diff options
Diffstat (limited to 'lib/unicore/DCoreProperties.txt')
-rw-r--r-- | lib/unicore/DCoreProperties.txt | 700 |
1 files changed, 518 insertions, 182 deletions
diff --git a/lib/unicore/DCoreProperties.txt b/lib/unicore/DCoreProperties.txt index bc97e2173d..afc2abd97e 100644 --- a/lib/unicore/DCoreProperties.txt +++ b/lib/unicore/DCoreProperties.txt @@ -1,6 +1,6 @@ -# DerivedCoreProperties-13.0.0.txt -# Date: 2020-01-22, 00:07:19 GMT -# © 2020 Unicode®, Inc. +# DerivedCoreProperties-14.0.0.txt +# Date: 2021-08-12, 23:12:53 GMT +# © 2021 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -341,8 +341,10 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0829..082C ; Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN 0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; Alphabetic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; Alphabetic # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Alphabetic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Alphabetic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Alphabetic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; Alphabetic # Lm ARABIC SMALL FARSI YEH 08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA 08E3..08E9 ; Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN 08F0..0902 ; Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA @@ -471,6 +473,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0C4A..0C4C ; Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C55..0C56 ; Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Alphabetic # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Alphabetic # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Alphabetic # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C80 ; Alphabetic # Lo KANNADA SIGN SPACING CANDRABINDU @@ -490,7 +493,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CCA..0CCB ; Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; Alphabetic # Lo KANNADA LETTER FA +0CDD..0CDE ; Alphabetic # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -614,10 +617,9 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 16A0..16EA ; Alphabetic # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; Alphabetic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; Alphabetic # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Alphabetic # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Alphabetic # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; Alphabetic # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1713 ; Alphabetic # Mn [2] TAGALOG VOWEL SIGN I..TAGALOG VOWEL SIGN U -1720..1731 ; Alphabetic # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +171F..1731 ; Alphabetic # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1732..1733 ; Alphabetic # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1740..1751 ; Alphabetic # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; Alphabetic # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U @@ -670,6 +672,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1A73..1A74 ; Alphabetic # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG 1AA7 ; Alphabetic # Lm TAI THAM SIGN MAI YAMOK 1ABF..1AC0 ; Alphabetic # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ACC..1ACE ; Alphabetic # Mn [3] COMBINING LATIN SMALL LETTER INSULAR G..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Alphabetic # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Alphabetic # Mc BALINESE SIGN BISAH 1B05..1B33 ; Alphabetic # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -680,7 +683,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1B3D..1B41 ; Alphabetic # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; Alphabetic # Mn BALINESE VOWEL SIGN PEPET 1B43 ; Alphabetic # Mc BALINESE VOWEL SIGN PEPET TEDUNG -1B45..1B4B ; Alphabetic # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Alphabetic # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B80..1B81 ; Alphabetic # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; Alphabetic # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; Alphabetic # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -760,9 +763,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 2183..2184 ; Alphabetic # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; Alphabetic # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND 24B6..24E9 ; Alphabetic # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Alphabetic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Alphabetic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Alphabetic # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Alphabetic # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Alphabetic # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Alphabetic # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; Alphabetic # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -802,8 +803,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 31A0..31BF ; Alphabetic # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; Alphabetic # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Alphabetic # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Alphabetic # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; Alphabetic # Lm YI SYLLABLE WU A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Alphabetic # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -828,8 +828,11 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; Alphabetic # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Alphabetic # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Alphabetic # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Alphabetic # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Alphabetic # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -985,9 +988,20 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 104D8..104FB ; Alphabetic # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; Alphabetic # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Alphabetic # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; Alphabetic # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Alphabetic # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Alphabetic # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Alphabetic # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Alphabetic # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Alphabetic # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Alphabetic # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Alphabetic # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; Alphabetic # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Alphabetic # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Alphabetic # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; Alphabetic # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Alphabetic # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Alphabetic # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; Alphabetic # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Alphabetic # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Alphabetic # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1028,6 +1042,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; Alphabetic # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; Alphabetic # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; Alphabetic # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; Alphabetic # Mc BRAHMI SIGN CANDRABINDU @@ -1035,11 +1050,15 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11002 ; Alphabetic # Mc BRAHMI SIGN VISARGA 11003..11037 ; Alphabetic # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11045 ; Alphabetic # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU +11071..11072 ; Alphabetic # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; Alphabetic # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; Alphabetic # Lo BRAHMI LETTER OLD TAMIL LLA 11082 ; Alphabetic # Mc KAITHI SIGN VISARGA 11083..110AF ; Alphabetic # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; Alphabetic # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Alphabetic # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; Alphabetic # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110C2 ; Alphabetic # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; Alphabetic # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11100..11102 ; Alphabetic # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11103..11126 ; Alphabetic # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -1144,6 +1163,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11722..11725 ; Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Alphabetic # Mc AHOM VOWEL SIGN E 11727..1172A ; Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11740..11746 ; Alphabetic # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Alphabetic # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; Alphabetic # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; Alphabetic # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -1185,7 +1205,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA 11A9D ; Alphabetic # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; Alphabetic # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA @@ -1227,10 +1247,12 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 12000..12399 ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; Alphabetic # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; Alphabetic # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; Alphabetic # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Alphabetic # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Alphabetic # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; Alphabetic # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; Alphabetic # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; Alphabetic # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; Alphabetic # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -1249,7 +1271,10 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 17000..187F7 ; Alphabetic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Alphabetic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Alphabetic # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Alphabetic # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Alphabetic # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -1288,6 +1313,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1D78A..1D7A8 ; Alphabetic # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Alphabetic # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Alphabetic # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Alphabetic # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; Alphabetic # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; Alphabetic # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -1296,7 +1324,12 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1E100..1E12C ; Alphabetic # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Alphabetic # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; Alphabetic # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; Alphabetic # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Alphabetic # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Alphabetic # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Alphabetic # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; Alphabetic # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E947 ; Alphabetic # Mn ADLAM HAMZA @@ -1337,15 +1370,15 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1F130..1F149 ; Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -20000..2A6DD ; Alphabetic # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Alphabetic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Alphabetic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Alphabetic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 132875 +# Total code points: 133396 # ================================================ @@ -1798,7 +1831,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 2170..217F ; Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Lowercase # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Lowercase # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Lowercase # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Lowercase # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Lowercase # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Lowercase # L& LATIN SMALL LETTER H WITH DESCENDER @@ -1970,9 +2003,15 @@ A7B9 ; Lowercase # L& LATIN SMALL LETTER U WITH STROKE A7BB ; Lowercase # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Lowercase # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Lowercase # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Lowercase # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Lowercase # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lowercase # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lowercase # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Lowercase # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Lowercase # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Lowercase # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Lowercase # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -1985,6 +2024,14 @@ FB13..FB17 ; Lowercase # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN S FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lowercase # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Lowercase # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Lowercase # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Lowercase # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Lowercase # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Lowercase # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10CC0..10CF2 ; Lowercase # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lowercase # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y @@ -2016,9 +2063,11 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7AA..1D7C2 ; Lowercase # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Lowercase # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Lowercase # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Lowercase # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2344 +# Total code points: 2471 # ================================================ @@ -2458,7 +2507,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 2160..216F ; Uppercase # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Uppercase # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Uppercase # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Uppercase # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Uppercase # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Uppercase # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Uppercase # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Uppercase # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -2623,13 +2672,21 @@ A7B8 ; Uppercase # L& LATIN CAPITAL LETTER U WITH STROKE A7BA ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Uppercase # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Uppercase # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Uppercase # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Uppercase # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Uppercase # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Uppercase # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Uppercase # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Uppercase # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Uppercase # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Uppercase # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Uppercase # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Uppercase # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Uppercase # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -2669,7 +2726,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1911 +# Total code points: 1951 # ================================================ @@ -2761,9 +2818,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 2160..217F ; Cased # Nl [32] ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2183..2184 ; Cased # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 24B6..24E9 ; Cased # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Cased # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Cased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Cased # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Cased # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Cased # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Cased # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; Cased # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -2778,8 +2833,10 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7BF ; Cased # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Cased # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Cased # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Cased # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2794,6 +2851,18 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10400..1044F ; Cased # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 104B0..104D3 ; Cased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 104D8..104FB ; Cased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10570..1057A ; Cased # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Cased # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Cased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Cased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Cased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Cased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Cased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Cased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Cased # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Cased # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Cased # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Cased # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10C80..10CB2 ; Cased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Cased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Cased # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -2828,12 +2897,14 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D78A..1D7A8 ; Cased # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Cased # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Cased # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Cased # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Cased # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E900..1E943 ; Cased # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1F130..1F149 ; Cased # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4286 +# Total code points: 4453 # ================================================ @@ -2908,7 +2979,11 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0828 ; Case_Ignorable # Lm SAMARITAN MODIFIER LETTER I 0829..082D ; Case_Ignorable # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Case_Ignorable # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Case_Ignorable # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0888 ; Case_Ignorable # Sk ARABIC RAISED ROUND DOT +0890..0891 ; Case_Ignorable # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +0898..089F ; Case_Ignorable # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08C9 ; Case_Ignorable # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; Case_Ignorable # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E2 ; Case_Ignorable # Cf ARABIC DISPUTED END OF AYAH 08E3..0902 ; Case_Ignorable # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Case_Ignorable # Mn DEVANAGARI VOWEL SIGN OE @@ -2951,6 +3026,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0BCD ; Case_Ignorable # Mn TAMIL SIGN VIRAMA 0C00 ; Case_Ignorable # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Case_Ignorable # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Case_Ignorable # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Case_Ignorable # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Case_Ignorable # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Case_Ignorable # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -3003,7 +3079,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10FC ; Case_Ignorable # Lm MODIFIER LETTER GEORGIAN NAR 135D..135F ; Case_Ignorable # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Case_Ignorable # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Case_Ignorable # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Case_Ignorable # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Case_Ignorable # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Case_Ignorable # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Case_Ignorable # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -3014,6 +3090,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 17DD ; Case_Ignorable # Mn KHMER SIGN ATTHACAN 180B..180D ; Case_Ignorable # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Case_Ignorable # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Case_Ignorable # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1843 ; Case_Ignorable # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1885..1886 ; Case_Ignorable # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Case_Ignorable # Mn MONGOLIAN LETTER ALI GALI DAGALGA @@ -3033,7 +3110,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Case_Ignorable # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Case_Ignorable # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3060,8 +3137,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D2C..1D6A ; Case_Ignorable # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D78 ; Case_Ignorable # Lm MODIFIER LETTER CYRILLIC EN 1D9B..1DBF ; Case_Ignorable # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; Case_Ignorable # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Case_Ignorable # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Case_Ignorable # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Case_Ignorable # Sk GREEK KORONIS 1FBF..1FC1 ; Case_Ignorable # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI 1FCD..1FCF ; Case_Ignorable # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -3114,6 +3190,7 @@ A720..A721 ; Case_Ignorable # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE.. A770 ; Case_Ignorable # Lm MODIFIER LETTER US A788 ; Case_Ignorable # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Case_Ignorable # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN +A7F2..A7F4 ; Case_Ignorable # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Case_Ignorable # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A802 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN HASANTA @@ -3156,7 +3233,7 @@ ABE5 ; Case_Ignorable # Mn MEETEI MAYEK VOWEL SIGN ANAP ABE8 ; Case_Ignorable # Mn MEETEI MAYEK VOWEL SIGN UNAP ABED ; Case_Ignorable # Mn MEETEI MAYEK APUN IYEK FB1E ; Case_Ignorable # Mn HEBREW POINT JUDEO-SPANISH VARIKA -FBB2..FBC1 ; Case_Ignorable # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Case_Ignorable # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FE00..FE0F ; Case_Ignorable # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FE13 ; Case_Ignorable # Po PRESENTATION FORM FOR VERTICAL COLON FE20..FE2F ; Case_Ignorable # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF @@ -3175,6 +3252,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 101FD ; Case_Ignorable # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE 102E0 ; Case_Ignorable # Mn COPTIC EPACT THOUSANDS MARK 10376..1037A ; Case_Ignorable # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10780..10785 ; Case_Ignorable # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Case_Ignorable # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Case_Ignorable # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10A01..10A03 ; Case_Ignorable # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R 10A05..10A06 ; Case_Ignorable # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0F ; Case_Ignorable # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA @@ -3184,12 +3264,16 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10D24..10D27 ; Case_Ignorable # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Case_Ignorable # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Case_Ignorable # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Case_Ignorable # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Case_Ignorable # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Case_Ignorable # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Case_Ignorable # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA 110BD ; Case_Ignorable # Cf KAITHI NUMBER SIGN +110C2 ; Case_Ignorable # Mn KAITHI VOWEL SIGN VOCALIC R 110CD ; Case_Ignorable # Cf KAITHI NUMBER SIGN ABOVE 11100..11102 ; Case_Ignorable # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Case_Ignorable # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU @@ -3274,8 +3358,13 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Case_Ignorable # Lm OLD CHINESE ITERATION MARK 16FE4 ; Case_Ignorable # Mn KHITAN SMALL SCRIPT FILLER +1AFF0..1AFF3 ; Case_Ignorable # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Case_Ignorable # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Case_Ignorable # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1BC9D..1BC9E ; Case_Ignorable # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BCA0..1BCA3 ; Case_Ignorable # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; Case_Ignorable # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Case_Ignorable # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Case_Ignorable # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D173..1D17A ; Case_Ignorable # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE 1D17B..1D182 ; Case_Ignorable # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE @@ -3295,6 +3384,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E026..1E02A ; Case_Ignorable # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Case_Ignorable # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E137..1E13D ; Case_Ignorable # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E2AE ; Case_Ignorable # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Case_Ignorable # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA @@ -3304,7 +3394,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2413 +# Total code points: 2602 # ================================================ @@ -3738,7 +3828,7 @@ E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELEC 2160..216F ; Changes_When_Lowercased # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Changes_When_Lowercased # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Changes_When_Lowercased # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Changes_When_Lowercased # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_Lowercased # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_Lowercased # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -3903,19 +3993,27 @@ A7B8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER U WITH S A7BA ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Lowercased # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_Lowercased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_Lowercased # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Lowercased # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Lowercased # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Lowercased # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Lowercased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Lowercased # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1393 +# Total code points: 1433 # ================================================ @@ -4363,7 +4461,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 2170..217F ; Changes_When_Uppercased # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Changes_When_Uppercased # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Changes_When_Uppercased # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Changes_When_Uppercased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Changes_When_Uppercased # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Changes_When_Uppercased # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Changes_When_Uppercased # L& LATIN SMALL LETTER H WITH DESCENDER @@ -4528,9 +4626,13 @@ A7B9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER U WITH STR A7BB ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Changes_When_Uppercased # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Changes_When_Uppercased # L& LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Uppercased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -4539,12 +4641,16 @@ FB13..FB17 ; Changes_When_Uppercased # L& [5] ARMENIAN SMALL LIGATURE MEN N FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Uppercased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Changes_When_Uppercased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Changes_When_Uppercased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Uppercased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Uppercased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Uppercased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Uppercased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Uppercased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1485 +# Total code points: 1525 # ================================================ @@ -4991,7 +5097,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 2170..217F ; Changes_When_Titlecased # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2184 ; Changes_When_Titlecased # L& LATIN SMALL LETTER REVERSED C 24D0..24E9 ; Changes_When_Titlecased # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C30..2C5E ; Changes_When_Titlecased # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Changes_When_Titlecased # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Changes_When_Titlecased # L& LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Changes_When_Titlecased # L& LATIN SMALL LETTER H WITH DESCENDER @@ -5156,9 +5262,13 @@ A7B9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER U WITH STR A7BB ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL A A7BD ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL I A7BF ; Changes_When_Titlecased # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER OLD POLISH O A7C3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S A7F6 ; Changes_When_Titlecased # L& LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Titlecased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5167,12 +5277,16 @@ FB13..FB17 ; Changes_When_Titlecased # L& [5] ARMENIAN SMALL LIGATURE MEN N FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Titlecased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Changes_When_Titlecased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Changes_When_Titlecased # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Titlecased # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Titlecased # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Titlecased # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Changes_When_Titlecased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Titlecased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1412 +# Total code points: 1452 # ================================================ @@ -5616,7 +5730,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 2160..216F ; Changes_When_Casefolded # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND 2183 ; Changes_When_Casefolded # L& ROMAN NUMERAL REVERSED ONE HUNDRED 24B6..24CF ; Changes_When_Casefolded # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z -2C00..2C2E ; Changes_When_Casefolded # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Changes_When_Casefolded # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Changes_When_Casefolded # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER H WITH DESCENDER @@ -5781,9 +5895,13 @@ A7B8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER U WITH S A7BA ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL A A7BC ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL I A7BE ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7F5 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H AB70..ABBF ; Changes_When_Casefolded # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Changes_When_Casefolded # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST @@ -5791,12 +5909,16 @@ FB13..FB17 ; Changes_When_Casefolded # L& [5] ARMENIAN SMALL LIGATURE MEN N FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Changes_When_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Changes_When_Casefolded # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Casefolded # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Casefolded # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Casefolded # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Changes_When_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1466 +# Total code points: 1506 # ================================================ @@ -5893,9 +6015,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 2160..217F ; Changes_When_Casemapped # Nl [32] ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 2183..2184 ; Changes_When_Casemapped # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 24B6..24E9 ; Changes_When_Casemapped # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; Changes_When_Casemapped # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Changes_When_Casemapped # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C70 ; Changes_When_Casemapped # L& [17] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN CAPITAL LETTER TURNED ALPHA +2C00..2C70 ; Changes_When_Casemapped # L& [113] GLAGOLITIC CAPITAL LETTER AZU..LATIN CAPITAL LETTER TURNED ALPHA 2C72..2C73 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER W WITH HOOK..LATIN SMALL LETTER W WITH HOOK 2C75..2C76 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER HALF H..LATIN SMALL LETTER HALF H 2C7E..2CE3 ; Changes_When_Casemapped # L& [102] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SMALL LETTER OLD NUBIAN WAU @@ -5912,8 +6032,9 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7BF ; Changes_When_Casemapped # L& [16] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Changes_When_Casemapped # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7B0..A7CA ; Changes_When_Casemapped # L& [27] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D6..A7D9 ; Changes_When_Casemapped # L& [4] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN SMALL LETTER SIGMOID S A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5924,13 +6045,21 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 10400..1044F ; Changes_When_Casemapped # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 104B0..104D3 ; Changes_When_Casemapped # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 104D8..104FB ; Changes_When_Casemapped # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10570..1057A ; Changes_When_Casemapped # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Changes_When_Casemapped # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Changes_When_Casemapped # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Changes_When_Casemapped # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Changes_When_Casemapped # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Changes_When_Casemapped # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Changes_When_Casemapped # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Changes_When_Casemapped # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10C80..10CB2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Changes_When_Casemapped # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2847 +# Total code points: 2927 # ================================================ @@ -6003,8 +6132,10 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0828 ; ID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; ID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; ID_Start # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; ID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; ID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ID_Start # Lo DEVANAGARI OM @@ -6070,6 +6201,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0C2A..0C39 ; ID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ID_Start # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -6078,7 +6210,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0CAA..0CB3 ; ID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ID_Start # Lo KANNADA SIGN AVAGRAHA -0CDE ; ID_Start # Lo KANNADA LETTER FA +0CDD..0CDE ; ID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -6153,9 +6285,8 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 16A0..16EA ; ID_Start # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ID_Start # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ID_Start # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ID_Start # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ID_Start # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; ID_Start # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; ID_Start # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; ID_Start # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; ID_Start # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; ID_Start # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; ID_Start # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -6179,7 +6310,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 1A20..1A54 ; ID_Start # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; ID_Start # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; ID_Start # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; ID_Start # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ID_Start # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; ID_Start # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; ID_Start # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; ID_Start # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -6242,9 +6373,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 2160..2182 ; ID_Start # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; ID_Start # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ID_Start # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; ID_Start # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ID_Start # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ID_Start # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ID_Start # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ID_Start # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ID_Start # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ID_Start # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -6283,8 +6412,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 31A0..31BF ; ID_Start # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; ID_Start # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID_Start # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID_Start # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; ID_Start # Lm YI SYLLABLE WU A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; ID_Start # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -6307,8 +6435,11 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ID_Start # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ID_Start # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6418,9 +6549,20 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 104D8..104FB ; ID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ID_Start # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ID_Start # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ID_Start # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ID_Start # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ID_Start # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -6456,9 +6598,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; ID_Start # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; ID_Start # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ID_Start # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; ID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; ID_Start # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; ID_Start # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; ID_Start # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; ID_Start # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; ID_Start # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -6500,6 +6645,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; ID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; ID_Start # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; ID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; ID_Start # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; ID_Start # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; ID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF..11906 ; ID_Start # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E @@ -6519,7 +6665,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; ID_Start # Lo SOYOMBO LETTER A 11A5C..11A89 ; ID_Start # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; ID_Start # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ID_Start # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; ID_Start # Lo BHAIKSUKI SIGN AVAGRAHA @@ -6537,10 +6683,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 12000..12399 ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; ID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; ID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; ID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; ID_Start # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; ID_Start # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; ID_Start # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; ID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -6555,7 +6703,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17000..187F7 ; ID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; ID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; ID_Start # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; ID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; ID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -6593,10 +6744,18 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78A..1D7A8 ; ID_Start # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; ID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; ID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; ID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; ID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; ID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ID_Start # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; ID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; ID_Start # Lm ADLAM NASALIZATION MARK @@ -6633,15 +6792,15 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1EEA1..1EEA3 ; ID_Start # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; ID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; ID_Start # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; ID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; ID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; ID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 131482 +# Total code points: 131997 # ================================================ @@ -6746,9 +6905,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0840..0858 ; ID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; ID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; ID_Continue # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; ID_Continue # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; ID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0898..089F ; ID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; ID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ID_Continue # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; ID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; ID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; ID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; ID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -6886,6 +7048,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C0E..0C10 ; ID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; ID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; ID_Continue # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; ID_Continue # Mn TELUGU SIGN NUKTA 0C3D ; ID_Continue # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; ID_Continue # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; ID_Continue # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -6893,6 +7056,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C4A..0C4D ; ID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; ID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; ID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ID_Continue # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; ID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; ID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -6914,7 +7078,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CCA..0CCB ; ID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; ID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; ID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; ID_Continue # Lo KANNADA LETTER FA +0CDD..0CDE ; ID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -7058,11 +7222,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16A0..16EA ; ID_Continue # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ID_Continue # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ID_Continue # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ID_Continue # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ID_Continue # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; ID_Continue # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; ID_Continue # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; ID_Continue # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; ID_Continue # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; ID_Continue # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; ID_Continue # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; ID_Continue # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; ID_Continue # Mc HANUNOO SIGN PAMUDPOD 1740..1751 ; ID_Continue # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; ID_Continue # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1760..176C ; ID_Continue # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -7081,6 +7246,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 17DD ; ID_Continue # Mn KHMER SIGN ATTHACAN 17E0..17E9 ; ID_Continue # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 180B..180D ; ID_Continue # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; ID_Continue # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; ID_Continue # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; ID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -7128,7 +7294,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; ID_Continue # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; ID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -7140,7 +7306,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1B3D..1B41 ; ID_Continue # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; ID_Continue # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; ID_Continue # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; ID_Continue # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ID_Continue # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; ID_Continue # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B6B..1B73 ; ID_Continue # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1B81 ; ID_Continue # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR @@ -7194,8 +7360,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78 ; ID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; ID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; ID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; ID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; ID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; ID_Continue # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; ID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; ID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; ID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -7243,9 +7408,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2160..2182 ; ID_Continue # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; ID_Continue # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ID_Continue # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; ID_Continue # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ID_Continue # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ID_Continue # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ID_Continue # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ID_Continue # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ID_Continue # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ID_Continue # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -7290,8 +7453,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 31A0..31BF ; ID_Continue # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; ID_Continue # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; ID_Continue # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; ID_Continue # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; ID_Continue # Lm YI SYLLABLE WU A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; ID_Continue # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -7319,8 +7481,11 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ID_Continue # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; ID_Continue # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; ID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -7499,9 +7664,20 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 104D8..104FB ; ID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ID_Continue # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ID_Continue # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ID_Continue # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ID_Continue # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ID_Continue # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -7547,6 +7723,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F46..10F50 ; ID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F70..10F81 ; ID_Continue # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; ID_Continue # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; ID_Continue # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ID_Continue # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; ID_Continue # Mc BRAHMI SIGN CANDRABINDU @@ -7555,6 +7733,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11003..11037 ; ID_Continue # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11046 ; ID_Continue # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11066..1106F ; ID_Continue # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; ID_Continue # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; ID_Continue # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; ID_Continue # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; ID_Continue # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; ID_Continue # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; ID_Continue # Mc KAITHI SIGN VISARGA 11083..110AF ; ID_Continue # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -7562,6 +7744,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 110B3..110B6 ; ID_Continue # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; ID_Continue # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; ID_Continue # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; ID_Continue # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; ID_Continue # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; ID_Continue # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11100..11102 ; ID_Continue # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -7687,6 +7870,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11726 ; ID_Continue # Mc AHOM VOWEL SIGN E 11727..1172B ; ID_Continue # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 11730..11739 ; ID_Continue # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; ID_Continue # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; ID_Continue # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; ID_Continue # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; ID_Continue # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -7737,7 +7921,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; ID_Continue # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; ID_Continue # Mc BHAIKSUKI VOWEL SIGN AA @@ -7783,11 +7967,14 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 12000..12399 ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; ID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; ID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; ID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; ID_Continue # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A70..16ABE ; ID_Continue # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; ID_Continue # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; ID_Continue # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; ID_Continue # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B2F ; ID_Continue # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -7810,7 +7997,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 17000..187F7 ; ID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; ID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; ID_Continue # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; ID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; ID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -7819,6 +8009,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1BC80..1BC88 ; ID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; ID_Continue # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9D..1BC9E ; ID_Continue # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; ID_Continue # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; ID_Continue # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; ID_Continue # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; ID_Continue # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; ID_Continue # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -7863,6 +8055,9 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DA84 ; ID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; ID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; ID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; ID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; ID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -7873,9 +8068,15 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1E137..1E13D ; ID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; ID_Continue # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; ID_Continue # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ID_Continue # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; ID_Continue # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; ID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; ID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; ID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ID_Continue # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; ID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E900..1E943 ; ID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -7916,8 +8117,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1EEA5..1EEA9 ; ID_Continue # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; ID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; ID_Continue # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; ID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; ID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; ID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 @@ -7925,7 +8126,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 134434 +# Total code points: 135072 # ================================================ @@ -7995,8 +8196,10 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0828 ; XID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; XID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; XID_Start # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; XID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; XID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; XID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; XID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; XID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; XID_Start # Lo DEVANAGARI OM @@ -8062,6 +8265,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0C2A..0C39 ; XID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; XID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; XID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; XID_Start # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; XID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; XID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -8070,7 +8274,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0CAA..0CB3 ; XID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; XID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; XID_Start # Lo KANNADA SIGN AVAGRAHA -0CDE ; XID_Start # Lo KANNADA LETTER FA +0CDD..0CDE ; XID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; XID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; XID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; XID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -8145,9 +8349,8 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 16A0..16EA ; XID_Start # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; XID_Start # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; XID_Start # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; XID_Start # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; XID_Start # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; XID_Start # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; XID_Start # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; XID_Start # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; XID_Start # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; XID_Start # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; XID_Start # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -8171,7 +8374,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 1A20..1A54 ; XID_Start # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1AA7 ; XID_Start # Lm TAI THAM SIGN MAI YAMOK 1B05..1B33 ; XID_Start # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; XID_Start # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; XID_Start # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; XID_Start # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; XID_Start # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; XID_Start # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -8234,9 +8437,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 2160..2182 ; XID_Start # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; XID_Start # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; XID_Start # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; XID_Start # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; XID_Start # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; XID_Start # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; XID_Start # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; XID_Start # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; XID_Start # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; XID_Start # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -8274,8 +8475,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 31A0..31BF ; XID_Start # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; XID_Start # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; XID_Start # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; XID_Start # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; XID_Start # Lm YI SYLLABLE WU A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; XID_Start # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -8298,8 +8498,11 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; XID_Start # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; XID_Start # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; XID_Start # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; XID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; XID_Start # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -8414,9 +8617,20 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 104D8..104FB ; XID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; XID_Start # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; XID_Start # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; XID_Start # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; XID_Start # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; XID_Start # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; XID_Start # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; XID_Start # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; XID_Start # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; XID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Start # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Start # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; XID_Start # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; XID_Start # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; XID_Start # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; XID_Start # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Start # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Start # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -8452,9 +8666,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; XID_Start # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; XID_Start # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; XID_Start # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; XID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; XID_Start # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; XID_Start # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; XID_Start # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; XID_Start # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; XID_Start # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -8496,6 +8713,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11680..116AA ; XID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; XID_Start # Lo TAKRI LETTER ARCHAIC KHA 11700..1171A ; XID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; XID_Start # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; XID_Start # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; XID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF..11906 ; XID_Start # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E @@ -8515,7 +8733,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11A50 ; XID_Start # Lo SOYOMBO LETTER A 11A5C..11A89 ; XID_Start # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; XID_Start # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; XID_Start # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; XID_Start # Lo BHAIKSUKI SIGN AVAGRAHA @@ -8533,10 +8751,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 12000..12399 ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; XID_Start # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; XID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; XID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Start # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; XID_Start # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; XID_Start # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; XID_Start # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; XID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -8551,7 +8771,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 17000..187F7 ; XID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; XID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; XID_Start # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; XID_Start # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; XID_Start # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -8589,10 +8812,18 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78A..1D7A8 ; XID_Start # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; XID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; XID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; XID_Start # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; XID_Start # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; XID_Start # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; XID_Start # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; XID_Start # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; XID_Start # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; XID_Start # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; XID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; XID_Start # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; XID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; XID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; XID_Start # Lm ADLAM NASALIZATION MARK @@ -8629,15 +8860,15 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1EEA1..1EEA3 ; XID_Start # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; XID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; XID_Start # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; XID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; XID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; XID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 131459 +# Total code points: 131974 # ================================================ @@ -8738,9 +8969,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0840..0858 ; XID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; XID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; XID_Continue # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE -08D3..08E1 ; XID_Continue # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0870..0887 ; XID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; XID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0898..089F ; XID_Continue # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08A0..08C8 ; XID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; XID_Continue # Lm ARABIC SMALL FARSI YEH +08CA..08E1 ; XID_Continue # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; XID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; XID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; XID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -8878,6 +9112,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C0E..0C10 ; XID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; XID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA 0C2A..0C39 ; XID_Continue # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3C ; XID_Continue # Mn TELUGU SIGN NUKTA 0C3D ; XID_Continue # Lo TELUGU SIGN AVAGRAHA 0C3E..0C40 ; XID_Continue # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; XID_Continue # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -8885,6 +9120,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C4A..0C4D ; XID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; XID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; XID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; XID_Continue # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; XID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; XID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -8906,7 +9142,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CCA..0CCB ; XID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; XID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; XID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; XID_Continue # Lo KANNADA LETTER FA +0CDD..0CDE ; XID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; XID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -9050,11 +9286,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16A0..16EA ; XID_Continue # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; XID_Continue # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; XID_Continue # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; XID_Continue # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; XID_Continue # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1700..1711 ; XID_Continue # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA 1712..1714 ; XID_Continue # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1720..1731 ; XID_Continue # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; XID_Continue # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; XID_Continue # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; XID_Continue # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1732..1733 ; XID_Continue # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; XID_Continue # Mc HANUNOO SIGN PAMUDPOD 1740..1751 ; XID_Continue # Lo [18] BUHID LETTER A..BUHID LETTER HA 1752..1753 ; XID_Continue # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1760..176C ; XID_Continue # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -9073,6 +9310,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 17DD ; XID_Continue # Mn KHMER SIGN ATTHACAN 17E0..17E9 ; XID_Continue # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 180B..180D ; XID_Continue # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; XID_Continue # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1810..1819 ; XID_Continue # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; XID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; XID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -9120,7 +9358,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; XID_Continue # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; XID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -9132,7 +9370,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1B3D..1B41 ; XID_Continue # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B42 ; XID_Continue # Mn BALINESE VOWEL SIGN PEPET 1B43..1B44 ; XID_Continue # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; XID_Continue # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; XID_Continue # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; XID_Continue # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B6B..1B73 ; XID_Continue # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B80..1B81 ; XID_Continue # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR @@ -9186,8 +9424,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78 ; XID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; XID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; XID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF9 ; XID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; XID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; XID_Continue # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; XID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; XID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; XID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -9235,9 +9472,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 2160..2182 ; XID_Continue # Nl [35] ROMAN NUMERAL ONE..ROMAN NUMERAL TEN THOUSAND 2183..2184 ; XID_Continue # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; XID_Continue # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND -2C00..2C2E ; XID_Continue # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; XID_Continue # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; XID_Continue # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; XID_Continue # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; XID_Continue # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; XID_Continue # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; XID_Continue # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -9281,8 +9516,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 31A0..31BF ; XID_Continue # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; XID_Continue # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; XID_Continue # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; XID_Continue # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; XID_Continue # Lm YI SYLLABLE WU A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; XID_Continue # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -9310,8 +9544,11 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; XID_Continue # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; XID_Continue # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; XID_Continue # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; XID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; XID_Continue # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -9496,9 +9733,20 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 104D8..104FB ; XID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; XID_Continue # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; XID_Continue # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; XID_Continue # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; XID_Continue # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; XID_Continue # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; XID_Continue # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; XID_Continue # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; XID_Continue # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; XID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; XID_Continue # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; XID_Continue # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; XID_Continue # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; XID_Continue # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; XID_Continue # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; XID_Continue # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; XID_Continue # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; XID_Continue # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -9544,6 +9792,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F46..10F50 ; XID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F70..10F81 ; XID_Continue # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F82..10F85 ; XID_Continue # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 10FB0..10FC4 ; XID_Continue # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; XID_Continue # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11000 ; XID_Continue # Mc BRAHMI SIGN CANDRABINDU @@ -9552,6 +9802,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11003..11037 ; XID_Continue # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11038..11046 ; XID_Continue # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 11066..1106F ; XID_Continue # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11070 ; XID_Continue # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11071..11072 ; XID_Continue # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11073..11074 ; XID_Continue # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +11075 ; XID_Continue # Lo BRAHMI LETTER OLD TAMIL LLA 1107F..11081 ; XID_Continue # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; XID_Continue # Mc KAITHI SIGN VISARGA 11083..110AF ; XID_Continue # Lo [45] KAITHI LETTER A..KAITHI LETTER HA @@ -9559,6 +9813,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 110B3..110B6 ; XID_Continue # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B7..110B8 ; XID_Continue # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; XID_Continue # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; XID_Continue # Mn KAITHI VOWEL SIGN VOCALIC R 110D0..110E8 ; XID_Continue # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 110F0..110F9 ; XID_Continue # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11100..11102 ; XID_Continue # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA @@ -9684,6 +9939,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11726 ; XID_Continue # Mc AHOM VOWEL SIGN E 11727..1172B ; XID_Continue # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER 11730..11739 ; XID_Continue # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +11740..11746 ; XID_Continue # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; XID_Continue # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; XID_Continue # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 1182F..11837 ; XID_Continue # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA @@ -9734,7 +9990,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; XID_Continue # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; XID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; XID_Continue # Mc BHAIKSUKI VOWEL SIGN AA @@ -9780,11 +10036,14 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 12000..12399 ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; XID_Continue # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 13000..1342E ; XID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; XID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; XID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; XID_Continue # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; XID_Continue # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16A70..16ABE ; XID_Continue # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; XID_Continue # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; XID_Continue # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF0..16AF4 ; XID_Continue # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B00..16B2F ; XID_Continue # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -9807,7 +10066,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 17000..187F7 ; XID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; XID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; XID_Continue # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; XID_Continue # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; XID_Continue # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -9816,6 +10078,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1BC80..1BC88 ; XID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; XID_Continue # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9D..1BC9E ; XID_Continue # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; XID_Continue # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; XID_Continue # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165..1D166 ; XID_Continue # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; XID_Continue # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; XID_Continue # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -9860,6 +10124,9 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DA84 ; XID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; XID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; XID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1DF00..1DF09 ; XID_Continue # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; XID_Continue # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; XID_Continue # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E000..1E006 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E008..1E018 ; XID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU 1E01B..1E021 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI @@ -9870,9 +10137,15 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1E137..1E13D ; XID_Continue # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; XID_Continue # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; XID_Continue # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; XID_Continue # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2AE ; XID_Continue # Mn TOTO SIGN RISING TONE 1E2C0..1E2EB ; XID_Continue # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2EC..1E2EF ; XID_Continue # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E2F0..1E2F9 ; XID_Continue # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; XID_Continue # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; XID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; XID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E900..1E943 ; XID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -9913,8 +10186,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1EEA5..1EEA9 ; XID_Continue # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; XID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; XID_Continue # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; XID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; XID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; XID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 @@ -9922,7 +10195,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 134415 +# Total code points: 135053 # ================================================ @@ -9943,6 +10216,7 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO 17B4..17B5 ; Default_Ignorable_Code_Point # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Default_Ignorable_Code_Point # Cf MONGOLIAN VOWEL SEPARATOR +180F ; Default_Ignorable_Code_Point # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 200B..200F ; Default_Ignorable_Code_Point # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK 202A..202E ; Default_Ignorable_Code_Point # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2060..2064 ; Default_Ignorable_Code_Point # Cf [5] WORD JOINER..INVISIBLE PLUS @@ -9963,7 +10237,7 @@ E0080..E00FF ; Default_Ignorable_Code_Point # Cn [128] <reserved-E0080>..<reser E0100..E01EF ; Default_Ignorable_Code_Point # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 4173 +# Total code points: 4174 # ================================================ @@ -9997,7 +10271,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0825..0827 ; Grapheme_Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Grapheme_Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Grapheme_Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Grapheme_Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Grapheme_Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Grapheme_Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Grapheme_Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Grapheme_Extend # Mn DEVANAGARI VOWEL SIGN OE 093C ; Grapheme_Extend # Mn DEVANAGARI SIGN NUKTA @@ -10044,6 +10319,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0BD7 ; Grapheme_Extend # Mc TAMIL AU LENGTH MARK 0C00 ; Grapheme_Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Grapheme_Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Grapheme_Extend # Mn TELUGU SIGN NUKTA 0C3E..0C40 ; Grapheme_Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Grapheme_Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Grapheme_Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -10099,7 +10375,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 109D ; Grapheme_Extend # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; Grapheme_Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Grapheme_Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Grapheme_Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Grapheme_Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Grapheme_Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Grapheme_Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Grapheme_Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -10108,6 +10384,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 17C9..17D3 ; Grapheme_Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Grapheme_Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Grapheme_Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Grapheme_Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Grapheme_Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Grapheme_Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Grapheme_Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -10125,7 +10402,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 1A7F ; Grapheme_Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Grapheme_Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Grapheme_Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AC0 ; Grapheme_Extend # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Grapheme_Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Grapheme_Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Grapheme_Extend # Mn BALINESE SIGN REREKAN 1B35 ; Grapheme_Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -10149,8 +10426,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 1CED ; Grapheme_Extend # Mn VEDIC SIGN TIRYAK 1CF4 ; Grapheme_Extend # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Grapheme_Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Grapheme_Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Grapheme_Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Grapheme_Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Grapheme_Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Grapheme_Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Grapheme_Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -10215,11 +10491,15 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 10D24..10D27 ; Grapheme_Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Grapheme_Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10F46..10F50 ; Grapheme_Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Grapheme_Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Grapheme_Extend # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Grapheme_Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Grapheme_Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Grapheme_Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Grapheme_Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Grapheme_Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Grapheme_Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Grapheme_Extend # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Grapheme_Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Grapheme_Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; Grapheme_Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -10305,6 +10585,8 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Grapheme_Extend # Mn KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; Grapheme_Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Grapheme_Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Grapheme_Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D165 ; Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM 1D167..1D169 ; Grapheme_Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16E..1D172 ; Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5 @@ -10324,13 +10606,14 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1E023..1E024 ; Grapheme_Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Grapheme_Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E130..1E136 ; Grapheme_Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Grapheme_Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Grapheme_Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Grapheme_Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Grapheme_Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1979 +# Total code points: 2090 # ================================================ @@ -10451,7 +10734,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 060C..060D ; Grapheme_Base # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR 060E..060F ; Grapheme_Base # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 061B ; Grapheme_Base # Po ARABIC SEMICOLON -061E..061F ; Grapheme_Base # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; Grapheme_Base # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 0620..063F ; Grapheme_Base # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; Grapheme_Base # Lm ARABIC TATWEEL 0641..064A ; Grapheme_Base # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -10489,8 +10772,11 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0840..0858 ; Grapheme_Base # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; Grapheme_Base # Po MANDAIC PUNCTUATION 0860..086A ; Grapheme_Base # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; Grapheme_Base # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; Grapheme_Base # Lo [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Grapheme_Base # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0888 ; Grapheme_Base # Sk ARABIC RAISED ROUND DOT +0889..088E ; Grapheme_Base # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Grapheme_Base # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; Grapheme_Base # Lm ARABIC SMALL FARSI YEH 0903 ; Grapheme_Base # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; Grapheme_Base # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093B ; Grapheme_Base # Mc DEVANAGARI VOWEL SIGN OOE @@ -10603,6 +10889,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0C3D ; Grapheme_Base # Lo TELUGU SIGN AVAGRAHA 0C41..0C44 ; Grapheme_Base # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C58..0C5A ; Grapheme_Base # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Grapheme_Base # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Grapheme_Base # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; Grapheme_Base # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C77 ; Grapheme_Base # Po TELUGU SIGN SIDDHAM @@ -10622,7 +10909,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0CC3..0CC4 ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR 0CC7..0CC8 ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI 0CCA..0CCB ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO -0CDE ; Grapheme_Base # Lo KANNADA LETTER FA +0CDD..0CDE ; Grapheme_Base # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Grapheme_Base # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE6..0CEF ; Grapheme_Base # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; Grapheme_Base # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -10768,9 +11055,10 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 16EB..16ED ; Grapheme_Base # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 16EE..16F0 ; Grapheme_Base # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; Grapheme_Base # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Grapheme_Base # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Grapheme_Base # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; Grapheme_Base # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; Grapheme_Base # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +1715 ; Grapheme_Base # Mc TAGALOG SIGN PAMUDPOD +171F..1731 ; Grapheme_Base # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1734 ; Grapheme_Base # Mc HANUNOO SIGN PAMUDPOD 1735..1736 ; Grapheme_Base # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION 1740..1751 ; Grapheme_Base # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; Grapheme_Base # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA @@ -10831,11 +11119,12 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1B3B ; Grapheme_Base # Mc BALINESE VOWEL SIGN RA REPA TEDUNG 1B3D..1B41 ; Grapheme_Base # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG 1B43..1B44 ; Grapheme_Base # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG -1B45..1B4B ; Grapheme_Base # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Grapheme_Base # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B50..1B59 ; Grapheme_Base # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B60 ; Grapheme_Base # Po [7] BALINESE PANTI..BALINESE PAMENENG 1B61..1B6A ; Grapheme_Base # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; Grapheme_Base # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING +1B7D..1B7E ; Grapheme_Base # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1B82 ; Grapheme_Base # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; Grapheme_Base # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BA1 ; Grapheme_Base # Mc SUNDANESE CONSONANT SIGN PAMINGKAL @@ -10940,7 +11229,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 208D ; Grapheme_Base # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Grapheme_Base # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; Grapheme_Base # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BF ; Grapheme_Base # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; Grapheme_Base # Sc [33] EURO-CURRENCY SIGN..SOM SIGN 2100..2101 ; Grapheme_Base # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT 2102 ; Grapheme_Base # L& DOUBLE-STRUCK CAPITAL C 2103..2106 ; Grapheme_Base # So [4] DEGREE CELSIUS..CADA UNA @@ -11099,9 +11388,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2B4D..2B73 ; Grapheme_Base # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95 ; Grapheme_Base # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B97..2BFF ; Grapheme_Base # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL -2C00..2C2E ; Grapheme_Base # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; Grapheme_Base # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; Grapheme_Base # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; Grapheme_Base # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Grapheme_Base # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Grapheme_Base # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CE5..2CEA ; Grapheme_Base # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA @@ -11164,7 +11451,16 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2E42 ; Grapheme_Base # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 2E43..2E4F ; Grapheme_Base # Po [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER 2E50..2E51 ; Grapheme_Base # So [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR -2E52 ; Grapheme_Base # Po TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; Grapheme_Base # Po [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK +2E55 ; Grapheme_Base # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Grapheme_Base # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Grapheme_Base # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Grapheme_Base # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Grapheme_Base # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Grapheme_Base # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Grapheme_Base # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Grapheme_Base # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5D ; Grapheme_Base # Pd OBLIQUE HYPHEN 2E80..2E99 ; Grapheme_Base # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; Grapheme_Base # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; Grapheme_Base # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -11237,8 +11533,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 32C0..33FF ; Grapheme_Base # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL 3400..4DBF ; Grapheme_Base # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF 4DC0..4DFF ; Grapheme_Base # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FFC ; Grapheme_Base # Lo [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Grapheme_Base # Lo [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Grapheme_Base # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A015 ; Grapheme_Base # Lm YI SYLLABLE WU A016..A48C ; Grapheme_Base # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; Grapheme_Base # So [55] YI RADICAL QOT..YI RADICAL KE @@ -11271,8 +11566,11 @@ A788 ; Grapheme_Base # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; Grapheme_Base # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7CA ; Grapheme_Base # L& [9] LATIN CAPITAL LETTER ANGLICANA W..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CA ; Grapheme_Base # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Grapheme_Base # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; Grapheme_Base # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; Grapheme_Base # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Grapheme_Base # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Grapheme_Base # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -11387,15 +11685,17 @@ FB3E ; Grapheme_Base # Lo HEBREW LETTER MEM WITH DAGESH FB40..FB41 ; Grapheme_Base # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH FB43..FB44 ; Grapheme_Base # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; Grapheme_Base # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBB2..FBC1 ; Grapheme_Base # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Grapheme_Base # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FBD3..FD3D ; Grapheme_Base # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; Grapheme_Base # Pe ORNATE LEFT PARENTHESIS FD3F ; Grapheme_Base # Ps ORNATE RIGHT PARENTHESIS +FD40..FD4F ; Grapheme_Base # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Grapheme_Base # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM FD92..FDC7 ; Grapheme_Base # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDCF ; Grapheme_Base # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Grapheme_Base # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; Grapheme_Base # Sc RIAL SIGN -FDFD ; Grapheme_Base # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FDFD..FDFF ; Grapheme_Base # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE10..FE16 ; Grapheme_Base # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; Grapheme_Base # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET FE18 ; Grapheme_Base # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET @@ -11533,9 +11833,20 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10500..10527 ; Grapheme_Base # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Grapheme_Base # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; Grapheme_Base # Po CAUCASIAN ALBANIAN CITATION MARK +10570..1057A ; Grapheme_Base # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Grapheme_Base # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Grapheme_Base # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Grapheme_Base # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; Grapheme_Base # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Grapheme_Base # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Grapheme_Base # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Grapheme_Base # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; Grapheme_Base # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; Grapheme_Base # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; Grapheme_Base # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; Grapheme_Base # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Grapheme_Base # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Grapheme_Base # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; Grapheme_Base # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; Grapheme_Base # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; Grapheme_Base # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -11603,6 +11914,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10F30..10F45 ; Grapheme_Base # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; Grapheme_Base # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; Grapheme_Base # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F70..10F81 ; Grapheme_Base # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10F86..10F89 ; Grapheme_Base # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 10FB0..10FC4 ; Grapheme_Base # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FC5..10FCB ; Grapheme_Base # No [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED 10FE0..10FF6 ; Grapheme_Base # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH @@ -11612,6 +11925,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11047..1104D ; Grapheme_Base # Po [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 11052..11065 ; Grapheme_Base # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11066..1106F ; Grapheme_Base # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +11071..11072 ; Grapheme_Base # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; Grapheme_Base # Lo BRAHMI LETTER OLD TAMIL LLA 11082 ; Grapheme_Base # Mc KAITHI SIGN VISARGA 11083..110AF ; Grapheme_Base # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110B0..110B2 ; Grapheme_Base # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II @@ -11713,6 +12028,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 116AE..116AF ; Grapheme_Base # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II 116B6 ; Grapheme_Base # Mc TAKRI SIGN VIRAMA 116B8 ; Grapheme_Base # Lo TAKRI LETTER ARCHAIC KHA +116B9 ; Grapheme_Base # Po TAKRI ABBREVIATION SIGN 116C0..116C9 ; Grapheme_Base # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11700..1171A ; Grapheme_Base # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 11720..11721 ; Grapheme_Base # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA @@ -11721,6 +12037,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1173A..1173B ; Grapheme_Base # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 1173C..1173E ; Grapheme_Base # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1173F ; Grapheme_Base # So AHOM SYMBOL VI +11740..11746 ; Grapheme_Base # Lo [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Grapheme_Base # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 1182C..1182E ; Grapheme_Base # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II 11838 ; Grapheme_Base # Mc DOGRA SIGN VISARGA @@ -11762,7 +12079,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11A9A..11A9C ; Grapheme_Base # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9D ; Grapheme_Base # Lo SOYOMBO MARK PLUTA 11A9E..11AA2 ; Grapheme_Base # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 -11AC0..11AF8 ; Grapheme_Base # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; Grapheme_Base # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Grapheme_Base # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Grapheme_Base # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; Grapheme_Base # Mc BHAIKSUKI VOWEL SIGN AA @@ -11802,12 +12119,16 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 12400..1246E ; Grapheme_Base # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; Grapheme_Base # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 12480..12543 ; Grapheme_Base # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; Grapheme_Base # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +12FF1..12FF2 ; Grapheme_Base # Po [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 13000..1342E ; Grapheme_Base # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 14400..14646 ; Grapheme_Base # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Grapheme_Base # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Grapheme_Base # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; Grapheme_Base # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16A6E..16A6F ; Grapheme_Base # Po [2] MRO DANDA..MRO DOUBLE DANDA +16A70..16ABE ; Grapheme_Base # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AC0..16AC9 ; Grapheme_Base # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16AD0..16AED ; Grapheme_Base # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16AF5 ; Grapheme_Base # Po BASSA VAH FULL STOP 16B00..16B2F ; Grapheme_Base # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU @@ -11834,7 +12155,10 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 17000..187F7 ; Grapheme_Base # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Grapheme_Base # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Grapheme_Base # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Grapheme_Base # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1AFF0..1AFF3 ; Grapheme_Base # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Grapheme_Base # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Grapheme_Base # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; Grapheme_Base # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU 1B150..1B152 ; Grapheme_Base # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO 1B164..1B167 ; Grapheme_Base # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Grapheme_Base # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -11844,6 +12168,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1BC90..1BC99 ; Grapheme_Base # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; Grapheme_Base # So DUPLOYAN SIGN O WITH CROSS 1BC9F ; Grapheme_Base # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1CF50..1CFC3 ; Grapheme_Base # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; Grapheme_Base # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; Grapheme_Base # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; Grapheme_Base # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -11852,7 +12177,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1D16D ; Grapheme_Base # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT 1D183..1D184 ; Grapheme_Base # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; Grapheme_Base # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; Grapheme_Base # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; Grapheme_Base # So [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; Grapheme_Base # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; Grapheme_Base # So GREEK MUSICAL LEIMMA 1D2E0..1D2F3 ; Grapheme_Base # No [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN @@ -11905,14 +12230,22 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1DA76..1DA83 ; Grapheme_Base # So [14] SIGNWRITING LIMB COMBINATION..SIGNWRITING LOCATION DEPTH 1DA85..1DA86 ; Grapheme_Base # So [2] SIGNWRITING LOCATION TORSO..SIGNWRITING LOCATION LIMBS DIGITS 1DA87..1DA8B ; Grapheme_Base # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS +1DF00..1DF09 ; Grapheme_Base # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; Grapheme_Base # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; Grapheme_Base # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1E100..1E12C ; Grapheme_Base # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; Grapheme_Base # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E140..1E149 ; Grapheme_Base # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E14E ; Grapheme_Base # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1E14F ; Grapheme_Base # So NYIAKENG PUACHUE HMONG CIRCLED CA +1E290..1E2AD ; Grapheme_Base # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Grapheme_Base # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E2F0..1E2F9 ; Grapheme_Base # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E2FF ; Grapheme_Base # Sc WANCHO NGUN SIGN +1E7E0..1E7E6 ; Grapheme_Base # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Grapheme_Base # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Grapheme_Base # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Grapheme_Base # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Grapheme_Base # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; Grapheme_Base # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E900..1E943 ; Grapheme_Base # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA @@ -11977,40 +12310,41 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F300..1F3FA ; Grapheme_Base # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; Grapheme_Base # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F400..1F6D7 ; Grapheme_Base # So [728] RAT..ELEVATOR -1F6E0..1F6EC ; Grapheme_Base # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DD..1F6EC ; Grapheme_Base # So [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING 1F6F0..1F6FC ; Grapheme_Base # So [13] SATELLITE..ROLLER SKATE 1F700..1F773 ; Grapheme_Base # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D8 ; Grapheme_Base # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 1F7E0..1F7EB ; Grapheme_Base # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; Grapheme_Base # So HEAVY EQUALS SIGN 1F800..1F80B ; Grapheme_Base # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; Grapheme_Base # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; Grapheme_Base # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Grapheme_Base # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; Grapheme_Base # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; Grapheme_Base # So [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; Grapheme_Base # So [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; Grapheme_Base # So [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; Grapheme_Base # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; Grapheme_Base # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA74 ; Grapheme_Base # So [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; Grapheme_Base # So [3] DROP OF BLOOD..STETHOSCOPE +1FA78..1FA7C ; Grapheme_Base # So [5] DROP OF BLOOD..CRUTCH 1FA80..1FA86 ; Grapheme_Base # So [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; Grapheme_Base # So [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; Grapheme_Base # So [7] FLY..FEATHER -1FAC0..1FAC2 ; Grapheme_Base # So [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; Grapheme_Base # So [7] BLUEBERRIES..TEAPOT +1FA90..1FAAC ; Grapheme_Base # So [29] RINGED PLANET..HAMSA +1FAB0..1FABA ; Grapheme_Base # So [11] FLY..NEST WITH EGGS +1FAC0..1FAC5 ; Grapheme_Base # So [6] ANATOMICAL HEART..PERSON WITH CROWN +1FAD0..1FAD9 ; Grapheme_Base # So [10] BLUEBERRIES..JAR +1FAE0..1FAE7 ; Grapheme_Base # So [8] MELTING FACE..BUBBLES +1FAF0..1FAF6 ; Grapheme_Base # So [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS 1FB00..1FB92 ; Grapheme_Base # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; Grapheme_Base # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON 1FBF0..1FBF9 ; Grapheme_Base # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -20000..2A6DD ; Grapheme_Base # Lo [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Grapheme_Base # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Grapheme_Base # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; Grapheme_Base # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Grapheme_Base # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Grapheme_Base # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -# Total code points: 141814 +# Total code points: 142539 # ================================================ @@ -12034,7 +12368,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 0F84 ; Grapheme_Link # Mn TIBETAN MARK HALANTA 1039..103A ; Grapheme_Link # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT 1714 ; Grapheme_Link # Mn TAGALOG SIGN VIRAMA -1734 ; Grapheme_Link # Mn HANUNOO SIGN PAMUDPOD +1715 ; Grapheme_Link # Mc TAGALOG SIGN PAMUDPOD +1734 ; Grapheme_Link # Mc HANUNOO SIGN PAMUDPOD 17D2 ; Grapheme_Link # Mn KHMER SIGN COENG 1A60 ; Grapheme_Link # Mn TAI THAM SIGN SAKOT 1B44 ; Grapheme_Link # Mc BALINESE ADEG ADEG @@ -12051,6 +12386,7 @@ AAF6 ; Grapheme_Link # Mn MEETEI MAYEK VIRAMA ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 10A3F ; Grapheme_Link # Mn KHAROSHTHI VIRAMA 11046 ; Grapheme_Link # Mn BRAHMI VIRAMA +11070 ; Grapheme_Link # Mn BRAHMI SIGN OLD TAMIL VIRAMA 1107F ; Grapheme_Link # Mn BRAHMI NUMBER JOINER 110B9 ; Grapheme_Link # Mn KAITHI SIGN VIRAMA 11133..11134 ; Grapheme_Link # Mn [2] CHAKMA VIRAMA..CHAKMA MAAYYAA @@ -12075,6 +12411,6 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 11D44..11D45 ; Grapheme_Link # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA 11D97 ; Grapheme_Link # Mn GUNJALA GONDI VIRAMA -# Total code points: 61 +# Total code points: 63 # EOF |