diff options
Diffstat (limited to 'util/unicode/data/SentenceBreakProperty.txt')
-rw-r--r-- | util/unicode/data/SentenceBreakProperty.txt | 172 |
1 files changed, 124 insertions, 48 deletions
diff --git a/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt index cd698150f4..cd0532a619 100644 --- a/util/unicode/data/SentenceBreakProperty.txt +++ b/util/unicode/data/SentenceBreakProperty.txt @@ -1,6 +1,6 @@ -# SentenceBreakProperty-10.0.0.txt -# Date: 2017-03-08, 08:42:08 GMT -# © 2017 Unicode®, Inc. +# SentenceBreakProperty-12.1.0.txt +# Date: 2019-03-10, 10:53:28 GMT +# © 2019 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 # @@ -49,12 +49,13 @@ 0730..074A ; Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH 07A6..07B0 ; Extend # Mn [11] THAANA ABAFILI..THAANA SUKUN 07EB..07F3 ; Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; Extend # Mn NKO DANTAYALAN 0816..0819 ; Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH 081B..0823 ; Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -77,6 +78,7 @@ 09CD ; Extend # Mn BENGALI SIGN VIRAMA 09D7 ; Extend # Mc BENGALI AU LENGTH MARK 09E2..09E3 ; Extend # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; Extend # Mn BENGALI SANDHI MARK 0A01..0A02 ; Extend # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; Extend # Mc GURMUKHI SIGN VISARGA 0A3C ; Extend # Mn GURMUKHI SIGN NUKTA @@ -121,6 +123,7 @@ 0BD7 ; Extend # Mc TAMIL AU LENGTH MARK 0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE 0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; Extend # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI @@ -160,8 +163,7 @@ 0E34..0E3A ; Extend # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU 0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN 0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN -0EB4..0EB9 ; Extend # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU -0EBB..0EBC ; Extend # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO 0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA 0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS 0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA @@ -274,7 +276,6 @@ 1CE1 ; Extend # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CE2..1CE8 ; Extend # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL 1CED ; Extend # Mn VEDIC SIGN TIRYAK -1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE @@ -307,6 +308,7 @@ A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISA A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; Extend # Mn DEVANAGARI VOWEL SIGN AY A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R A952..A953 ; Extend # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA @@ -316,8 +318,8 @@ A9B3 ; Extend # Mn JAVANESE SIGN CECAK TELU A9B4..A9B5 ; Extend # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG A9B6..A9B9 ; Extend # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT A9BA..A9BB ; Extend # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE -A9BC ; Extend # Mn JAVANESE VOWEL SIGN PEPET -A9BD..A9C0 ; Extend # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON +A9BC..A9BD ; Extend # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9BE..A9C0 ; Extend # Mc [3] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE PANGKON A9E5 ; Extend # Mn MYANMAR SIGN SHAN SAW AA29..AA2E ; Extend # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE AA2F..AA30 ; Extend # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI @@ -360,6 +362,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10A38..10A3A ; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA 11002 ; Extend # Mc BRAHMI SIGN VISARGA @@ -374,13 +378,14 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Extend # Mc CHAKMA VOWEL SIGN E 1112D..11134 ; Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11145..11146 ; Extend # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI 11173 ; Extend # Mn MAHAJANI SIGN NUKTA 11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA 11182 ; Extend # Mc SHARADA SIGN VISARGA 111B3..111B5 ; Extend # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II 111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O 111BF..111C0 ; Extend # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA -111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111C9..111CC ; Extend # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK 1122C..1122E ; Extend # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II 1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11232..11233 ; Extend # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU @@ -393,7 +398,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU 11302..11303 ; Extend # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA -1133C ; Extend # Mn GRANTHA SIGN NUKTA +1133B..1133C ; Extend # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 1133E..1133F ; Extend # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I 11340 ; Extend # Mn GRANTHA VOWEL SIGN II 11341..11344 ; Extend # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR @@ -409,6 +414,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11445 ; Extend # Mc NEWA SIGN VISARGA 11446 ; Extend # Mn NEWA SIGN NUKTA +1145E ; Extend # Mn NEWA SANDHI MARK 114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E @@ -442,9 +448,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Extend # Mc AHOM VOWEL SIGN E 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER -11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU -11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +1182C..1182E ; Extend # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II +1182F..11837 ; Extend # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11838 ; Extend # Mc DOGRA SIGN VISARGA +11839..1183A ; Extend # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +119D1..119D3 ; Extend # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II +119D4..119D7 ; Extend # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; Extend # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119DC..119DF ; Extend # Mc [4] NANDINAGARI VOWEL SIGN O..NANDINAGARI SIGN VISARGA +119E0 ; Extend # Mn NANDINAGARI SIGN VIRAMA +119E4 ; Extend # Mc NANDINAGARI VOWEL SIGN PRISHTHAMATRA E +11A01..11A0A ; Extend # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA 11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA 11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA @@ -472,9 +486,18 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O 11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA 11D47 ; Extend # Mn MASARAM GONDI RA-KARA +11D8A..11D8E ; Extend # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D90..11D91 ; Extend # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D93..11D94 ; Extend # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D95 ; Extend # Mn GUNJALA GONDI SIGN ANUSVARA +11D96 ; Extend # Mc GUNJALA GONDI SIGN VISARGA +11D97 ; Extend # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11EF5..11EF6 ; Extend # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM -16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG +16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1D165..1D166 ; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM @@ -495,12 +518,14 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2277 +# Total code points: 2368 # ================================================ @@ -527,11 +552,13 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR 110BD ; Format # Cf KAITHI NUMBER SIGN +110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE +13430..13438 ; Format # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT 1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Format # Cf LANGUAGE TAG -# Total code points: 53 +# Total code points: 63 # ================================================ @@ -824,7 +851,7 @@ E0001 ; Format # Cf LANGUAGE TAG 052B ; Lower # L& CYRILLIC SMALL LETTER DZZHE 052D ; Lower # L& CYRILLIC SMALL LETTER DCHE 052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER -0561..0587 ; Lower # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +0560..0588 ; Lower # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE 13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV 1C80..1C88 ; Lower # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL @@ -1157,13 +1184,19 @@ A7A3 ; Lower # L& LATIN SMALL LETTER K WITH OBLIQUE STROKE A7A5 ; Lower # L& LATIN SMALL LETTER N WITH OBLIQUE STROKE A7A7 ; Lower # L& LATIN SMALL LETTER R WITH OBLIQUE STROKE A7A9 ; Lower # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE +A7AF ; Lower # L& LATIN LETTER SMALL CAPITAL Q A7B5 ; Lower # L& LATIN SMALL LETTER BETA A7B7 ; Lower # L& LATIN SMALL LETTER OMEGA +A7B9 ; Lower # L& LATIN SMALL LETTER U WITH STROKE +A7BB ; Lower # L& LATIN SMALL LETTER GLOTTAL A +A7BD ; Lower # L& LATIN SMALL LETTER GLOTTAL I +A7BF ; Lower # L& LATIN SMALL LETTER GLOTTAL U +A7C3 ; Lower # L& LATIN SMALL LETTER ANGLICANA W A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Lower # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG AB5C..AB5F ; Lower # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK -AB60..AB65 ; Lower # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA +AB60..AB67 ; Lower # L& [8] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK AB70..ABBF ; Lower # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH @@ -1172,6 +1205,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 104D8..104FB ; Lower # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO +16E60..16E7F ; Lower # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z 1D44E..1D454 ; Lower # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G 1D456..1D467 ; Lower # L& [18] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL Z @@ -1202,7 +1236,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA 1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2251 +# Total code points: 2293 # ================================================ @@ -1801,11 +1835,18 @@ A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE A7AA..A7AE ; Upper # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Upper # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Upper # L& LATIN CAPITAL LETTER OMEGA +A7B8 ; Upper # L& LATIN CAPITAL LETTER U WITH STROKE +A7BA ; Upper # L& LATIN CAPITAL LETTER GLOTTAL A +A7BC ; Upper # L& LATIN CAPITAL LETTER GLOTTAL I +A7BE ; Upper # L& LATIN CAPITAL LETTER GLOTTAL U +A7C2 ; Upper # L& LATIN CAPITAL LETTER ANGLICANA W +A7C4..A7C6 ; Upper # L& [3] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER Z WITH PALATAL HOOK FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Upper # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO +16E40..16E5F ; Upper # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z 1D434..1D44D ; Upper # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z 1D468..1D481 ; Upper # L& [26] MATHEMATICAL BOLD ITALIC CAPITAL A..MATHEMATICAL BOLD ITALIC CAPITAL Z @@ -1842,7 +1883,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1853 +# Total code points: 1893 # ================================================ @@ -1856,7 +1897,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0374 ; OLetter # Lm GREEK NUMERAL SIGN 0559 ; OLetter # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING 05D0..05EA ; OLetter # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; OLetter # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05EF..05F2 ; OLetter # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 05F3 ; OLetter # Po HEBREW PUNCTUATION GERESH 0620..063F ; OLetter # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; OLetter # Lm ARABIC TATWEEL @@ -1978,16 +2019,10 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0E46 ; OLetter # Lm THAI CHARACTER MAIYAMOK 0E81..0E82 ; OLetter # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG 0E84 ; OLetter # Lo LAO LETTER KHO TAM -0E87..0E88 ; OLetter # Lo [2] LAO LETTER NGO..LAO LETTER CO -0E8A ; OLetter # Lo LAO LETTER SO TAM -0E8D ; OLetter # Lo LAO LETTER NYO -0E94..0E97 ; OLetter # Lo [4] LAO LETTER DO..LAO LETTER THO TAM -0E99..0E9F ; OLetter # Lo [7] LAO LETTER NO..LAO LETTER FO SUNG -0EA1..0EA3 ; OLetter # Lo [3] LAO LETTER MO..LAO LETTER LO LING +0E86..0E8A ; OLetter # Lo [5] LAO LETTER PALI GHA..LAO LETTER SO TAM +0E8C..0EA3 ; OLetter # Lo [24] LAO LETTER PALI JHA..LAO LETTER LO LING 0EA5 ; OLetter # Lo LAO LETTER LO LOOT -0EA7 ; OLetter # Lo LAO LETTER WO -0EAA..0EAB ; OLetter # Lo [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG -0EAD..0EB0 ; OLetter # Lo [4] LAO LETTER O..LAO VOWEL SIGN A +0EA7..0EB0 ; OLetter # Lo [10] LAO LETTER WO..LAO VOWEL SIGN A 0EB2..0EB3 ; OLetter # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM 0EBD ; OLetter # Lo LAO SEMIVOWEL SIGN NYO 0EC0..0EC4 ; OLetter # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI @@ -2006,9 +2041,10 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 106E..1070 ; OLetter # Lo [3] MYANMAR LETTER EASTERN PWO KAREN NNA..MYANMAR LETTER EASTERN PWO KAREN GHWA 1075..1081 ; OLetter # Lo [13] MYANMAR LETTER SHAN KA..MYANMAR LETTER SHAN HA 108E ; OLetter # Lo MYANMAR LETTER RUMAI PALAUNG FA -10D0..10FA ; OLetter # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10D0..10FA ; OLetter # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN 10FC ; OLetter # Lm MODIFIER LETTER GEORGIAN NAR -10FD..1248 ; OLetter # Lo [332] GEORGIAN LETTER AEN..ETHIOPIC SYLLABLE QWA +10FD..10FF ; OLetter # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; OLetter # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA 124A..124D ; OLetter # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE 1250..1256 ; OLetter # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO 1258 ; OLetter # Lo ETHIOPIC SYLLABLE QHWA @@ -2042,7 +2078,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 17DC ; OLetter # Lo KHMER SIGN AVAKRAHASANYA 1820..1842 ; OLetter # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; OLetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -1844..1877 ; OLetter # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1844..1878 ; OLetter # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS 1880..1884 ; OLetter # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 1887..18A8 ; OLetter # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; OLetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA @@ -2064,9 +2100,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1C4D..1C4F ; OLetter # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; OLetter # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; OLetter # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C90..1CBA ; OLetter # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; OLetter # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CE9..1CEC ; OLetter # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL -1CEE..1CF1 ; OLetter # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA +1CEE..1CF3 ; OLetter # Lo [6] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; OLetter # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CFA ; OLetter # Lo VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA 2135..2138 ; OLetter # Lo [4] ALEF SYMBOL..DALET SYMBOL 2180..2182 ; OLetter # Nl [3] ROMAN NUMERAL ONE THOUSAND C D..ROMAN NUMERAL TEN THOUSAND 2185..2188 ; OLetter # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND @@ -2096,12 +2135,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 30A1..30FA ; OLetter # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; OLetter # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; OLetter # Lo KATAKANA DIGRAPH KOTO -3105..312E ; OLetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE +3105..312F ; OLetter # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; OLetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; OLetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; OLetter # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FEA ; OLetter # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +4E00..9FEF ; OLetter # Lo [20976] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEF A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; OLetter # Lm YI SYLLABLE WU A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -2127,7 +2166,7 @@ A840..A873 ; OLetter # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABIN A882..A8B3 ; OLetter # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8F2..A8F7 ; OLetter # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; OLetter # Lo DEVANAGARI HEADSTROKE -A8FD ; OLetter # Lo DEVANAGARI JAIN OM +A8FD..A8FE ; OLetter # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY A90A..A925 ; OLetter # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A930..A946 ; OLetter # Lo [23] REJANG LETTER KA..REJANG LETTER A A960..A97C ; OLetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH @@ -2231,7 +2270,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10A00 ; OLetter # Lo KHAROSHTHI LETTER A 10A10..10A13 ; OLetter # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA 10A15..10A17 ; OLetter # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA -10A19..10A33 ; OLetter # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA +10A19..10A35 ; OLetter # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA 10A60..10A7C ; OLetter # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH 10A80..10A9C ; OLetter # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH 10AC0..10AC7 ; OLetter # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW @@ -2241,10 +2280,16 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10B60..10B72 ; OLetter # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW 10B80..10B91 ; OLetter # Lo [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW 10C00..10C48 ; OLetter # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH +10D00..10D23 ; OLetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL +10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH +10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10FE0..10FF6 ; OLetter # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; OLetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11083..110AF ; OLetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; OLetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; OLetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA +11144 ; OLetter # Lo CHAKMA LETTER LHAA 11150..11172 ; OLetter # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11176 ; OLetter # Lo MAHAJANI LIGATURE SHRI 11183..111B2 ; OLetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA @@ -2270,6 +2315,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11400..11434 ; OLetter # Lo [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; OLetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1145F ; OLetter # Lo NEWA LETTER VEDIC ANUSVARA 11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; OLetter # Lo TIRHUTA OM @@ -2278,14 +2324,20 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11600..1162F ; OLetter # Lo [48] MODI LETTER A..MODI LETTER LLA 11644 ; OLetter # Lo MODI SIGN HUVA 11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA -11700..11719 ; OLetter # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +116B8 ; OLetter # Lo TAKRI LETTER ARCHAIC KHA +11700..1171A ; OLetter # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11800..1182B ; OLetter # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118FF ; OLetter # Lo WARANG CITI OM +119A0..119A7 ; OLetter # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR +119AA..119D0 ; OLetter # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA +119E1 ; OLetter # Lo NANDINAGARI SIGN AVAGRAHA +119E3 ; OLetter # Lo NANDINAGARI HEADSTROKE 11A00 ; OLetter # Lo ZANABAZAR SQUARE LETTER A 11A0B..11A32 ; OLetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA 11A3A ; OLetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA 11A50 ; OLetter # Lo SOYOMBO LETTER A -11A5C..11A83 ; OLetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA -11A86..11A89 ; OLetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A5C..11A89 ; OLetter # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A9D ; OLetter # Lo SOYOMBO MARK PLUTA 11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; OLetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; OLetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -2295,6 +2347,11 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11D08..11D09 ; OLetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O 11D0B..11D30 ; OLetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA 11D46 ; OLetter # Lo MASARAM GONDI REPHA +11D60..11D65 ; OLetter # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; OLetter # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; OLetter # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D98 ; OLetter # Lo GUNJALA GONDI OM +11EE0..11EF2 ; OLetter # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -2307,19 +2364,27 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16B40..16B43 ; OLetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16B63..16B77 ; OLetter # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; OLetter # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ -16F00..16F44 ; OLetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA +16F00..16F4A ; OLetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; OLetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -17000..187EC ; OLetter # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +16FE3 ; OLetter # Lm OLD CHINESE ITERATION MARK +17000..187F7 ; OLetter # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18AF2 ; OLetter # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 1B000..1B11E ; OLetter # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B150..1B152 ; OLetter # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B164..1B167 ; OLetter # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; OLetter # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1E100..1E12C ; OLetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W +1E137..1E13D ; OLetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E14E ; OLetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E2C0..1E2EB ; OLetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E800..1E8C4 ; OLetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E94B ; OLetter # Lm ADLAM NASALIZATION MARK 1EE00..1EE03 ; OLetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; OLetter # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; OLetter # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -2360,7 +2425,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 121354 +# Total code points: 121822 # ================================================ @@ -2401,7 +2466,9 @@ A9D0..A9D9 ; Numeric # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE A9F0..A9F9 ; Numeric # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DIGIT NINE AA50..AA59 ; Numeric # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE +FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE 11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE @@ -2415,12 +2482,15 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N 118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE 11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE +1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 582 +# Total code points: 632 # ================================================ @@ -2436,10 +2506,13 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP 0021 ; STerm # Po EXCLAMATION MARK 003F ; STerm # Po QUESTION MARK 0589 ; STerm # Po ARMENIAN FULL STOP -061F ; STerm # Po ARABIC QUESTION MARK +061E..061F ; STerm # Po [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK 06D4 ; STerm # Po ARABIC FULL STOP 0700..0702 ; STerm # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP 07F9 ; STerm # Po NKO EXCLAMATION MARK +0837 ; STerm # Po SAMARITAN PUNCTUATION MELODIC QITSA +0839 ; STerm # Po SAMARITAN PUNCTUATION QITSA +083D..083E ; STerm # Po [2] SAMARITAN PUNCTUATION SOF MASHFAAT..SAMARITAN PUNCTUATION ANNAAU 0964..0965 ; STerm # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA 104A..104B ; STerm # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION 1362 ; STerm # Po ETHIOPIC FULL STOP @@ -2475,6 +2548,7 @@ FF01 ; STerm # Po FULLWIDTH EXCLAMATION MARK FF1F ; STerm # Po FULLWIDTH QUESTION MARK FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA +10F55..10F59 ; STerm # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT 11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA 110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK @@ -2492,14 +2566,16 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 11A42..11A43 ; STerm # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD 11A9B..11A9C ; STerm # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD 11C41..11C42 ; STerm # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA +11EF7..11EF8 ; STerm # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION 16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; STerm # Po BASSA VAH FULL STOP 16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB 16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS +16E98 ; STerm # Po MEDEFAIDRIN FULL STOP 1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; STerm # Po SIGNWRITING FULL STOP -# Total code points: 125 +# Total code points: 138 # ================================================ |