From a7164d9e7b3c3ec6813e06a42d82180d766e15ca Mon Sep 17 00:00:00 2001 From: Sam Atman Date: Wed, 30 Apr 2025 20:32:23 -0400 Subject: Unicode 16.0 Went smoothly, needed to add some scripts and adjust the magic numbers, but other than that, all set. --- data/unicode/LineBreak.txt | 170 +++++++++++++++++++++++++++++++-------------- 1 file changed, 116 insertions(+), 54 deletions(-) (limited to 'data/unicode/LineBreak.txt') diff --git a/data/unicode/LineBreak.txt b/data/unicode/LineBreak.txt index b6bc679..3ce2582 100644 --- a/data/unicode/LineBreak.txt +++ b/data/unicode/LineBreak.txt @@ -1,8 +1,8 @@ -# LineBreak-15.1.0.txt -# Date: 2023-07-28, 13:19:22 GMT [KW] -# © 2023 Unicode®, Inc. +# LineBreak-16.0.0.txt +# Date: 2024-07-29, 16:26:55 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/ @@ -280,7 +280,7 @@ 0888 ; AL # Sk ARABIC RAISED ROUND DOT 0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL 0890..0891 ; NU # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE -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 08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; AL # Lm ARABIC SMALL FARSI YEH 08CA..08E1 ; CM # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA @@ -748,7 +748,7 @@ 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 19D0..19D9 ; NU # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE -19DA ; SA # No NEW TAI LUE THAM DIGIT ONE +19DA ; NU # No NEW TAI LUE THAM DIGIT ONE 19DE..19DF ; SA # So [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV 19E0..19FF ; AL # So [32] KHMER SYMBOL PATHAMASAT..KHMER SYMBOL DAP-PRAM ROC 1A00..1A16 ; AL # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA @@ -790,14 +790,15 @@ 1B43 ; CM # Mc BALINESE VOWEL SIGN PEPET TEDUNG 1B44 ; VI # Mc BALINESE ADEG ADEG 1B45..1B4C ; AK # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA -1B50..1B59 ; ID # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE +1B4E..1B4F ; BA # Po [2] BALINESE INVERTED CARIK SIKI..BALINESE INVERTED CARIK PAREREN +1B50..1B59 ; AS # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1B5A..1B5B ; BA # Po [2] BALINESE PANTI..BALINESE PAMADA 1B5C ; ID # Po BALINESE WINDU 1B5D..1B60 ; BA # Po [4] BALINESE CARIK PAMUNGKAH..BALINESE PAMENENG 1B61..1B6A ; ID # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B6B..1B73 ; CM # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 1B74..1B7C ; ID # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING -1B7D..1B7E ; BA # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG +1B7D..1B7F ; BA # Po [3] BALINESE PANTI LANTANG..BALINESE PANTI BAWAK 1B80..1B81 ; CM # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR 1B82 ; CM # Mc SUNDANESE SIGN PANGWISAD 1B83..1BA0 ; AL # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -832,7 +833,7 @@ 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 1C7E..1C7F ; BA # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD -1C80..1C88 ; AL # Ll [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 # Lu [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN 1CBD..1CBF ; AL # Lu [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 @@ -1017,12 +1018,7 @@ 214C..214D ; AL # So [2] PER SIGN..AKTIESELSKAB 214E ; AL # Ll TURNED SMALL F 214F ; AL # So SYMBOL FOR SAMARITAN SOURCE -2150..2153 ; AL # No [4] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION ONE THIRD -2154..2155 ; AI # No [2] VULGAR FRACTION TWO THIRDS..VULGAR FRACTION ONE FIFTH -2156..215A ; AL # No [5] VULGAR FRACTION TWO FIFTHS..VULGAR FRACTION FIVE SIXTHS -215B ; AI # No VULGAR FRACTION ONE EIGHTH -215C..215D ; AL # No [2] VULGAR FRACTION THREE EIGHTHS..VULGAR FRACTION FIVE EIGHTHS -215E ; AI # No VULGAR FRACTION SEVEN EIGHTHS +2150..215E ; AI # No [15] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION SEVEN EIGHTHS 215F ; AL # No FRACTION NUMERATOR ONE 2160..216B ; AI # Nl [12] ROMAN NUMERAL ONE..ROMAN NUMERAL TWELVE 216C..216F ; AL # Nl [4] ROMAN NUMERAL FIFTY..ROMAN NUMERAL ONE THOUSAND @@ -1133,7 +1129,7 @@ 23E2..23EF ; AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR 23F0..23F3 ; ID # So [4] ALARM CLOCK..HOURGLASS WITH FLOWING SAND 23F4..23FF ; AL # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL -2400..2426 ; AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +2400..2429 ; AL # So [42] SYMBOL FOR NULL..SYMBOL FOR DELETE MEDIUM SHADE FORM 2440..244A ; AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; AI # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; AI # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -1407,13 +1403,13 @@ 2E52 ; AL # Po TIRONIAN SIGN CAPITAL ET 2E53..2E54 ; EX # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK 2E55 ; OP # Ps LEFT SQUARE BRACKET WITH STROKE -2E56 ; CL # Pe RIGHT SQUARE BRACKET WITH STROKE +2E56 ; CP # Pe RIGHT SQUARE BRACKET WITH STROKE 2E57 ; OP # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE -2E58 ; CL # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; CP # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE 2E59 ; OP # Ps TOP HALF LEFT PARENTHESIS -2E5A ; CL # Pe TOP HALF RIGHT PARENTHESIS +2E5A ; CP # Pe TOP HALF RIGHT PARENTHESIS 2E5B ; OP # Ps BOTTOM HALF LEFT PARENTHESIS -2E5C ; CL # Pe BOTTOM HALF RIGHT PARENTHESIS +2E5C ; CP # Pe BOTTOM HALF RIGHT PARENTHESIS 2E5D ; BA # Pd OBLIQUE HYPHEN 2E80..2E99 ; ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE @@ -1519,7 +1515,7 @@ 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 31F0..31FF ; CJ # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3200..321E ; ID # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU @@ -1578,10 +1574,10 @@ 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 # Ll 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 @@ -1643,7 +1639,7 @@ A9C1..A9C6 ; ID # Po [6] JAVANESE LEFT RERENGGAN..JAVANESE PADA WINDU A9C7..A9C9 ; BA # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI A9CA..A9CD ; ID # Po [4] JAVANESE PADA ADEG..JAVANESE TURNED PADA PISELEH A9CF ; BA # Lm JAVANESE PANGRANGKEP -A9D0..A9D9 ; ID # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE +A9D0..A9D9 ; AS # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE A9DE..A9DF ; ID # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN A9E0..A9E4 ; SA # Lo [5] MYANMAR LETTER SHAN GHA..MYANMAR LETTER SHAN BHA A9E5 ; SA # Mn MYANMAR SIGN SHAN SAW @@ -1662,7 +1658,7 @@ AA43 ; CM # Mn CHAM CONSONANT SIGN FINAL NG AA44..AA4B ; BA # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS AA4C ; CM # Mn CHAM CONSONANT SIGN FINAL M AA4D ; CM # Mc CHAM CONSONANT SIGN FINAL H -AA50..AA59 ; ID # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE +AA50..AA59 ; AS # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE AA5C ; ID # Po CHAM PUNCTUATION SPIRAL AA5D..AA5F ; BA # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA AA60..AA6F ; SA # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA @@ -2552,14 +2548,26 @@ FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN FDFC ; PO # Sc RIAL SIGN FDFD..FDFF ; AL # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F ; CM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE10 ; IS # Po PRESENTATION FORM FOR VERTICAL COMMA -FE11..FE12 ; CL # Po [2] PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP -FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON +FE10..FE12 ; CL # Po [3] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP +FE13..FE14 ; NS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON FE15..FE16 ; EX # Po [2] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; OP # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET FE18 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS -FE20..FE2F ; CM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FE20 ; GL # Mn COMBINING LIGATURE LEFT HALF +FE21 ; CM # Mn COMBINING LIGATURE RIGHT HALF +FE22 ; GL # Mn COMBINING DOUBLE TILDE LEFT HALF +FE23 ; CM # Mn COMBINING DOUBLE TILDE RIGHT HALF +FE24 ; GL # Mn COMBINING MACRON LEFT HALF +FE25 ; CM # Mn COMBINING MACRON RIGHT HALF +FE26..FE27 ; GL # Mn [2] COMBINING CONJOINING MACRON..COMBINING LIGATURE LEFT HALF BELOW +FE28 ; CM # Mn COMBINING LIGATURE RIGHT HALF BELOW +FE29 ; GL # Mn COMBINING TILDE LEFT HALF BELOW +FE2A ; CM # Mn COMBINING TILDE RIGHT HALF BELOW +FE2B ; GL # Mn COMBINING MACRON LEFT HALF BELOW +FE2C ; CM # Mn COMBINING MACRON RIGHT HALF BELOW +FE2D..FE2E ; GL # Mn [2] COMBINING CONJOINING MACRON BELOW..COMBINING CYRILLIC TITLO LEFT HALF +FE2F ; CM # Mn COMBINING CYRILLIC TITLO RIGHT HALF FE30 ; ID # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER FE31..FE32 ; ID # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH FE33..FE34 ; ID # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE @@ -2721,6 +2729,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 105A3..105B1 ; AL # Ll [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 105B3..105B9 ; AL # Ll [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 105BB..105BC ; AL # Ll [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 @@ -2795,12 +2804,23 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D30..10D39 ; NU # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10D40..10D49 ; NU # Nd [10] GARAY DIGIT ZERO..GARAY DIGIT NINE +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 # Lu [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA +10D69..10D6D ; CM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10D6E ; BA # Pd GARAY HYPHEN +10D6F ; AL # Lm GARAY REDUPLICATION MARK +10D70..10D85 ; AL # Ll [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 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EAD ; BA # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE -10EFD..10EFF ; CM # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA +10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EFC..10EFF ; CM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 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 @@ -2929,6 +2949,27 @@ FFFD ; AI # So REPLACEMENT CHARACTER 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 +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 +11392..113B5 ; AK # Lo [36] TULU-TIGALARI LETTER KA..TULU-TIGALARI LETTER LLLA +113B7 ; ID # Lo TULU-TIGALARI SIGN AVAGRAHA +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 +113D0 ; VI # Mn TULU-TIGALARI CONJOINER +113D1 ; AP # Lo TULU-TIGALARI REPHA +113D2 ; CM # Mn TULU-TIGALARI GEMINATION MARK +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 +113E1..113E2 ; CM # Mn [2] TULU-TIGALARI VEDIC TONE SVARITA..TULU-TIGALARI VEDIC TONE ANUDATTA 11400..11434 ; AL # Lo [53] NEWA LETTER A..NEWA LETTER HA 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 @@ -2994,8 +3035,11 @@ FFFD ; AI # So REPLACEMENT CHARACTER 116B8 ; AL # Lo TAKRI LETTER ARCHAIC KHA 116B9 ; AL # Po TAKRI ABBREVIATION SIGN 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 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 @@ -3031,7 +3075,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 11942 ; CM # Mc DIVES AKURU MEDIAL RA 11943 ; CM # Mn DIVES AKURU SIGN NUKTA 11944..11946 ; BA # Po [3] DIVES AKURU DOUBLE DANDA..DIVES AKURU END OF TEXT MARK -11950..11959 ; ID # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE +11950..11959 ; AS # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE 119A0..119A7 ; AL # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR 119AA..119D0 ; AL # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA 119D1..119D3 ; CM # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II @@ -3071,6 +3115,9 @@ FFFD ; AI # So REPLACEMENT CHARACTER 11AB0..11ABF ; AL # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11AC0..11AF8 ; AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11B00..11B09 ; BB # Po [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU +11BC0..11BE0 ; AL # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO +11BE1 ; AL # Po SUNUWAR SIGN PVO +11BF0..11BF9 ; NU # Nd [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE 11C00..11C08 ; AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C2F ; CM # Mc BHAIKSUKI VOWEL SIGN AA @@ -3132,6 +3179,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 11F43..11F44 ; BA # Po [2] KAWI DANDA..KAWI DOUBLE DANDA 11F45..11F4F ; ID # Po [11] KAWI PUNCTUATION SECTION MARKER..KAWI PUNCTUATION CLOSING SPIRAL 11F50..11F59 ; AS # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE +11F5A ; CM # Mn KAWI SIGN NUKTA 11FB0 ; AL # Lo LISU LETTER YHA 11FC0..11FD4 ; AL # No [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH 11FD5..11FDC ; AL # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI @@ -3170,10 +3218,16 @@ FFFD ; AI # So REPLACEMENT CHARACTER 13440 ; CM # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY 13441..13446 ; AL # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 13447..13455 ; CM # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +13460..143FA ; AL # Lo [3995] EGYPTIAN HIEROGLYPH-13460..EGYPTIAN HIEROGLYPH-143FA 14400..145CD ; AL # Lo [462] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A409 145CE ; OP # Lo ANATOLIAN HIEROGLYPH A410 BEGIN LOGOGRAM MARK 145CF ; CL # Lo ANATOLIAN HIEROGLYPH A410A END LOGOGRAM MARK 145D0..14646 ; AL # Lo [119] ANATOLIAN HIEROGLYPH A411..ANATOLIAN HIEROGLYPH A530 +16100..1611D ; AS # Lo [30] GURUNG KHEMA LETTER A..GURUNG KHEMA LETTER SA +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 +16130..16139 ; AS # Nd [10] GURUNG KHEMA DIGIT ZERO..GURUNG KHEMA DIGIT NINE 16800..16A38 ; AL # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; AL # Lo [31] MRO LETTER TA..MRO LETTER TEK 16A60..16A69 ; NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE @@ -3195,6 +3249,12 @@ FFFD ; AI # So REPLACEMENT CHARACTER 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 +16D6E..16D6F ; BA # Po [2] KIRAT RAI DANDA..KIRAT RAI DOUBLE DANDA +16D70..16D79 ; NU # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 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 16E97..16E98 ; BA # Po [2] MEDEFAIDRIN COMMA..MEDEFAIDRIN FULL STOP @@ -3213,6 +3273,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 17000..187F7 ; ID # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18AFF ; ID # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18B00..18CD5 ; AL # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF ; AL # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF 18D00..18D08 ; ID # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 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 @@ -3232,6 +3293,9 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1BC9D..1BC9E ; CM # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1BCA0..1BCA3 ; CM # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CC00..1CCEF ; AL # So [240] UP-POINTING GO-KART..OUTLINED LATIN CAPITAL LETTER Z +1CCF0..1CCF9 ; NU # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE +1CD00..1CEB3 ; AL # So [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET 1CF00..1CF2D ; CM # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; CM # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; AL # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -3337,6 +3401,11 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1E4EB ; AL # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; CM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; NU # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; AL # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; NU # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +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 @@ -3404,14 +3473,13 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F0D1..1F0F5 ; ID # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F0F6..1F0FF ; ID # Cn [10] .. 1F100..1F10C ; AI # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO -1F10D..1F10F ; ID # So [3] CIRCLED ZERO WITH SLASH..CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH +1F10D..1F10F ; AL # So [3] CIRCLED ZERO WITH SLASH..CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH 1F110..1F12D ; AI # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD 1F12E..1F12F ; AL # So [2] CIRCLED WZ..COPYLEFT SYMBOL 1F130..1F169 ; AI # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z -1F16A..1F16C ; AL # So [3] RAISED MC SIGN..RAISED MR SIGN -1F16D..1F16F ; ID # So [3] CIRCLED CC..CIRCLED HUMAN FIGURE +1F16A..1F16F ; AL # So [6] RAISED MC SIGN..CIRCLED HUMAN FIGURE 1F170..1F1AC ; AI # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD -1F1AD ; ID # So MASK WORK SYMBOL +1F1AD ; AL # So MASK WORK SYMBOL 1F1AE..1F1E5 ; ID # Cn [56] .. 1F1E6..1F1FF ; RI # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z 1F200..1F202 ; ID # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA @@ -3521,17 +3589,12 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F7F0 ; ID # So HEAVY EQUALS SIGN 1F7F1..1F7FF ; ID # Cn [15] .. 1F800..1F80B ; AL # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD -1F80C..1F80F ; ID # Cn [4] .. 1F810..1F847 ; AL # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW -1F848..1F84F ; ID # Cn [8] .. 1F850..1F859 ; AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW -1F85A..1F85F ; ID # Cn [6] .. 1F860..1F887 ; AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW -1F888..1F88F ; ID # Cn [8] .. 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F8AE..1F8AF ; ID # Cn [2] .. -1F8B0..1F8B1 ; ID # So [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F8B2..1F8FF ; ID # Cn [78] .. +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 1F90C ; EB # So PINCHED FINGERS 1F90D..1F90E ; ID # So [2] WHITE HEART..BROWN HEART @@ -3563,21 +3626,20 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1FA6E..1FA6F ; ID # Cn [2] .. 1FA70..1FA7C ; ID # So [13] BALLET SHOES..CRUTCH 1FA7D..1FA7F ; ID # Cn [3] .. -1FA80..1FA88 ; ID # So [9] YO-YO..FLUTE -1FA89..1FA8F ; ID # Cn [7] .. -1FA90..1FABD ; ID # So [46] RINGED PLANET..WING -1FABE ; ID # Cn -1FABF..1FAC2 ; ID # So [4] GOOSE..PEOPLE HUGGING +1FA80..1FA89 ; ID # So [10] YO-YO..HARP +1FA8A..1FA8E ; ID # Cn [5] .. +1FA8F..1FAC2 ; ID # So [52] SHOVEL..PEOPLE HUGGING 1FAC3..1FAC5 ; EB # So [3] PREGNANT MAN..PERSON WITH CROWN -1FAC6..1FACD ; ID # Cn [8] .. -1FACE..1FADB ; ID # So [14] MOOSE..PEA POD -1FADC..1FADF ; ID # Cn [4] .. -1FAE0..1FAE8 ; ID # So [9] MELTING FACE..SHAKING FACE -1FAE9..1FAEF ; ID # Cn [7] .. +1FAC6 ; ID # So FINGERPRINT +1FAC7..1FACD ; ID # Cn [7] .. +1FACE..1FADC ; ID # So [15] MOOSE..ROOT VEGETABLE +1FADD..1FADE ; ID # Cn [2] .. +1FADF..1FAE9 ; ID # So [11] SPLATTER..FACE WITH BAGS UNDER EYES +1FAEA..1FAEF ; ID # Cn [6] .. 1FAF0..1FAF8 ; EB # So [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND 1FAF9..1FAFF ; ID # Cn [7] .. 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 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 1FC00..1FFFD ; ID # Cn [1022] .. 20000..2A6DF ; ID # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -- cgit v1.2.3