A + * rotated version of 13132 13134 EGYPTIAN HIEROGLYPH F047 + * mirrored version of 13132 13135 EGYPTIAN HIEROGLYPH F047A + * mirrored version of 13133 13136 EGYPTIAN HIEROGLYPH F048 13137 EGYPTIAN HIEROGLYPH F049 + * mirrored version of 13136 13138 EGYPTIAN HIEROGLYPH F050 13139 EGYPTIAN HIEROGLYPH F051 + ~ 13139 FE00 rotated 90 degrees + ~ 13139 FE02 rotated 270 degrees 1313A EGYPTIAN HIEROGLYPH F051A 1313B EGYPTIAN HIEROGLYPH F051B + * variant of 1313A 1313C EGYPTIAN HIEROGLYPH F051C + * rotated version of 13139 1313D EGYPTIAN HIEROGLYPH F052 1313E EGYPTIAN HIEROGLYPH F053 @ G. Birds 1313F EGYPTIAN HIEROGLYPH G001 + * Egyptian vulture, Egyptological alef + * not to be confused with 13142 * transliterated as A723 x (hebrew letter alef - 05D0) x (arabic letter alef with hamza above - 0623) 13140 EGYPTIAN HIEROGLYPH G002 13141 EGYPTIAN HIEROGLYPH G003 13142 EGYPTIAN HIEROGLYPH G004 + * phonogram 'tw' + * not to be confused with 1313F 13143 EGYPTIAN HIEROGLYPH G005 13144 EGYPTIAN HIEROGLYPH G006 13145 EGYPTIAN HIEROGLYPH G006A @@ -36400,10 +37450,14 @@ FFFF 13167 EGYPTIAN HIEROGLYPH G035 13168 EGYPTIAN HIEROGLYPH G036 13169 EGYPTIAN HIEROGLYPH G036A + * stylistic variant, use of 13168 is preferred 1316A EGYPTIAN HIEROGLYPH G037 1316B EGYPTIAN HIEROGLYPH G037A + * stylistic variant, use of 1316A is preferred 1316C EGYPTIAN HIEROGLYPH G038 + * goose 1316D EGYPTIAN HIEROGLYPH G039 + * duck 1316E EGYPTIAN HIEROGLYPH G040 1316F EGYPTIAN HIEROGLYPH G041 13170 EGYPTIAN HIEROGLYPH G042 @@ -36428,10 +37482,13 @@ FFFF 13181 EGYPTIAN HIEROGLYPH H003 13182 EGYPTIAN HIEROGLYPH H004 13183 EGYPTIAN HIEROGLYPH H005 + ~ 13183 FE02 rotated 270 degrees 13184 EGYPTIAN HIEROGLYPH H006 13185 EGYPTIAN HIEROGLYPH H006A + * from hieratic 13186 EGYPTIAN HIEROGLYPH H007 13187 EGYPTIAN HIEROGLYPH H008 + ~ 13187 FE01 rotated 180 degrees @ I. Amphibious animals, reptiles, etc. 13188 EGYPTIAN HIEROGLYPH I001 13189 EGYPTIAN HIEROGLYPH I002 @@ -36462,9 +37519,11 @@ FFFF 1319E EGYPTIAN HIEROGLYPH K004 1319F EGYPTIAN HIEROGLYPH K005 131A0 EGYPTIAN HIEROGLYPH K006 + ~ 131A0 FE00 rotated 90 degrees + ~ 131A0 FE02 rotated 270 degrees 131A1 EGYPTIAN HIEROGLYPH K007 131A2 EGYPTIAN HIEROGLYPH K008 -@ L. Invertabrata and lesser animals +@ L. Invertebrata and lesser animals 131A3 EGYPTIAN HIEROGLYPH L001 131A4 EGYPTIAN HIEROGLYPH L002 131A5 EGYPTIAN HIEROGLYPH L002A @@ -36473,6 +37532,7 @@ FFFF 131A8 EGYPTIAN HIEROGLYPH L005 131A9 EGYPTIAN HIEROGLYPH L006 131AA EGYPTIAN HIEROGLYPH L006A + * mirrored version of 131A9 131AB EGYPTIAN HIEROGLYPH L007 131AC EGYPTIAN HIEROGLYPH L008 @ M. Trees and plants @@ -36481,6 +37541,8 @@ FFFF 131AF EGYPTIAN HIEROGLYPH M001B 131B0 EGYPTIAN HIEROGLYPH M002 131B1 EGYPTIAN HIEROGLYPH M003 + ~ 131B1 FE00 rotated 90 degrees + ~ 131B1 FE01 rotated 180 degrees 131B2 EGYPTIAN HIEROGLYPH M003A 131B3 EGYPTIAN HIEROGLYPH M004 131B4 EGYPTIAN HIEROGLYPH M005 @@ -36488,8 +37550,11 @@ FFFF 131B6 EGYPTIAN HIEROGLYPH M007 131B7 EGYPTIAN HIEROGLYPH M008 131B8 EGYPTIAN HIEROGLYPH M009 + ~ 131B8 FE00 rotated 90 degrees 131B9 EGYPTIAN HIEROGLYPH M010 + ~ 131B9 FE00 rotated 90 degrees 131BA EGYPTIAN HIEROGLYPH M010A + ~ 131BA FE02 rotated 270 degrees 131BB EGYPTIAN HIEROGLYPH M011 131BC EGYPTIAN HIEROGLYPH M012 * 1,000 @@ -36516,18 +37581,22 @@ FFFF 131C9 EGYPTIAN HIEROGLYPH M016 131CA EGYPTIAN HIEROGLYPH M016A 131CB EGYPTIAN HIEROGLYPH M017 - * yod + * egyptological yod + * transliterated as A7BD x (hebrew letter yod - 05D9) x (arabic letter yeh - 064A) + ~ 131CB FE00 rotated 90 degrees 131CC EGYPTIAN HIEROGLYPH M017A - * transliterated as y + * phonogram 'y' x (egyptian hieroglyph z004 - 133ED) 131CD EGYPTIAN HIEROGLYPH M018 131CE EGYPTIAN HIEROGLYPH M019 131CF EGYPTIAN HIEROGLYPH M020 131D0 EGYPTIAN HIEROGLYPH M021 131D1 EGYPTIAN HIEROGLYPH M022 + * classifier 'bud, lotus bud' 131D2 EGYPTIAN HIEROGLYPH M022A + *phonogram 'nn' 131D3 EGYPTIAN HIEROGLYPH M023 131D4 EGYPTIAN HIEROGLYPH M024 131D5 EGYPTIAN HIEROGLYPH M024A @@ -36543,41 +37612,65 @@ FFFF 131DF EGYPTIAN HIEROGLYPH M032 131E0 EGYPTIAN HIEROGLYPH M033 131E1 EGYPTIAN HIEROGLYPH M033A + * variant of 131E0 131E2 EGYPTIAN HIEROGLYPH M033B + * variant of 131E0 131E3 EGYPTIAN HIEROGLYPH M034 131E4 EGYPTIAN HIEROGLYPH M035 131E5 EGYPTIAN HIEROGLYPH M036 131E6 EGYPTIAN HIEROGLYPH M037 + * older variant of 131E5 131E7 EGYPTIAN HIEROGLYPH M038 131E8 EGYPTIAN HIEROGLYPH M039 131E9 EGYPTIAN HIEROGLYPH M040 + * phonogram 'js' + * not to be confused with 132A7 or 1342A 131EA EGYPTIAN HIEROGLYPH M040A 131EB EGYPTIAN HIEROGLYPH M041 131EC EGYPTIAN HIEROGLYPH M042 131ED EGYPTIAN HIEROGLYPH M043 131EE EGYPTIAN HIEROGLYPH M044 + * thorn + * not to be confused with 133DA + ~ 131EE FE01 rotated 180 degrees + ~ 131EE FE02 rotated 270 degrees @ N. Sky, earth, water 131EF EGYPTIAN HIEROGLYPH N001 131F0 EGYPTIAN HIEROGLYPH N002 131F1 EGYPTIAN HIEROGLYPH N003 + * older variant of 131F0 131F2 EGYPTIAN HIEROGLYPH N004 131F3 EGYPTIAN HIEROGLYPH N005 + * sun + * not to be confused with 13082 or 133F8 131F4 EGYPTIAN HIEROGLYPH N006 131F5 EGYPTIAN HIEROGLYPH N007 131F6 EGYPTIAN HIEROGLYPH N008 131F7 EGYPTIAN HIEROGLYPH N009 + * variant of 131F8 131F8 EGYPTIAN HIEROGLYPH N010 + * variant of 131F7 + ~ 131F8 FE01 rotated 180 degrees 131F9 EGYPTIAN HIEROGLYPH N011 + ~ 131F9 FE00 rotated 90 degrees + ~ 131F9 FE01 rotated 180 degrees 131FA EGYPTIAN HIEROGLYPH N012 + ~ 131FA FE00 rotated 90 degrees + ~ 131FA FE01 rotated 180 degrees 131FB EGYPTIAN HIEROGLYPH N013 131FC EGYPTIAN HIEROGLYPH N014 131FD EGYPTIAN HIEROGLYPH N015 131FE EGYPTIAN HIEROGLYPH N016 131FF EGYPTIAN HIEROGLYPH N017 + * land + * variant of 131FE 13200 EGYPTIAN HIEROGLYPH N018 + * island + * not to be confused with 132F0, 133D4, or 133F3 13201 EGYPTIAN HIEROGLYPH N018A 13202 EGYPTIAN HIEROGLYPH N018B 13203 EGYPTIAN HIEROGLYPH N019 + * logogram 'akhti' 13204 EGYPTIAN HIEROGLYPH N020 13205 EGYPTIAN HIEROGLYPH N021 13206 EGYPTIAN HIEROGLYPH N022 @@ -36585,10 +37678,13 @@ FFFF 13208 EGYPTIAN HIEROGLYPH N024 13209 EGYPTIAN HIEROGLYPH N025 1320A EGYPTIAN HIEROGLYPH N025A + * stylistic variant, use of 13209 is preferred 1320B EGYPTIAN HIEROGLYPH N026 1320C EGYPTIAN HIEROGLYPH N027 1320D EGYPTIAN HIEROGLYPH N028 1320E EGYPTIAN HIEROGLYPH N029 + * hill + * not to be confused with 133D8 * transliterated as q or as 1E33 x (hebrew letter qof - 05E7) x (arabic letter qaf - 0642) @@ -36596,21 +37692,34 @@ FFFF 13210 EGYPTIAN HIEROGLYPH N031 13211 EGYPTIAN HIEROGLYPH N032 13212 EGYPTIAN HIEROGLYPH N033 + * classifier 'granule, grain' + * not to be confused with 130C9 13213 EGYPTIAN HIEROGLYPH N033A + * classifier 'granules, grains' + * not to be confused with 133E7 13214 EGYPTIAN HIEROGLYPH N034 13215 EGYPTIAN HIEROGLYPH N034A + * stylistic variant, use of 13214 is preferred 13216 EGYPTIAN HIEROGLYPH N035 * transliterated as n + ~ 13216 FE02 rotated 270 degrees 13217 EGYPTIAN HIEROGLYPH N035A + * classifier 'liquid' 13218 EGYPTIAN HIEROGLYPH N036 13219 EGYPTIAN HIEROGLYPH N037 + * lake * transliterated as 0161 + * not to be confused with 1328C 1321A EGYPTIAN HIEROGLYPH N037A + * variant of 13219 1321B EGYPTIAN HIEROGLYPH N038 + * variant of 13219 1321C EGYPTIAN HIEROGLYPH N039 + * variant of 13219 1321D EGYPTIAN HIEROGLYPH N040 1321E EGYPTIAN HIEROGLYPH N041 1321F EGYPTIAN HIEROGLYPH N042 + * variant of 1321E @ NL. Nomes of Lower Egypt 13220 EGYPTIAN HIEROGLYPH NL001 13221 EGYPTIAN HIEROGLYPH NL002 @@ -36672,7 +37781,9 @@ FFFF x (arabic letter heh - 0647) 13255 EGYPTIAN HIEROGLYPH O005 13256 EGYPTIAN HIEROGLYPH O005A + * mirrored version of 13255 13257 EGYPTIAN HIEROGLYPH O006 + ~ 13257 FE01 rotated 180 degrees 13258 EGYPTIAN HIEROGLYPH O006A * beginning of hwt or serekh enclosure x (egyptian hieroglyph o033a - 13282) @@ -36716,12 +37827,19 @@ FFFF 13279 EGYPTIAN HIEROGLYPH O027 1327A EGYPTIAN HIEROGLYPH O028 1327B EGYPTIAN HIEROGLYPH O029 + ~ 1327B FE02 rotated 270 degrees 1327C EGYPTIAN HIEROGLYPH O029A + * rotated variant of 1327B 1327D EGYPTIAN HIEROGLYPH O030 + * supporting pole + * not to be confused with 13361 1327E EGYPTIAN HIEROGLYPH O030A 1327F EGYPTIAN HIEROGLYPH O031 + ~ 1327F FE00 rotated 90 degrees + ~ 1327F FE01 rotated 180 degrees 13280 EGYPTIAN HIEROGLYPH O032 13281 EGYPTIAN HIEROGLYPH O033 + * classifier 'serekh' 13282 EGYPTIAN HIEROGLYPH O033A * end of serekh enclosure x (egyptian hieroglyph o006a - 13258) @@ -36730,6 +37848,7 @@ FFFF x (egyptian hieroglyph s029 - 132F4) 13284 EGYPTIAN HIEROGLYPH O035 13285 EGYPTIAN HIEROGLYPH O036 + ~ 13285 FE00 rotated 90 degrees 13286 EGYPTIAN HIEROGLYPH O036A * beginning of fortified wall cartouche 13287 EGYPTIAN HIEROGLYPH O036B @@ -36741,10 +37860,14 @@ FFFF 1328A EGYPTIAN HIEROGLYPH O037 1328B EGYPTIAN HIEROGLYPH O038 1328C EGYPTIAN HIEROGLYPH O039 + * stone, brick + * not to be confused with 13219 + ~ 1328C FE00 rotated 90 degrees 1328D EGYPTIAN HIEROGLYPH O040 1328E EGYPTIAN HIEROGLYPH O041 1328F EGYPTIAN HIEROGLYPH O042 13290 EGYPTIAN HIEROGLYPH O043 + * older variant of 1328F 13291 EGYPTIAN HIEROGLYPH O044 13292 EGYPTIAN HIEROGLYPH O045 13293 EGYPTIAN HIEROGLYPH O046 @@ -36754,26 +37877,36 @@ FFFF 13297 EGYPTIAN HIEROGLYPH O050 13298 EGYPTIAN HIEROGLYPH O050A 13299 EGYPTIAN HIEROGLYPH O050B + * mirrored version of 13298 1329A EGYPTIAN HIEROGLYPH O051 @ P. Ships and parts of ships 1329B EGYPTIAN HIEROGLYPH P001 + * classifier 'ship, travel' 1329C EGYPTIAN HIEROGLYPH P001A + * classifier 'upset, overturn' 1329D EGYPTIAN HIEROGLYPH P002 1329E EGYPTIAN HIEROGLYPH P003 + * sacred ship 1329F EGYPTIAN HIEROGLYPH P003A + * mirrored variant of 1329E 132A0 EGYPTIAN HIEROGLYPH P004 132A1 EGYPTIAN HIEROGLYPH P005 132A2 EGYPTIAN HIEROGLYPH P006 132A3 EGYPTIAN HIEROGLYPH P007 132A4 EGYPTIAN HIEROGLYPH P008 + ~ 132A4 FE01 rotated 180 degrees + ~ 132A4 FE02 rotated 270 degrees 132A5 EGYPTIAN HIEROGLYPH P009 132A6 EGYPTIAN HIEROGLYPH P010 132A7 EGYPTIAN HIEROGLYPH P011 + * mooring post + * not to be confused with 131E9 or 1342A @ Q. Domestic and funerary furniture 132A8 EGYPTIAN HIEROGLYPH Q001 132A9 EGYPTIAN HIEROGLYPH Q002 132AA EGYPTIAN HIEROGLYPH Q003 * transliterated as p + ~ 132AA FE00 rotated 90 degrees 132AB EGYPTIAN HIEROGLYPH Q004 132AC EGYPTIAN HIEROGLYPH Q005 132AD EGYPTIAN HIEROGLYPH Q006 @@ -36808,6 +37941,7 @@ FFFF 132C9 EGYPTIAN HIEROGLYPH R022 132CA EGYPTIAN HIEROGLYPH R023 132CB EGYPTIAN HIEROGLYPH R024 + ~ 132CB FE00 rotated 90 degrees 132CC EGYPTIAN HIEROGLYPH R025 132CD EGYPTIAN HIEROGLYPH R026 132CE EGYPTIAN HIEROGLYPH R027 @@ -36826,6 +37960,7 @@ FFFF 132DA EGYPTIAN HIEROGLYPH S008 132DB EGYPTIAN HIEROGLYPH S009 132DC EGYPTIAN HIEROGLYPH S010 + ~ 132DC FE00 rotated 90 degrees 132DD EGYPTIAN HIEROGLYPH S011 132DE EGYPTIAN HIEROGLYPH S012 132DF EGYPTIAN HIEROGLYPH S013 @@ -36837,8 +37972,11 @@ FFFF 132E5 EGYPTIAN HIEROGLYPH S017 132E6 EGYPTIAN HIEROGLYPH S017A 132E7 EGYPTIAN HIEROGLYPH S018 + ~ 132E7 FE00 rotated 90 degrees + ~ 132E7 FE02 rotated 270 degrees 132E8 EGYPTIAN HIEROGLYPH S019 132E9 EGYPTIAN HIEROGLYPH S020 + ~ 132E9 FE02 rotated 270 degrees 132EA EGYPTIAN HIEROGLYPH S021 132EB EGYPTIAN HIEROGLYPH S022 132EC EGYPTIAN HIEROGLYPH S023 @@ -36846,6 +37984,8 @@ FFFF 132EE EGYPTIAN HIEROGLYPH S025 132EF EGYPTIAN HIEROGLYPH S026 132F0 EGYPTIAN HIEROGLYPH S026A + * loin-cloth + * not to be confused with 13200, 133D4, or 133F3 132F1 EGYPTIAN HIEROGLYPH S026B 132F2 EGYPTIAN HIEROGLYPH S027 132F3 EGYPTIAN HIEROGLYPH S028 @@ -36856,24 +37996,36 @@ FFFF 132F6 EGYPTIAN HIEROGLYPH S031 132F7 EGYPTIAN HIEROGLYPH S032 132F8 EGYPTIAN HIEROGLYPH S033 + ~ 132F8 FE02 rotated 270 degrees 132F9 EGYPTIAN HIEROGLYPH S034 132FA EGYPTIAN HIEROGLYPH S035 132FB EGYPTIAN HIEROGLYPH S035A + * variant of 132FA 132FC EGYPTIAN HIEROGLYPH S036 + * older variant of 132FA 132FD EGYPTIAN HIEROGLYPH S037 + ~ 132FD FE02 rotated 270 degrees 132FE EGYPTIAN HIEROGLYPH S038 132FF EGYPTIAN HIEROGLYPH S039 13300 EGYPTIAN HIEROGLYPH S040 + * phonogram 'wꜣs' 13301 EGYPTIAN HIEROGLYPH S041 + * phonogram 'ḏꜣm' 13302 EGYPTIAN HIEROGLYPH S042 + ~ 13302 FE02 rotated 270 degrees 13303 EGYPTIAN HIEROGLYPH S043 + ~ 13303 FE02 rotated 270 degrees 13304 EGYPTIAN HIEROGLYPH S044 13305 EGYPTIAN HIEROGLYPH S045 13306 EGYPTIAN HIEROGLYPH S046 @ T. Warfare, hunting, butchery 13307 EGYPTIAN HIEROGLYPH T001 + ~ 13307 FE00 rotated 90 degrees 13308 EGYPTIAN HIEROGLYPH T002 + * classifier 'striking, hitting' + ~ 13308 FE01 rotated 180 degrees 13309 EGYPTIAN HIEROGLYPH T003 + * classifier 'mace' 1330A EGYPTIAN HIEROGLYPH T003A 1330B EGYPTIAN HIEROGLYPH T004 1330C EGYPTIAN HIEROGLYPH T005 @@ -36881,51 +38033,86 @@ FFFF 1330E EGYPTIAN HIEROGLYPH T007 1330F EGYPTIAN HIEROGLYPH T007A 13310 EGYPTIAN HIEROGLYPH T008 + * older variant of 13311 + ~ 13310 FE02 rotated 270 degrees 13311 EGYPTIAN HIEROGLYPH T008A + ~ 13311 FE02 rotated 270 degrees 13312 EGYPTIAN HIEROGLYPH T009 + ~ 13312 FE01 rotated 180 degrees + ~ 13312 FE02 rotated 270 degrees 13313 EGYPTIAN HIEROGLYPH T009A + * older variant of 13312 + ~ 13313 FE01 rotated 180 degrees + ~ 13313 FE02 rotated 270 degrees 13314 EGYPTIAN HIEROGLYPH T010 + ~ 13314 FE01 rotated 180 degrees + ~ 13314 FE02 rotated 270 degrees 13315 EGYPTIAN HIEROGLYPH T011 13316 EGYPTIAN HIEROGLYPH T011A 13317 EGYPTIAN HIEROGLYPH T012 13318 EGYPTIAN HIEROGLYPH T013 13319 EGYPTIAN HIEROGLYPH T014 1331A EGYPTIAN HIEROGLYPH T015 + * older variant of 13319 1331B EGYPTIAN HIEROGLYPH T016 + ~ 1331B FE00 rotated 90 degrees + ~ 1331B FE01 rotated 180 degrees 1331C EGYPTIAN HIEROGLYPH T016A + ~ 1331C FE02 rotated 270 degrees 1331D EGYPTIAN HIEROGLYPH T017 1331E EGYPTIAN HIEROGLYPH T018 1331F EGYPTIAN HIEROGLYPH T019 13320 EGYPTIAN HIEROGLYPH T020 + * older variant of 1331F 13321 EGYPTIAN HIEROGLYPH T021 + ~ 13321 FE01 rotated 180 degrees + ~ 13321 FE02 rotated 270 degrees 13322 EGYPTIAN HIEROGLYPH T022 + ~ 13322 FE00 rotated 90 degrees + ~ 13322 FE01 rotated 180 degrees 13323 EGYPTIAN HIEROGLYPH T023 + * more recent variant of 13322 13324 EGYPTIAN HIEROGLYPH T024 13325 EGYPTIAN HIEROGLYPH T025 13326 EGYPTIAN HIEROGLYPH T026 13327 EGYPTIAN HIEROGLYPH T027 + * older variant of 13326 13328 EGYPTIAN HIEROGLYPH T028 13329 EGYPTIAN HIEROGLYPH T029 1332A EGYPTIAN HIEROGLYPH T030 + * classifier 'knife, cutting' 1332B EGYPTIAN HIEROGLYPH T031 + * phonogram 'sšm' 1332C EGYPTIAN HIEROGLYPH T032 1332D EGYPTIAN HIEROGLYPH T032A 1332E EGYPTIAN HIEROGLYPH T033 + * older variant of 13326 1332F EGYPTIAN HIEROGLYPH T033A 13330 EGYPTIAN HIEROGLYPH T034 13331 EGYPTIAN HIEROGLYPH T035 + * variant of 13330 + ~ 13331 FE01 rotated 180 degrees + ~ 13331 FE02 rotated 270 degrees 13332 EGYPTIAN HIEROGLYPH T036 @ U. Agriculture, crafts, and professions 13333 EGYPTIAN HIEROGLYPH U001 13334 EGYPTIAN HIEROGLYPH U002 + * stylistic variant of 13333 13335 EGYPTIAN HIEROGLYPH U003 13336 EGYPTIAN HIEROGLYPH U004 13337 EGYPTIAN HIEROGLYPH U005 + * stylistic variant of 13336 13338 EGYPTIAN HIEROGLYPH U006 13339 EGYPTIAN HIEROGLYPH U006A + * stylistic variant of 13338 1333A EGYPTIAN HIEROGLYPH U006B + * mirrored version of 13339 1333B EGYPTIAN HIEROGLYPH U007 + * variant of 13338 + ~ 1333B FE00 rotated 90 degrees 1333C EGYPTIAN HIEROGLYPH U008 + * variant of 1333B + ~ 1333C FE00 rotated 90 degrees 1333D EGYPTIAN HIEROGLYPH U009 1333E EGYPTIAN HIEROGLYPH U010 1333F EGYPTIAN HIEROGLYPH U011 @@ -36936,18 +38123,25 @@ FFFF 13344 EGYPTIAN HIEROGLYPH U016 13345 EGYPTIAN HIEROGLYPH U017 13346 EGYPTIAN HIEROGLYPH U018 + * variant of 13345 13347 EGYPTIAN HIEROGLYPH U019 13348 EGYPTIAN HIEROGLYPH U020 + * older variant of 13347 13349 EGYPTIAN HIEROGLYPH U021 1334A EGYPTIAN HIEROGLYPH U022 + ~ 1334A FE02 rotated 270 degrees 1334B EGYPTIAN HIEROGLYPH U023 1334C EGYPTIAN HIEROGLYPH U023A + * stylistic variant of 1334B 1334D EGYPTIAN HIEROGLYPH U024 1334E EGYPTIAN HIEROGLYPH U025 + * older variant of 1334D 1334F EGYPTIAN HIEROGLYPH U026 13350 EGYPTIAN HIEROGLYPH U027 + * older variant of 1334F 13351 EGYPTIAN HIEROGLYPH U028 13352 EGYPTIAN HIEROGLYPH U029 + * older variant of 13351 13353 EGYPTIAN HIEROGLYPH U029A 13354 EGYPTIAN HIEROGLYPH U030 13355 EGYPTIAN HIEROGLYPH U031 @@ -36961,11 +38155,17 @@ FFFF 1335D EGYPTIAN HIEROGLYPH U038 1335E EGYPTIAN HIEROGLYPH U039 1335F EGYPTIAN HIEROGLYPH U040 + * cursive variant of 1335E 13360 EGYPTIAN HIEROGLYPH U041 13361 EGYPTIAN HIEROGLYPH U042 + * pitchfork + * not to be confused with 1327D + ~ 13361 FE02 rotated 270 degrees @ V. Rope, fiber, baskets, bags, etc. 13362 EGYPTIAN HIEROGLYPH V001 * 100 + * classifier 'cord, rope' + * not to be confused with 133F2 13363 EGYPTIAN HIEROGLYPH V001A * 200 13364 EGYPTIAN HIEROGLYPH V001B @@ -36990,13 +38190,21 @@ FFFF 1336F EGYPTIAN HIEROGLYPH V004 13370 EGYPTIAN HIEROGLYPH V005 13371 EGYPTIAN HIEROGLYPH V006 + * phonogram 'šs' 13372 EGYPTIAN HIEROGLYPH V007 + * phonogram 'šn' 13373 EGYPTIAN HIEROGLYPH V007A + ~ 13373 FE02 rotated 270 degrees 13374 EGYPTIAN HIEROGLYPH V007B 13375 EGYPTIAN HIEROGLYPH V008 13376 EGYPTIAN HIEROGLYPH V009 13377 EGYPTIAN HIEROGLYPH V010 + * logogram 'name' + ~ 13377 FE00 rotated 90 degrees 13378 EGYPTIAN HIEROGLYPH V011 + * classifier 'restrain, split' + x (egyptian hieroglyph v011d - 1342F) + ~ 13378 FE00 rotated 90 degrees 13379 EGYPTIAN HIEROGLYPH V011A * beginning of cartouche 1337A EGYPTIAN HIEROGLYPH V011B @@ -37005,19 +38213,25 @@ FFFF * end of knotless cartouche 1337C EGYPTIAN HIEROGLYPH V012 1337D EGYPTIAN HIEROGLYPH V012A + ~ 1337D FE02 rotated 270 degrees 1337E EGYPTIAN HIEROGLYPH V012B 1337F EGYPTIAN HIEROGLYPH V013 * transliterated as 1E6F 13380 EGYPTIAN HIEROGLYPH V014 + * variant of 1337F 13381 EGYPTIAN HIEROGLYPH V015 13382 EGYPTIAN HIEROGLYPH V016 13383 EGYPTIAN HIEROGLYPH V017 13384 EGYPTIAN HIEROGLYPH V018 + * older variant of 13383 13385 EGYPTIAN HIEROGLYPH V019 + ~ 13385 FE02 rotated 270 degrees 13386 EGYPTIAN HIEROGLYPH V020 * 10 + * not to be confused with 133AD 13387 EGYPTIAN HIEROGLYPH V020A * 20 + * not to be confused with 133AE 13388 EGYPTIAN HIEROGLYPH V020B * 30 13389 EGYPTIAN HIEROGLYPH V020C @@ -37034,20 +38248,29 @@ FFFF * 90 1338F EGYPTIAN HIEROGLYPH V020I * 20 + * variant of 13387 13390 EGYPTIAN HIEROGLYPH V020J * 30 + * variant of 13388 13391 EGYPTIAN HIEROGLYPH V020K * 40 + * variant of 13389 13392 EGYPTIAN HIEROGLYPH V020L * 50 + * variant of 1338A 13393 EGYPTIAN HIEROGLYPH V021 13394 EGYPTIAN HIEROGLYPH V022 13395 EGYPTIAN HIEROGLYPH V023 + * older variant of 13394 13396 EGYPTIAN HIEROGLYPH V023A 13397 EGYPTIAN HIEROGLYPH V024 13398 EGYPTIAN HIEROGLYPH V025 + * more recent variant of 13397 13399 EGYPTIAN HIEROGLYPH V026 + ~ 13399 FE00 rotated 90 degrees 1339A EGYPTIAN HIEROGLYPH V027 + * older variant of 13399 + ~ 1339A FE00 rotated 90 degrees 1339B EGYPTIAN HIEROGLYPH V028 * transliterated as 1E25 x (arabic letter hah - 062D) @@ -37056,30 +38279,40 @@ FFFF 1339E EGYPTIAN HIEROGLYPH V029A 1339F EGYPTIAN HIEROGLYPH V030 133A0 EGYPTIAN HIEROGLYPH V030A + * stylistic variant, use of 1339F is preferred 133A1 EGYPTIAN HIEROGLYPH V031 * transliterated as k x (hebrew letter kaf - 05DB) x (arabic letter kaf - 0643) 133A2 EGYPTIAN HIEROGLYPH V031A + * from hieratic 133A3 EGYPTIAN HIEROGLYPH V032 133A4 EGYPTIAN HIEROGLYPH V033 133A5 EGYPTIAN HIEROGLYPH V033A 133A6 EGYPTIAN HIEROGLYPH V034 + * more recent variant of 133A4 133A7 EGYPTIAN HIEROGLYPH V035 133A8 EGYPTIAN HIEROGLYPH V036 133A9 EGYPTIAN HIEROGLYPH V037 133AA EGYPTIAN HIEROGLYPH V037A 133AB EGYPTIAN HIEROGLYPH V038 + * bandage + * not to be confused with 1308B 133AC EGYPTIAN HIEROGLYPH V039 133AD EGYPTIAN HIEROGLYPH V040 * 10 in dates + * not to be confused with 13386 133AE EGYPTIAN HIEROGLYPH V040A * 20 in dates + * not to be confused with 13387 @ W. Vessels of stone and earthenware 133AF EGYPTIAN HIEROGLYPH W001 + ~ 133AF FE02 rotated 270 degrees 133B0 EGYPTIAN HIEROGLYPH W002 + ~ 133B0 FE02 rotated 270 degrees 133B1 EGYPTIAN HIEROGLYPH W003 133B2 EGYPTIAN HIEROGLYPH W003A + * stylistic variant, use of 133B1 is preferred 133B3 EGYPTIAN HIEROGLYPH W004 133B4 EGYPTIAN HIEROGLYPH W005 133B5 EGYPTIAN HIEROGLYPH W006 @@ -37087,93 +38320,142 @@ FFFF 133B7 EGYPTIAN HIEROGLYPH W008 133B8 EGYPTIAN HIEROGLYPH W009 133B9 EGYPTIAN HIEROGLYPH W009A + * mirrored version of 133B8 133BA EGYPTIAN HIEROGLYPH W010 133BB EGYPTIAN HIEROGLYPH W010A 133BC EGYPTIAN HIEROGLYPH W011 * transliterated as g 133BD EGYPTIAN HIEROGLYPH W012 + * older variant of 133BC 133BE EGYPTIAN HIEROGLYPH W013 133BF EGYPTIAN HIEROGLYPH W014 + ~ 133BF FE02 rotated 270 degrees 133C0 EGYPTIAN HIEROGLYPH W014A 133C1 EGYPTIAN HIEROGLYPH W015 133C2 EGYPTIAN HIEROGLYPH W016 133C3 EGYPTIAN HIEROGLYPH W017 133C4 EGYPTIAN HIEROGLYPH W017A + * cursive variant of 133C3 133C5 EGYPTIAN HIEROGLYPH W018 + * older variant of 133C3 133C6 EGYPTIAN HIEROGLYPH W018A + * cursive variant of 133C5 133C7 EGYPTIAN HIEROGLYPH W019 133C8 EGYPTIAN HIEROGLYPH W020 133C9 EGYPTIAN HIEROGLYPH W021 133CA EGYPTIAN HIEROGLYPH W022 133CB EGYPTIAN HIEROGLYPH W023 133CC EGYPTIAN HIEROGLYPH W024 + * phonogram 'nw' 133CD EGYPTIAN HIEROGLYPH W024A + * monogram 'nw(n)' or 'nww' 133CE EGYPTIAN HIEROGLYPH W025 @ X. Loaves and cakes 133CF EGYPTIAN HIEROGLYPH X001 * transliterated as t 133D0 EGYPTIAN HIEROGLYPH X002 133D1 EGYPTIAN HIEROGLYPH X003 + * variant of 133D0 133D2 EGYPTIAN HIEROGLYPH X004 133D3 EGYPTIAN HIEROGLYPH X004A + * variant of 133D2 + ~ 133D3 FE00 rotated 90 degrees 133D4 EGYPTIAN HIEROGLYPH X004B + * cake + * variant of 133D2 + * not to be confused with 13200, 132F0, or 133F3 133D5 EGYPTIAN HIEROGLYPH X005 + * hieratic + * variant of 133D4 133D6 EGYPTIAN HIEROGLYPH X006 133D7 EGYPTIAN HIEROGLYPH X006A 133D8 EGYPTIAN HIEROGLYPH X007 + * classifier 'food' + * not to be confused with 1320E 133D9 EGYPTIAN HIEROGLYPH X008 133DA EGYPTIAN HIEROGLYPH X008A + * bread + * variant of 133D9 + * not to be confused with 131EE @ Y. Writings, games, music 133DB EGYPTIAN HIEROGLYPH Y001 133DC EGYPTIAN HIEROGLYPH Y001A + * rotated variant of 133DB 133DD EGYPTIAN HIEROGLYPH Y002 + * older variant of 133DB + ~ 133DD FE02 rotated 270 degrees 133DE EGYPTIAN HIEROGLYPH Y003 133DF EGYPTIAN HIEROGLYPH Y004 + * mirrored version of 133DE 133E0 EGYPTIAN HIEROGLYPH Y005 133E1 EGYPTIAN HIEROGLYPH Y006 133E2 EGYPTIAN HIEROGLYPH Y007 133E3 EGYPTIAN HIEROGLYPH Y008 @ Z. Strokes, signs derived from Hieratic, geometrical figures 133E4 EGYPTIAN HIEROGLYPH Z001 - x (egyptian hieroglyph z015 - 133FA) + * semogram index + * classifier 'single' + * not to be confused with 133FA 133E5 EGYPTIAN HIEROGLYPH Z002 - * plurality - x (egyptian hieroglyph z015b - 133FC) + * classifier 'plural' + * not to be confused with 133FC 133E6 EGYPTIAN HIEROGLYPH Z002A + * stylistic variant of 133E5 133E7 EGYPTIAN HIEROGLYPH Z002B + * classifier 'plural' + * not to be confused with 13213 133E8 EGYPTIAN HIEROGLYPH Z002C + * variant of 133E6 133E9 EGYPTIAN HIEROGLYPH Z002D + * variant of 133E8 133EA EGYPTIAN HIEROGLYPH Z003 + * variant of 133E5 133EB EGYPTIAN HIEROGLYPH Z003A + * variant of 133EA 133EC EGYPTIAN HIEROGLYPH Z003B - * 3 + * variant of 133E7 133ED EGYPTIAN HIEROGLYPH Z004 - * duality + * classifier 'dual' * transliterated as y x (egyptian hieroglyph m017a - 131CC) 133EE EGYPTIAN HIEROGLYPH Z004A - * duality - x (egyptian hieroglyph z015a - 133FB) + * variant of 133ED + * classifier 'dual' + * transliterated as y + * not to be confused with 133FB 133EF EGYPTIAN HIEROGLYPH Z005 133F0 EGYPTIAN HIEROGLYPH Z005A + * variant of 133EF 133F1 EGYPTIAN HIEROGLYPH Z006 133F2 EGYPTIAN HIEROGLYPH Z007 + * phonogram 'w' + * not to be confused with 13362 + ~ 133F2 FE00 rotated 90 degrees 133F3 EGYPTIAN HIEROGLYPH Z008 + * oval + * not to be confused with 13200, 132F0, or 133D4 133F4 EGYPTIAN HIEROGLYPH Z009 133F5 EGYPTIAN HIEROGLYPH Z010 + * older variant of 133F4 + ~ 133F5 FE00 rotated 90 degrees 133F6 EGYPTIAN HIEROGLYPH Z011 + ~ 133F6 FE00 rotated 90 degrees 133F7 EGYPTIAN HIEROGLYPH Z012 + * hieratic 133F8 EGYPTIAN HIEROGLYPH Z013 + * circle, unmarked round sign + * not to be confused with 13082 or 131F3 133F9 EGYPTIAN HIEROGLYPH Z014 + * hieratic 133FA EGYPTIAN HIEROGLYPH Z015 * 1 - x (egyptian hieroglyph z001 - 133E4) + * not to be confused with 133E4 133FB EGYPTIAN HIEROGLYPH Z015A * 2 - x (egyptian hieroglyph z004a - 133EE) + * not to be confused with 133EE 133FC EGYPTIAN HIEROGLYPH Z015B * 3 - x (egyptian hieroglyph z002 - 133E5) + * not to be confused with 133E5 x (egyptian hieroglyph z003 - 133EA) 133FD EGYPTIAN HIEROGLYPH Z015C * 4 @@ -37189,6 +38471,7 @@ FFFF * 9 13403 EGYPTIAN HIEROGLYPH Z015I * 5 + ~ 13403 FE00 rotated 90 degrees 13404 EGYPTIAN HIEROGLYPH Z016 * 1 in dates 13405 EGYPTIAN HIEROGLYPH Z016A @@ -37218,34 +38501,58 @@ FFFF 13412 EGYPTIAN HIEROGLYPH AA006 13413 EGYPTIAN HIEROGLYPH AA007 13414 EGYPTIAN HIEROGLYPH AA007A + * mirrored version of 13413 13415 EGYPTIAN HIEROGLYPH AA007B 13416 EGYPTIAN HIEROGLYPH AA008 + ~ 13416 FE00 rotated 90 degrees 13417 EGYPTIAN HIEROGLYPH AA009 13418 EGYPTIAN HIEROGLYPH AA010 13419 EGYPTIAN HIEROGLYPH AA011 + ~ 13419 FE00 rotated 90 degrees + ~ 13419 FE01 rotated 180 degrees + ~ 13419 FE02 rotated 270 degrees 1341A EGYPTIAN HIEROGLYPH AA012 + * older variant of 13419 + ~ 1341A FE00 rotated 90 degrees 1341B EGYPTIAN HIEROGLYPH AA013 1341C EGYPTIAN HIEROGLYPH AA014 + * older variant of 1341B 1341D EGYPTIAN HIEROGLYPH AA015 1341E EGYPTIAN HIEROGLYPH AA016 + * variant of 1341D 1341F EGYPTIAN HIEROGLYPH AA017 13420 EGYPTIAN HIEROGLYPH AA018 + * more recent variant of 1341F 13421 EGYPTIAN HIEROGLYPH AA019 13422 EGYPTIAN HIEROGLYPH AA020 13423 EGYPTIAN HIEROGLYPH AA021 + ~ 13423 FE00 rotated 90 degrees 13424 EGYPTIAN HIEROGLYPH AA022 13425 EGYPTIAN HIEROGLYPH AA023 13426 EGYPTIAN HIEROGLYPH AA024 + * older variant of 13425 13427 EGYPTIAN HIEROGLYPH AA025 13428 EGYPTIAN HIEROGLYPH AA026 13429 EGYPTIAN HIEROGLYPH AA027 1342A EGYPTIAN HIEROGLYPH AA028 + * phonogram 'qd' + * not to be confused with 131E9 and 132A7 1342B EGYPTIAN HIEROGLYPH AA029 + * older variant of 1342A 1342C EGYPTIAN HIEROGLYPH AA030 + ~ 1342C FE02 rotated 270 degrees 1342D EGYPTIAN HIEROGLYPH AA031 + * older variant of 1342C 1342E EGYPTIAN HIEROGLYPH AA032 -@@ 13430 Egyptian Hieroglyph Format Controls 1343F -@+ These format controls are used to render Egyptian hieroglyphic quadrats. + ~ 1342E FE02 rotated 270 degrees +@ Addition to group V +@+ This is part of the cartouche set: 13379, 1337A, 1337B, and 1342F. +1342F EGYPTIAN HIEROGLYPH V011D + * knotted beginning of cartouche + * not to be confused with 13378 +@~ ! +@@ 13430 Egyptian Hieroglyph Format Controls 1345F +@+ These format controls are used to render Egyptian hieroglyphic spatial arrangements, including quadrats, overlays, insertions, and blank, lost or damaged sections. @ Joiners 13430 EGYPTIAN HIEROGLYPH VERTICAL JOINER = sign separator: subordination (Manuel de Codage) @@ -37261,6 +38568,45 @@ FFFF @ Segment scoping delimiters 13437 EGYPTIAN HIEROGLYPH BEGIN SEGMENT 13438 EGYPTIAN HIEROGLYPH END SEGMENT +@ Sign insertion controls +13439 EGYPTIAN HIEROGLYPH INSERT AT MIDDLE +1343A EGYPTIAN HIEROGLYPH INSERT AT TOP +1343B EGYPTIAN HIEROGLYPH INSERT AT BOTTOM +@ Enclosure controls +1343C EGYPTIAN HIEROGLYPH BEGIN ENCLOSURE +1343D EGYPTIAN HIEROGLYPH END ENCLOSURE +1343E EGYPTIAN HIEROGLYPH BEGIN WALLED ENCLOSURE +1343F EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +@ Mirror control +13440 EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +@ Blank and lost signs +13441 EGYPTIAN HIEROGLYPH FULL BLANK +13442 EGYPTIAN HIEROGLYPH HALF BLANK +13443 EGYPTIAN HIEROGLYPH LOST SIGN + ~ 13443 FE00 expanded +13444 EGYPTIAN HIEROGLYPH HALF LOST SIGN + ~ 13444 FE00 expanded +13445 EGYPTIAN HIEROGLYPH TALL LOST SIGN + ~ 13445 FE00 expanded +13446 EGYPTIAN HIEROGLYPH WIDE LOST SIGN + ~ 13446 FE00 expanded +@ Damage modifiers +13447 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START +13448 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM START +13449 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START +1344A EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP END +1344B EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP +1344C EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM START AND TOP END +1344D EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START AND TOP +1344E EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM END +1344F EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START AND BOTTOM END +13450 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM +13451 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT START AND BOTTOM +13452 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT END +13453 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP AND END +13454 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT BOTTOM AND END +13455 EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +@~ ! @@ 14400 Anatolian Hieroglyphs 1467F @+ In the names list, most of the comments are in Latin. Those which have a Luwian phonetic value are identified as syllabic. @ A. The human body and clothing @@ -38942,6 +40288,99 @@ FFFF @ Punctuation 16A6E MRO DANDA 16A6F MRO DOUBLE DANDA +@@ 16A70 Tangsa 16ACF +@ Vowels +16A70 TANGSA LETTER OZ +16A71 TANGSA LETTER OC +16A72 TANGSA LETTER OQ +16A73 TANGSA LETTER OX +16A74 TANGSA LETTER AZ +16A75 TANGSA LETTER AC +16A76 TANGSA LETTER AQ +16A77 TANGSA LETTER AX +16A78 TANGSA LETTER VZ +16A79 TANGSA LETTER VC +16A7A TANGSA LETTER VQ +16A7B TANGSA LETTER VX +16A7C TANGSA LETTER EZ +16A7D TANGSA LETTER EC +16A7E TANGSA LETTER EQ +16A7F TANGSA LETTER EX +16A80 TANGSA LETTER IZ +16A81 TANGSA LETTER IC +16A82 TANGSA LETTER IQ +16A83 TANGSA LETTER IX +16A84 TANGSA LETTER UZ +16A85 TANGSA LETTER UC +16A86 TANGSA LETTER UQ +16A87 TANGSA LETTER UX +16A88 TANGSA LETTER AWZ +16A89 TANGSA LETTER AWC +16A8A TANGSA LETTER AWQ +16A8B TANGSA LETTER AWX +16A8C TANGSA LETTER UIZ +16A8D TANGSA LETTER UIC +16A8E TANGSA LETTER UIQ +16A8F TANGSA LETTER UIX +16A90 TANGSA LETTER FINAL NG +16A91 TANGSA LETTER LONG UEX +16A92 TANGSA LETTER SHORT UEZ +16A93 TANGSA LETTER SHORT AWX +16A94 TANGSA LETTER UEC +16A95 TANGSA LETTER UEZ +16A96 TANGSA LETTER UEQ +16A97 TANGSA LETTER UEX +16A98 TANGSA LETTER UIUZ +16A99 TANGSA LETTER UIUC +16A9A TANGSA LETTER UIUQ +16A9B TANGSA LETTER UIUX +16A9C TANGSA LETTER MZ +16A9D TANGSA LETTER MC +16A9E TANGSA LETTER MQ +16A9F TANGSA LETTER MX +@ Consonants +16AA0 TANGSA LETTER KA +16AA1 TANGSA LETTER KHA +16AA2 TANGSA LETTER GA +16AA3 TANGSA LETTER NGA +16AA4 TANGSA LETTER SA +16AA5 TANGSA LETTER YA +16AA6 TANGSA LETTER WA +16AA7 TANGSA LETTER PA +16AA8 TANGSA LETTER NYA +16AA9 TANGSA LETTER PHA +16AAA TANGSA LETTER BA +16AAB TANGSA LETTER MA +16AAC TANGSA LETTER NA +16AAD TANGSA LETTER HA +16AAE TANGSA LETTER LA +16AAF TANGSA LETTER HTA +16AB0 TANGSA LETTER TA +16AB1 TANGSA LETTER DA +16AB2 TANGSA LETTER RA +16AB3 TANGSA LETTER NHA +16AB4 TANGSA LETTER SHA +16AB5 TANGSA LETTER CA +16AB6 TANGSA LETTER TSA +16AB7 TANGSA LETTER GHA +16AB8 TANGSA LETTER HTTA +16AB9 TANGSA LETTER THA +16ABA TANGSA LETTER XA +16ABB TANGSA LETTER FA +16ABC TANGSA LETTER DHA +16ABD TANGSA LETTER CHA +16ABE TANGSA LETTER ZA +@ Digits +16AC0 TANGSA DIGIT ZERO +16AC1 TANGSA DIGIT ONE +16AC2 TANGSA DIGIT TWO +16AC3 TANGSA DIGIT THREE +16AC4 TANGSA DIGIT FOUR +16AC5 TANGSA DIGIT FIVE +16AC6 TANGSA DIGIT SIX +16AC7 TANGSA DIGIT SEVEN +16AC8 TANGSA DIGIT EIGHT +16AC9 TANGSA DIGIT NINE @@ 16AD0 Bassa Vah 16AFF @ Consonant letters 16AD0 BASSA VAH LETTER ENNI @@ -40587,6 +42026,7 @@ FFFF 18BDC KHITAN SMALL SCRIPT CHARACTER-18BDC 18BDD KHITAN SMALL SCRIPT CHARACTER-18BDD 18BDE KHITAN SMALL SCRIPT CHARACTER-18BDE + x (khitan small script character-18cca - 18CCA) 18BDF KHITAN SMALL SCRIPT CHARACTER-18BDF 18BE0 KHITAN SMALL SCRIPT CHARACTER-18BE0 18BE1 KHITAN SMALL SCRIPT CHARACTER-18BE1 @@ -40835,6 +42275,7 @@ FFFF 18CC8 KHITAN SMALL SCRIPT CHARACTER-18CC8 18CC9 KHITAN SMALL SCRIPT CHARACTER-18CC9 18CCA KHITAN SMALL SCRIPT CHARACTER-18CCA + x (khitan small script character-18bde - 18BDE) 18CCB KHITAN SMALL SCRIPT CHARACTER-18CCB @ Radical-19 18CCC KHITAN SMALL SCRIPT CHARACTER-18CCC @@ -40849,6 +42290,23 @@ FFFF 18CD4 KHITAN SMALL SCRIPT CHARACTER-18CD4 18CD5 KHITAN SMALL SCRIPT CHARACTER-18CD5 @@ 18D00 Tangut Supplement 18D08 +@@ 1AFF0 Kana Extended-B 1AFFF +@+ This block contains tone marks occasionally used in furigana extensions to annotate Minnan Chinese. +@ Tone marks +1AFF0 KATAKANA LETTER MINNAN TONE-2 +1AFF1 KATAKANA LETTER MINNAN TONE-3 +1AFF2 KATAKANA LETTER MINNAN TONE-4 +1AFF3 KATAKANA LETTER MINNAN TONE-5 +1AFF5 KATAKANA LETTER MINNAN TONE-7 +1AFF6 KATAKANA LETTER MINNAN TONE-8 +@ Nasalized tone marks +1AFF7 KATAKANA LETTER MINNAN NASALIZED TONE-1 +1AFF8 KATAKANA LETTER MINNAN NASALIZED TONE-2 +1AFF9 KATAKANA LETTER MINNAN NASALIZED TONE-3 +1AFFA KATAKANA LETTER MINNAN NASALIZED TONE-4 +1AFFB KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD KATAKANA LETTER MINNAN NASALIZED TONE-7 +1AFFE KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ 1B000 Kana Supplement 1B0FF @ Historic Katakana 1B000 KATAKANA LETTER ARCHAIC E @@ -41429,12 +42887,21 @@ FFFF * derived from 65E0 1B11E HENTAIGANA LETTER N-MU-MO-2 * derived from 65E0 +@ Historic Hiragana +1B11F HIRAGANA LETTER ARCHAIC WU + * derived from 6C59 +@ Historic Katakana +1B120 KATAKANA LETTER ARCHAIC YI +1B121 KATAKANA LETTER ARCHAIC YE +1B122 KATAKANA LETTER ARCHAIC WU @@ 1B130 Small Kana Extension 1B16F @ Historic small hiragana letters +1B132 HIRAGANA LETTER SMALL KO 1B150 HIRAGANA LETTER SMALL WI 1B151 HIRAGANA LETTER SMALL WE 1B152 HIRAGANA LETTER SMALL WO @ Historic small katakana letters +1B155 KATAKANA LETTER SMALL KO 1B164 KATAKANA LETTER SMALL WI 1B165 KATAKANA LETTER SMALL WE 1B166 KATAKANA LETTER SMALL WO @@ -42344,6 +43811,210 @@ FFFF = Sloan contracted ending oo/o + ZWSP 1BCA3 SHORTHAND FORMAT UP STEP = Sloan contracted ending uh/au/aui + ZWSP +@@ 1CF00 Znamenny Musical Notation 1CFCF +@ Combining red marks +1CF00 ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT +1CF01 ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON LEFT +1CF02 ZNAMENNY COMBINING MARK TSATA ON LEFT +1CF03 ZNAMENNY COMBINING MARK GORAZDO NIZKO ON LEFT +1CF04 ZNAMENNY COMBINING MARK NIZKO ON LEFT +1CF05 ZNAMENNY COMBINING MARK SREDNE ON LEFT +1CF06 ZNAMENNY COMBINING MARK MALO POVYSHE ON LEFT +1CF07 ZNAMENNY COMBINING MARK POVYSHE ON LEFT +1CF08 ZNAMENNY COMBINING MARK VYSOKO ON LEFT +1CF09 ZNAMENNY COMBINING MARK MALO POVYSHE S KHOKHLOM ON LEFT +1CF0A ZNAMENNY COMBINING MARK POVYSHE S KHOKHLOM ON LEFT +1CF0B ZNAMENNY COMBINING MARK VYSOKO S KHOKHLOM ON LEFT +1CF0C ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON RIGHT +1CF0D ZNAMENNY COMBINING MARK NIZKO S KRYZHEM ON RIGHT +1CF0E ZNAMENNY COMBINING MARK TSATA ON RIGHT +1CF0F ZNAMENNY COMBINING MARK GORAZDO NIZKO ON RIGHT +1CF10 ZNAMENNY COMBINING MARK NIZKO ON RIGHT +1CF11 ZNAMENNY COMBINING MARK SREDNE ON RIGHT +1CF12 ZNAMENNY COMBINING MARK MALO POVYSHE ON RIGHT +1CF13 ZNAMENNY COMBINING MARK POVYSHE ON RIGHT +1CF14 ZNAMENNY COMBINING MARK VYSOKO ON RIGHT +1CF15 ZNAMENNY COMBINING MARK MALO POVYSHE S KHOKHLOM ON RIGHT +1CF16 ZNAMENNY COMBINING MARK POVYSHE S KHOKHLOM ON RIGHT +1CF17 ZNAMENNY COMBINING MARK VYSOKO S KHOKHLOM ON RIGHT +1CF18 ZNAMENNY COMBINING MARK TSATA S KRYZHEM +1CF19 ZNAMENNY COMBINING MARK MALO POVYSHE S KRYZHEM +1CF1A ZNAMENNY COMBINING MARK STRANNO MALO POVYSHE +1CF1B ZNAMENNY COMBINING MARK POVYSHE S KRYZHEM +1CF1C ZNAMENNY COMBINING MARK POVYSHE STRANNO +1CF1D ZNAMENNY COMBINING MARK VYSOKO S KRYZHEM +1CF1E ZNAMENNY COMBINING MARK MALO POVYSHE STRANNO +1CF1F ZNAMENNY COMBINING MARK GORAZDO VYSOKO +1CF20 ZNAMENNY COMBINING MARK ZELO +1CF21 ZNAMENNY COMBINING MARK ON +1CF22 ZNAMENNY COMBINING MARK RAVNO +1CF23 ZNAMENNY COMBINING MARK TIKHAYA +1CF24 ZNAMENNY COMBINING MARK BORZAYA +1CF25 ZNAMENNY COMBINING MARK UDARKA +1CF26 ZNAMENNY COMBINING MARK PODVERTKA +1CF27 ZNAMENNY COMBINING MARK LOMKA +1CF28 ZNAMENNY COMBINING MARK KUPNAYA +1CF29 ZNAMENNY COMBINING MARK KACHKA +1CF2A ZNAMENNY COMBINING MARK ZEVOK +1CF2B ZNAMENNY COMBINING MARK SKOBA +1CF2C ZNAMENNY COMBINING MARK RAZSEKA +1CF2D ZNAMENNY COMBINING MARK KRYZH ON LEFT +@ Combining black marks +1CF30 ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO +1CF31 ZNAMENNY COMBINING TONAL RANGE MARK SVETLO +1CF32 ZNAMENNY COMBINING TONAL RANGE MARK TRESVETLO +1CF33 ZNAMENNY COMBINING MARK ZADERZHKA + = ottyazhka +1CF34 ZNAMENNY COMBINING MARK DEMESTVENNY ZADERZHKA +1CF35 ZNAMENNY COMBINING MARK OTSECHKA +1CF36 ZNAMENNY COMBINING MARK PODCHASHIE +1CF37 ZNAMENNY COMBINING MARK PODCHASHIE WITH VERTICAL STROKE +1CF38 ZNAMENNY COMBINING MARK CHASHKA +1CF39 ZNAMENNY COMBINING MARK CHASHKA POLNAYA +1CF3A ZNAMENNY COMBINING MARK OBLACHKO +1CF3B ZNAMENNY COMBINING MARK SOROCHYA NOZHKA + = sokolik +1CF3C ZNAMENNY COMBINING MARK TOCHKA +1CF3D ZNAMENNY COMBINING MARK DVOETOCHIE +1CF3E ZNAMENNY COMBINING ATTACHING VERTICAL OMET +1CF3F ZNAMENNY COMBINING MARK CURVED OMET +1CF40 ZNAMENNY COMBINING MARK KRYZH +1CF41 ZNAMENNY COMBINING LOWER TONAL RANGE INDICATOR +@ Modifying marks for priznaki +1CF42 ZNAMENNY PRIZNAK MODIFIER LEVEL-2 +1CF43 ZNAMENNY PRIZNAK MODIFIER LEVEL-3 +1CF44 ZNAMENNY PRIZNAK MODIFIER DIRECTION FLIP +1CF45 ZNAMENNY PRIZNAK MODIFIER KRYZH +1CF46 ZNAMENNY PRIZNAK MODIFIER ROG +@ Znamenny neumes +1CF50 ZNAMENNY NEUME KRYUK +1CF51 ZNAMENNY NEUME KRYUK TIKHY +1CF52 ZNAMENNY NEUME PARAKLIT +1CF53 ZNAMENNY NEUME DVA V CHELNU +1CF54 ZNAMENNY NEUME KLYUCH + = kryuk klyuchevoy +1CF55 ZNAMENNY NEUME ZANOZHEK +1CF56 ZNAMENNY NEUME STOPITSA +1CF57 ZNAMENNY NEUME STOPITSA S OCHKOM +1CF58 ZNAMENNY NEUME PEREVODKA +1CF59 ZNAMENNY NEUME PEREVODKA NEPOSTOYANNAYA +1CF5A ZNAMENNY NEUME STOPITSA WITH SOROCHYA NOZHKA + * not a decomposable character +1CF5B ZNAMENNY NEUME CHELYUSTKA +1CF5C ZNAMENNY NEUME PALKA +1CF5D ZNAMENNY NEUME ZAPYATAYA +1CF5E ZNAMENNY NEUME GOLUBCHIK BORZY +1CF5F ZNAMENNY NEUME GOLUBCHIK TIKHY +1CF60 ZNAMENNY NEUME GOLUBCHIK MRACHNY +1CF61 ZNAMENNY NEUME GOLUBCHIK SVETLY +1CF62 ZNAMENNY NEUME GOLUBCHIK TRESVETLY + = golubchik nepostoyanny +1CF63 ZNAMENNY NEUME VRAKHIYA PROSTAYA +1CF64 ZNAMENNY NEUME VRAKHIYA MRACHNAYA +1CF65 ZNAMENNY NEUME VRAKHIYA SVETLAYA +1CF66 ZNAMENNY NEUME VRAKHIYA TRESVETLAYA + = vrakhia nepostoyannaya +1CF67 ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA PROSTAYA +1CF68 ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA MRACHNAYA +1CF69 ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA SVETLAYA +1CF6A ZNAMENNY NEUME VRAKHIYA KLYUCHEVAYA TRESVETLAYA + = vrakhia klyuchevaya nepostoyannaya +1CF6B ZNAMENNY NEUME DOUBLE ZAPYATAYA +1CF6C ZNAMENNY NEUME REVERSED CHELYUSTKA +1CF6D ZNAMENNY NEUME DERBITSA +1CF6E ZNAMENNY NEUME KHAMILO +1CF6F ZNAMENNY NEUME CHASHKA +1CF70 ZNAMENNY NEUME PODCHASHIE +1CF71 ZNAMENNY NEUME SKAMEYTSA MRACHNAYA +1CF72 ZNAMENNY NEUME SKAMEYTSA SVETLAYA +1CF73 ZNAMENNY NEUME SKAMEYTSA TRESVETLAYA +1CF74 ZNAMENNY NEUME SKAMEYTSA TIKHAYA +1CF75 ZNAMENNY NEUME DEMESTVENNY KLYUCH + = skameytsa klyuchevaya +1CF76 ZNAMENNY NEUME SKAMEYTSA KLYUCHEVAYA SVETLAYA +1CF77 ZNAMENNY NEUME SKAMEYTSA KLYUCHENEPOSTOYANNAYA +1CF78 ZNAMENNY NEUME SKAMEYTSA KLYUCHEVAYA TIKHAYA +1CF79 ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA PROSTAYA +1CF7A ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA SVETLAYA +1CF7B ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA NEPOSTOYANNAYA +1CF7C ZNAMENNY NEUME SKAMEYTSA DVOECHELNAYA KLYUCHEVAYA +1CF7D ZNAMENNY NEUME SLOZHITIE +1CF7E ZNAMENNY NEUME SLOZHITIE S ZAPYATOY +1CF7F ZNAMENNY NEUME SLOZHITIE ZAKRYTOE +1CF80 ZNAMENNY NEUME SLOZHITIE S KRYZHEM +1CF81 ZNAMENNY NEUME KRYZH +1CF82 ZNAMENNY NEUME ROG +1CF83 ZNAMENNY NEUME FITA +1CF84 ZNAMENNY NEUME KOBYLA +1CF85 ZNAMENNY NEUME ZMEYTSA + = litso +1CF86 ZNAMENNY NEUME STATYA +1CF87 ZNAMENNY NEUME STATYA S ZAPYATOY +1CF88 ZNAMENNY NEUME STATYA S KRYZHEM +1CF89 ZNAMENNY NEUME STATYA S ZAPYATOY I KRYZHEM +1CF8A ZNAMENNY NEUME STATYA S KRYZHEM I ZAPYATOY +1CF8B ZNAMENNY NEUME STATYA ZAKRYTAYA +1CF8C ZNAMENNY NEUME STATYA ZAKRYTAYA S ZAPYATOY +1CF8D ZNAMENNY NEUME STATYA S ROGOM +1CF8E ZNAMENNY NEUME STATYA S DVUMYA ZAPYATYMI +1CF8F ZNAMENNY NEUME STATYA S ZAPYATOY I PODCHASHIEM +1CF90 ZNAMENNY NEUME POLKULIZMY + * not a decomposable character +1CF91 ZNAMENNY NEUME STATYA NEPOSTOYANNAYA +1CF92 ZNAMENNY NEUME STRELA PROSTAYA +1CF93 ZNAMENNY NEUME STRELA MRACHNOTIKHAYA +1CF94 ZNAMENNY NEUME STRELA KRYZHEVAYA + = strela polukryzhevaya +1CF95 ZNAMENNY NEUME STRELA POLUPOVODNAYA +1CF96 ZNAMENNY NEUME STRELA POVODNAYA +1CF97 ZNAMENNY NEUME STRELA NEPOSTOYANNAYA +1CF98 ZNAMENNY NEUME STRELA KLYUCHEPOVODNAYA +1CF99 ZNAMENNY NEUME STRELA KLYUCHENEPOSTOYANNAYA +1CF9A ZNAMENNY NEUME STRELA TIKHAYA PUTNAYA +1CF9B ZNAMENNY NEUME STRELA DVOECHELNAYA +1CF9C ZNAMENNY NEUME STRELA DVOECHELNOKRYZHEVAYA +1CF9D ZNAMENNY NEUME STRELA DVOECHELNOPOVODNAYA +1CF9E ZNAMENNY NEUME STRELA DVOECHELNAYA KLYUCHEVAYA +1CF9F ZNAMENNY NEUME STRELA DVOECHELNOPOVODNAYA KLYUCHEVAYA +1CFA0 ZNAMENNY NEUME STRELA GROMNAYA WITH SINGLE ZAPYATAYA +1CFA1 ZNAMENNY NEUME STRELA GROMOPOVODNAYA WITH SINGLE ZAPYATAYA +1CFA2 ZNAMENNY NEUME STRELA GROMNAYA +1CFA3 ZNAMENNY NEUME STRELA GROMOPOVODNAYA +1CFA4 ZNAMENNY NEUME STRELA GROMOPOVODNAYA WITH DOUBLE ZAPYATAYA +1CFA5 ZNAMENNY NEUME STRELA GROMOKRYZHEVAYA +1CFA6 ZNAMENNY NEUME STRELA GROMOKRYZHEVAYA POVODNAYA + = strela gromomrachnaya s kryzhem +1CFA7 ZNAMENNY NEUME MECHIK +1CFA8 ZNAMENNY NEUME MECHIK POVODNY +1CFA9 ZNAMENNY NEUME MECHIK KLYUCHEVOY +1CFAA ZNAMENNY NEUME MECHIK KLYUCHEPOVODNY +1CFAB ZNAMENNY NEUME MECHIK KLYUCHENEPOSTOYANNY +1CFAC ZNAMENNY NEUME STRELA TRYASOGLASNAYA +1CFAD ZNAMENNY NEUME STRELA TRYASOPOVODNAYA +1CFAE ZNAMENNY NEUME STRELA TRYASOSTRELNAYA +1CFAF ZNAMENNY NEUME OSOKA +1CFB0 ZNAMENNY NEUME OSOKA SVETLAYA +1CFB1 ZNAMENNY NEUME OSOKA TRESVETLAYA + = osoka nepostoyannaya +1CFB2 ZNAMENNY NEUME OSOKA KRYUKOVAYA SVETLAYA +1CFB3 ZNAMENNY NEUME OSOKA KLYUCHEVAYA SVETLAYA +1CFB4 ZNAMENNY NEUME OSOKA KLYUCHEVAYA NEPOSTOYANNAYA +1CFB5 ZNAMENNY NEUME STRELA KRYUKOVAYA +1CFB6 ZNAMENNY NEUME STRELA KRYUKOVAYA POVODNAYA +1CFB7 ZNAMENNY NEUME STRELA KRYUKOVAYA GROMNAYA WITH SINGLE ZAPYATAYA +1CFB8 ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA WITH SINGLE ZAPYATAYA +1CFB9 ZNAMENNY NEUME STRELA KRYUKOVAYA GROMNAYA +1CFBA ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA +1CFBB ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOPOVODNAYA WITH DOUBLE ZAPYATAYA +1CFBC ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOKRYZHEVAYA +1CFBD ZNAMENNY NEUME STRELA KRYUKOVAYA GROMOKRYZHEVAYA POVODNAYA + = strela kryukovaya gromomrachnaya s kryzhem +1CFBE ZNAMENNY NEUME STRELA KRYUKOVAYA TRYASKA +1CFBF ZNAMENNY NEUME KUFISMA +1CFC0 ZNAMENNY NEUME OBLAKO +1CFC1 ZNAMENNY NEUME DUDA +1CFC2 ZNAMENNY NEUME NEMKA +1CFC3 ZNAMENNY NEUME PAUK @@ 1D000 Byzantine Musical Symbols 1D0FF @@+ @ Prosodies (Prosodics) @@ -42943,6 +44614,11 @@ FFFF 1D1E7 MUSICAL SYMBOL KIEVAN EIGHTH NOTE STEM UP @ Accidental 1D1E8 MUSICAL SYMBOL KIEVAN FLAT SIGN +@ Iranian notation +@+ The following range is specific to Iranian classical music. +@ Accidentals for quarter tones +1D1E9 MUSICAL SYMBOL SORI +1D1EA MUSICAL SYMBOL KORON @@ 1D200 Ancient Greek Musical Notation 1D24F @ Ancient Greek vocalic notation @+ In a few instances vocalic and instrumental symbols have been unified with each other. In other instances they have been unified with regular Greek letters. @@ -43111,6 +44787,28 @@ FFFF 1D244 COMBINING GREEK MUSICAL PENTASEME x (metrical pentaseme - 23D9) 1D245 GREEK MUSICAL LEIMMA +@@ 1D2C0 Kaktovik Numerals 1D2DF +@ Numerals +1D2C0 KAKTOVIK NUMERAL ZERO +1D2C1 KAKTOVIK NUMERAL ONE +1D2C2 KAKTOVIK NUMERAL TWO +1D2C3 KAKTOVIK NUMERAL THREE +1D2C4 KAKTOVIK NUMERAL FOUR +1D2C5 KAKTOVIK NUMERAL FIVE +1D2C6 KAKTOVIK NUMERAL SIX +1D2C7 KAKTOVIK NUMERAL SEVEN +1D2C8 KAKTOVIK NUMERAL EIGHT +1D2C9 KAKTOVIK NUMERAL NINE +1D2CA KAKTOVIK NUMERAL TEN +1D2CB KAKTOVIK NUMERAL ELEVEN +1D2CC KAKTOVIK NUMERAL TWELVE +1D2CD KAKTOVIK NUMERAL THIRTEEN +1D2CE KAKTOVIK NUMERAL FOURTEEN +1D2CF KAKTOVIK NUMERAL FIFTEEN +1D2D0 KAKTOVIK NUMERAL SIXTEEN +1D2D1 KAKTOVIK NUMERAL SEVENTEEN +1D2D2 KAKTOVIK NUMERAL EIGHTEEN +1D2D3 KAKTOVIK NUMERAL NINETEEN @@ 1D2E0 Mayan Numerals 1D2FF @ Mayan numerals 1D2E0 MAYAN NUMERAL ZERO @@ -43588,57 +45286,93 @@ FFFF @ Script symbols @+ Script symbols already encoded in the Letterlike Symbols block are omitted here to avoid duplicate encoding. Fonts that use a less elaborate style are also acceptable for many uses, as long as they can be distinguished from serifed and italic styles. 1D49C MATHEMATICAL SCRIPT CAPITAL A + ~ 1D49C FE00 chancery style + ~ 1D49C FE01 roundhand style # 0041 latin capital letter a 1D49D x (script capital b - 212C) 1D49E MATHEMATICAL SCRIPT CAPITAL C + ~ 1D49E FE00 chancery style + ~ 1D49E FE01 roundhand style # 0043 latin capital letter c 1D49F MATHEMATICAL SCRIPT CAPITAL D + ~ 1D49F FE00 chancery style + ~ 1D49F FE01 roundhand style # 0044 latin capital letter d 1D4A0 x (script capital e - 2130) 1D4A1 x (script capital f - 2131) 1D4A2 MATHEMATICAL SCRIPT CAPITAL G + ~ 1D4A2 FE00 chancery style + ~ 1D4A2 FE01 roundhand style # 0047 latin capital letter g 1D4A3 x (script capital h - 210B) 1D4A4 x (script capital i - 2110) 1D4A5 MATHEMATICAL SCRIPT CAPITAL J + ~ 1D4A5 FE00 chancery style + ~ 1D4A5 FE01 roundhand style # 004A latin capital letter j 1D4A6 MATHEMATICAL SCRIPT CAPITAL K + ~ 1D4A6 FE00 chancery style + ~ 1D4A6 FE01 roundhand style # 004B latin capital letter k 1D4A7 x (script capital l - 2112) 1D4A8 x (script capital m - 2133) 1D4A9 MATHEMATICAL SCRIPT CAPITAL N + ~ 1D4A9 FE00 chancery style + ~ 1D4A9 FE01 roundhand style # 004E latin capital letter n 1D4AA MATHEMATICAL SCRIPT CAPITAL O + ~ 1D4AA FE00 chancery style + ~ 1D4AA FE01 roundhand style # 004F latin capital letter o 1D4AB MATHEMATICAL SCRIPT CAPITAL P = power set + ~ 1D4AB FE00 chancery style + ~ 1D4AB FE01 roundhand style # 0050 latin capital letter p 1D4AC MATHEMATICAL SCRIPT CAPITAL Q + ~ 1D4AC FE00 chancery style + ~ 1D4AC FE01 roundhand style # 0051 latin capital letter q 1D4AD x (script capital r - 211B) 1D4AE MATHEMATICAL SCRIPT CAPITAL S + ~ 1D4AE FE00 chancery style + ~ 1D4AE FE01 roundhand style # 0053 latin capital letter s 1D4AF MATHEMATICAL SCRIPT CAPITAL T + ~ 1D4AF FE00 chancery style + ~ 1D4AF FE01 roundhand style # 0054 latin capital letter t 1D4B0 MATHEMATICAL SCRIPT CAPITAL U + ~ 1D4B0 FE00 chancery style + ~ 1D4B0 FE01 roundhand style # 0055 latin capital letter u 1D4B1 MATHEMATICAL SCRIPT CAPITAL V + ~ 1D4B1 FE00 chancery style + ~ 1D4B1 FE01 roundhand style # 0056 latin capital letter v 1D4B2 MATHEMATICAL SCRIPT CAPITAL W + ~ 1D4B2 FE00 chancery style + ~ 1D4B2 FE01 roundhand style # 0057 latin capital letter w 1D4B3 MATHEMATICAL SCRIPT CAPITAL X + ~ 1D4B3 FE00 chancery style + ~ 1D4B3 FE01 roundhand style # 0058 latin capital letter x 1D4B4 MATHEMATICAL SCRIPT CAPITAL Y + ~ 1D4B4 FE00 chancery style + ~ 1D4B4 FE01 roundhand style # 0059 latin capital letter y 1D4B5 MATHEMATICAL SCRIPT CAPITAL Z + ~ 1D4B5 FE00 chancery style + ~ 1D4B5 FE01 roundhand style # 005A latin capital letter z 1D4B6 MATHEMATICAL SCRIPT SMALL A # 0061 latin small letter a @@ -45355,6 +47089,7 @@ FFFF # 0038 digit eight 1D7FF MATHEMATICAL MONOSPACE DIGIT NINE # 0039 digit nine +@~ Standardized Variation Sequences @@ 1D800 Sutton SignWriting 1DAAF @ Hand shapes with index finger 1D800 SIGNWRITING HAND-FIST INDEX @@ -46050,6 +47785,52 @@ FFFF 1DAAD SIGNWRITING ROTATION MODIFIER-14 1DAAE SIGNWRITING ROTATION MODIFIER-15 1DAAF SIGNWRITING ROTATION MODIFIER-16 +@@ 1DF00 Latin Extended-G 1DFFF +@ Extended IPA for disordered speech +1DF00 LATIN SMALL LETTER FENG DIGRAPH WITH TRILL +1DF01 LATIN SMALL LETTER REVERSED SCRIPT G +1DF02 LATIN LETTER SMALL CAPITAL TURNED G +1DF03 LATIN SMALL LETTER REVERSED K +1DF04 LATIN LETTER SMALL CAPITAL L WITH BELT +1DF05 LATIN SMALL LETTER LEZH WITH RETROFLEX HOOK +1DF06 LATIN SMALL LETTER TURNED Y WITH BELT +1DF07 LATIN SMALL LETTER REVERSED ENG +@ IPA extensions +1DF08 LATIN SMALL LETTER TURNED R WITH LONG LEG AND RETROFLEX HOOK +1DF09 LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +@ Clicks +1DF0B LATIN SMALL LETTER ESH WITH DOUBLE BAR +1DF0C LATIN SMALL LETTER ESH WITH DOUBLE BAR AND CURL +1DF0D LATIN SMALL LETTER TURNED T WITH CURL +1DF0E LATIN LETTER INVERTED GLOTTAL STOP WITH CURL +1DF0F LATIN LETTER STRETCHED C WITH CURL +1DF10 LATIN LETTER SMALL CAPITAL TURNED K +@ Lateral +1DF11 LATIN SMALL LETTER L WITH FISHHOOK +@ Letters with palatal hooks +1DF12 LATIN SMALL LETTER DEZH DIGRAPH WITH PALATAL HOOK +1DF13 LATIN SMALL LETTER L WITH BELT AND PALATAL HOOK +1DF14 LATIN SMALL LETTER ENG WITH PALATAL HOOK +1DF15 LATIN SMALL LETTER TURNED R WITH PALATAL HOOK +1DF16 LATIN SMALL LETTER R WITH FISHHOOK AND PALATAL HOOK +1DF17 LATIN SMALL LETTER TESH DIGRAPH WITH PALATAL HOOK +1DF18 LATIN SMALL LETTER EZH WITH PALATAL HOOK +@ Letters with retroflex hooks +1DF19 LATIN SMALL LETTER DEZH DIGRAPH WITH RETROFLEX HOOK +1DF1A LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK +1DF1B LATIN SMALL LETTER O WITH RETROFLEX HOOK +1DF1C LATIN SMALL LETTER TESH DIGRAPH WITH RETROFLEX HOOK +1DF1D LATIN SMALL LETTER C WITH RETROFLEX HOOK +@ IPA extension +1DF1E LATIN SMALL LETTER S WITH CURL +@ Letters for Malayalam transliteration +1DF25 LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK +1DF26 LATIN SMALL LETTER L WITH MID-HEIGHT LEFT HOOK +1DF27 LATIN SMALL LETTER N WITH MID-HEIGHT LEFT HOOK +1DF28 LATIN SMALL LETTER R WITH MID-HEIGHT LEFT HOOK +1DF29 LATIN SMALL LETTER S WITH MID-HEIGHT LEFT HOOK +1DF2A LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK @@ 1E000 Glagolitic Supplement 1E02F @ Combining letters 1E000 COMBINING GLAGOLITIC LETTER AZU @@ -46090,6 +47871,140 @@ FFFF 1E028 COMBINING GLAGOLITIC LETTER BIG YUS 1E029 COMBINING GLAGOLITIC LETTER IOTATED BIG YUS 1E02A COMBINING GLAGOLITIC LETTER FITA +@@ 1E030 Cyrillic Extended-D 1E08F +@+ These are phonetic extensions, used in a manner analogous to IPA. Additional Cyrillic modifier letters are found in other blocks. + x (modifier letter cyrillic en - 1D78) + x (modifier letter cyrillic hard sign - A69C) + x (modifier letter cyrillic soft sign - A69D) +@ Superscript modifier letters +1E030 MODIFIER LETTER CYRILLIC SMALL A + # 0430 +1E031 MODIFIER LETTER CYRILLIC SMALL BE + # 0431 +1E032 MODIFIER LETTER CYRILLIC SMALL VE + # 0432 +1E033 MODIFIER LETTER CYRILLIC SMALL GHE + # 0433 +1E034 MODIFIER LETTER CYRILLIC SMALL DE + # 0434 +1E035 MODIFIER LETTER CYRILLIC SMALL IE + # 0435 +1E036 MODIFIER LETTER CYRILLIC SMALL ZHE + # 0436 +1E037 MODIFIER LETTER CYRILLIC SMALL ZE + # 0437 +1E038 MODIFIER LETTER CYRILLIC SMALL I + # 0438 +1E039 MODIFIER LETTER CYRILLIC SMALL KA + # 043A +1E03A MODIFIER LETTER CYRILLIC SMALL EL + # 043B +1E03B MODIFIER LETTER CYRILLIC SMALL EM + # 043C +1E03C MODIFIER LETTER CYRILLIC SMALL O + # 043E +1E03D MODIFIER LETTER CYRILLIC SMALL PE + # 043F +1E03E MODIFIER LETTER CYRILLIC SMALL ER + # 0440 +1E03F MODIFIER LETTER CYRILLIC SMALL ES + # 0441 +1E040 MODIFIER LETTER CYRILLIC SMALL TE + # 0442 +1E041 MODIFIER LETTER CYRILLIC SMALL U + # 0443 +1E042 MODIFIER LETTER CYRILLIC SMALL EF + # 0444 +1E043 MODIFIER LETTER CYRILLIC SMALL HA + # 0445 +1E044 MODIFIER LETTER CYRILLIC SMALL TSE + # 0446 +1E045 MODIFIER LETTER CYRILLIC SMALL CHE + # 0447 +1E046 MODIFIER LETTER CYRILLIC SMALL SHA + # 0448 +1E047 MODIFIER LETTER CYRILLIC SMALL YERU + # 044B +1E048 MODIFIER LETTER CYRILLIC SMALL E + # 044D +1E049 MODIFIER LETTER CYRILLIC SMALL YU + # 044E +1E04A MODIFIER LETTER CYRILLIC SMALL DZZE + # A689 +1E04B MODIFIER LETTER CYRILLIC SMALL SCHWA + # 04D9 +1E04C MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I + # 0456 +1E04D MODIFIER LETTER CYRILLIC SMALL JE + # 0458 +1E04E MODIFIER LETTER CYRILLIC SMALL BARRED O + # 04E9 +1E04F MODIFIER LETTER CYRILLIC SMALL STRAIGHT U + # 04AF +1E050 MODIFIER LETTER CYRILLIC SMALL PALOCHKA + # 04CF +@ Subscript modifier letters +1E051 CYRILLIC SUBSCRIPT SMALL LETTER A + # 0430 +1E052 CYRILLIC SUBSCRIPT SMALL LETTER BE + # 0431 +1E053 CYRILLIC SUBSCRIPT SMALL LETTER VE + # 0432 +1E054 CYRILLIC SUBSCRIPT SMALL LETTER GHE + # 0433 +1E055 CYRILLIC SUBSCRIPT SMALL LETTER DE + # 0434 +1E056 CYRILLIC SUBSCRIPT SMALL LETTER IE + # 0435 +1E057 CYRILLIC SUBSCRIPT SMALL LETTER ZHE + # 0436 +1E058 CYRILLIC SUBSCRIPT SMALL LETTER ZE + # 0437 +1E059 CYRILLIC SUBSCRIPT SMALL LETTER I + # 0438 +1E05A CYRILLIC SUBSCRIPT SMALL LETTER KA + # 043A +1E05B CYRILLIC SUBSCRIPT SMALL LETTER EL + # 043B +1E05C CYRILLIC SUBSCRIPT SMALL LETTER O + # 043E +1E05D CYRILLIC SUBSCRIPT SMALL LETTER PE + # 043F +1E05E CYRILLIC SUBSCRIPT SMALL LETTER ES + # 0441 +1E05F CYRILLIC SUBSCRIPT SMALL LETTER U + # 0443 +1E060 CYRILLIC SUBSCRIPT SMALL LETTER EF + # 0444 +1E061 CYRILLIC SUBSCRIPT SMALL LETTER HA + # 0445 +1E062 CYRILLIC SUBSCRIPT SMALL LETTER TSE + # 0446 +1E063 CYRILLIC SUBSCRIPT SMALL LETTER CHE + # 0447 +1E064 CYRILLIC SUBSCRIPT SMALL LETTER SHA + # 0448 +1E065 CYRILLIC SUBSCRIPT SMALL LETTER HARD SIGN + # 044A +1E066 CYRILLIC SUBSCRIPT SMALL LETTER YERU + # 044B +1E067 CYRILLIC SUBSCRIPT SMALL LETTER GHE WITH UPTURN + # 0491 +1E068 CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I + # 0456 +1E069 CYRILLIC SUBSCRIPT SMALL LETTER DZE + # 0455 +1E06A CYRILLIC SUBSCRIPT SMALL LETTER DZHE + # 045F +@ Superscript modifier letters +1E06B MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER + # 04AB +1E06C MODIFIER LETTER CYRILLIC SMALL YERU WITH BACK YER + # A651 +1E06D MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE + # 04B1 +@ Diacritical mark +1E08F COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I @@ 1E100 Nyiakeng Puachue Hmong 1E14F @+ The Nyiakeng Puachue Hmong script (Nyiaj Keeb Puaj Txwm in RPA orthography) is also known as Pa Dao (Paj Ntaub) and Chervang script (Txawj Vaag). @ Consonant onsets @@ -46207,6 +48122,41 @@ FFFF 1E14F NYIAKENG PUACHUE HMONG CIRCLED CA * used to indicate ownership x (nyiakeng puachue hmong letter ca - 1E108) +@@ 1E290 Toto 1E2BF +@ Basic consonants +1E290 TOTO LETTER PA +1E291 TOTO LETTER BA +1E292 TOTO LETTER TA +1E293 TOTO LETTER DA +1E294 TOTO LETTER KA +1E295 TOTO LETTER GA +1E296 TOTO LETTER MA +1E297 TOTO LETTER NA +1E298 TOTO LETTER NGA +1E299 TOTO LETTER SA +1E29A TOTO LETTER CHA +1E29B TOTO LETTER YA +1E29C TOTO LETTER WA +1E29D TOTO LETTER JA +1E29E TOTO LETTER HA +1E29F TOTO LETTER RA +1E2A0 TOTO LETTER LA +@ Basic vowels +1E2A1 TOTO LETTER I +1E2A2 TOTO LETTER BREATHY I +1E2A3 TOTO LETTER IU +1E2A4 TOTO LETTER BREATHY IU +1E2A5 TOTO LETTER U +1E2A6 TOTO LETTER E +1E2A7 TOTO LETTER BREATHY E +1E2A8 TOTO LETTER EO +1E2A9 TOTO LETTER BREATHY EO +1E2AA TOTO LETTER O +1E2AB TOTO LETTER AE +1E2AC TOTO LETTER BREATHY AE +1E2AD TOTO LETTER A +@ Sign +1E2AE TOTO SIGN RISING TONE @@ 1E2C0 Wancho 1E2FF @ Letters 1E2C0 WANCHO LETTER AA @@ -46273,6 +48223,116 @@ FFFF 1E2FF WANCHO NGUN SIGN = rupee x (indian rupee sign - 20B9) +@@ 1E4D0 Nag Mundari 1E4FF +@ Letters +1E4D0 NAG MUNDARI LETTER O +1E4D1 NAG MUNDARI LETTER OP +1E4D2 NAG MUNDARI LETTER OL +1E4D3 NAG MUNDARI LETTER OY +1E4D4 NAG MUNDARI LETTER ONG +1E4D5 NAG MUNDARI LETTER A +1E4D6 NAG MUNDARI LETTER AJ +1E4D7 NAG MUNDARI LETTER AB +1E4D8 NAG MUNDARI LETTER ANY +1E4D9 NAG MUNDARI LETTER AH +1E4DA NAG MUNDARI LETTER I +1E4DB NAG MUNDARI LETTER IS +1E4DC NAG MUNDARI LETTER IDD +1E4DD NAG MUNDARI LETTER IT +1E4DE NAG MUNDARI LETTER IH +1E4DF NAG MUNDARI LETTER U +1E4E0 NAG MUNDARI LETTER UC +1E4E1 NAG MUNDARI LETTER UD +1E4E2 NAG MUNDARI LETTER UK +1E4E3 NAG MUNDARI LETTER UR +1E4E4 NAG MUNDARI LETTER E +1E4E5 NAG MUNDARI LETTER ENN +1E4E6 NAG MUNDARI LETTER EG +1E4E7 NAG MUNDARI LETTER EM +1E4E8 NAG MUNDARI LETTER EN +1E4E9 NAG MUNDARI LETTER ETT +1E4EA NAG MUNDARI LETTER ELL +@ Various signs +1E4EB NAG MUNDARI SIGN OJOD + * precedes modified letters such as AB or UD + * may indicate consonant gemination +1E4EC NAG MUNDARI SIGN MUHOR + * vowel nasalization +1E4ED NAG MUNDARI SIGN TOYOR + * indicates a long vowel +1E4EE NAG MUNDARI SIGN IKIR + * vowel preceded by the 'w' sound +1E4EF NAG MUNDARI SIGN SUTUH + * mostly used for close transliteration of other languages +@ Digits +1E4F0 NAG MUNDARI DIGIT ZERO +1E4F1 NAG MUNDARI DIGIT ONE +1E4F2 NAG MUNDARI DIGIT TWO +1E4F3 NAG MUNDARI DIGIT THREE +1E4F4 NAG MUNDARI DIGIT FOUR +1E4F5 NAG MUNDARI DIGIT FIVE +1E4F6 NAG MUNDARI DIGIT SIX +1E4F7 NAG MUNDARI DIGIT SEVEN +1E4F8 NAG MUNDARI DIGIT EIGHT +1E4F9 NAG MUNDARI DIGIT NINE +@@ 1E7E0 Ethiopic Extended-B 1E7FF +@ Syllables for Gurage +1E7E0 ETHIOPIC SYLLABLE HHYA + x (ethiopic syllable xya - 2DD0) +1E7E1 ETHIOPIC SYLLABLE HHYU + x (ethiopic syllable xyu - 2DD1) +1E7E2 ETHIOPIC SYLLABLE HHYI + x (ethiopic syllable xyi - 2DD2) +1E7E3 ETHIOPIC SYLLABLE HHYAA + x (ethiopic syllable xyaa - 2DD3) +1E7E4 ETHIOPIC SYLLABLE HHYEE + x (ethiopic syllable xyee - 2DD4) +1E7E5 ETHIOPIC SYLLABLE HHYE + x (ethiopic syllable xye - 2DD5) +1E7E6 ETHIOPIC SYLLABLE HHYO + x (ethiopic syllable xyo - 2DD6) +1E7E8 ETHIOPIC SYLLABLE GURAGE HHWA + x (ethiopic syllable kxwa - 12C0) +1E7E9 ETHIOPIC SYLLABLE HHWI + x (ethiopic syllable kxwi - 12C2) +1E7EA ETHIOPIC SYLLABLE HHWEE + x (ethiopic syllable kxwee - 12C4) +1E7EB ETHIOPIC SYLLABLE HHWE + x (ethiopic syllable kxwe - 12C5) +1E7ED ETHIOPIC SYLLABLE GURAGE MWI + x (ethiopic syllable mwi - 1381) +1E7EE ETHIOPIC SYLLABLE GURAGE MWEE + x (ethiopic syllable mwee - 1382) +1E7F0 ETHIOPIC SYLLABLE GURAGE QWI + x (ethiopic syllable qwi - 124A) +1E7F1 ETHIOPIC SYLLABLE GURAGE QWEE + x (ethiopic syllable qwee - 124C) +1E7F2 ETHIOPIC SYLLABLE GURAGE QWE + x (ethiopic syllable qwe - 124D) +1E7F3 ETHIOPIC SYLLABLE GURAGE BWI + x (ethiopic syllable bwi - 1385) +1E7F4 ETHIOPIC SYLLABLE GURAGE BWEE + x (ethiopic syllable bwee - 1386) +1E7F5 ETHIOPIC SYLLABLE GURAGE KWI + x (ethiopic syllable kwi - 12B2) +1E7F6 ETHIOPIC SYLLABLE GURAGE KWEE + x (ethiopic syllable kwee - 12B4) +1E7F7 ETHIOPIC SYLLABLE GURAGE KWE + x (ethiopic syllable kwe - 12B5) +1E7F8 ETHIOPIC SYLLABLE GURAGE GWI + x (ethiopic syllable gwi - 1312) +1E7F9 ETHIOPIC SYLLABLE GURAGE GWEE + x (ethiopic syllable gwee - 1314) +1E7FA ETHIOPIC SYLLABLE GURAGE GWE + x (ethiopic syllable gwe - 1315) +1E7FB ETHIOPIC SYLLABLE GURAGE FWI + x (ethiopic syllable fwi - 1389) +1E7FC ETHIOPIC SYLLABLE GURAGE FWEE + x (ethiopic syllable fwee - 138A) +1E7FD ETHIOPIC SYLLABLE GURAGE PWI + x (ethiopic syllable pwi - 138D) +1E7FE ETHIOPIC SYLLABLE GURAGE PWEE + x (ethiopic syllable pwee - 138E) @@ 1E800 Mende Kikakui 1E8DF @+ Annotations refer to the syllabaries of Amara Mansaray and David Dalby. @ Syllables in k- @@ -48671,9 +50731,11 @@ FFFF 1F448 WHITE LEFT POINTING BACKHAND INDEX x (white left pointing index - 261C) x (black left pointing backhand index - 1F59C) + x (leftwards hand - 1FAF2) 1F449 WHITE RIGHT POINTING BACKHAND INDEX x (white right pointing index - 261E) x (black right pointing backhand index - 1F59D) + x (rightwards hand - 1FAF1) 1F44A FISTED HAND SIGN = punch x (raised fist - 270A) @@ -48745,6 +50807,7 @@ FFFF @ Fairy tale symbols 1F478 PRINCESS x (prince - 1F934) + x (person with crown - 1FAC5) 1F479 JAPANESE OGRE 1F47A JAPANESE GOBLIN 1F47B GHOST @@ -48803,6 +50866,7 @@ FFFF x (heavy black heart - 2764) x (white heart - 1F90D) x (orange heart - 1F9E1) + x (light blue heart - 1FA75) 1F49A GREEN HEART 1F49B YELLOW HEART 1F49C PURPLE HEART @@ -48826,6 +50890,7 @@ FFFF 1F4A7 DROPLET * represents a drop of sweat or drop of water x (black droplet - 1F322) + x (drop of blood - 1FA78) 1F4A8 DASH SYMBOL = running dash, briffits 1F4A9 PILE OF POO @@ -49005,6 +51070,7 @@ FFFF 1F50A SPEAKER WITH THREE SOUND WAVES = sound 1F50B BATTERY + x (low battery - 1FAAB) 1F50C ELECTRIC PLUG 1F50D LEFT-POINTING MAGNIFYING GLASS = search @@ -49422,6 +51488,7 @@ FFFF = rated for sex = kiss x (kiss mark - 1F48B) + x (biting lip - 1FAE6) 1F5E3 SPEAKING HEAD IN SILHOUETTE = rated for strong language @ Sound symbols @@ -49810,6 +51877,10 @@ FFFF 1F6D6 HUT 1F6D7 ELEVATOR @ Miscellaneous symbols +1F6DC WIRELESS +1F6DD PLAYGROUND SLIDE +1F6DE WHEEL +1F6DF RING BUOY 1F6E0 HAMMER AND WRENCH = tools, repair facility x (hammer and pick - 2692) @@ -49941,8 +52012,9 @@ FFFF x (alchemical symbol for sal-ammoniac - 1F739) 1F728 ALCHEMICAL SYMBOL FOR VERDIGRIS = aes viride, copper subacetate - = early astronomical symbol for earth + = astronomical symbol for earth x (circled plus - 2295) + x (earth - 2641) @ Symbols for tin and lead ore 1F729 ALCHEMICAL SYMBOL FOR TIN ORE x (jupiter - 2643) @@ -50081,10 +52153,27 @@ FFFF @ Measures 1F772 ALCHEMICAL SYMBOL FOR HALF DRAM = drachma semis + * handwritten ligature of 0292 + 00DF, typically spelled out as ʒss x (latin small letter ezh - 0292) 1F773 ALCHEMICAL SYMBOL FOR HALF OUNCE = uncia semis + * handwritten ligature of 2125 + 00DF, typically spelled out as 2125 ss x (ounce sign - 2125) +@ Other symbol +1F774 LOT OF FORTUNE + = pars fortunae + x (circled times - 2297) +@ Eclipse symbols +1F775 OCCULTATION + x (conjunction - 260C) +1F776 LUNAR ECLIPSE + x (opposition - 260D) +@ Symbols for dwarf planets +1F77B HAUMEA +1F77C MAKEMAKE +1F77D GONGGONG +1F77E QUAOAR +1F77F ORCUS @@ 1F780 Geometric Shapes Extended 1F7FF @+ These geometric shapes originate from the Webdings/Wingdings collections. @ Isosceles right triangles @@ -50238,6 +52327,9 @@ FFFF 1F7D6 NEGATIVE CIRCLED TRIANGLE 1F7D7 CIRCLED SQUARE 1F7D8 NEGATIVE CIRCLED SQUARE +@ Nine pointed star +1F7D9 NINE POINTED WHITE STAR + * commonly used by members of the Bahá'í faith @ Colored circles @+ For use with emoji. Constitute a set as follows: 26AA, 26AB, 1F534, 1F535, 1F7E0-1F7E4 1F7E0 LARGE ORANGE CIRCLE @@ -50254,6 +52346,14 @@ FFFF 1F7E9 LARGE GREEN SQUARE 1F7EA LARGE PURPLE SQUARE 1F7EB LARGE BROWN SQUARE +@ Miscellaneous symbol +1F7F0 HEAVY EQUALS SIGN + * symbol of equality + x (equals sign - 003D) + x (heavy multiplication x - 2716) + x (heavy plus sign - 2795) + x (geta mark - 3013) + x (roman sextans sign - 10190) @@ 1F800 Supplemental Arrows-C 1F8FF @ Arrows with triangle arrowheads 1F800 LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD @@ -50457,7 +52557,7 @@ FFFF @ Hand symbol 1F90C PINCHED FINGERS @ Colored heart symbols -@+ For use with emoji. Constitute a set as follows: 2764, 1F499-1F49C, 1F5A4, 1F90D, 1F90E, and 1F9E1. +@+ For use with emoji. Constitute a set as follows: 2764, 1F499-1F49C, 1F5A4, 1F90D, 1F90E, 1F9E1, and 1FA75-1FA77. 1F90D WHITE HEART 1F90E BROWN HEART @ Hand symbol @@ -50477,9 +52577,12 @@ FFFF 1F919 CALL ME HAND 1F91A RAISED BACK OF HAND 1F91B LEFT-FACING FIST + x (leftwards hand - 1FAF2) 1F91C RIGHT-FACING FIST + x (rightwards hand - 1FAF1) 1F91D HANDSHAKE 1F91E HAND WITH INDEX AND MIDDLE FINGERS CROSSED + x (hand with index finger and thumb crossed - 1FAF0) 1F91F I LOVE YOU HAND SIGN * can be abbreviated ILY @ Emoticon faces @@ -50504,6 +52607,7 @@ FFFF 1F92F SHOCKED FACE WITH EXPLODING HEAD @ Portrait and role symbols 1F930 PREGNANT WOMAN + x (pregnant person - 1FAC4) 1F931 BREAST-FEEDING 1F932 PALMS UP TOGETHER * used for prayer in some cultures @@ -50581,6 +52685,7 @@ FFFF = chicken egg 1F95B GLASS OF MILK = milk + x (pouring liquid - 1FAD7) 1F95C PEANUTS 1F95D KIWIFRUIT 1F95E PANCAKES @@ -50622,6 +52727,7 @@ FFFF 1F976 FREEZING FACE 1F977 NINJA 1F978 DISGUISED FACE +1F979 FACE HOLDING BACK TEARS 1F97A FACE WITH PLEADING EYES @ Clothing 1F97B SARI @@ -50724,6 +52830,8 @@ FFFF 1F9C9 MATE DRINK 1F9CA ICE CUBE 1F9CB BUBBLE TEA +@ Fantasy being +1F9CC TROLL @ Portrait and accessibility symbols 1F9CD STANDING PERSON 1F9CE KNEELING PERSON @@ -50968,10 +53076,19 @@ FFFF 1FA72 BRIEFS 1FA73 SHORTS 1FA74 THONG SANDAL + = flip flop +@ Colored heart symbols +@+ For use with emoji. Constitute a set as follows: 2764, 1F499-1F49C, 1F5A4, 1F90D, 1F90E, 1F9E1, and 1FA75-1FA77. +1FA75 LIGHT BLUE HEART +1FA76 GREY HEART +1FA77 PINK HEART @ Medical symbols 1FA78 DROP OF BLOOD + x (droplet - 1F4A7) 1FA79 ADHESIVE BANDAGE 1FA7A STETHOSCOPE +1FA7B X-RAY +1FA7C CRUTCH @ Toys and sport symbols 1FA80 YO-YO 1FA81 KITE @@ -50980,6 +53097,9 @@ FFFF 1FA84 MAGIC WAND 1FA85 PINATA 1FA86 NESTING DOLLS +@ Musical instruments +1FA87 MARACAS +1FA88 FLUTE @ Miscellaneous objects 1FA90 RINGED PLANET 1FA91 CHAIR @@ -51006,6 +53126,17 @@ FFFF 1FAA6 HEADSTONE 1FAA7 PLACARD 1FAA8 ROCK +1FAA9 MIRROR BALL +1FAAA IDENTIFICATION CARD + = ID +1FAAB LOW BATTERY + x (battery - 1F50B) +1FAAC HAMSA +1FAAD FOLDING HAND FAN +1FAAE HAIR PICK +@ Religious symbol +1FAAF KHANDA + x (adi shakti - 262C) @ Animals and nature 1FAB0 FLY 1FAB1 WORM @@ -51014,11 +53145,27 @@ FFFF 1FAB4 POTTED PLANT 1FAB5 WOOD 1FAB6 FEATHER +1FAB7 LOTUS +1FAB8 CORAL +1FAB9 EMPTY NEST +1FABA NEST WITH EGGS +1FABB HYACINTH +1FABC JELLYFISH +1FABD WING +1FABF GOOSE @ Body parts 1FAC0 ANATOMICAL HEART 1FAC1 LUNGS @ People 1FAC2 PEOPLE HUGGING +1FAC3 PREGNANT MAN +1FAC4 PREGNANT PERSON + x (pregnant woman - 1F930) +1FAC5 PERSON WITH CROWN + x (princess - 1F478) +@ Animals and nature +1FACE MOOSE +1FACF DONKEY @ Food and drink 1FAD0 BLUEBERRIES 1FAD1 BELL PEPPER @@ -51027,6 +53174,36 @@ FFFF 1FAD4 TAMALE 1FAD5 FONDUE 1FAD6 TEAPOT +1FAD7 POURING LIQUID + x (glass of milk - 1F95B) +1FAD8 BEANS +1FAD9 JAR +1FADA GINGER ROOT +1FADB PEA POD +@ Faces +1FAE0 MELTING FACE +1FAE1 SALUTING FACE +1FAE2 FACE WITH OPEN EYES AND HAND OVER MOUTH +1FAE3 FACE WITH PEEKING EYE +1FAE4 FACE WITH DIAGONAL MOUTH +1FAE5 DOTTED LINE FACE +@ Emotion +1FAE6 BITING LIP + x (lips - 1F5E2) +1FAE7 BUBBLES +@ Face +1FAE8 SHAKING FACE +@ Hand symbols +1FAF0 HAND WITH INDEX FINGER AND THUMB CROSSED + x (hand with index and middle fingers crossed - 1F91E) +1FAF1 RIGHTWARDS HAND +1FAF2 LEFTWARDS HAND +1FAF3 PALM DOWN HAND +1FAF4 PALM UP HAND +1FAF5 INDEX POINTING AT THE VIEWER +1FAF6 HEART HANDS +1FAF7 LEFTWARDS PUSHING HAND +1FAF8 RIGHTWARDS PUSHING HAND @@ 1FB00 Symbols for Legacy Computing 1FBFF @ Block mosaic terminal graphic characters @+ The term "sextant" refers to block mosaics divided into six parts. @@ -51342,8 +53519,8 @@ FFFF @+ These codes are intended for process-internal uses. 1FFFE 1FFFF -@@ 20000 CJK Unified Ideographs Extension B 2A6DD -@@ 2A700 CJK Unified Ideographs Extension C 2B734 +@@ 20000 CJK Unified Ideographs Extension B 2A6DF +@@ 2A700 CJK Unified Ideographs Extension C 2B739 @@ 2B740 CJK Unified Ideographs Extension D 2B81D @@ 2B820 CJK Unified Ideographs Extension E 2CEA1 @@ 2CEB0 CJK Unified Ideographs Extension F 2EBE0 @@ -51440,6 +53617,7 @@ FFFF 2F82B CJK COMPATIBILITY IDEOGRAPH-2F82B : 5317 2F82C CJK COMPATIBILITY IDEOGRAPH-2F82C + x 20984 : 5349 2F82D CJK COMPATIBILITY IDEOGRAPH-2F82D : 5351 @@ -51470,6 +53648,7 @@ FFFF 2F83A CJK COMPATIBILITY IDEOGRAPH-2F83A : 53F1 2F83B CJK COMPATIBILITY IDEOGRAPH-2F83B + x 4DB8 : 5406 2F83C CJK COMPATIBILITY IDEOGRAPH-2F83C : 549E @@ -51546,6 +53725,7 @@ FFFF 2F85F CJK COMPATIBILITY IDEOGRAPH-2F85F : 5962 2F860 CJK COMPATIBILITY IDEOGRAPH-2F860 + x 216A7 : 216A8 2F861 CJK COMPATIBILITY IDEOGRAPH-2F861 : 216EA @@ -51586,6 +53766,7 @@ FFFF 2F873 CJK COMPATIBILITY IDEOGRAPH-2F873 : 5C06 2F874 CJK COMPATIBILITY IDEOGRAPH-2F874 + x 22450 : 5F53 2F875 CJK COMPATIBILITY IDEOGRAPH-2F875 : 5C22 @@ -51594,6 +53775,7 @@ FFFF 2F877 CJK COMPATIBILITY IDEOGRAPH-2F877 : 5C60 2F878 CJK COMPATIBILITY IDEOGRAPH-2F878 + x 4DB9 : 5C6E 2F879 CJK COMPATIBILITY IDEOGRAPH-2F879 : 5CC0 @@ -51835,6 +54017,7 @@ FFFF 2F8EF CJK COMPATIBILITY IDEOGRAPH-2F8EF : 6B21 2F8F0 CJK COMPATIBILITY IDEOGRAPH-2F8F0 + x 4DBE : 238A7 2F8F1 CJK COMPATIBILITY IDEOGRAPH-2F8F1 : 6B54 @@ -51861,6 +54044,7 @@ FFFF 2F8FC CJK COMPATIBILITY IDEOGRAPH-2F8FC : 6CBF 2F8FD CJK COMPATIBILITY IDEOGRAPH-2F8FD + x 2DC09 : 6CCD 2F8FE CJK COMPATIBILITY IDEOGRAPH-2F8FE : 6C67 @@ -51877,6 +54061,7 @@ FFFF 2F904 CJK COMPATIBILITY IDEOGRAPH-2F904 : 6D78 2F905 CJK COMPATIBILITY IDEOGRAPH-2F905 + x 23D40 : 6D85 2F906 CJK COMPATIBILITY IDEOGRAPH-2F906 : 23D1E @@ -51895,6 +54080,7 @@ FFFF 2F90D CJK COMPATIBILITY IDEOGRAPH-2F90D : 23ED1 2F90E CJK COMPATIBILITY IDEOGRAPH-2F90E + x 23F1C : 6DF9 2F90F CJK COMPATIBILITY IDEOGRAPH-2F90F : 6F6E @@ -51923,6 +54109,7 @@ FFFF 2F91B CJK COMPATIBILITY IDEOGRAPH-2F91B : 20525 2F91C CJK COMPATIBILITY IDEOGRAPH-2F91C + x 242B3 : 7145 2F91D CJK COMPATIBILITY IDEOGRAPH-2F91D : 24263 @@ -51945,6 +54132,7 @@ FFFF 2F926 CJK COMPATIBILITY IDEOGRAPH-2F926 : 24735 2F927 CJK COMPATIBILITY IDEOGRAPH-2F927 + x 2AEC5 : 24814 2F928 CJK COMPATIBILITY IDEOGRAPH-2F928 : 737A @@ -52001,6 +54189,7 @@ FFFF 2F942 CJK COMPATIBILITY IDEOGRAPH-2F942 : 250F2 2F943 CJK COMPATIBILITY IDEOGRAPH-2F943 + x 2511A : 25119 2F944 CJK COMPATIBILITY IDEOGRAPH-2F944 : 25133 @@ -52017,6 +54206,7 @@ FFFF 2F94A CJK COMPATIBILITY IDEOGRAPH-2F94A : 778B 2F94B CJK COMPATIBILITY IDEOGRAPH-2F94B + x 25271 : 4046 2F94C CJK COMPATIBILITY IDEOGRAPH-2F94C : 4096 @@ -52451,6 +54641,7 @@ FFFF 2FFFE 2FFFF @@ 30000 CJK Unified Ideographs Extension G 3134A +@@ 31350 CJK Unified Ideographs Extension H 323AF @@ 3FF80 Unassigned 3FFFF @ Noncharacters @+ These codes are intended for process-internal uses. diff --git a/third_party/ucd/PropertyValueAliases.txt b/third_party/ucd/PropertyValueAliases.txt index 2023baf4..863301b1 100644 --- a/third_party/ucd/PropertyValueAliases.txt +++ b/third_party/ucd/PropertyValueAliases.txt @@ -1,11 +1,11 @@ -# PropertyValueAliases-13.0.0.txt -# Date: 2019-11-13, 21:52:10 GMT -# © 2019 Unicode®, Inc. +# PropertyValueAliases-15.0.0.txt +# Date: 2022-08-05, 23:42:17 GMT +# © 2022 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/ # # This file contains aliases for property values used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression @@ -89,6 +89,8 @@ age; 11.0 ; V11_0 age; 12.0 ; V12_0 age; 12.1 ; V12_1 age; 13.0 ; V13_0 +age; 14.0 ; V14_0 +age; 15.0 ; V15_0 age; NA ; Unassigned # Alphabetic (Alpha) @@ -134,7 +136,6 @@ Bidi_M; Y ; Yes ; T # Bidi_Mirroring_Glyph (bmg) -# @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; # Bidi_Paired_Bracket (bpb) @@ -160,6 +161,8 @@ blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers blk; Ancient_Symbols ; Ancient_Symbols blk; Arabic ; Arabic blk; Arabic_Ext_A ; Arabic_Extended_A +blk; Arabic_Ext_B ; Arabic_Extended_B +blk; Arabic_Ext_C ; Arabic_Extended_C blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A blk; Arabic_PF_B ; Arabic_Presentation_Forms_B @@ -204,6 +207,7 @@ blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F blk; CJK_Ext_G ; CJK_Unified_Ideographs_Extension_G +blk; CJK_Ext_H ; CJK_Unified_Ideographs_Extension_H blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement blk; CJK_Strokes ; CJK_Strokes blk; CJK_Symbols ; CJK_Symbols_And_Punctuation @@ -216,14 +220,17 @@ blk; Cuneiform ; Cuneiform blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation blk; Currency_Symbols ; Currency_Symbols blk; Cypriot_Syllabary ; Cypriot_Syllabary +blk; Cypro_Minoan ; Cypro_Minoan blk; Cyrillic ; Cyrillic blk; Cyrillic_Ext_A ; Cyrillic_Extended_A blk; Cyrillic_Ext_B ; Cyrillic_Extended_B blk; Cyrillic_Ext_C ; Cyrillic_Extended_C +blk; Cyrillic_Ext_D ; Cyrillic_Extended_D blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary blk; Deseret ; Deseret blk; Devanagari ; Devanagari blk; Devanagari_Ext ; Devanagari_Extended +blk; Devanagari_Ext_A ; Devanagari_Extended_A blk; Diacriticals ; Combining_Diacritical_Marks blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols @@ -246,6 +253,7 @@ blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement blk; Ethiopic ; Ethiopic blk; Ethiopic_Ext ; Ethiopic_Extended blk; Ethiopic_Ext_A ; Ethiopic_Extended_A +blk; Ethiopic_Ext_B ; Ethiopic_Extended_B blk; Ethiopic_Sup ; Ethiopic_Supplement blk; Geometric_Shapes ; Geometric_Shapes blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended @@ -284,13 +292,16 @@ blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B blk; Javanese ; Javanese blk; Kaithi ; Kaithi +blk; Kaktovik_Numerals ; Kaktovik_Numerals blk; Kana_Ext_A ; Kana_Extended_A +blk; Kana_Ext_B ; Kana_Extended_B blk; Kana_Sup ; Kana_Supplement blk; Kanbun ; Kanbun blk; Kangxi ; Kangxi_Radicals blk; Kannada ; Kannada blk; Katakana ; Katakana blk; Katakana_Ext ; Katakana_Phonetic_Extensions +blk; Kawi ; Kawi blk; Kayah_Li ; Kayah_Li blk; Kharoshthi ; Kharoshthi blk; Khitan_Small_Script ; Khitan_Small_Script @@ -306,6 +317,8 @@ blk; Latin_Ext_B ; Latin_Extended_B blk; Latin_Ext_C ; Latin_Extended_C blk; Latin_Ext_D ; Latin_Extended_D blk; Latin_Ext_E ; Latin_Extended_E +blk; Latin_Ext_F ; Latin_Extended_F +blk; Latin_Ext_G ; Latin_Extended_G blk; Lepcha ; Lepcha blk; Letterlike_Symbols ; Letterlike_Symbols blk; Limbu ; Limbu @@ -353,6 +366,7 @@ blk; Myanmar ; Myanmar blk; Myanmar_Ext_A ; Myanmar_Extended_A blk; Myanmar_Ext_B ; Myanmar_Extended_B blk; Nabataean ; Nabataean +blk; Nag_Mundari ; Nag_Mundari blk; Nandinagari ; Nandinagari blk; NB ; No_Block blk; New_Tai_Lue ; New_Tai_Lue @@ -372,6 +386,7 @@ blk; Old_Persian ; Old_Persian blk; Old_Sogdian ; Old_Sogdian blk; Old_South_Arabian ; Old_South_Arabian blk; Old_Turkic ; Old_Turkic +blk; Old_Uyghur ; Old_Uyghur blk; Oriya ; Oriya blk; Ornamental_Dingbats ; Ornamental_Dingbats blk; Osage ; Osage @@ -433,6 +448,7 @@ blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols blk; Takri ; Takri blk; Tamil ; Tamil blk; Tamil_Sup ; Tamil_Supplement +blk; Tangsa ; Tangsa blk; Tangut ; Tangut blk; Tangut_Components ; Tangut_Components blk; Tangut_Sup ; Tangut_Supplement @@ -442,13 +458,16 @@ blk; Thai ; Thai blk; Tibetan ; Tibetan blk; Tifinagh ; Tifinagh blk; Tirhuta ; Tirhuta +blk; Toto ; Toto blk; Transport_And_Map ; Transport_And_Map_Symbols blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended +blk; UCAS_Ext_A ; Unified_Canadian_Aboriginal_Syllabics_Extended_A blk; Ugaritic ; Ugaritic blk; Vai ; Vai blk; Vedic_Ext ; Vedic_Extensions blk; Vertical_Forms ; Vertical_Forms +blk; Vithkuqi ; Vithkuqi blk; VS ; Variation_Selectors blk; VS_Sup ; Variation_Selectors_Supplement blk; Wancho ; Wancho @@ -458,6 +477,7 @@ blk; Yi_Radicals ; Yi_Radicals blk; Yi_Syllables ; Yi_Syllables blk; Yijing ; Yijing_Hexagram_Symbols blk; Zanabazar_Square ; Zanabazar_Square +blk; Znamenny_Music ; Znamenny_Musical_Notation # Canonical_Combining_Class (ccc) @@ -650,7 +670,6 @@ EPres; Y ; Yes ; T # Equivalent_Unified_Ideograph (EqUIdeo) -# @missing: 0000..10FFFF; Equivalent_Unified_Ideograph; # Expands_On_NFC (XO_NFC) @@ -1032,6 +1051,8 @@ jg ; Taw ; Taw jg ; Teh_Marbuta ; Teh_Marbuta jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal jg ; Teth ; Teth +jg ; Thin_Yeh ; Thin_Yeh +jg ; Vertical_Tail ; Vertical_Tail jg ; Waw ; Waw jg ; Yeh ; Yeh jg ; Yeh_Barree ; Yeh_Barree @@ -1128,7 +1149,6 @@ NFD_QC; Y ; Yes # NFKC_Casefold (NFKC_CF) -# @missing: 0000..10FFFF; NFKC_Casefold; # NFKC_Quick_Check (NFKC_QC) @@ -1262,6 +1282,7 @@ sc ; Cham ; Cham sc ; Cher ; Cherokee sc ; Chrs ; Chorasmian sc ; Copt ; Coptic ; Qaac +sc ; Cpmn ; Cypro_Minoan sc ; Cprt ; Cypriot sc ; Cyrl ; Cyrillic sc ; Deva ; Devanagari @@ -1297,6 +1318,7 @@ sc ; Ital ; Old_Italic sc ; Java ; Javanese sc ; Kali ; Kayah_Li sc ; Kana ; Katakana +sc ; Kawi ; Kawi sc ; Khar ; Kharoshthi sc ; Khmr ; Khmer sc ; Khoj ; Khojki @@ -1329,6 +1351,7 @@ sc ; Mroo ; Mro sc ; Mtei ; Meetei_Mayek sc ; Mult ; Multani sc ; Mymr ; Myanmar +sc ; Nagm ; Nag_Mundari sc ; Nand ; Nandinagari sc ; Narb ; Old_North_Arabian sc ; Nbat ; Nabataean @@ -1341,6 +1364,7 @@ sc ; Orkh ; Old_Turkic sc ; Orya ; Oriya sc ; Osge ; Osage sc ; Osma ; Osmanya +sc ; Ougr ; Old_Uyghur sc ; Palm ; Palmyrene sc ; Pauc ; Pau_Cin_Hau sc ; Perm ; Old_Permic @@ -1383,8 +1407,11 @@ sc ; Thaa ; Thaana sc ; Thai ; Thai sc ; Tibt ; Tibetan sc ; Tirh ; Tirhuta +sc ; Tnsa ; Tangsa +sc ; Toto ; Toto sc ; Ugar ; Ugaritic sc ; Vaii ; Vai +sc ; Vith ; Vithkuqi sc ; Wara ; Warang_Citi sc ; Wcho ; Wancho sc ; Xpeo ; Old_Persian @@ -1398,7 +1425,6 @@ sc ; Zzzz ; Unknown # Script_Extensions (scx) -# @missing: 0000..10FFFF; Script_Extensions;