diff options
Diffstat (limited to 'src/unicode/PropList.txt')
| -rw-r--r-- | src/unicode/PropList.txt | 101 |
1 files changed, 68 insertions, 33 deletions
diff --git a/src/unicode/PropList.txt b/src/unicode/PropList.txt index e64b422..3f1b6ec 100644 --- a/src/unicode/PropList.txt +++ b/src/unicode/PropList.txt @@ -1,6 +1,6 @@ -# PropList-17.0.0.txt -# Date: 2025-06-30, 06:19:01 GMT -# © 2025 Unicode®, Inc. +# PropList-18.0.0.txt +# Date: 2026-08-07, 16:20:14 GMT +# © 2026 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html # @@ -167,6 +167,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET 2E4C ; Terminal_Punctuation # Po MEDIEVAL COMMA 2E4E..2E4F ; Terminal_Punctuation # Po [2] PUNCTUS ELEVATUS MARK..CORNISH VERSE DIVIDER 2E53..2E54 ; Terminal_Punctuation # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK +2E60..2E61 ; Terminal_Punctuation # Po [2] WIGGLY EXCLAMATION MARK..INVERTED WIGGLY EXCLAMATION MARK 3001..3002 ; Terminal_Punctuation # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP A4FE..A4FF ; Terminal_Punctuation # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D..A60F ; Terminal_Punctuation # Po [3] VAI COMMA..VAI QUESTION MARK @@ -234,7 +235,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 291 +# Total code points: 293 # ================================================ @@ -368,7 +369,7 @@ FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT 1D540..1D544 ; Other_Math # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M 1D546 ; Other_Math # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O 1D54A..1D550 ; Other_Math # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y -1D552..1D6A5 ; Other_Math # L& [340] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J +1D552..1D6A6 ; Other_Math # L& [341] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL LIGATURE LONG S WITH DESCENDER S 1D6A8..1D6C0 ; Other_Math # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA 1D6C2..1D6DA ; Other_Math # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA 1D6DC..1D6FA ; Other_Math # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA @@ -414,8 +415,10 @@ FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT 1EEA1..1EEA3 ; Other_Math # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; Other_Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; Other_Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN +1F7DB ; Other_Math # So BULLET IN DOUBLE CIRCLE +1F7F1..1F7FF ; Other_Math # So [15] CIRCLE WITH DOUBLE VERTICAL AND HORIZONTAL LINE..RHOMBUS -# Total code points: 1362 +# Total code points: 1379 # ================================================ @@ -444,7 +447,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 05BF ; Other_Alphabetic # Mn HEBREW POINT RAFE 05C1..05C2 ; Other_Alphabetic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Other_Alphabetic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7 ; Other_Alphabetic # Mn HEBREW POINT QAMATS QATAN +05C7..05C9 ; Other_Alphabetic # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 0610..061A ; Other_Alphabetic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA 064B..0657 ; Other_Alphabetic # Mn [13] ARABIC FATHATAN..ARABIC INVERTED DAMMA 0659..065F ; Other_Alphabetic # Mn [7] ARABIC ZWARAKAY..ARABIC WAVY HAMZA BELOW @@ -702,6 +705,10 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69 ; Other_Alphabetic # Mn GARAY VOWEL SIGN E 10EAB..10EAC ; Other_Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10ECB..10ECD ; Other_Alphabetic # Mn [3] ARABIC NORTHEAST POINTING ARROWHEAD ABOVE..ARABIC SOUTHWEST POINTING ARROWHEAD BELOW +10EF3 ; Other_Alphabetic # Mn ARABIC SMALL HIGH NOON WITH FATHA +10EF5 ; Other_Alphabetic # Mn ARABIC SMALL HIGH NOON WITH DAMMA +10EF7..10EF8 ; Other_Alphabetic # Mn [2] ARABIC SMALL HIGH HEH INITIAL FORM..ARABIC SMALL HIGH WORD KABBIR 10EFA..10EFC ; Other_Alphabetic # Mn [3] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC COMBINING ALEF OVERLAY 11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU 11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA @@ -837,6 +844,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11D93..11D94 ; Other_Alphabetic # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU 11D95 ; Other_Alphabetic # Mn GUNJALA GONDI SIGN ANUSVARA 11D96 ; Other_Alphabetic # Mc GUNJALA GONDI SIGN VISARGA +11DF0 ; Other_Alphabetic # Mn BENGALI SIGN COMBINING ANUSVARA ABOVE 11EF3..11EF4 ; Other_Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; Other_Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 11F00..11F01 ; Other_Alphabetic # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA @@ -868,7 +876,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1510 +# Total code points: 1520 # ================================================ @@ -883,20 +891,23 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 16FE4 ; Ideographic # Mn KHITAN SMALL SCRIPT FILLER 16FF2..16FF3 ; Ideographic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 16FF4..16FF6 ; Ideographic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS -17000..18CD5 ; Ideographic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D1E ; Ideographic # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +17000..18CDA ; Ideographic # Lo [7387] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CDA +18CFF..18D20 ; Ideographic # Lo [34] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D20 18D80..18DF2 ; Ideographic # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 +18E00..19191 ; Ideographic # Lo [914] JURCHEN CHARACTER-18E00..JURCHEN CHARACTER-19191 +191A0..191D2 ; Ideographic # Lo [51] JURCHEN RADICAL-01..JURCHEN RADICAL-51 1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 20000..2A6DF ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B81D ; Ideographic # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2A700..2B81E ; Ideographic # Lo [4383] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81E 2B820..2CEAD ; Ideographic # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; Ideographic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..33479 ; Ideographic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 +3D000..3FC3F ; Ideographic # Lo [11328] SMALL SEAL CHARACTER-3D000..SMALL SEAL CHARACTER-3FC3F -# Total code points: 110943 +# Total code points: 123244 # ================================================ @@ -925,15 +936,17 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 037A ; Diacritic # Lm GREEK YPOGEGRAMMENI 0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS 0483..0487 ; Diacritic # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE -0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +0558..0559 ; Diacritic # Lm [2] MODIFIER LETTER ARMENIAN SMALL EH..ARMENIAN MODIFIER LETTER LEFT HALF RING +058B..058C ; Diacritic # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 0591..05BD ; Diacritic # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; Diacritic # Mn HEBREW POINT RAFE 05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT 05C4..05C5 ; Diacritic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT -05C7 ; Diacritic # Mn HEBREW POINT QAMATS QATAN +05C7..05C9 ; Diacritic # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH 064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN -0657..0658 ; Diacritic # Mn [2] ARABIC INVERTED DAMMA..ARABIC MARK NOON GHUNNA +0656..0658 ; Diacritic # Mn [3] ARABIC SUBSCRIPT ALEF..ARABIC MARK NOON GHUNNA 06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO +06E2 ; Diacritic # Mn ARABIC SMALL HIGH MEEM ISOLATED FORM 06E5..06E6 ; Diacritic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH 06EA..06EC ; Diacritic # Mn [3] ARABIC EMPTY CENTRE LOW STOP..ARABIC ROUNDED HIGH STOP WITH FILLED CENTRE 0730..074A ; Diacritic # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH @@ -943,7 +956,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0818..0819 ; Diacritic # Mn [2] SAMARITAN MARK OCCLUSION..SAMARITAN MARK DAGESH 0898..089F ; Diacritic # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA 08C9 ; Diacritic # Lm ARABIC SMALL FARSI YEH -08CA..08D2 ; Diacritic # Mn [9] ARABIC SMALL HIGH FARSI YEH..ARABIC LARGE ROUND DOT INSIDE CIRCLE BELOW +08CA..08D3 ; Diacritic # Mn [10] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL LOW WAW 08E3..08FE ; Diacritic # Mn [28] ARABIC TURNED DAMMA BELOW..ARABIC DAMMA WITH DOT 093C ; Diacritic # Mn DEVANAGARI SIGN NUKTA 094D ; Diacritic # Mn DEVANAGARI SIGN VIRAMA @@ -958,7 +971,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0AFD..0AFF ; Diacritic # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Diacritic # Mn ORIYA SIGN NUKTA 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA -0B55 ; Diacritic # Mn ORIYA SIGN OVERLINE +0B53..0B55 ; Diacritic # Mn [3] ORIYA SIGN DOT ABOVE..ORIYA SIGN OVERLINE 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA 0C3C ; Diacritic # Mn TELUGU SIGN NUKTA 0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA @@ -1001,8 +1014,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1AB0..1ABD ; Diacritic # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Diacritic # Me COMBINING PARENTHESES OVERLAY 1AC1..1ACB ; Diacritic # Mn [11] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING TRIPLE ACUTE ACCENT -1ACF..1ADD ; Diacritic # Mn [15] COMBINING DOUBLE CARON..COMBINING DOT-AND-RING BELOW -1AE0..1AEB ; Diacritic # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE +1ACF..1AF0 ; Diacritic # Mn [34] COMBINING DOUBLE CARON..COMBINING DOUBLE COMMA ABOVE 1B34 ; Diacritic # Mn BALINESE SIGN REREKAN 1B44 ; Diacritic # Mc BALINESE ADEG ADEG 1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG @@ -1031,6 +1043,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1FDD..1FDF ; Diacritic # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI 1FED..1FEF ; Diacritic # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA 1FFD..1FFE ; Diacritic # Sk [2] GREEK OXIA..GREEK DASIA +208F ; Diacritic # Lm MODIFIER LETTER HIGH AND LOW VERTICAL LINE 2CEF..2CF1 ; Diacritic # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS 2E2F ; Diacritic # Lm VERTICAL TILDE 302A..302D ; Diacritic # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK @@ -1092,7 +1105,9 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D4E ; Diacritic # Lm GARAY VOWEL LENGTH MARK 10D69..10D6D ; Diacritic # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK -10EFA ; Diacritic # Mn ARABIC DOUBLE VERTICAL BAR BELOW +10ECB..10ECF ; Diacritic # Mn [5] ARABIC NORTHEAST POINTING ARROWHEAD ABOVE..ARABIC LARGE CIRCLE ABOVE +10EF0..10EF7 ; Diacritic # Mn [8] ARABIC SMALL LOW UPRIGHT RECTANGULAR ZERO..ARABIC SMALL HIGH HEH INITIAL FORM +10EF9..10EFA ; Diacritic # Mn [2] ARABIC MARK CROWN..ARABIC DOUBLE VERTICAL BAR BELOW 10EFD..10EFF ; Diacritic # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Diacritic # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW @@ -1158,6 +1173,10 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1D17B..1D182 ; Diacritic # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D250..1D252 ; Diacritic # Mc [3] MUSICAL SYMBOL COMBINING FLAG-6..MUSICAL SYMBOL COMBINING FLAG-8 +1D25B..1D25C ; Diacritic # Mn [2] MUSICAL SYMBOL COMBINING TREMOLO-4..MUSICAL SYMBOL COMBINING TREMOLO-5 +1DFCD..1DFCF ; Diacritic # Lm [3] MODIFIER LETTER SMALL TURNED R WITH MID-HEIGHT LEFT HOOK..MODIFIER LETTER SMALL SPLIT U +1DFD1..1DFFF ; Diacritic # Lm [47] MODIFIER LETTER SMALL CAPITAL P..MODIFIER LETTER SMALL T WITH HOOK AND RETROFLEX HOOK 1E030..1E06D ; Diacritic # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E130..1E136 ; Diacritic # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E2AE ; Diacritic # Mn TOTO SIGN RISING TONE @@ -1167,7 +1186,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1247 +# Total code points: 1334 # ================================================ @@ -1177,7 +1196,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 07FA ; Extender # Lm NKO LAJANYALAN 0A71 ; Extender # Mn GURMUKHI ADDAK 0AFB ; Extender # Mn GUJARATI SIGN SHADDA -0B55 ; Extender # Mn ORIYA SIGN OVERLINE +0B54..0B55 ; Extender # Mn [2] ORIYA SIGN DOUBLE DOT ABOVE..ORIYA SIGN OVERLINE 0E46 ; Extender # Lm THAI CHARACTER MAIYAMOK 0EC6 ; Extender # Lm LAO KO LA 180A ; Extender # Po MONGOLIAN NIRUGU @@ -1216,7 +1235,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 1E5EF ; Extender # Mn OL ONAL SIGN IKIR 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 62 +# Total code points: 63 # ================================================ @@ -1227,13 +1246,15 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 02E0..02E4 ; Other_Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP 0345 ; Other_Lowercase # Mn COMBINING GREEK YPOGEGRAMMENI 037A ; Other_Lowercase # Lm GREEK YPOGEGRAMMENI +0558 ; Other_Lowercase # Lm MODIFIER LETTER ARMENIAN SMALL EH +058B..058C ; Other_Lowercase # Lm [2] MODIFIER LETTER ARMENIAN SMALL INI..MODIFIER LETTER ARMENIAN SMALL YI 10FC ; Other_Lowercase # Lm MODIFIER LETTER GEORGIAN NAR 1D2C..1D6A ; Other_Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D78 ; Other_Lowercase # Lm MODIFIER LETTER CYRILLIC EN 1D9B..1DBF ; Other_Lowercase # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA 2071 ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER I 207F ; Other_Lowercase # Lm SUPERSCRIPT LATIN SMALL LETTER N -2090..209C ; Other_Lowercase # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T +2090..209F ; Other_Lowercase # Lm [16] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER Z 2170..217F ; Other_Lowercase # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND 24D0..24E9 ; Other_Lowercase # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z 2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V @@ -1246,10 +1267,11 @@ AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W 10780 ; Other_Lowercase # Lm MODIFIER LETTER SMALL CAPITAL AA 10783..10785 ; Other_Lowercase # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK 10787..107B0 ; Other_Lowercase # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK -107B2..107BA ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +107B2..107BF ; Other_Lowercase # Lm [14] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL ESH WITH DOUBLE BAR +1DFCD..1DFFF ; Other_Lowercase # Lm [51] MODIFIER LETTER SMALL TURNED R WITH MID-HEIGHT LEFT HOOK..MODIFIER LETTER SMALL T WITH HOOK AND RETROFLEX HOOK 1E030..1E06D ; Other_Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE -# Total code points: 312 +# Total code points: 374 # ================================================ @@ -1334,9 +1356,12 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND 16FF0..16FF1 ; Other_Grapheme_Extend # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1D165..1D166 ; Other_Grapheme_Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D..1D172 ; Other_Grapheme_Extend # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 +1D250..1D252 ; Other_Grapheme_Extend # Mc [3] MUSICAL SYMBOL COMBINING FLAG-6..MUSICAL SYMBOL COMBINING FLAG-8 +1D25F ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING BUZZ ROLL STEM +1D280..1D281 ; Other_Grapheme_Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM BOW BEHIND BRIDGE..MUSICAL SYMBOL COMBINING STEM BOW ON TOP OF BRIDGE E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 160 +# Total code points: 166 # ================================================ @@ -1378,14 +1403,14 @@ FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21 FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24 FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29 20000..2A6DF ; Unified_Ideograph # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B81D ; Unified_Ideograph # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2A700..2B81E ; Unified_Ideograph # Lo [4383] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81E 2B820..2CEAD ; Unified_Ideograph # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; Unified_Ideograph # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 30000..3134A ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..33479 ; Unified_Ideograph # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 101996 +# Total code points: 101997 # ================================================ @@ -1451,10 +1476,12 @@ E0001 ; Deprecated # Cf LANGUAGE TAG 1D65E..1D65F ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J 1D692..1D693 ; Soft_Dotted # L& [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J 1DF1A ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK +1DF6F..1DF71 ; Soft_Dotted # L& [3] LATIN SMALL LETTER PHONOTYPIC DIPHTHONG AI..LATIN SMALL LETTER STRETCHED I +1DFD9 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J WITH STROKE 1E04C..1E04D ; Soft_Dotted # Lm [2] MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I..MODIFIER LETTER CYRILLIC SMALL JE 1E068 ; Soft_Dotted # Lm CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I -# Total code points: 50 +# Total code points: 54 # ================================================ @@ -1573,6 +1600,7 @@ FF65 ; Other_ID_Continue # Po HALFWIDTH KATAKANA MIDDLE DOT 2E2E ; Sentence_Terminal # Po REVERSED QUESTION MARK 2E3C ; Sentence_Terminal # Po STENOGRAPHIC FULL STOP 2E53..2E54 ; Sentence_Terminal # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK +2E60..2E61 ; Sentence_Terminal # Po [2] WIGGLY EXCLAMATION MARK..INVERTED WIGGLY EXCLAMATION MARK 3002 ; Sentence_Terminal # Po IDEOGRAPHIC FULL STOP A4FF ; Sentence_Terminal # Po LISU PUNCTUATION FULL STOP A60E..A60F ; Sentence_Terminal # Po [2] VAI FULL STOP..VAI QUESTION MARK @@ -1627,7 +1655,7 @@ FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP 1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP -# Total code points: 170 +# Total code points: 172 # ================================================ @@ -1877,7 +1905,11 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2E5B ; Pattern_Syntax # Ps BOTTOM HALF LEFT PARENTHESIS 2E5C ; Pattern_Syntax # Pe BOTTOM HALF RIGHT PARENTHESIS 2E5D ; Pattern_Syntax # Pd OBLIQUE HYPHEN -2E5E..2E7F ; Pattern_Syntax # Cn [34] <reserved-2E5E>..<reserved-2E7F> +2E5E..2E5F ; Pattern_Syntax # Cn [2] <reserved-2E5E>..<reserved-2E5F> +2E60..2E61 ; Pattern_Syntax # Po [2] WIGGLY EXCLAMATION MARK..INVERTED WIGGLY EXCLAMATION MARK +2E62 ; Pattern_Syntax # Ps LEFT PARENTHESIS WITH MIDDLE RING +2E63 ; Pattern_Syntax # Pe RIGHT PARENTHESIS WITH MIDDLE RING +2E64..2E7F ; Pattern_Syntax # Cn [28] <reserved-2E64>..<reserved-2E7F> 3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK 3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET 3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET @@ -1938,7 +1970,10 @@ FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT 08CD..08CF ; Modifier_Combining_Mark # Mn [3] ARABIC SMALL HIGH ZAH..ARABIC LARGE ROUND DOT BELOW 08D3 ; Modifier_Combining_Mark # Mn ARABIC SMALL LOW WAW 08F3 ; Modifier_Combining_Mark # Mn ARABIC SMALL HIGH WAW +10EF4 ; Modifier_Combining_Mark # Mn ARABIC SMALL LOW NOON WITH FATHA +10EF6 ; Modifier_Combining_Mark # Mn ARABIC SMALL LOW NOON WITH DAMMA +10EF9 ; Modifier_Combining_Mark # Mn ARABIC MARK CROWN -# Total code points: 14 +# Total code points: 17 # EOF |