diff options
Diffstat (limited to 'localedata/unicode-gen/DerivedCoreProperties.txt')
| -rw-r--r-- | localedata/unicode-gen/DerivedCoreProperties.txt | 515 |
1 files changed, 369 insertions, 146 deletions
diff --git a/localedata/unicode-gen/DerivedCoreProperties.txt b/localedata/unicode-gen/DerivedCoreProperties.txt index 16cd9b88bf..d855349df1 100644 --- a/localedata/unicode-gen/DerivedCoreProperties.txt +++ b/localedata/unicode-gen/DerivedCoreProperties.txt @@ -1,6 +1,6 @@ -# DerivedCoreProperties-10.0.0.txt -# Date: 2017-03-19, 00:05:15 GMT -# © 2017 Unicode®, Inc. +# DerivedCoreProperties-11.0.0.txt +# Date: 2018-02-21, 05:34:02 GMT +# © 2018 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 # @@ -295,14 +295,14 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 048A..052F ; Alphabetic # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; Alphabetic # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; Alphabetic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0561..0587 ; Alphabetic # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; Alphabetic # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 05B0..05BD ; Alphabetic # Mn [14] HEBREW POINT SHEVA..HEBREW POINT METEG 05BF ; Alphabetic # Mn HEBREW POINT RAFE 05C1..05C2 ; Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Alphabetic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C7 ; Alphabetic # Mn HEBREW POINT QAMATS QATAN 05D0..05EA ; Alphabetic # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; Alphabetic # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; Alphabetic # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0610..061A ; Alphabetic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 0620..063F ; Alphabetic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; Alphabetic # Lm ARABIC TATWEEL @@ -588,9 +588,10 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 10A0..10C5 ; Alphabetic # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; Alphabetic # L& GEORGIAN CAPITAL LETTER YN 10CD ; Alphabetic # L& GEORGIAN CAPITAL LETTER AEN -10D0..10FA ; Alphabetic # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; Alphabetic # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; Alphabetic # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; Alphabetic # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; Alphabetic # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; Alphabetic # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; Alphabetic # Lo ETHIOPIC SYLLABLE QHWA @@ -636,7 +637,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 17DC ; Alphabetic # Lo KHMER SIGN AVAKRAHASANYA 1820..1842 ; Alphabetic # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Alphabetic # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -1844..1877 ; Alphabetic # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; Alphabetic # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; Alphabetic # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1885..1886 ; Alphabetic # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 1887..18A8 ; Alphabetic # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA @@ -706,6 +707,8 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1C5A..1C77 ; Alphabetic # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; Alphabetic # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C80..1C88 ; Alphabetic # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; Alphabetic # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Alphabetic # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CE9..1CEC ; Alphabetic # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; Alphabetic # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA @@ -795,12 +798,12 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 30A1..30FA ; Alphabetic # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; Alphabetic # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; Alphabetic # Lo KATAKANA DIGRAPH KOTO -3105..312E ; Alphabetic # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; Alphabetic # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; Alphabetic # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; Alphabetic # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; Alphabetic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FEA ; Alphabetic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; Alphabetic # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; Alphabetic # Lm YI SYLLABLE WU A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -826,8 +829,7 @@ 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..A7AE ; Alphabetic # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; Alphabetic # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; Alphabetic # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Alphabetic # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -845,7 +847,7 @@ A8B4..A8C3 ; Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTR A8C5 ; Alphabetic # Mn SAURASHTRA SIGN CANDRABINDU A8F2..A8F7 ; Alphabetic # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; Alphabetic # Lo DEVANAGARI HEADSTROKE -A8FD ; Alphabetic # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; Alphabetic # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY A90A..A925 ; Alphabetic # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A926..A92A ; Alphabetic # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O A930..A946 ; Alphabetic # Lo [23] REJANG LETTER KA..REJANG LETTER A @@ -997,7 +999,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10A0C..10A0F ; Alphabetic # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA 10A10..10A13 ; Alphabetic # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; Alphabetic # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; Alphabetic # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A19..10A35 ; Alphabetic # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 10A60..10A7C ; Alphabetic # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH 10A80..10A9C ; Alphabetic # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH 10AC0..10AC7 ; Alphabetic # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW @@ -1009,6 +1011,11 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10C00..10C48 ; Alphabetic # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10C80..10CB2 ; Alphabetic # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Alphabetic # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D00..10D23 ; Alphabetic # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D24..10D27 ; Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +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 11000 ; Alphabetic # Mc BRAHMI SIGN CANDRABINDU 11001 ; Alphabetic # Mn BRAHMI SIGN ANUSVARA 11002 ; Alphabetic # Mc BRAHMI SIGN VISARGA @@ -1025,6 +1032,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11127..1112B ; Alphabetic # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Alphabetic # Mc CHAKMA VOWEL SIGN E 1112D..11132 ; Alphabetic # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK +11144 ; Alphabetic # Lo CHAKMA LETTER LHAA +11145..11146 ; Alphabetic # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI 11150..11172 ; Alphabetic # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11176 ; Alphabetic # Lo MAHAJANI LIGATURE SHRI 11180..11181 ; Alphabetic # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA @@ -1110,18 +1119,20 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 116AD ; Alphabetic # Mn TAKRI VOWEL SIGN AA 116AE..116AF ; Alphabetic # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II 116B0..116B5 ; Alphabetic # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU -11700..11719 ; Alphabetic # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11700..1171A ; Alphabetic # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F ; Alphabetic # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11720..11721 ; Alphabetic # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 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 +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 +11838 ; Alphabetic # Mc DOGRA SIGN VISARGA 118A0..118DF ; Alphabetic # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; Alphabetic # Lo WARANG CITI OM 11A00 ; Alphabetic # Lo ZANABAZAR SQUARE LETTER A -11A01..11A06 ; Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A07..11A08 ; Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU -11A09..11A0A ; Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A01..11A0A ; Alphabetic # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A0B..11A32 ; Alphabetic # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA 11A35..11A38 ; Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA 11A39 ; Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA @@ -1135,6 +1146,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11A86..11A89 ; Alphabetic # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA +11A9D ; Alphabetic # Lo SOYOMBO MARK PLUTA 11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -1161,6 +1173,18 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11D43 ; Alphabetic # Mn MASARAM GONDI SIGN CANDRA 11D46 ; Alphabetic # Lo MASARAM GONDI REPHA 11D47 ; Alphabetic # Mn MASARAM GONDI RA-KARA +11D60..11D65 ; Alphabetic # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; Alphabetic # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; Alphabetic # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D8A..11D8E ; Alphabetic # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D90..11D91 ; Alphabetic # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D93..11D94 ; Alphabetic # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D95 ; Alphabetic # Mn GUNJALA GONDI SIGN ANUSVARA +11D96 ; Alphabetic # Mc GUNJALA GONDI SIGN VISARGA +11D98 ; Alphabetic # Lo GUNJALA GONDI OM +11EE0..11EF2 ; Alphabetic # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11EF3..11EF4 ; Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11EF5..11EF6 ; Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 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 @@ -1174,12 +1198,13 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16B40..16B43 ; Alphabetic # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; Alphabetic # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Alphabetic # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16E40..16E7F ; Alphabetic # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F44 ; Alphabetic # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; Alphabetic # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; Alphabetic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; Alphabetic # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; Alphabetic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +17000..187F1 ; Alphabetic # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1 18800..18AF2 ; Alphabetic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -1269,7 +1294,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 126629 +# Total code points: 126989 # ================================================ @@ -1552,7 +1577,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 052B ; Lowercase # L& CYRILLIC SMALL LETTER DZZHE 052D ; Lowercase # L& CYRILLIC SMALL LETTER DCHE 052F ; Lowercase # L& CYRILLIC SMALL LETTER EL WITH DESCENDER -0561..0587 ; Lowercase # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; Lowercase # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +10D0..10FA ; Lowercase # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FD..10FF ; Lowercase # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13F8..13FD ; Lowercase # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Lowercase # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D00..1D2B ; Lowercase # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL @@ -1885,8 +1912,10 @@ A7A3 ; Lowercase # L& LATIN SMALL LETTER K WITH OBLIQUE STROKE A7A5 ; Lowercase # L& LATIN SMALL LETTER N WITH OBLIQUE STROKE A7A7 ; Lowercase # L& LATIN SMALL LETTER R WITH OBLIQUE STROKE A7A9 ; Lowercase # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE +A7AF ; Lowercase # L& LATIN LETTER SMALL CAPITAL Q A7B5 ; Lowercase # L& LATIN SMALL LETTER BETA A7B7 ; Lowercase # L& LATIN SMALL LETTER OMEGA +A7B9 ; Lowercase # L& LATIN SMALL LETTER U WITH STROKE A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Lowercase # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG @@ -1900,6 +1929,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 104D8..104FB ; Lowercase # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 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 1D41A..1D433 ; Lowercase # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z 1D44E..1D454 ; Lowercase # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G 1D456..1D467 ; Lowercase # L& [18] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL Z @@ -1930,7 +1960,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2252 +# Total code points: 2334 # ================================================ @@ -2213,6 +2243,8 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 10C7 ; Uppercase # L& GEORGIAN CAPITAL LETTER YN 10CD ; Uppercase # L& GEORGIAN CAPITAL LETTER AEN 13A0..13F5 ; Uppercase # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV +1C90..1CBA ; Uppercase # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Uppercase # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1E00 ; Uppercase # L& LATIN CAPITAL LETTER A WITH RING BELOW 1E02 ; Uppercase # L& LATIN CAPITAL LETTER B WITH DOT ABOVE 1E04 ; Uppercase # L& LATIN CAPITAL LETTER B WITH DOT BELOW @@ -2529,11 +2561,13 @@ A7A8 ; Uppercase # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE A7AA..A7AE ; Uppercase # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Uppercase # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Uppercase # L& LATIN CAPITAL LETTER OMEGA +A7B8 ; Uppercase # L& LATIN CAPITAL LETTER U WITH STROKE 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 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 1D400..1D419 ; Uppercase # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z 1D434..1D44D ; Uppercase # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z 1D468..1D481 ; Uppercase # L& [26] MATHEMATICAL BOLD ITALIC CAPITAL A..MATHEMATICAL BOLD ITALIC CAPITAL Z @@ -2570,7 +2604,7 @@ 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: 1822 +# Total code points: 1901 # ================================================ @@ -2606,13 +2640,17 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 03F7..0481 ; Cased # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 048A..052F ; Cased # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; Cased # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0561..0587 ; Cased # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; Cased # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 10A0..10C5 ; Cased # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; Cased # L& GEORGIAN CAPITAL LETTER YN 10CD ; Cased # L& GEORGIAN CAPITAL LETTER AEN +10D0..10FA ; Cased # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FD..10FF ; Cased # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13A0..13F5 ; Cased # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV 13F8..13FD ; Cased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Cased # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; Cased # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Cased # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1D00..1D2B ; Cased # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Cased # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; Cased # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -2675,8 +2713,7 @@ 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..A7AE ; Cased # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; Cased # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; Cased # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Cased # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG @@ -2693,6 +2730,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 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 +16E40..16E7F ; Cased # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1D400..1D454 ; Cased # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G 1D456..1D49C ; Cased # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A 1D49E..1D49F ; Cased # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D @@ -2728,7 +2766,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 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: 4105 +# Total code points: 4266 # ================================================ @@ -2793,6 +2831,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 07EB..07F3 ; Case_Ignorable # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE 07F4..07F5 ; Case_Ignorable # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE 07FA ; Case_Ignorable # Lm NKO LAJANYALAN +07FD ; Case_Ignorable # Mn NKO DANTAYALAN 0816..0819 ; Case_Ignorable # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH 081A ; Case_Ignorable # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT 081B..0823 ; Case_Ignorable # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A @@ -2801,7 +2840,7 @@ 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 -08D4..08E1 ; Case_Ignorable # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08D3..08E1 ; Case_Ignorable # Mn [15] ARABIC SMALL LOW WAW..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 @@ -2816,6 +2855,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 09C1..09C4 ; Case_Ignorable # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR 09CD ; Case_Ignorable # Mn BENGALI SIGN VIRAMA 09E2..09E3 ; Case_Ignorable # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; Case_Ignorable # Mn BENGALI SANDHI MARK 0A01..0A02 ; Case_Ignorable # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A3C ; Case_Ignorable # Mn GURMUKHI SIGN NUKTA 0A41..0A42 ; Case_Ignorable # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU @@ -2842,6 +2882,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0BC0 ; Case_Ignorable # Mn TAMIL VOWEL SIGN II 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 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 @@ -3011,6 +3052,7 @@ A80B ; Case_Ignorable # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Case_Ignorable # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E A8C4..A8C5 ; Case_Ignorable # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Case_Ignorable # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; Case_Ignorable # Mn DEVANAGARI VOWEL SIGN AY A926..A92D ; Case_Ignorable # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Case_Ignorable # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R A980..A982 ; Case_Ignorable # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR @@ -3067,19 +3109,22 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10A38..10A3A ; Case_Ignorable # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; Case_Ignorable # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Case_Ignorable # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; Case_Ignorable # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Case_Ignorable # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 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 +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 1112D..11134 ; Case_Ignorable # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA 11173 ; Case_Ignorable # Mn MAHAJANI SIGN NUKTA 11180..11181 ; Case_Ignorable # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA 111B6..111BE ; Case_Ignorable # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O -111CA..111CC ; Case_Ignorable # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111C9..111CC ; Case_Ignorable # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK 1122F..11231 ; Case_Ignorable # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Case_Ignorable # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Case_Ignorable # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA @@ -3087,13 +3132,14 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 112DF ; Case_Ignorable # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Case_Ignorable # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Case_Ignorable # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU -1133C ; Case_Ignorable # Mn GRANTHA SIGN NUKTA +1133B..1133C ; Case_Ignorable # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 11340 ; Case_Ignorable # Mn GRANTHA VOWEL SIGN II 11366..1136C ; Case_Ignorable # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Case_Ignorable # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA 11438..1143F ; Case_Ignorable # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Case_Ignorable # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Case_Ignorable # Mn NEWA SIGN NUKTA +1145E ; Case_Ignorable # Mn NEWA SANDHI MARK 114B3..114B8 ; Case_Ignorable # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Case_Ignorable # Mn TIRHUTA VOWEL SIGN SHORT E 114BF..114C0 ; Case_Ignorable # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA @@ -3112,8 +3158,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1171D..1171F ; Case_Ignorable # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Case_Ignorable # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Case_Ignorable # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER -11A01..11A06 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A09..11A0A ; Case_Ignorable # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +1182F..11837 ; Case_Ignorable # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; Case_Ignorable # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +11A01..11A0A ; Case_Ignorable # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A33..11A38 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA 11A3B..11A3E ; Case_Ignorable # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA 11A47 ; Case_Ignorable # Mn ZANABAZAR SQUARE SUBJOINER @@ -3133,6 +3180,10 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11D3C..11D3D ; Case_Ignorable # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O 11D3F..11D45 ; Case_Ignorable # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA 11D47 ; Case_Ignorable # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; Case_Ignorable # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; Case_Ignorable # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; Case_Ignorable # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; Case_Ignorable # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -3165,7 +3216,7 @@ 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: 2314 +# Total code points: 2357 # ================================================ @@ -3449,6 +3500,8 @@ E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELEC 10C7 ; Changes_When_Lowercased # L& GEORGIAN CAPITAL LETTER YN 10CD ; Changes_When_Lowercased # L& GEORGIAN CAPITAL LETTER AEN 13A0..13F5 ; Changes_When_Lowercased # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV +1C90..1CBA ; Changes_When_Lowercased # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Changes_When_Lowercased # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1E00 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER A WITH RING BELOW 1E02 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER B WITH DOT ABOVE 1E04 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER B WITH DOT BELOW @@ -3758,14 +3811,16 @@ A7A8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH O A7AA..A7AE ; Changes_When_Lowercased # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Changes_When_Lowercased # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER OMEGA +A7B8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER U WITH STROKE 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 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: 1304 +# Total code points: 1383 # ================================================ @@ -4059,6 +4114,8 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 052D ; Changes_When_Uppercased # L& CYRILLIC SMALL LETTER DCHE 052F ; Changes_When_Uppercased # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Changes_When_Uppercased # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +10D0..10FA ; Changes_When_Uppercased # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FD..10FF ; Changes_When_Uppercased # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13F8..13FD ; Changes_When_Uppercased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Changes_When_Uppercased # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D79 ; Changes_When_Uppercased # L& LATIN SMALL LETTER INSULAR G @@ -4371,6 +4428,7 @@ A7A7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER R WITH OBL A7A9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE A7B5 ; Changes_When_Uppercased # L& LATIN SMALL LETTER BETA A7B7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER OMEGA +A7B9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER U WITH STROKE AB53 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Uppercased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Changes_When_Uppercased # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST @@ -4380,9 +4438,10 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 104D8..104FB ; Changes_When_Uppercased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 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: 1396 +# Total code points: 1475 # ================================================ @@ -4989,6 +5048,7 @@ A7A7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER R WITH OBL A7A9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE A7B5 ; Changes_When_Titlecased # L& LATIN SMALL LETTER BETA A7B7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER OMEGA +A7B9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER U WITH STROKE AB53 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Titlecased # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Changes_When_Titlecased # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST @@ -4998,9 +5058,10 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 104D8..104FB ; Changes_When_Titlecased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 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: 1369 +# Total code points: 1402 # ================================================ @@ -5292,6 +5353,8 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 10CD ; Changes_When_Casefolded # L& GEORGIAN CAPITAL LETTER AEN 13F8..13FD ; Changes_When_Casefolded # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Changes_When_Casefolded # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; Changes_When_Casefolded # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Changes_When_Casefolded # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1E00 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER A WITH RING BELOW 1E02 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER B WITH DOT ABOVE 1E04 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER B WITH DOT BELOW @@ -5603,6 +5666,7 @@ A7A8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH O A7AA..A7AE ; Changes_When_Casefolded # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Changes_When_Casefolded # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER OMEGA +A7B8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER U WITH STROKE 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 FB13..FB17 ; Changes_When_Casefolded # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH @@ -5611,9 +5675,10 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 104B0..104D3 ; Changes_When_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 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: 1377 +# Total code points: 1456 # ================================================ @@ -5672,9 +5737,13 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 10A0..10C5 ; Changes_When_Casemapped # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; Changes_When_Casemapped # L& GEORGIAN CAPITAL LETTER YN 10CD ; Changes_When_Casemapped # L& GEORGIAN CAPITAL LETTER AEN +10D0..10FA ; Changes_When_Casemapped # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FD..10FF ; Changes_When_Casemapped # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN 13A0..13F5 ; Changes_When_Casemapped # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV 13F8..13FD ; Changes_When_Casemapped # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Changes_When_Casemapped # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; Changes_When_Casemapped # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Changes_When_Casemapped # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1D79 ; Changes_When_Casemapped # L& LATIN SMALL LETTER INSULAR G 1D7D ; Changes_When_Casemapped # L& LATIN SMALL LETTER P WITH STROKE 1E00..1E9B ; Changes_When_Casemapped # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE @@ -5724,7 +5793,7 @@ 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..A793 ; Changes_When_Casemapped # L& [4] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH BAR A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; Changes_When_Casemapped # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A7B0..A7B9 ; Changes_When_Casemapped # L& [10] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER U WITH STROKE AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Changes_When_Casemapped # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST @@ -5737,9 +5806,10 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 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: 2669 +# Total code points: 2827 # ================================================ @@ -5786,9 +5856,9 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 048A..052F ; ID_Start # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; ID_Start # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; ID_Start # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0561..0587 ; ID_Start # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; ID_Start # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 05D0..05EA ; ID_Start # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; ID_Start # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; ID_Start # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0620..063F ; ID_Start # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; ID_Start # Lm ARABIC TATWEEL 0641..064A ; ID_Start # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -5940,9 +6010,10 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 10A0..10C5 ; ID_Start # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; ID_Start # L& GEORGIAN CAPITAL LETTER YN 10CD ; ID_Start # L& GEORGIAN CAPITAL LETTER AEN -10D0..10FA ; ID_Start # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; ID_Start # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; ID_Start # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; ID_Start # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; ID_Start # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; ID_Start # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; ID_Start # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; ID_Start # Lo ETHIOPIC SYLLABLE QHWA @@ -5978,7 +6049,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 17DC ; ID_Start # Lo KHMER SIGN AVAKRAHASANYA 1820..1842 ; ID_Start # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ID_Start # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -1844..1877 ; ID_Start # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; ID_Start # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; ID_Start # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1885..1886 ; ID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 1887..18A8 ; ID_Start # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA @@ -6002,6 +6073,8 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 1C5A..1C77 ; ID_Start # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; ID_Start # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C80..1C88 ; ID_Start # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; ID_Start # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; ID_Start # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CE9..1CEC ; ID_Start # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; ID_Start # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF5..1CF6 ; ID_Start # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA @@ -6089,12 +6162,12 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 30A1..30FA ; ID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; ID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; ID_Start # Lo KATAKANA DIGRAPH KOTO -3105..312E ; ID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; ID_Start # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; ID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; ID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FEA ; ID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; ID_Start # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ID_Start # Lm YI SYLLABLE WU A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -6118,8 +6191,7 @@ 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..A7AE ; ID_Start # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; ID_Start # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; ID_Start # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE 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 A7FA ; ID_Start # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -6131,7 +6203,7 @@ A840..A873 ; ID_Start # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABI A882..A8B3 ; ID_Start # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8F2..A8F7 ; ID_Start # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; ID_Start # Lo DEVANAGARI HEADSTROKE -A8FD ; ID_Start # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; ID_Start # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY A90A..A925 ; ID_Start # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A930..A946 ; ID_Start # Lo [23] REJANG LETTER KA..REJANG LETTER A A960..A97C ; ID_Start # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH @@ -6247,7 +6319,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10A00 ; ID_Start # Lo KHAROSHTHI LETTER A 10A10..10A13 ; ID_Start # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; ID_Start # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; ID_Start # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A19..10A35 ; ID_Start # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 10A60..10A7C ; ID_Start # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH 10A80..10A9C ; ID_Start # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH 10AC0..10AC7 ; ID_Start # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW @@ -6259,10 +6331,15 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10C00..10C48 ; ID_Start # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10C80..10CB2 ; ID_Start # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; ID_Start # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D00..10D23 ; ID_Start # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +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 11003..11037 ; ID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 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 +11144 ; ID_Start # Lo CHAKMA LETTER LHAA 11150..11172 ; ID_Start # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11176 ; ID_Start # Lo MAHAJANI LIGATURE SHRI 11183..111B2 ; ID_Start # Lo [48] SHARADA LETTER A..SHARADA LETTER HA @@ -6296,7 +6373,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11600..1162F ; ID_Start # Lo [48] MODI LETTER A..MODI LETTER LLA 11644 ; ID_Start # Lo MODI SIGN HUVA 11680..116AA ; ID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA -11700..11719 ; ID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11700..1171A ; ID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +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 ; ID_Start # Lo WARANG CITI OM 11A00 ; ID_Start # Lo ZANABAZAR SQUARE LETTER A @@ -6305,6 +6383,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; ID_Start # Lo SOYOMBO LETTER A 11A5C..11A83 ; ID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA 11A86..11A89 ; ID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A9D ; ID_Start # Lo SOYOMBO MARK PLUTA 11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -6314,6 +6393,11 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11D08..11D09 ; ID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O 11D0B..11D30 ; ID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA 11D46 ; ID_Start # Lo MASARAM GONDI REPHA +11D60..11D65 ; ID_Start # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; ID_Start # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; ID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D98 ; ID_Start # Lo GUNJALA GONDI OM +11EE0..11EF2 ; ID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 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 @@ -6326,11 +6410,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16B40..16B43 ; ID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; ID_Start # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; ID_Start # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16E40..16E7F ; ID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F44 ; ID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; ID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; ID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; ID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +17000..187F1 ; ID_Start # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1 18800..18AF2 ; ID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -6410,7 +6495,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 125334 +# Total code points: 125660 # ================================================ @@ -6464,14 +6549,14 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 048A..052F ; ID_Continue # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; ID_Continue # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; ID_Continue # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0561..0587 ; ID_Continue # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; ID_Continue # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0591..05BD ; ID_Continue # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; ID_Continue # Mn HEBREW POINT RAFE 05C1..05C2 ; ID_Continue # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; ID_Continue # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C7 ; ID_Continue # Mn HEBREW POINT QAMATS QATAN 05D0..05EA ; ID_Continue # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; ID_Continue # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; ID_Continue # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0610..061A ; ID_Continue # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 0620..063F ; ID_Continue # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; ID_Continue # Lm ARABIC TATWEEL @@ -6503,6 +6588,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 07EB..07F3 ; ID_Continue # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE 07F4..07F5 ; ID_Continue # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE 07FA ; ID_Continue # Lm NKO LAJANYALAN +07FD ; ID_Continue # Mn NKO DANTAYALAN 0800..0815 ; ID_Continue # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 0816..0819 ; ID_Continue # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH 081A ; ID_Continue # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT @@ -6516,7 +6602,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; ID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON -08D4..08E1 ; ID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08D3..08E1 ; ID_Continue # Mn [15] ARABIC SMALL LOW WAW..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 @@ -6559,6 +6645,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 09E6..09EF ; ID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09F0..09F1 ; ID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; ID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA +09FE ; ID_Continue # Mn BENGALI SANDHI MARK 0A01..0A02 ; ID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; ID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; ID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -6648,6 +6735,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0BE6..0BEF ; ID_Continue # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE 0C00 ; ID_Continue # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; ID_Continue # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C04 ; ID_Continue # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE 0C05..0C0C ; ID_Continue # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L 0C0E..0C10 ; ID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; ID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA @@ -6800,9 +6888,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10A0..10C5 ; ID_Continue # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; ID_Continue # L& GEORGIAN CAPITAL LETTER YN 10CD ; ID_Continue # L& GEORGIAN CAPITAL LETTER AEN -10D0..10FA ; ID_Continue # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; ID_Continue # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; ID_Continue # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; ID_Continue # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; ID_Continue # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; ID_Continue # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; ID_Continue # Lo ETHIOPIC SYLLABLE QHWA @@ -6855,7 +6944,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 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 -1844..1877 ; ID_Continue # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; ID_Continue # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; ID_Continue # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1885..1886 ; ID_Continue # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 1887..18A8 ; ID_Continue # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA @@ -6944,6 +7033,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1C5A..1C77 ; ID_Continue # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; ID_Continue # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C80..1C88 ; ID_Continue # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; ID_Continue # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; ID_Continue # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CD0..1CD2 ; ID_Continue # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; ID_Continue # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE1 ; ID_Continue # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -7053,12 +7144,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30A1..30FA ; ID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; ID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; ID_Continue # Lo KATAKANA DIGRAPH KOTO -3105..312E ; ID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; ID_Continue # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; ID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; ID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FEA ; ID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; ID_Continue # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ID_Continue # Lm YI SYLLABLE WU A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -7087,8 +7178,7 @@ 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..A7AE ; ID_Continue # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; ID_Continue # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; ID_Continue # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE 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 A7FA ; ID_Continue # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -7111,7 +7201,8 @@ A8D0..A8D9 ; ID_Continue # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT N A8E0..A8F1 ; ID_Continue # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A8F2..A8F7 ; ID_Continue # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; ID_Continue # Lo DEVANAGARI HEADSTROKE -A8FD ; ID_Continue # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; ID_Continue # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY +A8FF ; ID_Continue # Mn DEVANAGARI VOWEL SIGN AY A900..A909 ; ID_Continue # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE A90A..A925 ; ID_Continue # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A926..A92D ; ID_Continue # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU @@ -7286,7 +7377,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10A0C..10A0F ; ID_Continue # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA 10A10..10A13 ; ID_Continue # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; ID_Continue # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; ID_Continue # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A19..10A35 ; ID_Continue # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 10A38..10A3A ; ID_Continue # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; ID_Continue # Mn KHAROSHTHI VIRAMA 10A60..10A7C ; ID_Continue # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH @@ -7301,6 +7392,13 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10C00..10C48 ; ID_Continue # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10C80..10CB2 ; ID_Continue # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; ID_Continue # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D00..10D23 ; ID_Continue # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D24..10D27 ; ID_Continue # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D30..10D39 ; ID_Continue # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL +10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH +10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F46..10F50 ; ID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 11000 ; ID_Continue # Mc BRAHMI SIGN CANDRABINDU 11001 ; ID_Continue # Mn BRAHMI SIGN ANUSVARA 11002 ; ID_Continue # Mc BRAHMI SIGN VISARGA @@ -7322,6 +7420,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1112C ; ID_Continue # Mc CHAKMA VOWEL SIGN E 1112D..11134 ; ID_Continue # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA 11136..1113F ; ID_Continue # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE +11144 ; ID_Continue # Lo CHAKMA LETTER LHAA +11145..11146 ; ID_Continue # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI 11150..11172 ; ID_Continue # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11173 ; ID_Continue # Mn MAHAJANI SIGN NUKTA 11176 ; ID_Continue # Lo MAHAJANI LIGATURE SHRI @@ -7332,7 +7432,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 111B6..111BE ; ID_Continue # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O 111BF..111C0 ; ID_Continue # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA 111C1..111C4 ; ID_Continue # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM -111CA..111CC ; ID_Continue # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111C9..111CC ; ID_Continue # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK 111D0..111D9 ; ID_Continue # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 111DA ; ID_Continue # Lo SHARADA EKAM 111DC ; ID_Continue # Lo SHARADA HEADSTROKE @@ -7363,7 +7463,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1132A..11330 ; ID_Continue # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA 11332..11333 ; ID_Continue # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA 11335..11339 ; ID_Continue # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA -1133C ; ID_Continue # Mn GRANTHA SIGN NUKTA +1133B..1133C ; ID_Continue # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 1133D ; ID_Continue # Lo GRANTHA SIGN AVAGRAHA 1133E..1133F ; ID_Continue # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I 11340 ; ID_Continue # Mn GRANTHA VOWEL SIGN II @@ -7385,6 +7485,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11446 ; ID_Continue # Mn NEWA SIGN NUKTA 11447..1144A ; ID_Continue # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11450..11459 ; ID_Continue # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145E ; ID_Continue # Mn NEWA SANDHI MARK 11480..114AF ; ID_Continue # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; ID_Continue # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; ID_Continue # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -7424,20 +7525,23 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 116B6 ; ID_Continue # Mc TAKRI SIGN VIRAMA 116B7 ; ID_Continue # Mn TAKRI SIGN NUKTA 116C0..116C9 ; ID_Continue # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE -11700..11719 ; ID_Continue # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11700..1171A ; ID_Continue # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F ; ID_Continue # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11720..11721 ; ID_Continue # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11722..11725 ; ID_Continue # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 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 +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 +11838 ; ID_Continue # Mc DOGRA SIGN VISARGA +11839..1183A ; ID_Continue # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA 118A0..118DF ; ID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; ID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118FF ; ID_Continue # Lo WARANG CITI OM 11A00 ; ID_Continue # Lo ZANABAZAR SQUARE LETTER A -11A01..11A06 ; ID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A07..11A08 ; ID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU -11A09..11A0A ; ID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A01..11A0A ; ID_Continue # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A0B..11A32 ; ID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA 11A33..11A38 ; ID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA 11A39 ; ID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA @@ -7453,6 +7557,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11A8A..11A96 ; ID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9D ; ID_Continue # Lo SOYOMBO MARK PLUTA 11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -7481,6 +7586,20 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11D46 ; ID_Continue # Lo MASARAM GONDI REPHA 11D47 ; ID_Continue # Mn MASARAM GONDI RA-KARA 11D50..11D59 ; ID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +11D60..11D65 ; ID_Continue # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; ID_Continue # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; ID_Continue # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D8A..11D8E ; ID_Continue # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D90..11D91 ; ID_Continue # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D93..11D94 ; ID_Continue # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D95 ; ID_Continue # Mn GUNJALA GONDI SIGN ANUSVARA +11D96 ; ID_Continue # Mc GUNJALA GONDI SIGN VISARGA +11D97 ; ID_Continue # Mn GUNJALA GONDI VIRAMA +11D98 ; ID_Continue # Lo GUNJALA GONDI OM +11DA0..11DA9 ; ID_Continue # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11EE0..11EF2 ; ID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11EF3..11EF4 ; ID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11EF5..11EF6 ; ID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 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 @@ -7497,13 +7616,14 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16B50..16B59 ; ID_Continue # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16B63..16B77 ; ID_Continue # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; ID_Continue # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16E40..16E7F ; ID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F44 ; ID_Continue # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; ID_Continue # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; ID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; ID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; ID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; ID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; ID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +17000..187F1 ; ID_Continue # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1 18800..18AF2 ; ID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -7607,7 +7727,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 128108 +# Total code points: 128510 # ================================================ @@ -7651,9 +7771,9 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 048A..052F ; XID_Start # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; XID_Start # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; XID_Start # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0561..0587 ; XID_Start # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; XID_Start # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 05D0..05EA ; XID_Start # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; XID_Start # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; XID_Start # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0620..063F ; XID_Start # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; XID_Start # Lm ARABIC TATWEEL 0641..064A ; XID_Start # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -7805,9 +7925,10 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 10A0..10C5 ; XID_Start # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; XID_Start # L& GEORGIAN CAPITAL LETTER YN 10CD ; XID_Start # L& GEORGIAN CAPITAL LETTER AEN -10D0..10FA ; XID_Start # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; XID_Start # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; XID_Start # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; XID_Start # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; XID_Start # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; XID_Start # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; XID_Start # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; XID_Start # Lo ETHIOPIC SYLLABLE QHWA @@ -7843,7 +7964,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 17DC ; XID_Start # Lo KHMER SIGN AVAKRAHASANYA 1820..1842 ; XID_Start # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; XID_Start # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -1844..1877 ; XID_Start # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; XID_Start # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; XID_Start # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1885..1886 ; XID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 1887..18A8 ; XID_Start # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA @@ -7867,6 +7988,8 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 1C5A..1C77 ; XID_Start # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; XID_Start # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C80..1C88 ; XID_Start # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; XID_Start # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; XID_Start # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CE9..1CEC ; XID_Start # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; XID_Start # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF5..1CF6 ; XID_Start # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA @@ -7953,12 +8076,12 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 30A1..30FA ; XID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; XID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; XID_Start # Lo KATAKANA DIGRAPH KOTO -3105..312E ; XID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; XID_Start # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; XID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; XID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; XID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FEA ; XID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; XID_Start # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; XID_Start # Lm YI SYLLABLE WU A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -7982,8 +8105,7 @@ 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..A7AE ; XID_Start # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; XID_Start # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; XID_Start # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE 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 A7FA ; XID_Start # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -7995,7 +8117,7 @@ A840..A873 ; XID_Start # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRAB A882..A8B3 ; XID_Start # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8F2..A8F7 ; XID_Start # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; XID_Start # Lo DEVANAGARI HEADSTROKE -A8FD ; XID_Start # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; XID_Start # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY A90A..A925 ; XID_Start # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A930..A946 ; XID_Start # Lo [23] REJANG LETTER KA..REJANG LETTER A A960..A97C ; XID_Start # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH @@ -8116,7 +8238,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10A00 ; XID_Start # Lo KHAROSHTHI LETTER A 10A10..10A13 ; XID_Start # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; XID_Start # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; XID_Start # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A19..10A35 ; XID_Start # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 10A60..10A7C ; XID_Start # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH 10A80..10A9C ; XID_Start # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH 10AC0..10AC7 ; XID_Start # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW @@ -8128,10 +8250,15 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10C00..10C48 ; XID_Start # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10C80..10CB2 ; XID_Start # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; XID_Start # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D00..10D23 ; XID_Start # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +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 11003..11037 ; XID_Start # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 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 +11144 ; XID_Start # Lo CHAKMA LETTER LHAA 11150..11172 ; XID_Start # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11176 ; XID_Start # Lo MAHAJANI LIGATURE SHRI 11183..111B2 ; XID_Start # Lo [48] SHARADA LETTER A..SHARADA LETTER HA @@ -8165,7 +8292,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11600..1162F ; XID_Start # Lo [48] MODI LETTER A..MODI LETTER LLA 11644 ; XID_Start # Lo MODI SIGN HUVA 11680..116AA ; XID_Start # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA -11700..11719 ; XID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11700..1171A ; XID_Start # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +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 ; XID_Start # Lo WARANG CITI OM 11A00 ; XID_Start # Lo ZANABAZAR SQUARE LETTER A @@ -8174,6 +8302,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11A50 ; XID_Start # Lo SOYOMBO LETTER A 11A5C..11A83 ; XID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA 11A86..11A89 ; XID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A9D ; XID_Start # Lo SOYOMBO MARK PLUTA 11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -8183,6 +8312,11 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11D08..11D09 ; XID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O 11D0B..11D30 ; XID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA 11D46 ; XID_Start # Lo MASARAM GONDI REPHA +11D60..11D65 ; XID_Start # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; XID_Start # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; XID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D98 ; XID_Start # Lo GUNJALA GONDI OM +11EE0..11EF2 ; XID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 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 @@ -8195,11 +8329,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16B40..16B43 ; XID_Start # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; XID_Start # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; XID_Start # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16E40..16E7F ; XID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F44 ; XID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; XID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; XID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; XID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +17000..187F1 ; XID_Start # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1 18800..18AF2 ; XID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -8279,7 +8414,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 125311 +# Total code points: 125637 # ================================================ @@ -8329,14 +8464,14 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 048A..052F ; XID_Continue # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; XID_Continue # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; XID_Continue # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0561..0587 ; XID_Continue # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; XID_Continue # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0591..05BD ; XID_Continue # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; XID_Continue # Mn HEBREW POINT RAFE 05C1..05C2 ; XID_Continue # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; XID_Continue # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT 05C7 ; XID_Continue # Mn HEBREW POINT QAMATS QATAN 05D0..05EA ; XID_Continue # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; XID_Continue # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; XID_Continue # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0610..061A ; XID_Continue # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 0620..063F ; XID_Continue # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; XID_Continue # Lm ARABIC TATWEEL @@ -8368,6 +8503,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 07EB..07F3 ; XID_Continue # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE 07F4..07F5 ; XID_Continue # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE 07FA ; XID_Continue # Lm NKO LAJANYALAN +07FD ; XID_Continue # Mn NKO DANTAYALAN 0800..0815 ; XID_Continue # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 0816..0819 ; XID_Continue # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH 081A ; XID_Continue # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT @@ -8381,7 +8517,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; XID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW 08B6..08BD ; XID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON -08D4..08E1 ; XID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08D3..08E1 ; XID_Continue # Mn [15] ARABIC SMALL LOW WAW..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 @@ -8424,6 +8560,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 09E6..09EF ; XID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09F0..09F1 ; XID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; XID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA +09FE ; XID_Continue # Mn BENGALI SANDHI MARK 0A01..0A02 ; XID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; XID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; XID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -8513,6 +8650,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0BE6..0BEF ; XID_Continue # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE 0C00 ; XID_Continue # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; XID_Continue # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C04 ; XID_Continue # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE 0C05..0C0C ; XID_Continue # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L 0C0E..0C10 ; XID_Continue # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; XID_Continue # Lo [23] TELUGU LETTER O..TELUGU LETTER NA @@ -8665,9 +8803,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10A0..10C5 ; XID_Continue # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; XID_Continue # L& GEORGIAN CAPITAL LETTER YN 10CD ; XID_Continue # L& GEORGIAN CAPITAL LETTER AEN -10D0..10FA ; XID_Continue # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; XID_Continue # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; XID_Continue # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; XID_Continue # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; XID_Continue # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; XID_Continue # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; XID_Continue # Lo ETHIOPIC SYLLABLE QHWA @@ -8720,7 +8859,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 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 -1844..1877 ; XID_Continue # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; XID_Continue # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; XID_Continue # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1885..1886 ; XID_Continue # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 1887..18A8 ; XID_Continue # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA @@ -8809,6 +8948,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1C5A..1C77 ; XID_Continue # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; XID_Continue # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C80..1C88 ; XID_Continue # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; XID_Continue # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; XID_Continue # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CD0..1CD2 ; XID_Continue # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; XID_Continue # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE1 ; XID_Continue # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -8917,12 +9058,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30A1..30FA ; XID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; XID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; XID_Continue # Lo KATAKANA DIGRAPH KOTO -3105..312E ; XID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; XID_Continue # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; XID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; XID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; XID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FEA ; XID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; XID_Continue # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; XID_Continue # Lm YI SYLLABLE WU A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -8951,8 +9092,7 @@ 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..A7AE ; XID_Continue # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; XID_Continue # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; XID_Continue # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE 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 A7FA ; XID_Continue # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -8975,7 +9115,8 @@ A8D0..A8D9 ; XID_Continue # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT A8E0..A8F1 ; XID_Continue # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A8F2..A8F7 ; XID_Continue # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; XID_Continue # Lo DEVANAGARI HEADSTROKE -A8FD ; XID_Continue # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; XID_Continue # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY +A8FF ; XID_Continue # Mn DEVANAGARI VOWEL SIGN AY A900..A909 ; XID_Continue # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE A90A..A925 ; XID_Continue # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A926..A92D ; XID_Continue # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU @@ -9156,7 +9297,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10A0C..10A0F ; XID_Continue # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA 10A10..10A13 ; XID_Continue # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; XID_Continue # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; XID_Continue # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A19..10A35 ; XID_Continue # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 10A38..10A3A ; XID_Continue # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; XID_Continue # Mn KHAROSHTHI VIRAMA 10A60..10A7C ; XID_Continue # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH @@ -9171,6 +9312,13 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10C00..10C48 ; XID_Continue # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 10C80..10CB2 ; XID_Continue # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; XID_Continue # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +10D00..10D23 ; XID_Continue # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D24..10D27 ; XID_Continue # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D30..10D39 ; XID_Continue # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL +10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH +10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F46..10F50 ; XID_Continue # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 11000 ; XID_Continue # Mc BRAHMI SIGN CANDRABINDU 11001 ; XID_Continue # Mn BRAHMI SIGN ANUSVARA 11002 ; XID_Continue # Mc BRAHMI SIGN VISARGA @@ -9192,6 +9340,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1112C ; XID_Continue # Mc CHAKMA VOWEL SIGN E 1112D..11134 ; XID_Continue # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA 11136..1113F ; XID_Continue # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE +11144 ; XID_Continue # Lo CHAKMA LETTER LHAA +11145..11146 ; XID_Continue # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI 11150..11172 ; XID_Continue # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11173 ; XID_Continue # Mn MAHAJANI SIGN NUKTA 11176 ; XID_Continue # Lo MAHAJANI LIGATURE SHRI @@ -9202,7 +9352,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 111B6..111BE ; XID_Continue # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O 111BF..111C0 ; XID_Continue # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA 111C1..111C4 ; XID_Continue # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM -111CA..111CC ; XID_Continue # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111C9..111CC ; XID_Continue # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK 111D0..111D9 ; XID_Continue # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 111DA ; XID_Continue # Lo SHARADA EKAM 111DC ; XID_Continue # Lo SHARADA HEADSTROKE @@ -9233,7 +9383,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1132A..11330 ; XID_Continue # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA 11332..11333 ; XID_Continue # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA 11335..11339 ; XID_Continue # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA -1133C ; XID_Continue # Mn GRANTHA SIGN NUKTA +1133B..1133C ; XID_Continue # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 1133D ; XID_Continue # Lo GRANTHA SIGN AVAGRAHA 1133E..1133F ; XID_Continue # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I 11340 ; XID_Continue # Mn GRANTHA VOWEL SIGN II @@ -9255,6 +9405,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11446 ; XID_Continue # Mn NEWA SIGN NUKTA 11447..1144A ; XID_Continue # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11450..11459 ; XID_Continue # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145E ; XID_Continue # Mn NEWA SANDHI MARK 11480..114AF ; XID_Continue # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; XID_Continue # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; XID_Continue # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -9294,20 +9445,23 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 116B6 ; XID_Continue # Mc TAKRI SIGN VIRAMA 116B7 ; XID_Continue # Mn TAKRI SIGN NUKTA 116C0..116C9 ; XID_Continue # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE -11700..11719 ; XID_Continue # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11700..1171A ; XID_Continue # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA 1171D..1171F ; XID_Continue # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11720..11721 ; XID_Continue # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11722..11725 ; XID_Continue # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 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 +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 +11838 ; XID_Continue # Mc DOGRA SIGN VISARGA +11839..1183A ; XID_Continue # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA 118A0..118DF ; XID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; XID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118FF ; XID_Continue # Lo WARANG CITI OM 11A00 ; XID_Continue # Lo ZANABAZAR SQUARE LETTER A -11A01..11A06 ; XID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A07..11A08 ; XID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU -11A09..11A0A ; XID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A01..11A0A ; XID_Continue # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A0B..11A32 ; XID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA 11A33..11A38 ; XID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA 11A39 ; XID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA @@ -9323,6 +9477,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11A8A..11A96 ; XID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA 11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9D ; XID_Continue # Lo SOYOMBO MARK PLUTA 11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; XID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -9351,6 +9506,20 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11D46 ; XID_Continue # Lo MASARAM GONDI REPHA 11D47 ; XID_Continue # Mn MASARAM GONDI RA-KARA 11D50..11D59 ; XID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +11D60..11D65 ; XID_Continue # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; XID_Continue # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; XID_Continue # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D8A..11D8E ; XID_Continue # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D90..11D91 ; XID_Continue # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D93..11D94 ; XID_Continue # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D95 ; XID_Continue # Mn GUNJALA GONDI SIGN ANUSVARA +11D96 ; XID_Continue # Mc GUNJALA GONDI SIGN VISARGA +11D97 ; XID_Continue # Mn GUNJALA GONDI VIRAMA +11D98 ; XID_Continue # Lo GUNJALA GONDI OM +11DA0..11DA9 ; XID_Continue # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11EE0..11EF2 ; XID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11EF3..11EF4 ; XID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11EF5..11EF6 ; XID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 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 @@ -9367,13 +9536,14 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16B50..16B59 ; XID_Continue # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 16B63..16B77 ; XID_Continue # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; XID_Continue # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16E40..16E7F ; XID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16F00..16F44 ; XID_Continue # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; XID_Continue # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; XID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; XID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; XID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; XID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; XID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +17000..187F1 ; XID_Continue # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1 18800..18AF2 ; XID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -9477,7 +9647,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 128089 +# Total code points: 128491 # ================================================ @@ -9545,12 +9715,13 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0730..074A ; Grapheme_Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH 07A6..07B0 ; Grapheme_Extend # Mn [11] THAANA ABAFILI..THAANA SUKUN 07EB..07F3 ; Grapheme_Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; Grapheme_Extend # Mn NKO DANTAYALAN 0816..0819 ; Grapheme_Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH 081B..0823 ; Grapheme_Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 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 -08D4..08E1 ; Grapheme_Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08D3..08E1 ; Grapheme_Extend # Mn [15] ARABIC SMALL LOW WAW..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 @@ -9565,6 +9736,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 09CD ; Grapheme_Extend # Mn BENGALI SIGN VIRAMA 09D7 ; Grapheme_Extend # Mc BENGALI AU LENGTH MARK 09E2..09E3 ; Grapheme_Extend # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; Grapheme_Extend # Mn BENGALI SANDHI MARK 0A01..0A02 ; Grapheme_Extend # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A3C ; Grapheme_Extend # Mn GURMUKHI SIGN NUKTA 0A41..0A42 ; Grapheme_Extend # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU @@ -9595,6 +9767,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0BCD ; Grapheme_Extend # Mn TAMIL SIGN VIRAMA 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 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 @@ -9723,6 +9896,7 @@ A80B ; Grapheme_Extend # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Grapheme_Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E A8C4..A8C5 ; Grapheme_Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Grapheme_Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; Grapheme_Extend # Mn DEVANAGARI VOWEL SIGN AY A926..A92D ; Grapheme_Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Grapheme_Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R A980..A982 ; Grapheme_Extend # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR @@ -9759,6 +9933,8 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 10A38..10A3A ; Grapheme_Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; Grapheme_Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Grapheme_Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; Grapheme_Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; Grapheme_Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 11001 ; Grapheme_Extend # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Grapheme_Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 1107F..11081 ; Grapheme_Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA @@ -9770,7 +9946,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 11173 ; Grapheme_Extend # Mn MAHAJANI SIGN NUKTA 11180..11181 ; Grapheme_Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA 111B6..111BE ; Grapheme_Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O -111CA..111CC ; Grapheme_Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111C9..111CC ; Grapheme_Extend # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK 1122F..11231 ; Grapheme_Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Grapheme_Extend # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Grapheme_Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA @@ -9778,7 +9954,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 112DF ; Grapheme_Extend # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Grapheme_Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Grapheme_Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU -1133C ; Grapheme_Extend # Mn GRANTHA SIGN NUKTA +1133B..1133C ; Grapheme_Extend # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 1133E ; Grapheme_Extend # Mc GRANTHA VOWEL SIGN AA 11340 ; Grapheme_Extend # Mn GRANTHA VOWEL SIGN II 11357 ; Grapheme_Extend # Mc GRANTHA AU LENGTH MARK @@ -9787,6 +9963,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 11438..1143F ; Grapheme_Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Grapheme_Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Grapheme_Extend # Mn NEWA SIGN NUKTA +1145E ; Grapheme_Extend # Mn NEWA SANDHI MARK 114B0 ; Grapheme_Extend # Mc TIRHUTA VOWEL SIGN AA 114B3..114B8 ; Grapheme_Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Grapheme_Extend # Mn TIRHUTA VOWEL SIGN SHORT E @@ -9808,8 +9985,9 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1171D..1171F ; Grapheme_Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Grapheme_Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Grapheme_Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER -11A01..11A06 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A09..11A0A ; Grapheme_Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +1182F..11837 ; Grapheme_Extend # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; Grapheme_Extend # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +11A01..11A0A ; Grapheme_Extend # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A33..11A38 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA 11A3B..11A3E ; Grapheme_Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA 11A47 ; Grapheme_Extend # Mn ZANABAZAR SQUARE SUBJOINER @@ -9829,6 +10007,10 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 11D3C..11D3D ; Grapheme_Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O 11D3F..11D45 ; Grapheme_Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA 11D47 ; Grapheme_Extend # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; Grapheme_Extend # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; Grapheme_Extend # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; Grapheme_Extend # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; Grapheme_Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 16AF0..16AF4 ; Grapheme_Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Grapheme_Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -9856,7 +10038,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1901 +# Total code points: 1943 # ================================================ @@ -9959,7 +10141,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0531..0556 ; Grapheme_Base # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; Grapheme_Base # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; Grapheme_Base # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK -0561..0587 ; Grapheme_Base # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; Grapheme_Base # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 0589 ; Grapheme_Base # Po ARMENIAN FULL STOP 058A ; Grapheme_Base # Pd ARMENIAN HYPHEN 058D..058E ; Grapheme_Base # So [2] RIGHT-FACING ARMENIAN ETERNITY SIGN..LEFT-FACING ARMENIAN ETERNITY SIGN @@ -9969,7 +10151,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 05C3 ; Grapheme_Base # Po HEBREW PUNCTUATION SOF PASUQ 05C6 ; Grapheme_Base # Po HEBREW PUNCTUATION NUN HAFUKHA 05D0..05EA ; Grapheme_Base # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; Grapheme_Base # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; Grapheme_Base # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 05F3..05F4 ; Grapheme_Base # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM 0606..0608 ; Grapheme_Base # Sm [3] ARABIC-INDIC CUBE ROOT..ARABIC RAY 0609..060A ; Grapheme_Base # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN @@ -10006,6 +10188,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 07F6 ; Grapheme_Base # So NKO SYMBOL OO DENNEN 07F7..07F9 ; Grapheme_Base # Po [3] NKO SYMBOL GBAKURUNEN..NKO EXCLAMATION MARK 07FA ; Grapheme_Base # Lm NKO LAJANYALAN +07FE..07FF ; Grapheme_Base # Sc [2] NKO DOROME SIGN..NKO TAMAN SIGN 0800..0815 ; Grapheme_Base # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 081A ; Grapheme_Base # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT 0824 ; Grapheme_Base # Lm SAMARITAN MODIFIER LETTER SHORT A @@ -10065,6 +10248,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0A5E ; Grapheme_Base # Lo GURMUKHI LETTER FA 0A66..0A6F ; Grapheme_Base # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE 0A72..0A74 ; Grapheme_Base # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR +0A76 ; Grapheme_Base # Po GURMUKHI ABBREVIATION SIGN 0A83 ; Grapheme_Base # Mc GUJARATI SIGN VISARGA 0A85..0A8D ; Grapheme_Base # Lo [9] GUJARATI LETTER A..GUJARATI VOWEL CANDRA E 0A8F..0A91 ; Grapheme_Base # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O @@ -10133,6 +10317,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0C7F ; Grapheme_Base # So TELUGU SIGN TUUMU 0C80 ; Grapheme_Base # Lo KANNADA SIGN SPACING CANDRABINDU 0C82..0C83 ; Grapheme_Base # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA +0C84 ; Grapheme_Base # Po KANNADA SIGN SIDDHAM 0C85..0C8C ; Grapheme_Base # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; Grapheme_Base # Lo [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; Grapheme_Base # Lo [23] KANNADA LETTER O..KANNADA LETTER NA @@ -10257,10 +10442,11 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 10A0..10C5 ; Grapheme_Base # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; Grapheme_Base # L& GEORGIAN CAPITAL LETTER YN 10CD ; Grapheme_Base # L& GEORGIAN CAPITAL LETTER AEN -10D0..10FA ; Grapheme_Base # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; Grapheme_Base # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FB ; Grapheme_Base # Po GEORGIAN PARAGRAPH SEPARATOR 10FC ; Grapheme_Base # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; Grapheme_Base # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; Grapheme_Base # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; Grapheme_Base # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; Grapheme_Base # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; Grapheme_Base # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; Grapheme_Base # Lo ETHIOPIC SYLLABLE QHWA @@ -10318,7 +10504,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1810..1819 ; Grapheme_Base # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1820..1842 ; Grapheme_Base # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Grapheme_Base # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -1844..1877 ; Grapheme_Base # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; Grapheme_Base # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; Grapheme_Base # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1887..18A8 ; Grapheme_Base # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; Grapheme_Base # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA @@ -10387,6 +10573,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1C78..1C7D ; Grapheme_Base # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F ; Grapheme_Base # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 1C80..1C88 ; Grapheme_Base # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C90..1CBA ; Grapheme_Base # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; Grapheme_Base # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CC0..1CC7 ; Grapheme_Base # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD3 ; Grapheme_Base # Po VEDIC SIGN NIHSHVASA 1CE1 ; Grapheme_Base # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -10623,10 +10811,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2B47..2B4C ; Grapheme_Base # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 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 -2B98..2BB9 ; Grapheme_Base # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX -2BBD..2BC8 ; Grapheme_Base # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD2 ; Grapheme_Base # So [9] TOP HALF BLACK CIRCLE..GROUP MARK -2BEC..2BEF ; Grapheme_Base # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS +2B98..2BC8 ; Grapheme_Base # So [49] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED +2BCA..2BFE ; Grapheme_Base # So [53] TOP HALF BLACK CIRCLE..REVERSED RIGHT ANGLE 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 @@ -10690,7 +10876,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2E40 ; Grapheme_Base # Pd DOUBLE HYPHEN 2E41 ; Grapheme_Base # Po REVERSED COMMA 2E42 ; Grapheme_Base # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E49 ; Grapheme_Base # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA +2E43..2E4E ; Grapheme_Base # Po [12] DASH WITH LEFT UPTURN..PUNCTUS ELEVATUS MARK 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 @@ -10742,7 +10928,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 30FB ; Grapheme_Base # Po KATAKANA MIDDLE DOT 30FC..30FE ; Grapheme_Base # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; Grapheme_Base # Lo KATAKANA DIGRAPH KOTO -3105..312E ; Grapheme_Base # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; Grapheme_Base # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; Grapheme_Base # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; Grapheme_Base # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; Grapheme_Base # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -10764,7 +10950,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 3300..33FF ; Grapheme_Base # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; Grapheme_Base # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DC0..4DFF ; Grapheme_Base # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FEA ; Grapheme_Base # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; Grapheme_Base # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; Grapheme_Base # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; Grapheme_Base # Lm YI SYLLABLE WU A016..A48C ; Grapheme_Base # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -10798,8 +10984,7 @@ 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..A7AE ; Grapheme_Base # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7B7 ; Grapheme_Base # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA +A790..A7B9 ; Grapheme_Base # L& [42] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER U WITH STROKE 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 A7FA ; Grapheme_Base # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -10825,7 +11010,7 @@ A8F2..A8F7 ; Grapheme_Base # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DE A8F8..A8FA ; Grapheme_Base # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET A8FB ; Grapheme_Base # Lo DEVANAGARI HEADSTROKE A8FC ; Grapheme_Base # Po DEVANAGARI SIGN SIDDHAM -A8FD ; Grapheme_Base # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; Grapheme_Base # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY A900..A909 ; Grapheme_Base # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE A90A..A925 ; Grapheme_Base # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A92E..A92F ; Grapheme_Base # Po [2] KAYAH LI SIGN CWI..KAYAH LI SIGN SHYA @@ -11089,8 +11274,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10A00 ; Grapheme_Base # Lo KHAROSHTHI LETTER A 10A10..10A13 ; Grapheme_Base # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; Grapheme_Base # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; Grapheme_Base # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA -10A40..10A47 ; Grapheme_Base # No [8] KHAROSHTHI DIGIT ONE..KHAROSHTHI NUMBER ONE THOUSAND +10A19..10A35 ; Grapheme_Base # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA +10A40..10A48 ; Grapheme_Base # No [9] KHAROSHTHI DIGIT ONE..KHAROSHTHI FRACTION ONE HALF 10A50..10A58 ; Grapheme_Base # Po [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES 10A60..10A7C ; Grapheme_Base # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH 10A7D..10A7E ; Grapheme_Base # No [2] OLD SOUTH ARABIAN NUMBER ONE..OLD SOUTH ARABIAN NUMBER FIFTY @@ -11115,7 +11300,15 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10C80..10CB2 ; Grapheme_Base # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Grapheme_Base # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10CFA..10CFF ; Grapheme_Base # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND +10D00..10D23 ; Grapheme_Base # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D30..10D39 ; Grapheme_Base # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE 10E60..10E7E ; Grapheme_Base # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS +10F00..10F1C ; Grapheme_Base # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL +10F1D..10F26 ; Grapheme_Base # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF +10F27 ; Grapheme_Base # Lo OLD SOGDIAN LIGATURE AYIN-DALETH +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 11000 ; Grapheme_Base # Mc BRAHMI SIGN CANDRABINDU 11002 ; Grapheme_Base # Mc BRAHMI SIGN VISARGA 11003..11037 ; Grapheme_Base # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA @@ -11134,6 +11327,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1112C ; Grapheme_Base # Mc CHAKMA VOWEL SIGN E 11136..1113F ; Grapheme_Base # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 11140..11143 ; Grapheme_Base # Po [4] CHAKMA SECTION MARK..CHAKMA QUESTION MARK +11144 ; Grapheme_Base # Lo CHAKMA LETTER LHAA +11145..11146 ; Grapheme_Base # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI 11150..11172 ; Grapheme_Base # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11174..11175 ; Grapheme_Base # Po [2] MAHAJANI ABBREVIATION SIGN..MAHAJANI SECTION MARK 11176 ; Grapheme_Base # Lo MAHAJANI LIGATURE SHRI @@ -11142,7 +11337,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 111B3..111B5 ; Grapheme_Base # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II 111BF..111C0 ; Grapheme_Base # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA 111C1..111C4 ; Grapheme_Base # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM -111C5..111C9 ; Grapheme_Base # Po [5] SHARADA DANDA..SHARADA SANDHI MARK +111C5..111C8 ; Grapheme_Base # Po [4] SHARADA DANDA..SHARADA SEPARATOR 111CD ; Grapheme_Base # Po SHARADA SUTRA MARK 111D0..111D9 ; Grapheme_Base # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 111DA ; Grapheme_Base # Lo SHARADA EKAM @@ -11218,19 +11413,22 @@ 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 116C0..116C9 ; Grapheme_Base # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE -11700..11719 ; Grapheme_Base # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +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 11726 ; Grapheme_Base # Mc AHOM VOWEL SIGN E 11730..11739 ; Grapheme_Base # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 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 +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 +1183B ; Grapheme_Base # Po DOGRA ABBREVIATION SIGN 118A0..118DF ; Grapheme_Base # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; Grapheme_Base # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; Grapheme_Base # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; Grapheme_Base # Lo WARANG CITI OM 11A00 ; Grapheme_Base # Lo ZANABAZAR SQUARE LETTER A -11A07..11A08 ; Grapheme_Base # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU 11A0B..11A32 ; Grapheme_Base # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA 11A39 ; Grapheme_Base # Mc ZANABAZAR SQUARE SIGN VISARGA 11A3A ; Grapheme_Base # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA @@ -11241,6 +11439,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11A86..11A89 ; Grapheme_Base # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A97 ; Grapheme_Base # Mc SOYOMBO SIGN VISARGA 11A9A..11A9C ; Grapheme_Base # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +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 11C00..11C08 ; Grapheme_Base # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L @@ -11261,6 +11460,17 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11D0B..11D30 ; Grapheme_Base # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA 11D46 ; Grapheme_Base # Lo MASARAM GONDI REPHA 11D50..11D59 ; Grapheme_Base # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +11D60..11D65 ; Grapheme_Base # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; Grapheme_Base # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; Grapheme_Base # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D8A..11D8E ; Grapheme_Base # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D93..11D94 ; Grapheme_Base # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D96 ; Grapheme_Base # Mc GUNJALA GONDI SIGN VISARGA +11D98 ; Grapheme_Base # Lo GUNJALA GONDI OM +11DA0..11DA9 ; Grapheme_Base # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11EE0..11EF2 ; Grapheme_Base # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11EF5..11EF6 ; Grapheme_Base # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11EF7..11EF8 ; Grapheme_Base # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION 12000..12399 ; Grapheme_Base # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Grapheme_Base # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; Grapheme_Base # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -11283,12 +11493,15 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16B5B..16B61 ; Grapheme_Base # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; Grapheme_Base # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; Grapheme_Base # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16E40..16E7F ; Grapheme_Base # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16E80..16E96 ; Grapheme_Base # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM +16E97..16E9A ; Grapheme_Base # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH 16F00..16F44 ; Grapheme_Base # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; Grapheme_Base # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; Grapheme_Base # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; Grapheme_Base # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; Grapheme_Base # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; Grapheme_Base # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +17000..187F1 ; Grapheme_Base # Lo [6130] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F1 18800..18AF2 ; Grapheme_Base # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; Grapheme_Base # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 1B170..1B2FB ; Grapheme_Base # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -11309,8 +11522,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1D1AE..1D1E8 ; Grapheme_Base # So [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN 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 1D300..1D356 ; Grapheme_Base # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING -1D360..1D371 ; Grapheme_Base # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE +1D360..1D378 ; Grapheme_Base # No [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE 1D400..1D454 ; Grapheme_Base # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G 1D456..1D49C ; Grapheme_Base # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A 1D49E..1D49F ; Grapheme_Base # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D @@ -11363,6 +11577,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1E900..1E943 ; Grapheme_Base # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E950..1E959 ; Grapheme_Base # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E95E..1E95F ; Grapheme_Base # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK +1EC71..1ECAB ; Grapheme_Base # No [59] INDIC SIYAQ NUMBER ONE..INDIC SIYAQ NUMBER PREFIXED NINE +1ECAC ; Grapheme_Base # So INDIC SIYAQ PLACEHOLDER +1ECAD..1ECAF ; Grapheme_Base # No [3] INDIC SIYAQ FRACTION ONE QUARTER..INDIC SIYAQ FRACTION THREE QUARTERS +1ECB0 ; Grapheme_Base # Sc INDIC SIYAQ RUPEE MARK +1ECB1..1ECB4 ; Grapheme_Base # No [4] INDIC SIYAQ NUMBER ALTERNATE ONE..INDIC SIYAQ ALTERNATE LAKH MARK 1EE00..1EE03 ; Grapheme_Base # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Grapheme_Base # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; Grapheme_Base # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -11404,8 +11623,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F0C1..1F0CF ; Grapheme_Base # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER 1F0D1..1F0F5 ; Grapheme_Base # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F100..1F10C ; Grapheme_Base # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO -1F110..1F12E ; Grapheme_Base # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ -1F130..1F16B ; Grapheme_Base # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN +1F110..1F16B ; Grapheme_Base # So [92] PARENTHESIZED LATIN CAPITAL LETTER A..RAISED MD SIGN 1F170..1F1AC ; Grapheme_Base # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD 1F1E6..1F202 ; Grapheme_Base # So [29] REGIONAL INDICATOR SYMBOL LETTER A..SQUARED KATAKANA SA 1F210..1F23B ; Grapheme_Base # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D @@ -11416,9 +11634,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F3FB..1F3FF ; Grapheme_Base # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F400..1F6D4 ; Grapheme_Base # So [725] RAT..PAGODA 1F6E0..1F6EC ; Grapheme_Base # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F8 ; Grapheme_Base # So [9] SATELLITE..FLYING SAUCER +1F6F0..1F6F9 ; Grapheme_Base # So [10] SATELLITE..SKATEBOARD 1F700..1F773 ; Grapheme_Base # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE -1F780..1F7D4 ; Grapheme_Base # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR +1F780..1F7D8 ; Grapheme_Base # So [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE 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 @@ -11426,11 +11644,14 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F900..1F90B ; Grapheme_Base # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F910..1F93E ; Grapheme_Base # So [47] ZIPPER-MOUTH FACE..HANDBALL -1F940..1F94C ; Grapheme_Base # So [13] WILTED FLOWER..CURLING STONE -1F950..1F96B ; Grapheme_Base # So [28] CROISSANT..CANNED FOOD -1F980..1F997 ; Grapheme_Base # So [24] CRAB..CRICKET -1F9C0 ; Grapheme_Base # So CHEESE WEDGE -1F9D0..1F9E6 ; Grapheme_Base # So [23] FACE WITH MONOCLE..SOCKS +1F940..1F970 ; Grapheme_Base # So [49] WILTED FLOWER..SMILING FACE WITH SMILING EYES AND THREE HEARTS +1F973..1F976 ; Grapheme_Base # So [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE +1F97A ; Grapheme_Base # So FACE WITH PLEADING EYES +1F97C..1F9A2 ; Grapheme_Base # So [39] LAB COAT..SWAN +1F9B0..1F9B9 ; Grapheme_Base # So [10] EMOJI COMPONENT RED HAIR..SUPERVILLAIN +1F9C0..1F9C2 ; Grapheme_Base # So [3] CHEESE WEDGE..SALT SHAKER +1F9D0..1F9FF ; Grapheme_Base # So [48] FACE WITH MONOCLE..NAZAR AMULET +1FA60..1FA6D ; Grapheme_Base # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 20000..2A6D6 ; Grapheme_Base # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Grapheme_Base # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D @@ -11438,7 +11659,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 2CEB0..2EBE0 ; Grapheme_Base # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 134733 +# Total code points: 135374 # ================================================ @@ -11490,12 +11711,14 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 1163F ; Grapheme_Link # Mn MODI SIGN VIRAMA 116B6 ; Grapheme_Link # Mc TAKRI SIGN VIRAMA 1172B ; Grapheme_Link # Mn AHOM SIGN KILLER +11839 ; Grapheme_Link # Mn DOGRA SIGN VIRAMA 11A34 ; Grapheme_Link # Mn ZANABAZAR SQUARE SIGN VIRAMA 11A47 ; Grapheme_Link # Mn ZANABAZAR SQUARE SUBJOINER 11A99 ; Grapheme_Link # Mn SOYOMBO SUBJOINER 11C3F ; Grapheme_Link # Mn BHAIKSUKI SIGN VIRAMA 11D44..11D45 ; Grapheme_Link # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA +11D97 ; Grapheme_Link # Mn GUNJALA GONDI VIRAMA -# Total code points: 54 +# Total code points: 56 # EOF |