From c6853cefe4b0de30d3fb04d7be8a0a78a23d51d3 Mon Sep 17 00:00:00 2001 From: Thomas Voss Date: Thu, 3 Oct 2024 01:24:50 +0200 Subject: Update for Unicode 16 --- data/DerivedLineBreak | 198 ++++++++++++++++++++++++++++++++++---------------- 1 file changed, 134 insertions(+), 64 deletions(-) (limited to 'data/DerivedLineBreak') diff --git a/data/DerivedLineBreak b/data/DerivedLineBreak index a0c7ab1..31d143e 100644 --- a/data/DerivedLineBreak +++ b/data/DerivedLineBreak @@ -1,8 +1,8 @@ -# DerivedLineBreak-15.1.0.txt -# Date: 2023-07-28, 23:34:03 GMT -# © 2023 Unicode®, Inc. +# DerivedLineBreak-16.0.0.txt +# Date: 2024-07-29, 16:26:50 GMT +# © 2024 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 https://www.unicode.org/terms_of_use.html +# For terms of use and license, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database # For documentation, see https://www.unicode.org/reports/tr44/ @@ -39,11 +39,12 @@ # 1F680..1F6FF Transport_And_Map_Symbols # 1F700..1F77F Alchemical_Symbols # 1F780..1F7FF Geometric_Shapes_Extended -# 1F800..1F8FF Supplemental_Arrows_C +# @missing: 1F000..1F7FF; Ideographic + # 1F900..1F9FF Supplemental_Symbols_And_Pictographs # 1FA00..1FA6F Chess_Symbols # 1FA70..1FAFF Symbols_And_Pictographs_Extended_A -# @missing: 1F000..1FAFF; Ideographic +# @missing: 1F900..1FAFF; Ideographic # @missing: 1FC00..1FFFD; Ideographic @@ -68,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762725 code points not listed here. -# Total code points: 900193 +# The above property value applies to 757653 code points not listed here. +# Total code points: 895121 # ================================================ @@ -215,10 +216,6 @@ FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET 2E25 ; CL # Pe BOTTOM RIGHT HALF BRACKET 2E27 ; CL # Pe RIGHT SIDEWAYS U BRACKET 2E29 ; CL # Pe RIGHT DOUBLE PARENTHESIS -2E56 ; CL # Pe RIGHT SQUARE BRACKET WITH STROKE -2E58 ; CL # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE -2E5A ; CL # Pe TOP HALF RIGHT PARENTHESIS -2E5C ; CL # Pe BOTTOM HALF RIGHT PARENTHESIS 3001..3002 ; CL # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP 3009 ; CL # Pe RIGHT ANGLE BRACKET 300B ; CL # Pe RIGHT DOUBLE ANGLE BRACKET @@ -231,7 +228,7 @@ FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET 301B ; CL # Pe RIGHT WHITE SQUARE BRACKET 301E..301F ; CL # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK FD3E ; CL # Pe ORNATE LEFT PARENTHESIS -FE11..FE12 ; CL # Po [2] PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP +FE10..FE12 ; CL # Po [3] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP FE18 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET FE36 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS FE38 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET @@ -266,7 +263,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 1343F ; CL # Cf EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 145CF ; CL # Lo ANATOLIAN HIEROGLYPH A410A END LOGOGRAM MARK -# Total code points: 97 +# Total code points: 94 # ================================================ @@ -320,12 +317,19 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 2007 ; GL # Zs FIGURE SPACE 2011 ; GL # Pd NON-BREAKING HYPHEN 202F ; GL # Zs NARROW NO-BREAK SPACE +FE20 ; GL # Mn COMBINING LIGATURE LEFT HALF +FE22 ; GL # Mn COMBINING DOUBLE TILDE LEFT HALF +FE24 ; GL # Mn COMBINING MACRON LEFT HALF +FE26..FE27 ; GL # Mn [2] COMBINING CONJOINING MACRON..COMBINING LIGATURE LEFT HALF BELOW +FE29 ; GL # Mn COMBINING TILDE LEFT HALF BELOW +FE2B ; GL # Mn COMBINING MACRON LEFT HALF BELOW +FE2D..FE2E ; GL # Mn [2] COMBINING CONJOINING MACRON BELOW..COMBINING CYRILLIC TITLO LEFT HALF 1107F ; GL # Mn BRAHMI NUMBER JOINER 13430..13436 ; GL # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE 13439..1343B ; GL # Cf [3] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH INSERT AT BOTTOM 16FE4 ; GL # Mn KHITAN SMALL SCRIPT FILLER -# Total code points: 32 +# Total code points: 41 # ================================================ @@ -344,6 +348,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 30FB ; NS # Po KATAKANA MIDDLE DOT 30FD..30FE ; NS # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK A015 ; NS # Lm YI SYLLABLE WU +FE13..FE14 ; NS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON FE54..FE55 ; NS # Po [2] SMALL SEMICOLON..SMALL COLON FF1A..FF1B ; NS # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON FF65 ; NS # Po HALFWIDTH KATAKANA MIDDLE DOT @@ -353,7 +358,7 @@ FF9E..FF9F ; NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KA 16FE3 ; NS # Lm OLD CHINESE ITERATION MARK 1F679..1F67B ; NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT -# Total code points: 33 +# Total code points: 35 # ================================================ @@ -407,10 +412,8 @@ FF1F ; EX # Po FULLWIDTH QUESTION MARK 060C..060D ; IS # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR 07F8 ; IS # Po NKO COMMA 2044 ; IS # Sm FRACTION SLASH -FE10 ; IS # Po PRESENTATION FORM FOR VERTICAL COMMA -FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON -# Total code points: 13 +# Total code points: 10 # ================================================ @@ -509,6 +512,7 @@ FFE0 ; PO # Sc FULLWIDTH CENT SIGN 1810..1819 ; NU # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1946..194F ; NU # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE 19D0..19D9 ; NU # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; NU # No NEW TAI LUE THAM DIGIT ONE 1A80..1A89 ; NU # Nd [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE 1A90..1A99 ; NU # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1BB0..1BB9 ; NU # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE @@ -521,6 +525,7 @@ A9F0..A9F9 ; NU # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DI ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 104A0..104A9 ; NU # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 10D30..10D39 ; NU # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; NU # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE 110BD ; NU # Cf KAITHI NUMBER SIGN 110CD ; NU # Cf KAITHI NUMBER SIGN ABOVE 110F0..110F9 ; NU # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE @@ -531,22 +536,27 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 114D0..114D9 ; NU # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; NU # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; NU # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE +116D0..116E3 ; NU # Nd [20] MYANMAR PAO DIGIT ZERO..MYANMAR EASTERN PWO KAREN DIGIT NINE 11730..11739 ; NU # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11BF0..11BF9 ; NU # Nd [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE 11C50..11C59 ; NU # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE 11D50..11D59 ; NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; NU # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE 16A60..16A69 ; NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16AC0..16AC9 ; NU # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE +1CCF0..1CCF9 ; NU # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; NU # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; NU # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5F1..1E5FA ; NU # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 624 +# Total code points: 695 # ================================================ @@ -851,7 +861,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1C4D..1C4F ; AL # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; AL # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; AL # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD -1C80..1C88 ; AL # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1C80..1C8A ; AL # L& [11] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER TJE 1C90..1CBA ; AL # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN 1CBD..1CBF ; AL # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN 1CC0..1CC7 ; AL # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA @@ -947,9 +957,6 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 214C..214D ; AL # So [2] PER SIGN..AKTIESELSKAB 214E ; AL # L& TURNED SMALL F 214F ; AL # So SYMBOL FOR SAMARITAN SOURCE -2150..2153 ; AL # No [4] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION ONE THIRD -2156..215A ; AL # No [5] VULGAR FRACTION TWO FIFTHS..VULGAR FRACTION FIVE SIXTHS -215C..215D ; AL # No [2] VULGAR FRACTION THREE EIGHTHS..VULGAR FRACTION FIVE EIGHTHS 215F ; AL # No FRACTION NUMERATOR ONE 216C..216F ; AL # Nl [4] ROMAN NUMERAL FIFTY..ROMAN NUMERAL ONE THOUSAND 217A..2182 ; AL # Nl [9] SMALL ROMAN NUMERAL ELEVEN..ROMAN NUMERAL TEN THOUSAND @@ -1013,7 +1020,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 23B4..23DB ; AL # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET 23E2..23EF ; AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR -23F4..2426 ; AL # So [51] BLACK MEDIUM LEFT-POINTING TRIANGLE..SYMBOL FOR SUBSTITUTE FORM TWO +23F4..2429 ; AL # So [54] BLACK MEDIUM LEFT-POINTING TRIANGLE..SYMBOL FOR DELETE MEDIUM SHADE FORM 2440..244A ; AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 24FF ; AL # No NEGATIVE CIRCLED DIGIT ZERO 254C..254F ; AL # So [4] BOX DRAWINGS LIGHT DOUBLE DASH HORIZONTAL..BOX DRAWINGS HEAVY DOUBLE DASH VERTICAL @@ -1133,10 +1140,10 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CA ; AL # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A790..A7CD ; AL # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7D0..A7D1 ; AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; AL # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7D9 ; AL # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7D5..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1238,6 +1245,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 105A3..105B1 ; AL # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; AL # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; AL # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +105C0..105F3 ; AL # Lo [52] TODHRI LETTER A..TODHRI LETTER OO 10600..10736 ; AL # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; AL # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; AL # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 @@ -1296,9 +1304,17 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10CC0..10CF2 ; AL # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10CFA..10CFF ; AL # No [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10D4A..10D4D ; AL # Lo [4] GARAY VOWEL SIGN A..GARAY VOWEL SIGN EE +10D4E ; AL # Lm GARAY VOWEL LENGTH MARK +10D4F ; AL # Lo GARAY SUKUN +10D50..10D65 ; AL # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D6F ; AL # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; AL # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA +10D8E..10D8F ; AL # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN 10E60..10E7E ; AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10E80..10EA9 ; AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -1373,6 +1389,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 11A5C..11A89 ; AL # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; AL # Lo SOYOMBO MARK PLUTA 11AB0..11AF8 ; AL # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL +11BC0..11BE0 ; AL # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO +11BE1 ; AL # Po SUNUWAR SIGN PVO 11C00..11C08 ; AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; AL # Lo BHAIKSUKI SIGN AVAGRAHA @@ -1401,6 +1419,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1328A..13378 ; AL # Lo [239] EGYPTIAN HIEROGLYPH O037..EGYPTIAN HIEROGLYPH V011 1337C..1342E ; AL # Lo [179] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH AA032 13441..13446 ; AL # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN +13460..143FA ; AL # Lo [3995] EGYPTIAN HIEROGLYPH-13460..EGYPTIAN HIEROGLYPH-143FA 14400..145CD ; AL # Lo [462] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A409 145D0..14646 ; AL # Lo [119] ANATOLIAN HIEROGLYPH A411..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; AL # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ @@ -1415,6 +1434,10 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 16B5B..16B61 ; AL # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16B63..16B77 ; AL # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS 16B7D..16B8F ; AL # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16D40..16D42 ; AL # Lm [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA +16D43..16D6A ; AL # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU +16D6B..16D6C ; AL # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT +16D6D ; AL # Po KIRAT RAI SIGN YUPI 16E40..16E7F ; AL # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; AL # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E99..16E9A ; AL # Po [2] MEDEFAIDRIN SYMBOL AIVA..MEDEFAIDRIN EXCLAMATION OH @@ -1422,6 +1445,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 16F50 ; AL # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; AL # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 18B00..18CD5 ; AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF ; AL # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF 1AFF0..1AFF3 ; AL # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; AL # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; AL # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -1430,6 +1454,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1BC80..1BC88 ; AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; AL # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1BC9C ; AL # So DUPLOYAN SIGN O WITH CROSS +1CC00..1CCEF ; AL # So [240] UP-POINTING GO-KART..OUTLINED LATIN CAPITAL LETTER Z +1CD00..1CEB3 ; AL # So [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 @@ -1503,6 +1529,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1E2C0..1E2EB ; AL # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; AL # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; AL # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; AL # Lo OL ONAL SIGN HODDOND +1E5FF ; AL # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1551,8 +1580,10 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; AL # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL +1F10D..1F10F ; AL # So [3] CIRCLED ZERO WITH SLASH..CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH 1F12E..1F12F ; AL # So [2] CIRCLED WZ..COPYLEFT SYMBOL -1F16A..1F16C ; AL # So [3] RAISED MC SIGN..RAISED MR SIGN +1F16A..1F16F ; AL # So [6] RAISED MC SIGN..CIRCLED HUMAN FIGURE +1F1AD ; AL # So MASK WORK SYMBOL 1F39C..1F39D ; AL # So [2] BEAMED ASCENDING MUSICAL NOTES..BEAMED DESCENDING MUSICAL NOTES 1F3B5..1F3B6 ; AL # So [2] MUSICAL NOTE..MULTIPLE MUSICAL NOTES 1F3BC ; AL # So MUSICAL SCORE @@ -1575,18 +1606,19 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F850..1F859 ; AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F8B0..1F8BB ; AL # So [12] ARROW POINTING UPWARDS THEN NORTH WEST..SOUTH WEST ARROW FROM BAR +1F8C0..1F8C1 ; AL # So [2] LEFTWARDS ARROW FROM DOWNWARDS ARROW..RIGHTWARDS ARROW FROM DOWNWARDS ARROW 1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1FA00..1FA53 ; AL # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK -1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON +1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 21729 +# Total code points: 26679 # ================================================ # Line_Break=Ideographic -1B50..1B59 ; ID # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5C ; ID # Po BALINESE WINDU 1B61..1B6A ; ID # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; ID # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING @@ -1660,7 +1692,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 3192..3195 ; ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK 3196..319F ; ID # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK 31A0..31BF ; ID # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH -31C0..31E3 ; ID # So [36] CJK STROKE T..CJK STROKE Q +31C0..31E5 ; ID # So [38] CJK STROKE T..CJK STROKE SZP 31EF ; ID # So IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION 3200..321E ; ID # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU 3220..3229 ; ID # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN @@ -1678,9 +1710,7 @@ A016..A48C ; ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; ID # So [55] YI RADICAL QOT..YI RADICAL KE A9C1..A9C6 ; ID # Po [6] JAVANESE LEFT RERENGGAN..JAVANESE PADA WINDU A9CA..A9CD ; ID # Po [4] JAVANESE PADA ADEG..JAVANESE TURNED PADA PISELEH -A9D0..A9D9 ; ID # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE A9DE..A9DF ; ID # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN -AA50..AA59 ; ID # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE AA5C ; ID # Po CHAM PUNCTUATION SPIRAL F900..FA6D ; ID # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; ID # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 @@ -1727,7 +1757,10 @@ FFE3 ; ID # Sk FULLWIDTH MACRON FFE4 ; ID # So FULLWIDTH BROKEN BAR 11049..1104D ; ID # Po [5] BRAHMI PUNCTUATION DOT..BRAHMI PUNCTUATION LOTUS 11052..11065 ; ID # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND -11950..11959 ; ID # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE +113B7 ; ID # Lo TULU-TIGALARI SIGN AVAGRAHA +113D3 ; ID # Lo TULU-TIGALARI SIGN PLUTA +113D4..113D5 ; ID # Po [2] TULU-TIGALARI DANDA..TULU-TIGALARI DOUBLE DANDA +113D7..113D8 ; ID # Po [2] TULU-TIGALARI SIGN OM PUSHPIKA..TULU-TIGALARI SIGN SHRII PUSHPIKA 11F45..11F4F ; ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL 17000..187F7 ; ID # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 @@ -1740,9 +1773,6 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F0B1..1F0BF ; ID # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER 1F0C1..1F0CF ; ID # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER 1F0D1..1F0F5 ; ID # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 -1F10D..1F10F ; ID # So [3] CIRCLED ZERO WITH SLASH..CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH -1F16D..1F16F ; ID # So [3] CIRCLED CC..CIRCLED HUMAN FIGURE -1F1AD ; ID # So MASK WORK SYMBOL 1F200..1F202 ; ID # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA 1F210..1F23B ; ID # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 @@ -1793,7 +1823,6 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F7D5..1F7D9 ; ID # So [5] CIRCLED TRIANGLE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; ID # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; ID # So HEAVY EQUALS SIGN -1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST 1F90D..1F90E ; ID # So [2] WHITE HEART..BROWN HEART 1F910..1F917 ; ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE 1F920..1F925 ; ID # So [6] FACE WITH COWBOY HAT..LYING FACE @@ -1808,11 +1837,11 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 1F9DE..1F9FF ; ID # So [34] GENIE..NAZAR AMULET 1FA60..1FA6D ; ID # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; ID # So [13] BALLET SHOES..CRUTCH -1FA80..1FA88 ; ID # So [9] YO-YO..FLUTE -1FA90..1FABD ; ID # So [46] RINGED PLANET..WING -1FABF..1FAC2 ; ID # So [4] GOOSE..PEOPLE HUGGING -1FACE..1FADB ; ID # So [14] MOOSE..PEA POD -1FAE0..1FAE8 ; ID # So [9] MELTING FACE..SHAKING FACE +1FA80..1FA89 ; ID # So [10] YO-YO..HARP +1FA8F..1FAC2 ; ID # So [52] SHOVEL..PEOPLE HUGGING +1FAC6 ; ID # So FINGERPRINT +1FACE..1FADC ; ID # So [15] MOOSE..ROOT VEGETABLE +1FADF..1FAE9 ; ID # So [11] SPLATTER..FACE WITH BAGS UNDER EYES 20000..2A6DF ; ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A700..2B739 ; ID # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D @@ -1823,8 +1852,8 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 30000..3134A ; ID # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# The above property value applies to 61978 code points not listed here. -# Total code points: 172568 +# The above property value applies to 61865 code points not listed here. +# Total code points: 172421 # ================================================ @@ -1881,7 +1910,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0825..0827 ; CM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; CM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -0898..089F ; CM # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +0897..089F ; CM # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08CA..08E1 ; CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; CM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; CM # Mc DEVANAGARI SIGN VISARGA @@ -2133,7 +2162,13 @@ ABEC ; CM # Mc MEETEI MAYEK LUM IYEK ABED ; CM # Mn MEETEI MAYEK APUN IYEK FB1E ; CM # Mn HEBREW POINT JUDEO-SPANISH VARIKA FE00..FE0F ; CM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE20..FE2F ; CM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FE21 ; CM # Mn COMBINING LIGATURE RIGHT HALF +FE23 ; CM # Mn COMBINING DOUBLE TILDE RIGHT HALF +FE25 ; CM # Mn COMBINING MACRON RIGHT HALF +FE28 ; CM # Mn COMBINING LIGATURE RIGHT HALF BELOW +FE2A ; CM # Mn COMBINING TILDE RIGHT HALF BELOW +FE2C ; CM # Mn COMBINING MACRON RIGHT HALF BELOW +FE2F ; CM # Mn COMBINING CYRILLIC TITLO RIGHT HALF FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR 101FD ; CM # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE 102E0 ; CM # Mn COPTIC EPACT THOUSANDS MARK @@ -2145,8 +2180,9 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 10A3F ; CM # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; CM # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; CM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFD..10EFF ; CM # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA +10EFC..10EFF ; CM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; CM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; CM # Mc BRAHMI SIGN CANDRABINDU @@ -2199,6 +2235,16 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 11362..11363 ; CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113B8..113BA ; CM # Mc [3] TULU-TIGALARI VOWEL SIGN AA..TULU-TIGALARI VOWEL SIGN II +113BB..113C0 ; CM # Mn [6] TULU-TIGALARI VOWEL SIGN U..TULU-TIGALARI VOWEL SIGN VOCALIC LL +113C2 ; CM # Mc TULU-TIGALARI VOWEL SIGN EE +113C5 ; CM # Mc TULU-TIGALARI VOWEL SIGN AI +113C7..113CA ; CM # Mc [4] TULU-TIGALARI VOWEL SIGN OO..TULU-TIGALARI SIGN CANDRA ANUNASIKA +113CC..113CD ; CM # Mc [2] TULU-TIGALARI SIGN ANUSVARA..TULU-TIGALARI SIGN VISARGA +113CE ; CM # Mn TULU-TIGALARI SIGN VIRAMA +113CF ; CM # Mc TULU-TIGALARI SIGN LOOPED VIRAMA +113D2 ; CM # Mn TULU-TIGALARI GEMINATION MARK +113E1..113E2 ; CM # Mn [2] TULU-TIGALARI VEDIC TONE SVARITA..TULU-TIGALARI VEDIC TONE ANUDATTA 11435..11437 ; CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II 11438..1143F ; CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11440..11441 ; CM # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU @@ -2294,8 +2340,12 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 11F3E..11F3F ; CM # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI 11F40 ; CM # Mn KAWI VOWEL SIGN EU 11F41 ; CM # Mc KAWI SIGN KILLER +11F5A ; CM # Mn KAWI SIGN NUKTA 13440 ; CM # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY 13447..13455 ; CM # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +1611E..16129 ; CM # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK +1612A..1612C ; CM # Mc [3] GURUNG KHEMA CONSONANT SIGN MEDIAL YA..GURUNG KHEMA CONSONANT SIGN MEDIAL HA +1612D..1612F ; CM # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA 16AF0..16AF4 ; CM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; CM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F4F ; CM # Mn MIAO SIGN CONSONANT MODIFIER BAR @@ -2330,13 +2380,14 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1E2AE ; CM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; CM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; CM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2429 +# Total code points: 2470 # ================================================ @@ -2398,9 +2449,10 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 17D8 ; BA # Po KHMER SIGN BEYYAL 17DA ; BA # Po KHMER SIGN KOOMUUT 1804..1805 ; BA # Po [2] MONGOLIAN COLON..MONGOLIAN FOUR DOTS +1B4E..1B4F ; BA # Po [2] BALINESE INVERTED CARIK SIKI..BALINESE INVERTED CARIK PAREREN 1B5A..1B5B ; BA # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5D..1B60 ; BA # Po [4] BALINESE CARIK PAMUNGKAH..BALINESE PAMENENG -1B7D..1B7E ; BA # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG +1B7D..1B7F ; BA # Po [3] BALINESE PANTI LANTANG..BALINESE PANTI BAWAK 1C3B..1C3F ; BA # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; BA # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 2000..2006 ; BA # Zs [7] EN QUAD..SIX-PER-EM SPACE @@ -2450,6 +2502,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 10A50..10A57 ; BA # Po [8] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION DOUBLE DANDA 10AF0..10AF5 ; BA # Po [6] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION TWO DOTS 10B39..10B3F ; BA # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION +10D6E ; BA # Pd GARAY HYPHEN 10EAD ; BA # Pd YEZIDI HYPHENATION MARK 11047..11048 ; BA # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA 110BE..110C1 ; BA # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA @@ -2482,11 +2535,12 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 16AF5 ; BA # Po BASSA VAH FULL STOP 16B37..16B39 ; BA # Po [3] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN CIM CHEEM 16B44 ; BA # Po PAHAWH HMONG SIGN XAUS +16D6E..16D6F ; BA # Po [2] KIRAT RAI DANDA..KIRAT RAI DOUBLE DANDA 16E97..16E98 ; BA # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 266 +# Total code points: 272 # ================================================ @@ -2602,7 +2656,6 @@ FFFC ; CB # So OBJECT REPLACEMENT CHARACTER 1970..1974 ; SA # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 1980..19AB ; SA # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA 19B0..19C9 ; SA # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 -19DA ; SA # No NEW TAI LUE THAM DIGIT ONE 19DE..19DF ; SA # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV 1A20..1A54 ; SA # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1A55 ; SA # Mc TAI THAM CONSONANT SIGN MEDIAL RA @@ -2647,7 +2700,9 @@ AADB..AADC ; SA # Lo [2] TAI VIET SYMBOL KON..TAI VIET SYMBOL NUENG AADD ; SA # Lm TAI VIET SYMBOL SAM AADE..AADF ; SA # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI 11700..1171A ; SA # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA -1171D..1171F ; SA # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +1171D ; SA # Mn AHOM CONSONANT SIGN MEDIAL LA +1171E ; SA # Mc AHOM CONSONANT SIGN MEDIAL RA +1171F ; SA # Mn AHOM CONSONANT SIGN MEDIAL LIGATING RA 11720..11721 ; SA # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11722..11725 ; SA # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; SA # Mc AHOM VOWEL SIGN E @@ -2656,7 +2711,7 @@ AADE..AADF ; SA # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI 1173F ; SA # So AHOM SYMBOL VI 11740..11746 ; SA # Lo [7] AHOM LETTER CA..AHOM LETTER LLA -# Total code points: 758 +# Total code points: 757 # ================================================ @@ -2690,9 +2745,7 @@ AADE..AADF ; SA # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI 2113 ; AI # L& SCRIPT SMALL L 2121..2122 ; AI # So [2] TELEPHONE SIGN..TRADE MARK SIGN 212B ; AI # L& ANGSTROM SIGN -2154..2155 ; AI # No [2] VULGAR FRACTION TWO THIRDS..VULGAR FRACTION ONE FIFTH -215B ; AI # No VULGAR FRACTION ONE EIGHTH -215E ; AI # No VULGAR FRACTION SEVEN EIGHTHS +2150..215E ; AI # No [15] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION SEVEN EIGHTHS 2160..216B ; AI # Nl [12] ROMAN NUMERAL ONE..ROMAN NUMERAL TWELVE 2170..2179 ; AI # Nl [10] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL TEN 2189 ; AI # No VULGAR FRACTION ZERO THIRDS @@ -2782,7 +2835,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F130..1F169 ; AI # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F1AC ; AI # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD -# Total code points: 707 +# Total code points: 718 # ================================================ @@ -3671,8 +3724,12 @@ D789..D7A3 ; H3 # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH 0029 ; CP # Pe RIGHT PARENTHESIS 005D ; CP # Pe RIGHT SQUARE BRACKET +2E56 ; CP # Pe RIGHT SQUARE BRACKET WITH STROKE +2E58 ; CP # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E5A ; CP # Pe TOP HALF RIGHT PARENTHESIS +2E5C ; CP # Pe BOTTOM HALF RIGHT PARENTHESIS -# Total code points: 2 +# Total code points: 6 # ================================================ @@ -3816,6 +3873,7 @@ A984..A9B2 ; AK # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA 11332..11333 ; AK # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA 11335..11339 ; AK # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA 11360..11361 ; AK # Lo [2] GRANTHA LETTER VOCALIC RR..GRANTHA LETTER VOCALIC LL +11392..113B5 ; AK # Lo [36] TULU-TIGALARI LETTER KA..TULU-TIGALARI LETTER LLLA 11900..11906 ; AK # Lo [7] DIVES AKURU LETTER A..DIVES AKURU LETTER E 11909 ; AK # Lo DIVES AKURU LETTER O 1190C..11913 ; AK # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA @@ -3824,32 +3882,43 @@ A984..A9B2 ; AK # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA 11F04..11F10 ; AK # Lo [13] KAWI LETTER A..KAWI LETTER O 11F12..11F33 ; AK # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA -# Total code points: 293 +# Total code points: 329 # ================================================ # Line_Break=Aksara_Prebase 11003..11004 ; AP # Lo [2] BRAHMI SIGN JIHVAMULIYA..BRAHMI SIGN UPADHMANIYA +113D1 ; AP # Lo TULU-TIGALARI REPHA 1193F ; AP # Lo DIVES AKURU PREFIXED NASAL SIGN 11941 ; AP # Lo DIVES AKURU INITIAL RA 11F02 ; AP # Lo KAWI SIGN REPHA -# Total code points: 5 +# Total code points: 6 # ================================================ # Line_Break=Aksara_Start +1B50..1B59 ; AS # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1BC0..1BE5 ; AS # Lo [38] BATAK LETTER A..BATAK LETTER U +A9D0..A9D9 ; AS # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE AA00..AA28 ; AS # Lo [41] CHAM LETTER A..CHAM LETTER HA +AA50..AA59 ; AS # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 11066..1106F ; AS # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE 11350 ; AS # Lo GRANTHA OM 1135E..1135F ; AS # Lo [2] GRANTHA LETTER VEDIC ANUSVARA..GRANTHA LETTER VEDIC DOUBLE ANUSVARA +11380..11389 ; AS # Lo [10] TULU-TIGALARI LETTER A..TULU-TIGALARI LETTER VOCALIC LL +1138B ; AS # Lo TULU-TIGALARI LETTER EE +1138E ; AS # Lo TULU-TIGALARI LETTER AI +11390..11391 ; AS # Lo [2] TULU-TIGALARI LETTER OO..TULU-TIGALARI LETTER AU +11950..11959 ; AS # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE 11EE0..11EF1 ; AS # Lo [18] MAKASAR LETTER KA..MAKASAR LETTER A 11F50..11F59 ; AS # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE +16100..1611D ; AS # Lo [30] GURUNG KHEMA LETTER A..GURUNG KHEMA LETTER SA +16130..16139 ; AS # Nd [10] GURUNG KHEMA DIGIT ZERO..GURUNG KHEMA DIGIT NINE -# Total code points: 120 +# Total code points: 214 # ================================================ @@ -3859,10 +3928,11 @@ AA00..AA28 ; AS # Lo [41] CHAM LETTER A..CHAM LETTER HA A9C0 ; VI # Mc JAVANESE PANGKON 11046 ; VI # Mn BRAHMI VIRAMA 1134D ; VI # Mc GRANTHA SIGN VIRAMA +113D0 ; VI # Mn TULU-TIGALARI CONJOINER 1193E ; VI # Mn DIVES AKURU VIRAMA 11F42 ; VI # Mn KAWI CONJOINER -# Total code points: 6 +# Total code points: 7 # ================================================ -- cgit v1.2.3