From 61949ee9d1dc2c6e80e447cf9c06fb0a11273677 Mon Sep 17 00:00:00 2001 From: Martin Mitas Date: Tue, 9 Jan 2024 02:08:48 +0100 Subject: [PATCH] Update to Unicode 15.1. --- scripts/unicode/CaseFolding.txt | 53 ++- scripts/unicode/DerivedGeneralCategory.txt | 407 ++++++++++++++------- src/md4c.c | 203 +++++----- 3 files changed, 421 insertions(+), 242 deletions(-) diff --git a/scripts/unicode/CaseFolding.txt b/scripts/unicode/CaseFolding.txt index 033788b2..69c5c64b 100644 --- a/scripts/unicode/CaseFolding.txt +++ b/scripts/unicode/CaseFolding.txt @@ -1,11 +1,11 @@ -# CaseFolding-13.0.0.txt -# Date: 2019-09-08, 23:30:59 GMT -# © 2019 Unicode®, Inc. +# CaseFolding-15.1.0.txt +# Date: 2023-05-12, 21:53:10 GMT +# © 2023 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 +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Case Folding Properties # @@ -929,6 +929,7 @@ 1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI 1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA 1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD3; S; 0390; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA 1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI 1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI 1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY @@ -937,6 +938,7 @@ 1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA 1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA 1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA +1FE3; S; 03B0; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA 1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI 1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI 1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI @@ -1050,6 +1052,7 @@ 2C2C; C; 2C5C; # GLAGOLITIC CAPITAL LETTER SHTAPIC 2C2D; C; 2C5D; # GLAGOLITIC CAPITAL LETTER TROKUTASTI A 2C2E; C; 2C5E; # GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F; C; 2C5F; # GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60; C; 2C61; # LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62; C; 026B; # LATIN CAPITAL LETTER L WITH MIDDLE TILDE 2C63; C; 1D7D; # LATIN CAPITAL LETTER P WITH STROKE @@ -1230,12 +1233,16 @@ A7B8; C; A7B9; # LATIN CAPITAL LETTER U WITH STROKE A7BA; C; A7BB; # LATIN CAPITAL LETTER GLOTTAL A A7BC; C; A7BD; # LATIN CAPITAL LETTER GLOTTAL I A7BE; C; A7BF; # LATIN CAPITAL LETTER GLOTTAL U +A7C0; C; A7C1; # LATIN CAPITAL LETTER OLD POLISH O A7C2; C; A7C3; # LATIN CAPITAL LETTER ANGLICANA W A7C4; C; A794; # LATIN CAPITAL LETTER C WITH PALATAL HOOK A7C5; C; 0282; # LATIN CAPITAL LETTER S WITH HOOK A7C6; C; 1D8E; # LATIN CAPITAL LETTER Z WITH PALATAL HOOK A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H AB70; C; 13A0; # CHEROKEE SMALL LETTER A AB71; C; 13A1; # CHEROKEE SMALL LETTER E @@ -1323,6 +1330,7 @@ FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T +FB05; S; FB06; # LATIN SMALL LIGATURE LONG S T FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH @@ -1431,6 +1439,41 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z 104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA 104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA 104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA +10570; C; 10597; # VITHKUQI CAPITAL LETTER A +10571; C; 10598; # VITHKUQI CAPITAL LETTER BBE +10572; C; 10599; # VITHKUQI CAPITAL LETTER BE +10573; C; 1059A; # VITHKUQI CAPITAL LETTER CE +10574; C; 1059B; # VITHKUQI CAPITAL LETTER CHE +10575; C; 1059C; # VITHKUQI CAPITAL LETTER DE +10576; C; 1059D; # VITHKUQI CAPITAL LETTER DHE +10577; C; 1059E; # VITHKUQI CAPITAL LETTER EI +10578; C; 1059F; # VITHKUQI CAPITAL LETTER E +10579; C; 105A0; # VITHKUQI CAPITAL LETTER FE +1057A; C; 105A1; # VITHKUQI CAPITAL LETTER GA +1057C; C; 105A3; # VITHKUQI CAPITAL LETTER HA +1057D; C; 105A4; # VITHKUQI CAPITAL LETTER HHA +1057E; C; 105A5; # VITHKUQI CAPITAL LETTER I +1057F; C; 105A6; # VITHKUQI CAPITAL LETTER IJE +10580; C; 105A7; # VITHKUQI CAPITAL LETTER JE +10581; C; 105A8; # VITHKUQI CAPITAL LETTER KA +10582; C; 105A9; # VITHKUQI CAPITAL LETTER LA +10583; C; 105AA; # VITHKUQI CAPITAL LETTER LLA +10584; C; 105AB; # VITHKUQI CAPITAL LETTER ME +10585; C; 105AC; # VITHKUQI CAPITAL LETTER NE +10586; C; 105AD; # VITHKUQI CAPITAL LETTER NJE +10587; C; 105AE; # VITHKUQI CAPITAL LETTER O +10588; C; 105AF; # VITHKUQI CAPITAL LETTER PE +10589; C; 105B0; # VITHKUQI CAPITAL LETTER QA +1058A; C; 105B1; # VITHKUQI CAPITAL LETTER RE +1058C; C; 105B3; # VITHKUQI CAPITAL LETTER SE +1058D; C; 105B4; # VITHKUQI CAPITAL LETTER SHE +1058E; C; 105B5; # VITHKUQI CAPITAL LETTER TE +1058F; C; 105B6; # VITHKUQI CAPITAL LETTER THE +10590; C; 105B7; # VITHKUQI CAPITAL LETTER U +10591; C; 105B8; # VITHKUQI CAPITAL LETTER VE +10592; C; 105B9; # VITHKUQI CAPITAL LETTER XE +10594; C; 105BB; # VITHKUQI CAPITAL LETTER Y +10595; C; 105BC; # VITHKUQI CAPITAL LETTER ZE 10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A 10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA 10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB diff --git a/scripts/unicode/DerivedGeneralCategory.txt b/scripts/unicode/DerivedGeneralCategory.txt index 3e82c7fc..285ffa8f 100644 --- a/scripts/unicode/DerivedGeneralCategory.txt +++ b/scripts/unicode/DerivedGeneralCategory.txt @@ -1,11 +1,11 @@ -# DerivedGeneralCategory-13.0.0.txt -# Date: 2019-10-21, 14:30:32 GMT -# © 2019 Unicode®, Inc. +# DerivedGeneralCategory-15.1.0.txt +# Date: 2023-07-28, 23:34:02 GMT +# © 2023 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 +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # ================================================ @@ -27,7 +27,6 @@ 05C8..05CF ; Cn # [8] .. 05EB..05EE ; Cn # [4] .. 05F5..05FF ; Cn # [11] .. -061D ; Cn # 070E ; Cn # 074B..074C ; Cn # [2] .. 07B2..07BF ; Cn # [14] .. @@ -36,9 +35,9 @@ 083F ; Cn # 085C..085D ; Cn # [2] .. 085F ; Cn # -086B..089F ; Cn # [53] .. -08B5 ; Cn # -08C8..08D2 ; Cn # [11] .. +086B..086F ; Cn # [5] .. +088F ; Cn # +0892..0897 ; Cn # [6] .. 0984 ; Cn # 098D..098E ; Cn # [2] .. 0991..0992 ; Cn # [2] .. @@ -116,12 +115,13 @@ 0C0D ; Cn # 0C11 ; Cn # 0C29 ; Cn # -0C3A..0C3C ; Cn # [3] .. +0C3A..0C3B ; Cn # [2] .. 0C45 ; Cn # 0C49 ; Cn # 0C4E..0C54 ; Cn # [7] .. 0C57 ; Cn # -0C5B..0C5F ; Cn # [5] .. +0C5B..0C5C ; Cn # [2] .. +0C5E..0C5F ; Cn # [2] .. 0C64..0C65 ; Cn # [2] .. 0C70..0C76 ; Cn # [7] .. 0C8D ; Cn # @@ -132,11 +132,11 @@ 0CC5 ; Cn # 0CC9 ; Cn # 0CCE..0CD4 ; Cn # [7] .. -0CD7..0CDD ; Cn # [7] .. +0CD7..0CDC ; Cn # [6] .. 0CDF ; Cn # 0CE4..0CE5 ; Cn # [2] .. 0CF0 ; Cn # -0CF3..0CFF ; Cn # [13] .. +0CF4..0CFF ; Cn # [12] .. 0D0D ; Cn # 0D11 ; Cn # 0D45 ; Cn # @@ -166,7 +166,7 @@ 0EBE..0EBF ; Cn # [2] .. 0EC5 ; Cn # 0EC7 ; Cn # -0ECE..0ECF ; Cn # [2] .. +0ECF ; Cn # 0EDA..0EDB ; Cn # [2] .. 0EE0..0EFF ; Cn # [32] .. 0F48 ; Cn # @@ -200,8 +200,7 @@ 13FE..13FF ; Cn # [2] .. 169D..169F ; Cn # [3] .. 16F9..16FF ; Cn # [7] .. -170D ; Cn # -1715..171F ; Cn # [11] .. +1716..171E ; Cn # [9] .. 1737..173F ; Cn # [9] .. 1754..175F ; Cn # [12] .. 176D ; Cn # @@ -210,7 +209,6 @@ 17DE..17DF ; Cn # [2] .. 17EA..17EF ; Cn # [6] .. 17FA..17FF ; Cn # [6] .. -180F ; Cn # 181A..181F ; Cn # [6] .. 1879..187F ; Cn # [7] .. 18AB..18AF ; Cn # [5] .. @@ -230,9 +228,9 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1AC1..1AFF ; Cn # [63] .. -1B4C..1B4F ; Cn # [4] .. -1B7D..1B7F ; Cn # [3] .. +1ACF..1AFF ; Cn # [49] .. +1B4D..1B4F ; Cn # [3] .. +1B7F ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. 1C4A..1C4C ; Cn # [3] .. @@ -240,7 +238,6 @@ 1CBB..1CBC ; Cn # [2] .. 1CC8..1CCF ; Cn # [8] .. 1CFB..1CFF ; Cn # [5] .. -1DFA ; Cn # 1F16..1F17 ; Cn # [2] .. 1F1E..1F1F ; Cn # [2] .. 1F46..1F47 ; Cn # [2] .. @@ -261,15 +258,13 @@ 2072..2073 ; Cn # [2] .. 208F ; Cn # 209D..209F ; Cn # [3] .. -20C0..20CF ; Cn # [16] .. +20C1..20CF ; Cn # [15] .. 20F1..20FF ; Cn # [15] .. 218C..218F ; Cn # [4] .. 2427..243F ; Cn # [25] .. 244B..245F ; Cn # [21] .. 2B74..2B75 ; Cn # [2] .. 2B96 ; Cn # -2C2F ; Cn # -2C5F ; Cn # 2CF4..2CF8 ; Cn # [5] .. 2D26 ; Cn # 2D28..2D2C ; Cn # [5] .. @@ -285,25 +280,25 @@ 2DCF ; Cn # 2DD7 ; Cn # 2DDF ; Cn # -2E53..2E7F ; Cn # [45] .. +2E5E..2E7F ; Cn # [34] .. 2E9A ; Cn # 2EF4..2EFF ; Cn # [12] .. 2FD6..2FEF ; Cn # [26] .. -2FFC..2FFF ; Cn # [4] .. 3040 ; Cn # 3097..3098 ; Cn # [2] .. 3100..3104 ; Cn # [5] .. 3130 ; Cn # 318F ; Cn # -31E4..31EF ; Cn # [12] .. +31E4..31EE ; Cn # [11] .. 321F ; Cn # -9FFD..9FFF ; Cn # [3] .. A48D..A48F ; Cn # [3] .. A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. -A7C0..A7C1 ; Cn # [2] .. -A7CB..A7F4 ; Cn # [42] .. +A7CB..A7CF ; Cn # [5] .. +A7D2 ; Cn # +A7D4 ; Cn # +A7DA..A7F1 ; Cn # [24] .. A82D..A82F ; Cn # [3] .. A83A..A83F ; Cn # [6] .. A878..A87F ; Cn # [8] .. @@ -339,11 +334,10 @@ FB3D ; Cn # FB3F ; Cn # FB42 ; Cn # FB45 ; Cn # -FBC2..FBD2 ; Cn # [17] .. -FD40..FD4F ; Cn # [16] .. +FBC3..FBD2 ; Cn # [16] .. FD90..FD91 ; Cn # [2] .. -FDC8..FDEF ; Cn # [40] .. -FDFE..FDFF ; Cn # [2] .. +FDC8..FDCE ; Cn # [7] .. +FDD0..FDEF ; Cn # [32] .. FE1A..FE1F ; Cn # [6] .. FE53 ; Cn # FE67 ; Cn # @@ -387,10 +381,20 @@ FFFE..FFFF ; Cn # [2] .. 104FC..104FF ; Cn # [4] .. 10528..1052F ; Cn # [8] .. 10564..1056E ; Cn # [11] .. -10570..105FF ; Cn # [144] .. +1057B ; Cn # +1058B ; Cn # +10593 ; Cn # +10596 ; Cn # +105A2 ; Cn # +105B2 ; Cn # +105BA ; Cn # +105BD..105FF ; Cn # [67] .. 10737..1073F ; Cn # [9] .. 10756..1075F ; Cn # [10] .. -10768..107FF ; Cn # [152] .. +10768..1077F ; Cn # [24] .. +10786 ; Cn # +107B1 ; Cn # +107BB..107FF ; Cn # [69] .. 10806..10807 ; Cn # [2] .. 10809 ; Cn # 10836 ; Cn # @@ -431,14 +435,15 @@ FFFE..FFFF ; Cn # [2] .. 10E7F ; Cn # 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. -10EB2..10EFF ; Cn # [78] .. +10EB2..10EFC ; Cn # [75] .. 10F28..10F2F ; Cn # [8] .. -10F5A..10FAF ; Cn # [86] .. +10F5A..10F6F ; Cn # [22] .. +10F8A..10FAF ; Cn # [38] .. 10FCC..10FDF ; Cn # [20] .. 10FF7..10FFF ; Cn # [9] .. 1104E..11051 ; Cn # [4] .. -11070..1107E ; Cn # [15] .. -110C2..110CC ; Cn # [11] .. +11076..1107E ; Cn # [9] .. +110C3..110CC ; Cn # [10] .. 110CE..110CF ; Cn # [2] .. 110E9..110EF ; Cn # [7] .. 110FA..110FF ; Cn # [6] .. @@ -448,7 +453,7 @@ FFFE..FFFF ; Cn # [2] .. 111E0 ; Cn # 111F5..111FF ; Cn # [11] .. 11212 ; Cn # -1123F..1127F ; Cn # [65] .. +11242..1127F ; Cn # [62] .. 11287 ; Cn # 11289 ; Cn # 1128E ; Cn # @@ -480,11 +485,11 @@ FFFE..FFFF ; Cn # [2] .. 11645..1164F ; Cn # [11] .. 1165A..1165F ; Cn # [6] .. 1166D..1167F ; Cn # [19] .. -116B9..116BF ; Cn # [7] .. +116BA..116BF ; Cn # [6] .. 116CA..116FF ; Cn # [54] .. 1171B..1171C ; Cn # [2] .. 1172C..1172F ; Cn # [4] .. -11740..117FF ; Cn # [192] .. +11747..117FF ; Cn # [185] .. 1183C..1189F ; Cn # [100] .. 118F3..118FE ; Cn # [12] .. 11907..11908 ; Cn # [2] .. @@ -499,8 +504,9 @@ FFFE..FFFF ; Cn # [2] .. 119D8..119D9 ; Cn # [2] .. 119E5..119FF ; Cn # [27] .. 11A48..11A4F ; Cn # [8] .. -11AA3..11ABF ; Cn # [29] .. -11AF9..11BFF ; Cn # [263] .. +11AA3..11AAF ; Cn # [13] .. +11AF9..11AFF ; Cn # [7] .. +11B0A..11BFF ; Cn # [246] .. 11C09 ; Cn # 11C37 ; Cn # 11C46..11C4F ; Cn # [10] .. @@ -521,20 +527,24 @@ FFFE..FFFF ; Cn # [2] .. 11D92 ; Cn # 11D99..11D9F ; Cn # [7] .. 11DAA..11EDF ; Cn # [310] .. -11EF9..11FAF ; Cn # [183] .. +11EF9..11EFF ; Cn # [7] .. +11F11 ; Cn # +11F3B..11F3D ; Cn # [3] .. +11F5A..11FAF ; Cn # [86] .. 11FB1..11FBF ; Cn # [15] .. 11FF2..11FFE ; Cn # [13] .. 1239A..123FF ; Cn # [102] .. 1246F ; Cn # 12475..1247F ; Cn # [11] .. -12544..12FFF ; Cn # [2748] .. -1342F ; Cn # -13439..143FF ; Cn # [4039] .. +12544..12F8F ; Cn # [2636] .. +12FF3..12FFF ; Cn # [13] .. +13456..143FF ; Cn # [4010] .. 14647..167FF ; Cn # [8633] .. 16A39..16A3F ; Cn # [7] .. 16A5F ; Cn # 16A6A..16A6D ; Cn # [4] .. -16A70..16ACF ; Cn # [96] .. +16ABF ; Cn # +16ACA..16ACF ; Cn # [6] .. 16AEE..16AEF ; Cn # [2] .. 16AF6..16AFF ; Cn # [10] .. 16B46..16B4F ; Cn # [10] .. @@ -550,20 +560,29 @@ FFFE..FFFF ; Cn # [2] .. 16FF2..16FFF ; Cn # [14] .. 187F8..187FF ; Cn # [8] .. 18CD6..18CFF ; Cn # [42] .. -18D09..1AFFF ; Cn # [8951] .. -1B11F..1B14F ; Cn # [49] .. -1B153..1B163 ; Cn # [17] .. +18D09..1AFEF ; Cn # [8935] .. +1AFF4 ; Cn # +1AFFC ; Cn # +1AFFF ; Cn # +1B123..1B131 ; Cn # [15] .. +1B133..1B14F ; Cn # [29] .. +1B153..1B154 ; Cn # [2] .. +1B156..1B163 ; Cn # [14] .. 1B168..1B16F ; Cn # [8] .. 1B2FC..1BBFF ; Cn # [2308] .. 1BC6B..1BC6F ; Cn # [5] .. 1BC7D..1BC7F ; Cn # [3] .. 1BC89..1BC8F ; Cn # [7] .. 1BC9A..1BC9B ; Cn # [2] .. -1BCA4..1CFFF ; Cn # [4956] .. +1BCA4..1CEFF ; Cn # [4700] .. +1CF2E..1CF2F ; Cn # [2] .. +1CF47..1CF4F ; Cn # [9] .. +1CFC4..1CFFF ; Cn # [60] .. 1D0F6..1D0FF ; Cn # [10] .. 1D127..1D128 ; Cn # [2] .. -1D1E9..1D1FF ; Cn # [23] .. -1D246..1D2DF ; Cn # [154] .. +1D1EB..1D1FF ; Cn # [21] .. +1D246..1D2BF ; Cn # [122] .. +1D2D4..1D2DF ; Cn # [12] .. 1D2F4..1D2FF ; Cn # [12] .. 1D357..1D35F ; Cn # [9] .. 1D379..1D3FF ; Cn # [135] .. @@ -589,18 +608,28 @@ FFFE..FFFF ; Cn # [2] .. 1D7CC..1D7CD ; Cn # [2] .. 1DA8C..1DA9A ; Cn # [15] .. 1DAA0 ; Cn # -1DAB0..1DFFF ; Cn # [1360] .. +1DAB0..1DEFF ; Cn # [1104] .. +1DF1F..1DF24 ; Cn # [6] .. +1DF2B..1DFFF ; Cn # [213] .. 1E007 ; Cn # 1E019..1E01A ; Cn # [2] .. 1E022 ; Cn # 1E025 ; Cn # -1E02B..1E0FF ; Cn # [213] .. +1E02B..1E02F ; Cn # [5] .. +1E06E..1E08E ; Cn # [33] .. +1E090..1E0FF ; Cn # [112] .. 1E12D..1E12F ; Cn # [3] .. 1E13E..1E13F ; Cn # [2] .. 1E14A..1E14D ; Cn # [4] .. -1E150..1E2BF ; Cn # [368] .. +1E150..1E28F ; Cn # [320] .. +1E2AF..1E2BF ; Cn # [17] .. 1E2FA..1E2FE ; Cn # [5] .. -1E300..1E7FF ; Cn # [1280] .. +1E300..1E4CF ; Cn # [464] .. +1E4FA..1E7DF ; Cn # [742] .. +1E7E7 ; Cn # +1E7EC ; Cn # +1E7EF ; Cn # +1E7FF ; Cn # 1E8C5..1E8C6 ; Cn # [2] .. 1E8D7..1E8FF ; Cn # [41] .. 1E94C..1E94F ; Cn # [4] .. @@ -654,46 +683,47 @@ FFFE..FFFF ; Cn # [2] .. 1F249..1F24F ; Cn # [7] .. 1F252..1F25F ; Cn # [14] .. 1F266..1F2FF ; Cn # [154] .. -1F6D8..1F6DF ; Cn # [8] .. +1F6D8..1F6DB ; Cn # [4] .. 1F6ED..1F6EF ; Cn # [3] .. 1F6FD..1F6FF ; Cn # [3] .. -1F774..1F77F ; Cn # [12] .. -1F7D9..1F7DF ; Cn # [7] .. -1F7EC..1F7FF ; Cn # [20] .. +1F777..1F77A ; Cn # [4] .. +1F7DA..1F7DF ; Cn # [6] .. +1F7EC..1F7EF ; Cn # [4] .. +1F7F1..1F7FF ; Cn # [15] .. 1F80C..1F80F ; Cn # [4] .. 1F848..1F84F ; Cn # [8] .. 1F85A..1F85F ; Cn # [6] .. 1F888..1F88F ; Cn # [8] .. 1F8AE..1F8AF ; Cn # [2] .. 1F8B2..1F8FF ; Cn # [78] .. -1F979 ; Cn # -1F9CC ; Cn # 1FA54..1FA5F ; Cn # [12] .. 1FA6E..1FA6F ; Cn # [2] .. -1FA75..1FA77 ; Cn # [3] .. -1FA7B..1FA7F ; Cn # [5] .. -1FA87..1FA8F ; Cn # [9] .. -1FAA9..1FAAF ; Cn # [7] .. -1FAB7..1FABF ; Cn # [9] .. -1FAC3..1FACF ; Cn # [13] .. -1FAD7..1FAFF ; Cn # [41] .. +1FA7D..1FA7F ; Cn # [3] .. +1FA89..1FA8F ; Cn # [7] .. +1FABE ; Cn # +1FAC6..1FACD ; Cn # [8] .. +1FADC..1FADF ; Cn # [4] .. +1FAE9..1FAEF ; Cn # [7] .. +1FAF9..1FAFF ; Cn # [7] .. 1FB93 ; Cn # 1FBCB..1FBEF ; Cn # [37] .. 1FBFA..1FFFF ; Cn # [1030] .. -2A6DE..2A6FF ; Cn # [34] .. -2B735..2B73F ; Cn # [11] .. +2A6E0..2A6FF ; Cn # [32] .. +2B73A..2B73F ; Cn # [6] .. 2B81E..2B81F ; Cn # [2] .. 2CEA2..2CEAF ; Cn # [14] .. -2EBE1..2F7FF ; Cn # [3103] .. +2EBE1..2EBEF ; Cn # [15] .. +2EE5E..2F7FF ; Cn # [2466] .. 2FA1E..2FFFF ; Cn # [1506] .. -3134B..E0000 ; Cn # [715958] .. +3134B..3134F ; Cn # [5] .. +323B0..E0000 ; Cn # [711761] .. E0002..E001F ; Cn # [30] .. E0080..E00FF ; Cn # [128] .. E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 830672 +# Total code points: 824718 # ================================================ @@ -1130,7 +1160,7 @@ FFFFE..FFFFF ; Cn # [2] .. 213E..213F ; Lu # [2] DOUBLE-STRUCK CAPITAL GAMMA..DOUBLE-STRUCK CAPITAL PI 2145 ; Lu # DOUBLE-STRUCK ITALIC CAPITAL D 2183 ; Lu # ROMAN NUMERAL REVERSED ONE HUNDRED -2C00..2C2E ; Lu # [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C00..2C2F ; Lu # [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI 2C60 ; Lu # LATIN CAPITAL LETTER L WITH DOUBLE BAR 2C62..2C64 ; Lu # [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL 2C67 ; Lu # LATIN CAPITAL LETTER H WITH DESCENDER @@ -1295,13 +1325,21 @@ A7B8 ; Lu # LATIN CAPITAL LETTER U WITH STROKE A7BA ; Lu # LATIN CAPITAL LETTER GLOTTAL A A7BC ; Lu # LATIN CAPITAL LETTER GLOTTAL I A7BE ; Lu # LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Lu # LATIN CAPITAL LETTER OLD POLISH O A7C2 ; Lu # LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Lu # [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Lu # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Lu # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S A7F5 ; Lu # LATIN CAPITAL LETTER REVERSED HALF H FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Lu # [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW 104B0..104D3 ; Lu # [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Lu # [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Lu # [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Lu # [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Lu # [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 10C80..10CB2 ; Lu # [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Lu # [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Lu # [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y @@ -1338,7 +1376,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA 1E900..1E921 ; Lu # [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1791 +# Total code points: 1831 # ================================================ @@ -1775,7 +1813,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 2146..2149 ; Ll # [4] DOUBLE-STRUCK ITALIC SMALL D..DOUBLE-STRUCK ITALIC SMALL J 214E ; Ll # TURNED SMALL F 2184 ; Ll # LATIN SMALL LETTER REVERSED C -2C30..2C5E ; Ll # [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +2C30..2C5F ; Ll # [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C61 ; Ll # LATIN SMALL LETTER L WITH DOUBLE BAR 2C65..2C66 ; Ll # [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE 2C68 ; Ll # LATIN SMALL LETTER H WITH DESCENDER @@ -1944,9 +1982,15 @@ A7B9 ; Ll # LATIN SMALL LETTER U WITH STROKE A7BB ; Ll # LATIN SMALL LETTER GLOTTAL A A7BD ; Ll # LATIN SMALL LETTER GLOTTAL I A7BF ; Ll # LATIN SMALL LETTER GLOTTAL U +A7C1 ; Ll # LATIN SMALL LETTER OLD POLISH O A7C3 ; Ll # LATIN SMALL LETTER ANGLICANA W A7C8 ; Ll # LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Ll # LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Ll # LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Ll # LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Ll # LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Ll # LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Ll # LATIN SMALL LETTER SIGMOID S A7F6 ; Ll # LATIN SMALL LETTER REVERSED HALF H A7FA ; Ll # LATIN LETTER SMALL CAPITAL TURNED M AB30..AB5A ; Ll # [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG @@ -1957,6 +2001,10 @@ FB13..FB17 ; Ll # [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGAT FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Ll # [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW 104D8..104FB ; Ll # [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Ll # [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Ll # [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Ll # [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Ll # [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10CC0..10CF2 ; Ll # [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Ll # [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Ll # [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y @@ -1988,9 +2036,12 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 1D7AA..1D7C2 ; Ll # [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Ll # [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Ll # MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Ll # [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Ll # [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; Ll # [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK 1E922..1E943 ; Ll # [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2155 +# Total code points: 2233 # ================================================ @@ -2028,6 +2079,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 081A ; Lm # SAMARITAN MODIFIER LETTER EPENTHETIC YUT 0824 ; Lm # SAMARITAN MODIFIER LETTER SHORT A 0828 ; Lm # SAMARITAN MODIFIER LETTER I +08C9 ; Lm # ARABIC SMALL FARSI YEH 0971 ; Lm # DEVANAGARI SIGN HIGH SPACING DOT 0E46 ; Lm # THAI CHARACTER MAIYAMOK 0EC6 ; Lm # LAO KO LA @@ -2058,6 +2110,7 @@ A69C..A69D ; Lm # [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER C A717..A71F ; Lm # [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A770 ; Lm # MODIFIER LETTER US A788 ; Lm # MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A7F2..A7F4 ; Lm # [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Lm # [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A9CF ; Lm # JAVANESE PANGRANGKEP A9E6 ; Lm # MYANMAR MODIFIER LETTER SHAN REDUPLICATION @@ -2068,14 +2121,22 @@ AB5C..AB5F ; Lm # [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U W AB69 ; Lm # MODIFIER LETTER SMALL TURNED W FF70 ; Lm # HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +10780..10785 ; Lm # [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lm # [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lm # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F93..16F9F ; Lm # [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; Lm # [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Lm # OLD CHINESE ITERATION MARK +1AFF0..1AFF3 ; Lm # [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Lm # [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Lm # [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1E030..1E06D ; Lm # [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E137..1E13D ; Lm # [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 260 +# Total code points: 397 # ================================================ @@ -2104,8 +2165,9 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0800..0815 ; Lo # [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Lo # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; Lo # [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08C7 ; Lo # [18] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +0870..0887 ; Lo # [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; Lo # [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; Lo # [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 0904..0939 ; Lo # [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; Lo # DEVANAGARI SIGN AVAGRAHA 0950 ; Lo # DEVANAGARI OM @@ -2170,6 +2232,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0C2A..0C39 ; Lo # [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; Lo # TELUGU SIGN AVAGRAHA 0C58..0C5A ; Lo # [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; Lo # TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Lo # [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; Lo # KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; Lo # [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -2178,7 +2241,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0CAA..0CB3 ; Lo # [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; Lo # [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; Lo # KANNADA SIGN AVAGRAHA -0CDE ; Lo # KANNADA LETTER FA +0CDD..0CDE ; Lo # [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; Lo # [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; Lo # [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; Lo # [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -2242,9 +2305,8 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1681..169A ; Lo # [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH 16A0..16EA ; Lo # [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16F1..16F8 ; Lo # [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; Lo # [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; Lo # [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; Lo # [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; Lo # [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; Lo # [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; Lo # [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; Lo # [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; Lo # [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -2264,7 +2326,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1A00..1A16 ; Lo # [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1A20..1A54 ; Lo # [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA 1B05..1B33 ; Lo # [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; Lo # [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; Lo # [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; Lo # [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; Lo # [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; Lo # [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -2297,8 +2359,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 31A0..31BF ; Lo # [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH 31F0..31FF ; Lo # [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DBF ; Lo # [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF -4E00..9FFC ; Lo # [20989] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFC -A000..A014 ; Lo # [21] YI SYLLABLE IT..YI SYLLABLE E +4E00..A014 ; Lo # [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E A016..A48C ; Lo # [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Lo # [40] LISU LETTER BA..LISU LETTER OE A500..A60B ; Lo # [268] VAI SYLLABLE EE..VAI SYLLABLE NG @@ -2426,9 +2487,12 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10F00..10F1C ; Lo # [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Lo # OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Lo # [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; Lo # [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 10FB0..10FC4 ; Lo # [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; Lo # [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; Lo # [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; Lo # [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; Lo # BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; Lo # [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; Lo # [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; Lo # [36] CHAKMA LETTER AA..CHAKMA LETTER HAA @@ -2442,6 +2506,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 111DC ; Lo # SHARADA HEADSTROKE 11200..11211 ; Lo # [18] KHOJKI LETTER A..KHOJKI LETTER JJA 11213..1122B ; Lo # [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1123F..11240 ; Lo # [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I 11280..11286 ; Lo # [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; Lo # MULTANI LETTER GHA 1128A..1128D ; Lo # [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -2470,6 +2535,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11680..116AA ; Lo # [43] TAKRI LETTER A..TAKRI LETTER RRA 116B8 ; Lo # TAKRI LETTER ARCHAIC KHA 11700..1171A ; Lo # [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; Lo # [7] AHOM LETTER CA..AHOM LETTER LLA 11800..1182B ; Lo # [44] DOGRA LETTER A..DOGRA LETTER RRA 118FF..11906 ; Lo # [8] WARANG CITI OM..DIVES AKURU LETTER E 11909 ; Lo # DIVES AKURU LETTER O @@ -2488,7 +2554,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11A50 ; Lo # SOYOMBO LETTER A 11A5C..11A89 ; Lo # [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; Lo # SOYOMBO MARK PLUTA -11AC0..11AF8 ; Lo # [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; Lo # [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; Lo # [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Lo # [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; Lo # BHAIKSUKI SIGN AVAGRAHA @@ -2502,13 +2568,19 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11D6A..11D89 ; Lo # [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; Lo # GUNJALA GONDI OM 11EE0..11EF2 ; Lo # [19] MAKASAR LETTER KA..MAKASAR ANGKA +11F02 ; Lo # KAWI SIGN REPHA +11F04..11F10 ; Lo # [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; Lo # [34] KAWI LETTER KA..KAWI LETTER JNYA 11FB0 ; Lo # LISU LETTER YHA 12000..12399 ; Lo # [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12480..12543 ; Lo # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; Lo # [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; Lo # [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; Lo # [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; Lo # [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; Lo # [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; Lo # [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; Lo # [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; Lo # [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; Lo # [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; Lo # [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B63..16B77 ; Lo # [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS @@ -2518,17 +2590,26 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 17000..187F7 ; Lo # [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Lo # [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18D00..18D08 ; Lo # [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 -1B000..1B11E ; Lo # [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B000..1B122 ; Lo # [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B132 ; Lo # HIRAGANA LETTER SMALL KO 1B150..1B152 ; Lo # [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B155 ; Lo # KATAKANA LETTER SMALL KO 1B164..1B167 ; Lo # [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B170..1B2FB ; Lo # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Lo # [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Lo # [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Lo # [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1BC90..1BC99 ; Lo # [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1DF0A ; Lo # LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK 1E100..1E12C ; Lo # [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E14E ; Lo # NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; Lo # [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Lo # [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; Lo # [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E7E0..1E7E6 ; Lo # [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; Lo # [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; Lo # [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; Lo # [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; Lo # [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1EE00..1EE03 ; Lo # [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Lo # [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF @@ -2563,15 +2644,17 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1EEA1..1EEA3 ; Lo # [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL 1EEA5..1EEA9 ; Lo # [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; Lo # [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -20000..2A6DD ; Lo # [42718] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DD -2A700..2B734 ; Lo # [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +20000..2A6DF ; Lo # [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B739 ; Lo # [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 2B740..2B81D ; Lo # [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Lo # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 2CEB0..2EBE0 ; Lo # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBF0..2EE5D ; Lo # [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; Lo # [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A +31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 127004 +# Total code points: 132234 # ================================================ @@ -2601,7 +2684,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0825..0827 ; Mn # [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Mn # [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Mn # [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D3..08E1 ; Mn # [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Mn # [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Mn # [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Mn # [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Mn # DEVANAGARI VOWEL SIGN OE 093C ; Mn # DEVANAGARI SIGN NUKTA @@ -2642,6 +2726,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0BCD ; Mn # TAMIL SIGN VIRAMA 0C00 ; Mn # TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C04 ; Mn # TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Mn # TELUGU SIGN NUKTA 0C3E..0C40 ; Mn # [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Mn # [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Mn # [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -2667,7 +2752,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0E47..0E4E ; Mn # [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN 0EB1 ; Mn # LAO VOWEL SIGN MAI KAN 0EB4..0EBC ; Mn # [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO -0EC8..0ECD ; Mn # [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; Mn # [7] LAO TONE MAI EK..LAO YAMAKKAN 0F18..0F19 ; Mn # [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS 0F35 ; Mn # TIBETAN MARK NGAS BZUNG NYI ZLA 0F37 ; Mn # TIBETAN MARK NGAS BZUNG SGOR RTAGS @@ -2691,7 +2776,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 109D ; Mn # MYANMAR VOWEL SIGN AITON AI 135D..135F ; Mn # [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Mn # [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Mn # [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1732..1733 ; Mn # [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U 1752..1753 ; Mn # [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Mn # [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Mn # [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -2700,6 +2785,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 17C9..17D3 ; Mn # [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Mn # KHMER SIGN ATTHACAN 180B..180D ; Mn # [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Mn # MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Mn # [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Mn # MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Mn # [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -2716,7 +2802,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A73..1A7C ; Mn # [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AC0 ; Mn # [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1ABF..1ACE ; Mn # [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2739,8 +2825,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1CED ; Mn # VEDIC SIGN TIRYAK 1CF4 ; Mn # VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Mn # [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Mn # [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Mn # [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Mn # [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; Mn # [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20E1 ; Mn # COMBINING LEFT RIGHT ARROW ABOVE 20E5..20F0 ; Mn # [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE @@ -2798,12 +2883,17 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 10AE5..10AE6 ; Mn # [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Mn # [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10EAB..10EAC ; Mn # [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFD..10EFF ; Mn # [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Mn # [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Mn # [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Mn # BRAHMI SIGN ANUSVARA 11038..11046 ; Mn # [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Mn # BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Mn # [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 1107F..11081 ; Mn # [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 110B3..110B6 ; Mn # [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI 110B9..110BA ; Mn # [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Mn # KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Mn # [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Mn # [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112D..11134 ; Mn # [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA @@ -2816,6 +2906,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 11234 ; Mn # KHOJKI SIGN ANUSVARA 11236..11237 ; Mn # [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; Mn # KHOJKI SIGN SUKUN +11241 ; Mn # KHOJKI VOWEL SIGN VOCALIC R 112DF ; Mn # KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Mn # [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Mn # [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -2877,12 +2968,20 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 11D95 ; Mn # GUNJALA GONDI SIGN ANUSVARA 11D97 ; Mn # GUNJALA GONDI VIRAMA 11EF3..11EF4 ; Mn # [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11F00..11F01 ; Mn # [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; Mn # [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; Mn # KAWI VOWEL SIGN EU +11F42 ; Mn # KAWI CONJOINER +13440 ; Mn # EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; Mn # [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 16AF0..16AF4 ; Mn # [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Mn # [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F4F ; Mn # MIAO SIGN CONSONANT MODIFIER BAR 16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW 16FE4 ; Mn # KHITAN SMALL SCRIPT FILLER 1BC9D..1BC9E ; Mn # [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Mn # [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Mn # [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1D167..1D169 ; Mn # [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D17B..1D182 ; Mn # [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D185..1D18B ; Mn # [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE @@ -2899,13 +2998,16 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E01B..1E021 ; Mn # [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Mn # [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Mn # [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; Mn # COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E130..1E136 ; Mn # [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Mn # TOTO SIGN RISING TONE 1E2EC..1E2EF ; Mn # [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; Mn # [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E8D0..1E8D6 ; Mn # [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1839 +# Total code points: 1985 # ================================================ @@ -2958,6 +3060,7 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL 0CC7..0CC8 ; Mc # [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI 0CCA..0CCB ; Mc # [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CD5..0CD6 ; Mc # [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CF3 ; Mc # KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D02..0D03 ; Mc # [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D3E..0D40 ; Mc # [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D46..0D48 ; Mc # [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -2980,6 +3083,8 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL 1087..108C ; Mc # [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3 108F ; Mc # MYANMAR SIGN RUMAI PALAUNG TONE-5 109A..109C ; Mc # [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A +1715 ; Mc # TAGALOG SIGN PAMUDPOD +1734 ; Mc # HANUNOO SIGN PAMUDPOD 17B6 ; Mc # KHMER VOWEL SIGN AA 17BE..17C5 ; Mc # [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU 17C7..17C8 ; Mc # [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU @@ -3094,12 +3199,16 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 11D93..11D94 ; Mc # [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU 11D96 ; Mc # GUNJALA GONDI SIGN VISARGA 11EF5..11EF6 ; Mc # [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F03 ; Mc # KAWI SIGN VISARGA +11F34..11F35 ; Mc # [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F3E..11F3F ; Mc # [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F41 ; Mc # KAWI SIGN KILLER 16F51..16F87 ; Mc # [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16FF0..16FF1 ; Mc # [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1D165..1D166 ; Mc # [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D..1D172 ; Mc # [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 -# Total code points: 443 +# Total code points: 452 # ================================================ @@ -3159,15 +3268,18 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11C50..11C59 ; Nd # [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE 11D50..11D59 ; Nd # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Nd # [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11F50..11F59 ; Nd # [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Nd # [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Nd # [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E4F0..1E4F9 ; Nd # [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 650 +# Total code points: 680 # ================================================ @@ -3254,6 +3366,7 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 11FC0..11FD4 ; No # [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH 16B5B..16B61 ; No # [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 16E80..16E96 ; No # [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM +1D2C0..1D2D3 ; No # [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN 1D2E0..1D2F3 ; No # [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN 1D360..1D378 ; No # [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE 1E8C7..1E8CF ; No # [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE @@ -3264,7 +3377,7 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 1ED2F..1ED3D ; No # [15] OTTOMAN SIYAQ ALTERNATE NUMBER TWO..OTTOMAN SIYAQ FRACTION ONE SIXTH 1F100..1F10C ; No # [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO -# Total code points: 895 +# Total code points: 915 # ================================================ @@ -3314,6 +3427,7 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 061C ; Cf # ARABIC LETTER MARK 06DD ; Cf # ARABIC END OF AYAH 070F ; Cf # SYRIAC ABBREVIATION MARK +0890..0891 ; Cf # [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Cf # ARABIC DISPUTED END OF AYAH 180E ; Cf # MONGOLIAN VOWEL SEPARATOR 200B..200F ; Cf # [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK @@ -3324,13 +3438,13 @@ FEFF ; Cf # ZERO WIDTH NO-BREAK SPACE FFF9..FFFB ; Cf # [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR 110BD ; Cf # KAITHI NUMBER SIGN 110CD ; Cf # KAITHI NUMBER SIGN ABOVE -13430..13438 ; Cf # [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +13430..1343F ; Cf # [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 1BCA0..1BCA3 ; Cf # [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D173..1D17A ; Cf # [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Cf # LANGUAGE TAG E0020..E007F ; Cf # [96] TAG SPACE..CANCEL TAG -# Total code points: 161 +# Total code points: 170 # ================================================ @@ -3364,6 +3478,7 @@ D800..DFFF ; Cs # [2048] .. 2E1A ; Pd # HYPHEN WITH DIAERESIS 2E3A..2E3B ; Pd # [2] TWO-EM DASH..THREE-EM DASH 2E40 ; Pd # DOUBLE HYPHEN +2E5D ; Pd # OBLIQUE HYPHEN 301C ; Pd # WAVE DASH 3030 ; Pd # WAVY DASH 30A0 ; Pd # KATAKANA-HIRAGANA DOUBLE HYPHEN @@ -3373,7 +3488,7 @@ FE63 ; Pd # SMALL HYPHEN-MINUS FF0D ; Pd # FULLWIDTH HYPHEN-MINUS 10EAD ; Pd # YEZIDI HYPHENATION MARK -# Total code points: 25 +# Total code points: 26 # ================================================ @@ -3425,6 +3540,10 @@ FF0D ; Pd # FULLWIDTH HYPHEN-MINUS 2E26 ; Ps # LEFT SIDEWAYS U BRACKET 2E28 ; Ps # LEFT DOUBLE PARENTHESIS 2E42 ; Ps # DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E55 ; Ps # LEFT SQUARE BRACKET WITH STROKE +2E57 ; Ps # LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Ps # TOP HALF LEFT PARENTHESIS +2E5B ; Ps # BOTTOM HALF LEFT PARENTHESIS 3008 ; Ps # LEFT ANGLE BRACKET 300A ; Ps # LEFT DOUBLE ANGLE BRACKET 300C ; Ps # LEFT CORNER BRACKET @@ -3455,7 +3574,7 @@ FF5B ; Ps # FULLWIDTH LEFT CURLY BRACKET FF5F ; Ps # FULLWIDTH LEFT WHITE PARENTHESIS FF62 ; Ps # HALFWIDTH LEFT CORNER BRACKET -# Total code points: 75 +# Total code points: 79 # ================================================ @@ -3504,6 +3623,10 @@ FF62 ; Ps # HALFWIDTH LEFT CORNER BRACKET 2E25 ; Pe # BOTTOM RIGHT HALF BRACKET 2E27 ; Pe # RIGHT SIDEWAYS U BRACKET 2E29 ; Pe # RIGHT DOUBLE PARENTHESIS +2E56 ; Pe # RIGHT SQUARE BRACKET WITH STROKE +2E58 ; Pe # RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E5A ; Pe # TOP HALF RIGHT PARENTHESIS +2E5C ; Pe # BOTTOM HALF RIGHT PARENTHESIS 3009 ; Pe # RIGHT ANGLE BRACKET 300B ; Pe # RIGHT DOUBLE ANGLE BRACKET 300D ; Pe # RIGHT CORNER BRACKET @@ -3534,7 +3657,7 @@ FF5D ; Pe # FULLWIDTH RIGHT CURLY BRACKET FF60 ; Pe # FULLWIDTH RIGHT WHITE PARENTHESIS FF63 ; Pe # HALFWIDTH RIGHT CORNER BRACKET -# Total code points: 73 +# Total code points: 77 # ================================================ @@ -3576,7 +3699,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 0609..060A ; Po # [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN 060C..060D ; Po # [2] ARABIC COMMA..ARABIC DATE SEPARATOR 061B ; Po # ARABIC SEMICOLON -061E..061F ; Po # [2] ARABIC TRIPLE DOT PUNCTUATION MARK..ARABIC QUESTION MARK +061D..061F ; Po # [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK 066A..066D ; Po # [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR 06D4 ; Po # ARABIC FULL STOP 0700..070D ; Po # [14] SYRIAC END OF PARAGRAPH..SYRIAC HARKLEAN ASTERISCUS @@ -3613,6 +3736,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 1AA0..1AA6 ; Po # [7] TAI THAM SIGN WIANG..TAI THAM SIGN REVERSED ROTATED RANA 1AA8..1AAD ; Po # [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1B5A..1B60 ; Po # [7] BALINESE PANTI..BALINESE PAMENENG +1B7D..1B7E ; Po # [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG 1BFC..1BFF ; Po # [4] BATAK SYMBOL BINDU NA METEK..BATAK SYMBOL BINDU PANGOLAT 1C3B..1C3F ; Po # [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; Po # [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD @@ -3641,7 +3765,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 2E3C..2E3F ; Po # [4] STENOGRAPHIC FULL STOP..CAPITULUM 2E41 ; Po # REVERSED COMMA 2E43..2E4F ; Po # [13] DASH WITH LEFT UPTURN..CORNISH VERSE DIVIDER -2E52 ; Po # TIRONIAN SIGN CAPITAL ET +2E52..2E54 ; Po # [3] TIRONIAN SIGN CAPITAL ET..MEDIEVAL QUESTION MARK 3001..3003 ; Po # [3] IDEOGRAPHIC COMMA..DITTO MARK 303D ; Po # PART ALTERNATION MARK 30FB ; Po # KATAKANA MIDDLE DOT @@ -3695,6 +3819,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 10B39..10B3F ; Po # [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION 10B99..10B9C ; Po # [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT 10F55..10F59 ; Po # [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; Po # [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS 11047..1104D ; Po # [7] BRAHMI DANDA..BRAHMI PUNCTUATION LOTUS 110BB..110BC ; Po # [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN 110BE..110C1 ; Po # [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA @@ -3713,6 +3838,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 115C1..115D7 ; Po # [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11643 ; Po # [3] MODI DANDA..MODI ABBREVIATION SIGN 11660..1166C ; Po # [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +116B9 ; Po # TAKRI ABBREVIATION SIGN 1173C..1173E ; Po # [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI 1183B ; Po # DOGRA ABBREVIATION SIGN 11944..11946 ; Po # [3] DIVES AKURU DOUBLE DANDA..DIVES AKURU END OF TEXT MARK @@ -3720,11 +3846,14 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 11A3F..11A46 ; Po # [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK 11A9A..11A9C ; Po # [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD 11A9E..11AA2 ; Po # [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 +11B00..11B09 ; Po # [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU 11C41..11C45 ; Po # [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 11C70..11C71 ; Po # [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD 11EF7..11EF8 ; Po # [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION +11F43..11F4F ; Po # [13] KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL 11FFF ; Po # TAMIL PUNCTUATION END OF TEXT 12470..12474 ; Po # [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON +12FF1..12FF2 ; Po # [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302 16A6E..16A6F ; Po # [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; Po # BASSA VAH FULL STOP 16B37..16B3B ; Po # [5] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS FEEM @@ -3735,7 +3864,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 593 +# Total code points: 628 # ================================================ @@ -3823,7 +3952,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 0BF9 ; Sc # TAMIL RUPEE SIGN 0E3F ; Sc # THAI CURRENCY SYMBOL BAHT 17DB ; Sc # KHMER CURRENCY SYMBOL RIEL -20A0..20BF ; Sc # [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20A0..20C0 ; Sc # [33] EURO-CURRENCY SIGN..SOM SIGN A838 ; Sc # NORTH INDIC RUPEE MARK FDFC ; Sc # RIAL SIGN FE69 ; Sc # SMALL DOLLAR SIGN @@ -3834,7 +3963,7 @@ FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 1E2FF ; Sc # WANCHO NGUN SIGN 1ECB0 ; Sc # INDIC SIYAQ RUPEE MARK -# Total code points: 62 +# Total code points: 63 # ================================================ @@ -3853,6 +3982,7 @@ FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 02EF..02FF ; Sk # [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW 0375 ; Sk # GREEK LOWER NUMERAL SIGN 0384..0385 ; Sk # [2] GREEK TONOS..GREEK DIALYTIKA TONOS +0888 ; Sk # ARABIC RAISED ROUND DOT 1FBD ; Sk # GREEK KORONIS 1FBF..1FC1 ; Sk # [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI 1FCD..1FCF ; Sk # [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -3865,13 +3995,13 @@ A720..A721 ; Sk # [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER A789..A78A ; Sk # [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN AB5B ; Sk # MODIFIER BREVE WITH INVERTED BREVE AB6A..AB6B ; Sk # [2] MODIFIER LETTER LEFT TACK..MODIFIER LETTER RIGHT TACK -FBB2..FBC1 ; Sk # [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW +FBB2..FBC2 ; Sk # [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE FF3E ; Sk # FULLWIDTH CIRCUMFLEX ACCENT FF40 ; Sk # FULLWIDTH GRAVE ACCENT FFE3 ; Sk # FULLWIDTH MACRON 1F3FB..1F3FF ; Sk # [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -# Total code points: 123 +# Total code points: 125 # ================================================ @@ -3963,7 +4093,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 2E80..2E99 ; So # [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; So # [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; So # [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE -2FF0..2FFB ; So # [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID +2FF0..2FFF ; So # [16] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION 3004 ; So # JAPANESE INDUSTRIAL STANDARD SYMBOL 3012..3013 ; So # [2] POSTAL MARK..GETA MARK 3020 ; So # POSTAL MARK FACE @@ -3972,6 +4102,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 3190..3191 ; So # [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3196..319F ; So # [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK 31C0..31E3 ; So # [36] CJK STROKE T..CJK STROKE Q +31EF ; So # IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION 3200..321E ; So # [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU 322A..3247 ; So # [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO 3250 ; So # PARTNERSHIP SIGN @@ -3984,7 +4115,9 @@ A828..A82B ; So # [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK- A836..A837 ; So # [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK A839 ; So # NORTH INDIC QUANTITY MARK AA77..AA79 ; So # [3] MYANMAR SYMBOL AITON EXCLAMATION..MYANMAR SYMBOL AITON TWO -FDFD ; So # ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FD40..FD4F ; So # [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FDCF ; So # ARABIC LIGATURE SALAAMUHU ALAYNAA +FDFD..FDFF ; So # [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FFE4 ; So # FULLWIDTH BROKEN BAR FFE8 ; So # HALFWIDTH FORMS LIGHT VERTICAL FFED..FFEE ; So # [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE @@ -4003,13 +4136,14 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B3C..16B3F ; So # [4] PAHAWH HMONG SIGN XYEEM NTXIV..PAHAWH HMONG SIGN XYEEM FAIB 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS +1CF50..1CFC3 ; So # [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK 1D000..1D0F5 ; So # [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; So # [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; So # [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE 1D16A..1D16C ; So # [3] MUSICAL SYMBOL FINGERED TREMOLO-1..MUSICAL SYMBOL FINGERED TREMOLO-3 1D183..1D184 ; So # [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN 1D18C..1D1A9 ; So # [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH -1D1AE..1D1E8 ; So # [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN +1D1AE..1D1EA ; So # [61] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KORON 1D200..1D241 ; So # [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; So # GREEK MUSICAL LEIMMA 1D300..1D356 ; So # [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING @@ -4035,32 +4169,31 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F260..1F265 ; So # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; So # [251] CYCLONE..AMPHORA 1F400..1F6D7 ; So # [728] RAT..ELEVATOR -1F6E0..1F6EC ; So # [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F6DC..1F6EC ; So # [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; So # [13] SATELLITE..ROLLER SKATE -1F700..1F773 ; So # [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE -1F780..1F7D8 ; So # [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE +1F700..1F776 ; So # [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE +1F77B..1F7D9 ; So # [95] HAUMEA..NINE POINTED WHITE STAR 1F7E0..1F7EB ; So # [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F7F0 ; So # HEAVY EQUALS SIGN 1F800..1F80B ; So # [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD 1F810..1F847 ; So # [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW 1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8B1 ; So # [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST -1F900..1F978 ; So # [121] CIRCLED CROSS FORMEE WITH FOUR DOTS..DISGUISED FACE -1F97A..1F9CB ; So # [82] FACE WITH PLEADING EYES..BUBBLE TEA -1F9CD..1FA53 ; So # [135] STANDING PERSON..BLACK CHESS KNIGHT-BISHOP +1F900..1FA53 ; So # [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP 1FA60..1FA6D ; So # [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER -1FA70..1FA74 ; So # [5] BALLET SHOES..THONG SANDAL -1FA78..1FA7A ; So # [3] DROP OF BLOOD..STETHOSCOPE -1FA80..1FA86 ; So # [7] YO-YO..NESTING DOLLS -1FA90..1FAA8 ; So # [25] RINGED PLANET..ROCK -1FAB0..1FAB6 ; So # [7] FLY..FEATHER -1FAC0..1FAC2 ; So # [3] ANATOMICAL HEART..PEOPLE HUGGING -1FAD0..1FAD6 ; So # [7] BLUEBERRIES..TEAPOT +1FA70..1FA7C ; So # [13] BALLET SHOES..CRUTCH +1FA80..1FA88 ; So # [9] YO-YO..FLUTE +1FA90..1FABD ; So # [46] RINGED PLANET..WING +1FABF..1FAC5 ; So # [7] GOOSE..PERSON WITH CROWN +1FACE..1FADB ; So # [14] MOOSE..PEA POD +1FAE0..1FAE8 ; So # [9] MELTING FACE..SHAKING FACE +1FAF0..1FAF8 ; So # [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; So # [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 6431 +# Total code points: 6639 # ================================================ diff --git a/src/md4c.c b/src/md4c.c index be5e7fa4..5c00e471 100644 --- a/src/md4c.c +++ b/src/md4c.c @@ -573,33 +573,35 @@ struct MD_UNICODE_FOLD_INFO_tag { R(0x0021,0x0023), R(0x0025,0x002a), R(0x002c,0x002f), R(0x003a,0x003b), R(0x003f,0x0040), R(0x005b,0x005d), S(0x005f), S(0x007b), S(0x007d), S(0x00a1), S(0x00a7), S(0x00ab), R(0x00b6,0x00b7), S(0x00bb), S(0x00bf), S(0x037e), S(0x0387), R(0x055a,0x055f), R(0x0589,0x058a), S(0x05be), S(0x05c0), - S(0x05c3), S(0x05c6), R(0x05f3,0x05f4), R(0x0609,0x060a), R(0x060c,0x060d), S(0x061b), R(0x061e,0x061f), + S(0x05c3), S(0x05c6), R(0x05f3,0x05f4), R(0x0609,0x060a), R(0x060c,0x060d), S(0x061b), R(0x061d,0x061f), R(0x066a,0x066d), S(0x06d4), R(0x0700,0x070d), R(0x07f7,0x07f9), R(0x0830,0x083e), S(0x085e), R(0x0964,0x0965), S(0x0970), S(0x09fd), S(0x0a76), S(0x0af0), S(0x0c77), S(0x0c84), S(0x0df4), S(0x0e4f), R(0x0e5a,0x0e5b), R(0x0f04,0x0f12), S(0x0f14), R(0x0f3a,0x0f3d), S(0x0f85), R(0x0fd0,0x0fd4), R(0x0fd9,0x0fda), R(0x104a,0x104f), S(0x10fb), R(0x1360,0x1368), S(0x1400), S(0x166e), R(0x169b,0x169c), R(0x16eb,0x16ed), R(0x1735,0x1736), R(0x17d4,0x17d6), R(0x17d8,0x17da), R(0x1800,0x180a), R(0x1944,0x1945), R(0x1a1e,0x1a1f), R(0x1aa0,0x1aa6), R(0x1aa8,0x1aad), R(0x1b5a,0x1b60), - R(0x1bfc,0x1bff), R(0x1c3b,0x1c3f), R(0x1c7e,0x1c7f), R(0x1cc0,0x1cc7), S(0x1cd3), R(0x2010,0x2027), - R(0x2030,0x2043), R(0x2045,0x2051), R(0x2053,0x205e), R(0x207d,0x207e), R(0x208d,0x208e), - R(0x2308,0x230b), R(0x2329,0x232a), R(0x2768,0x2775), R(0x27c5,0x27c6), R(0x27e6,0x27ef), - R(0x2983,0x2998), R(0x29d8,0x29db), R(0x29fc,0x29fd), R(0x2cf9,0x2cfc), R(0x2cfe,0x2cff), S(0x2d70), - R(0x2e00,0x2e2e), R(0x2e30,0x2e4f), S(0x2e52), R(0x3001,0x3003), R(0x3008,0x3011), R(0x3014,0x301f), - S(0x3030), S(0x303d), S(0x30a0), S(0x30fb), R(0xa4fe,0xa4ff), R(0xa60d,0xa60f), S(0xa673), S(0xa67e), - R(0xa6f2,0xa6f7), R(0xa874,0xa877), R(0xa8ce,0xa8cf), R(0xa8f8,0xa8fa), S(0xa8fc), R(0xa92e,0xa92f), - S(0xa95f), R(0xa9c1,0xa9cd), R(0xa9de,0xa9df), R(0xaa5c,0xaa5f), R(0xaade,0xaadf), R(0xaaf0,0xaaf1), - S(0xabeb), R(0xfd3e,0xfd3f), R(0xfe10,0xfe19), R(0xfe30,0xfe52), R(0xfe54,0xfe61), S(0xfe63), S(0xfe68), - R(0xfe6a,0xfe6b), R(0xff01,0xff03), R(0xff05,0xff0a), R(0xff0c,0xff0f), R(0xff1a,0xff1b), - R(0xff1f,0xff20), R(0xff3b,0xff3d), S(0xff3f), S(0xff5b), S(0xff5d), R(0xff5f,0xff65), R(0x10100,0x10102), - S(0x1039f), S(0x103d0), S(0x1056f), S(0x10857), S(0x1091f), S(0x1093f), R(0x10a50,0x10a58), S(0x10a7f), - R(0x10af0,0x10af6), R(0x10b39,0x10b3f), R(0x10b99,0x10b9c), S(0x10ead), R(0x10f55,0x10f59), + R(0x1b7d,0x1b7e), R(0x1bfc,0x1bff), R(0x1c3b,0x1c3f), R(0x1c7e,0x1c7f), R(0x1cc0,0x1cc7), S(0x1cd3), + R(0x2010,0x2027), R(0x2030,0x2043), R(0x2045,0x2051), R(0x2053,0x205e), R(0x207d,0x207e), + R(0x208d,0x208e), R(0x2308,0x230b), R(0x2329,0x232a), R(0x2768,0x2775), R(0x27c5,0x27c6), + R(0x27e6,0x27ef), R(0x2983,0x2998), R(0x29d8,0x29db), R(0x29fc,0x29fd), R(0x2cf9,0x2cfc), + R(0x2cfe,0x2cff), S(0x2d70), R(0x2e00,0x2e2e), R(0x2e30,0x2e4f), R(0x2e52,0x2e5d), R(0x3001,0x3003), + R(0x3008,0x3011), R(0x3014,0x301f), S(0x3030), S(0x303d), S(0x30a0), S(0x30fb), R(0xa4fe,0xa4ff), + R(0xa60d,0xa60f), S(0xa673), S(0xa67e), R(0xa6f2,0xa6f7), R(0xa874,0xa877), R(0xa8ce,0xa8cf), + R(0xa8f8,0xa8fa), S(0xa8fc), R(0xa92e,0xa92f), S(0xa95f), R(0xa9c1,0xa9cd), R(0xa9de,0xa9df), + R(0xaa5c,0xaa5f), R(0xaade,0xaadf), R(0xaaf0,0xaaf1), S(0xabeb), R(0xfd3e,0xfd3f), R(0xfe10,0xfe19), + R(0xfe30,0xfe52), R(0xfe54,0xfe61), S(0xfe63), S(0xfe68), R(0xfe6a,0xfe6b), R(0xff01,0xff03), + R(0xff05,0xff0a), R(0xff0c,0xff0f), R(0xff1a,0xff1b), R(0xff1f,0xff20), R(0xff3b,0xff3d), S(0xff3f), + S(0xff5b), S(0xff5d), R(0xff5f,0xff65), R(0x10100,0x10102), S(0x1039f), S(0x103d0), S(0x1056f), + S(0x10857), S(0x1091f), S(0x1093f), R(0x10a50,0x10a58), S(0x10a7f), R(0x10af0,0x10af6), + R(0x10b39,0x10b3f), R(0x10b99,0x10b9c), S(0x10ead), R(0x10f55,0x10f59), R(0x10f86,0x10f89), R(0x11047,0x1104d), R(0x110bb,0x110bc), R(0x110be,0x110c1), R(0x11140,0x11143), R(0x11174,0x11175), R(0x111c5,0x111c8), S(0x111cd), S(0x111db), R(0x111dd,0x111df), R(0x11238,0x1123d), S(0x112a9), R(0x1144b,0x1144f), R(0x1145a,0x1145b), S(0x1145d), S(0x114c6), R(0x115c1,0x115d7), R(0x11641,0x11643), - R(0x11660,0x1166c), R(0x1173c,0x1173e), S(0x1183b), R(0x11944,0x11946), S(0x119e2), R(0x11a3f,0x11a46), - R(0x11a9a,0x11a9c), R(0x11a9e,0x11aa2), R(0x11c41,0x11c45), R(0x11c70,0x11c71), R(0x11ef7,0x11ef8), - S(0x11fff), R(0x12470,0x12474), R(0x16a6e,0x16a6f), S(0x16af5), R(0x16b37,0x16b3b), S(0x16b44), - R(0x16e97,0x16e9a), S(0x16fe2), S(0x1bc9f), R(0x1da87,0x1da8b), R(0x1e95e,0x1e95f) + R(0x11660,0x1166c), S(0x116b9), R(0x1173c,0x1173e), S(0x1183b), R(0x11944,0x11946), S(0x119e2), + R(0x11a3f,0x11a46), R(0x11a9a,0x11a9c), R(0x11a9e,0x11aa2), R(0x11b00,0x11b09), R(0x11c41,0x11c45), + R(0x11c70,0x11c71), R(0x11ef7,0x11ef8), R(0x11f43,0x11f4f), S(0x11fff), R(0x12470,0x12474), + R(0x12ff1,0x12ff2), R(0x16a6e,0x16a6f), S(0x16af5), R(0x16b37,0x16b3b), S(0x16b44), R(0x16e97,0x16e9a), + S(0x16fe2), S(0x1bc9f), R(0x1da87,0x1da8b), R(0x1e95e,0x1e95f) }; #undef R #undef S @@ -619,88 +621,89 @@ struct MD_UNICODE_FOLD_INFO_tag { #define S(cp) (cp) /* Unicode "Pc", "Pd", "Pe", "Pf", "Pi", "Po", "Ps" categories. * (generated by scripts/build_folding_map.py) */ - static const unsigned FOLD_MAP_1[] = { - R(0x0041,0x005a), S(0x00b5), R(0x00c0,0x00d6), R(0x00d8,0x00de), R(0x0100,0x012e), R(0x0132,0x0136), - R(0x0139,0x0147), R(0x014a,0x0176), S(0x0178), R(0x0179,0x017d), S(0x017f), S(0x0181), S(0x0182), - S(0x0184), S(0x0186), S(0x0187), S(0x0189), S(0x018a), S(0x018b), S(0x018e), S(0x018f), S(0x0190), - S(0x0191), S(0x0193), S(0x0194), S(0x0196), S(0x0197), S(0x0198), S(0x019c), S(0x019d), S(0x019f), - R(0x01a0,0x01a4), S(0x01a6), S(0x01a7), S(0x01a9), S(0x01ac), S(0x01ae), S(0x01af), S(0x01b1), S(0x01b2), - S(0x01b3), S(0x01b5), S(0x01b7), S(0x01b8), S(0x01bc), S(0x01c4), S(0x01c5), S(0x01c7), S(0x01c8), - S(0x01ca), R(0x01cb,0x01db), R(0x01de,0x01ee), S(0x01f1), S(0x01f2), S(0x01f4), S(0x01f6), S(0x01f7), - R(0x01f8,0x021e), S(0x0220), R(0x0222,0x0232), S(0x023a), S(0x023b), S(0x023d), S(0x023e), S(0x0241), - S(0x0243), S(0x0244), S(0x0245), R(0x0246,0x024e), S(0x0345), S(0x0370), S(0x0372), S(0x0376), S(0x037f), - S(0x0386), R(0x0388,0x038a), S(0x038c), S(0x038e), S(0x038f), R(0x0391,0x03a1), R(0x03a3,0x03ab), - S(0x03c2), S(0x03cf), S(0x03d0), S(0x03d1), S(0x03d5), S(0x03d6), R(0x03d8,0x03ee), S(0x03f0), S(0x03f1), - S(0x03f4), S(0x03f5), S(0x03f7), S(0x03f9), S(0x03fa), R(0x03fd,0x03ff), R(0x0400,0x040f), - R(0x0410,0x042f), R(0x0460,0x0480), R(0x048a,0x04be), S(0x04c0), R(0x04c1,0x04cd), R(0x04d0,0x052e), - R(0x0531,0x0556), R(0x10a0,0x10c5), S(0x10c7), S(0x10cd), R(0x13f8,0x13fd), S(0x1c80), S(0x1c81), - S(0x1c82), S(0x1c83), S(0x1c84), S(0x1c85), S(0x1c86), S(0x1c87), S(0x1c88), R(0x1c90,0x1cba), - R(0x1cbd,0x1cbf), R(0x1e00,0x1e94), S(0x1e9b), R(0x1ea0,0x1efe), R(0x1f08,0x1f0f), R(0x1f18,0x1f1d), - R(0x1f28,0x1f2f), R(0x1f38,0x1f3f), R(0x1f48,0x1f4d), S(0x1f59), S(0x1f5b), S(0x1f5d), S(0x1f5f), - R(0x1f68,0x1f6f), S(0x1fb8), S(0x1fb9), S(0x1fba), S(0x1fbb), S(0x1fbe), R(0x1fc8,0x1fcb), S(0x1fd8), - S(0x1fd9), S(0x1fda), S(0x1fdb), S(0x1fe8), S(0x1fe9), S(0x1fea), S(0x1feb), S(0x1fec), S(0x1ff8), - S(0x1ff9), S(0x1ffa), S(0x1ffb), S(0x2126), S(0x212a), S(0x212b), S(0x2132), R(0x2160,0x216f), S(0x2183), - R(0x24b6,0x24cf), R(0x2c00,0x2c2e), S(0x2c60), S(0x2c62), S(0x2c63), S(0x2c64), R(0x2c67,0x2c6b), - S(0x2c6d), S(0x2c6e), S(0x2c6f), S(0x2c70), S(0x2c72), S(0x2c75), S(0x2c7e), S(0x2c7f), R(0x2c80,0x2ce2), - S(0x2ceb), S(0x2ced), S(0x2cf2), R(0xa640,0xa66c), R(0xa680,0xa69a), R(0xa722,0xa72e), R(0xa732,0xa76e), - S(0xa779), S(0xa77b), S(0xa77d), R(0xa77e,0xa786), S(0xa78b), S(0xa78d), S(0xa790), S(0xa792), - R(0xa796,0xa7a8), S(0xa7aa), S(0xa7ab), S(0xa7ac), S(0xa7ad), S(0xa7ae), S(0xa7b0), S(0xa7b1), S(0xa7b2), - S(0xa7b3), R(0xa7b4,0xa7be), S(0xa7c2), S(0xa7c4), S(0xa7c5), S(0xa7c6), S(0xa7c7), S(0xa7c9), S(0xa7f5), - R(0xab70,0xabbf), R(0xff21,0xff3a), R(0x10400,0x10427), R(0x104b0,0x104d3), R(0x10c80,0x10cb2), - R(0x118a0,0x118bf), R(0x16e40,0x16e5f), R(0x1e900,0x1e921) - }; - static const unsigned FOLD_MAP_1_DATA[] = { - 0x0061, 0x007a, 0x03bc, 0x00e0, 0x00f6, 0x00f8, 0x00fe, 0x0101, 0x012f, 0x0133, 0x0137, 0x013a, 0x0148, - 0x014b, 0x0177, 0x00ff, 0x017a, 0x017e, 0x0073, 0x0253, 0x0183, 0x0185, 0x0254, 0x0188, 0x0256, 0x0257, - 0x018c, 0x01dd, 0x0259, 0x025b, 0x0192, 0x0260, 0x0263, 0x0269, 0x0268, 0x0199, 0x026f, 0x0272, 0x0275, - 0x01a1, 0x01a5, 0x0280, 0x01a8, 0x0283, 0x01ad, 0x0288, 0x01b0, 0x028a, 0x028b, 0x01b4, 0x01b6, 0x0292, - 0x01b9, 0x01bd, 0x01c6, 0x01c6, 0x01c9, 0x01c9, 0x01cc, 0x01cc, 0x01dc, 0x01df, 0x01ef, 0x01f3, 0x01f3, - 0x01f5, 0x0195, 0x01bf, 0x01f9, 0x021f, 0x019e, 0x0223, 0x0233, 0x2c65, 0x023c, 0x019a, 0x2c66, 0x0242, - 0x0180, 0x0289, 0x028c, 0x0247, 0x024f, 0x03b9, 0x0371, 0x0373, 0x0377, 0x03f3, 0x03ac, 0x03ad, 0x03af, - 0x03cc, 0x03cd, 0x03ce, 0x03b1, 0x03c1, 0x03c3, 0x03cb, 0x03c3, 0x03d7, 0x03b2, 0x03b8, 0x03c6, 0x03c0, - 0x03d9, 0x03ef, 0x03ba, 0x03c1, 0x03b8, 0x03b5, 0x03f8, 0x03f2, 0x03fb, 0x037b, 0x037d, 0x0450, 0x045f, - 0x0430, 0x044f, 0x0461, 0x0481, 0x048b, 0x04bf, 0x04cf, 0x04c2, 0x04ce, 0x04d1, 0x052f, 0x0561, 0x0586, - 0x2d00, 0x2d25, 0x2d27, 0x2d2d, 0x13f0, 0x13f5, 0x0432, 0x0434, 0x043e, 0x0441, 0x0442, 0x0442, 0x044a, - 0x0463, 0xa64b, 0x10d0, 0x10fa, 0x10fd, 0x10ff, 0x1e01, 0x1e95, 0x1e61, 0x1ea1, 0x1eff, 0x1f00, 0x1f07, - 0x1f10, 0x1f15, 0x1f20, 0x1f27, 0x1f30, 0x1f37, 0x1f40, 0x1f45, 0x1f51, 0x1f53, 0x1f55, 0x1f57, 0x1f60, - 0x1f67, 0x1fb0, 0x1fb1, 0x1f70, 0x1f71, 0x03b9, 0x1f72, 0x1f75, 0x1fd0, 0x1fd1, 0x1f76, 0x1f77, 0x1fe0, - 0x1fe1, 0x1f7a, 0x1f7b, 0x1fe5, 0x1f78, 0x1f79, 0x1f7c, 0x1f7d, 0x03c9, 0x006b, 0x00e5, 0x214e, 0x2170, - 0x217f, 0x2184, 0x24d0, 0x24e9, 0x2c30, 0x2c5e, 0x2c61, 0x026b, 0x1d7d, 0x027d, 0x2c68, 0x2c6c, 0x0251, - 0x0271, 0x0250, 0x0252, 0x2c73, 0x2c76, 0x023f, 0x0240, 0x2c81, 0x2ce3, 0x2cec, 0x2cee, 0x2cf3, 0xa641, - 0xa66d, 0xa681, 0xa69b, 0xa723, 0xa72f, 0xa733, 0xa76f, 0xa77a, 0xa77c, 0x1d79, 0xa77f, 0xa787, 0xa78c, - 0x0265, 0xa791, 0xa793, 0xa797, 0xa7a9, 0x0266, 0x025c, 0x0261, 0x026c, 0x026a, 0x029e, 0x0287, 0x029d, - 0xab53, 0xa7b5, 0xa7bf, 0xa7c3, 0xa794, 0x0282, 0x1d8e, 0xa7c8, 0xa7ca, 0xa7f6, 0x13a0, 0x13ef, 0xff41, - 0xff5a, 0x10428, 0x1044f, 0x104d8, 0x104fb, 0x10cc0, 0x10cf2, 0x118c0, 0x118df, 0x16e60, 0x16e7f, 0x1e922, - 0x1e943 - }; - static const unsigned FOLD_MAP_2[] = { - S(0x00df), S(0x0130), S(0x0149), S(0x01f0), S(0x0587), S(0x1e96), S(0x1e97), S(0x1e98), S(0x1e99), - S(0x1e9a), S(0x1e9e), S(0x1f50), R(0x1f80,0x1f87), R(0x1f88,0x1f8f), R(0x1f90,0x1f97), R(0x1f98,0x1f9f), - R(0x1fa0,0x1fa7), R(0x1fa8,0x1faf), S(0x1fb2), S(0x1fb3), S(0x1fb4), S(0x1fb6), S(0x1fbc), S(0x1fc2), - S(0x1fc3), S(0x1fc4), S(0x1fc6), S(0x1fcc), S(0x1fd6), S(0x1fe4), S(0x1fe6), S(0x1ff2), S(0x1ff3), - S(0x1ff4), S(0x1ff6), S(0x1ffc), S(0xfb00), S(0xfb01), S(0xfb02), S(0xfb05), S(0xfb06), S(0xfb13), - S(0xfb14), S(0xfb15), S(0xfb16), S(0xfb17) - }; - static const unsigned FOLD_MAP_2_DATA[] = { - 0x0073,0x0073, 0x0069,0x0307, 0x02bc,0x006e, 0x006a,0x030c, 0x0565,0x0582, 0x0068,0x0331, 0x0074,0x0308, - 0x0077,0x030a, 0x0079,0x030a, 0x0061,0x02be, 0x0073,0x0073, 0x03c5,0x0313, 0x1f00,0x03b9, 0x1f07,0x03b9, - 0x1f00,0x03b9, 0x1f07,0x03b9, 0x1f20,0x03b9, 0x1f27,0x03b9, 0x1f20,0x03b9, 0x1f27,0x03b9, 0x1f60,0x03b9, - 0x1f67,0x03b9, 0x1f60,0x03b9, 0x1f67,0x03b9, 0x1f70,0x03b9, 0x03b1,0x03b9, 0x03ac,0x03b9, 0x03b1,0x0342, - 0x03b1,0x03b9, 0x1f74,0x03b9, 0x03b7,0x03b9, 0x03ae,0x03b9, 0x03b7,0x0342, 0x03b7,0x03b9, 0x03b9,0x0342, - 0x03c1,0x0313, 0x03c5,0x0342, 0x1f7c,0x03b9, 0x03c9,0x03b9, 0x03ce,0x03b9, 0x03c9,0x0342, 0x03c9,0x03b9, - 0x0066,0x0066, 0x0066,0x0069, 0x0066,0x006c, 0x0073,0x0074, 0x0073,0x0074, 0x0574,0x0576, 0x0574,0x0565, - 0x0574,0x056b, 0x057e,0x0576, 0x0574,0x056d - }; - static const unsigned FOLD_MAP_3[] = { - S(0x0390), S(0x03b0), S(0x1f52), S(0x1f54), S(0x1f56), S(0x1fb7), S(0x1fc7), S(0x1fd2), S(0x1fd3), - S(0x1fd7), S(0x1fe2), S(0x1fe3), S(0x1fe7), S(0x1ff7), S(0xfb03), S(0xfb04) - }; - static const unsigned FOLD_MAP_3_DATA[] = { - 0x03b9,0x0308,0x0301, 0x03c5,0x0308,0x0301, 0x03c5,0x0313,0x0300, 0x03c5,0x0313,0x0301, - 0x03c5,0x0313,0x0342, 0x03b1,0x0342,0x03b9, 0x03b7,0x0342,0x03b9, 0x03b9,0x0308,0x0300, - 0x03b9,0x0308,0x0301, 0x03b9,0x0308,0x0342, 0x03c5,0x0308,0x0300, 0x03c5,0x0308,0x0301, - 0x03c5,0x0308,0x0342, 0x03c9,0x0342,0x03b9, 0x0066,0x0066,0x0069, 0x0066,0x0066,0x006c - }; +static const unsigned FOLD_MAP_1[] = { + R(0x0041,0x005a), S(0x00b5), R(0x00c0,0x00d6), R(0x00d8,0x00de), R(0x0100,0x012e), R(0x0132,0x0136), + R(0x0139,0x0147), R(0x014a,0x0176), S(0x0178), R(0x0179,0x017d), S(0x017f), S(0x0181), S(0x0182), + S(0x0184), S(0x0186), S(0x0187), S(0x0189), S(0x018a), S(0x018b), S(0x018e), S(0x018f), S(0x0190), + S(0x0191), S(0x0193), S(0x0194), S(0x0196), S(0x0197), S(0x0198), S(0x019c), S(0x019d), S(0x019f), + R(0x01a0,0x01a4), S(0x01a6), S(0x01a7), S(0x01a9), S(0x01ac), S(0x01ae), S(0x01af), S(0x01b1), S(0x01b2), + S(0x01b3), S(0x01b5), S(0x01b7), S(0x01b8), S(0x01bc), S(0x01c4), S(0x01c5), S(0x01c7), S(0x01c8), + S(0x01ca), R(0x01cb,0x01db), R(0x01de,0x01ee), S(0x01f1), S(0x01f2), S(0x01f4), S(0x01f6), S(0x01f7), + R(0x01f8,0x021e), S(0x0220), R(0x0222,0x0232), S(0x023a), S(0x023b), S(0x023d), S(0x023e), S(0x0241), + S(0x0243), S(0x0244), S(0x0245), R(0x0246,0x024e), S(0x0345), S(0x0370), S(0x0372), S(0x0376), S(0x037f), + S(0x0386), R(0x0388,0x038a), S(0x038c), S(0x038e), S(0x038f), R(0x0391,0x03a1), R(0x03a3,0x03ab), + S(0x03c2), S(0x03cf), S(0x03d0), S(0x03d1), S(0x03d5), S(0x03d6), R(0x03d8,0x03ee), S(0x03f0), S(0x03f1), + S(0x03f4), S(0x03f5), S(0x03f7), S(0x03f9), S(0x03fa), R(0x03fd,0x03ff), R(0x0400,0x040f), + R(0x0410,0x042f), R(0x0460,0x0480), R(0x048a,0x04be), S(0x04c0), R(0x04c1,0x04cd), R(0x04d0,0x052e), + R(0x0531,0x0556), R(0x10a0,0x10c5), S(0x10c7), S(0x10cd), R(0x13f8,0x13fd), S(0x1c80), S(0x1c81), + S(0x1c82), S(0x1c83), S(0x1c84), S(0x1c85), S(0x1c86), S(0x1c87), S(0x1c88), R(0x1c90,0x1cba), + R(0x1cbd,0x1cbf), R(0x1e00,0x1e94), S(0x1e9b), R(0x1ea0,0x1efe), R(0x1f08,0x1f0f), R(0x1f18,0x1f1d), + R(0x1f28,0x1f2f), R(0x1f38,0x1f3f), R(0x1f48,0x1f4d), S(0x1f59), S(0x1f5b), S(0x1f5d), S(0x1f5f), + R(0x1f68,0x1f6f), S(0x1fb8), S(0x1fb9), S(0x1fba), S(0x1fbb), S(0x1fbe), R(0x1fc8,0x1fcb), S(0x1fd8), + S(0x1fd9), S(0x1fda), S(0x1fdb), S(0x1fe8), S(0x1fe9), S(0x1fea), S(0x1feb), S(0x1fec), S(0x1ff8), + S(0x1ff9), S(0x1ffa), S(0x1ffb), S(0x2126), S(0x212a), S(0x212b), S(0x2132), R(0x2160,0x216f), S(0x2183), + R(0x24b6,0x24cf), R(0x2c00,0x2c2f), S(0x2c60), S(0x2c62), S(0x2c63), S(0x2c64), R(0x2c67,0x2c6b), + S(0x2c6d), S(0x2c6e), S(0x2c6f), S(0x2c70), S(0x2c72), S(0x2c75), S(0x2c7e), S(0x2c7f), R(0x2c80,0x2ce2), + S(0x2ceb), S(0x2ced), S(0x2cf2), R(0xa640,0xa66c), R(0xa680,0xa69a), R(0xa722,0xa72e), R(0xa732,0xa76e), + S(0xa779), S(0xa77b), S(0xa77d), R(0xa77e,0xa786), S(0xa78b), S(0xa78d), S(0xa790), S(0xa792), + R(0xa796,0xa7a8), S(0xa7aa), S(0xa7ab), S(0xa7ac), S(0xa7ad), S(0xa7ae), S(0xa7b0), S(0xa7b1), S(0xa7b2), + S(0xa7b3), R(0xa7b4,0xa7c2), S(0xa7c4), S(0xa7c5), S(0xa7c6), S(0xa7c7), S(0xa7c9), S(0xa7d0), S(0xa7d6), + S(0xa7d8), S(0xa7f5), R(0xab70,0xabbf), R(0xff21,0xff3a), R(0x10400,0x10427), R(0x104b0,0x104d3), + R(0x10570,0x1057a), R(0x1057c,0x1058a), R(0x1058c,0x10592), S(0x10594), S(0x10595), R(0x10c80,0x10cb2), + R(0x118a0,0x118bf), R(0x16e40,0x16e5f), R(0x1e900,0x1e921) +}; +static const unsigned FOLD_MAP_1_DATA[] = { + 0x0061, 0x007a, 0x03bc, 0x00e0, 0x00f6, 0x00f8, 0x00fe, 0x0101, 0x012f, 0x0133, 0x0137, 0x013a, 0x0148, + 0x014b, 0x0177, 0x00ff, 0x017a, 0x017e, 0x0073, 0x0253, 0x0183, 0x0185, 0x0254, 0x0188, 0x0256, 0x0257, + 0x018c, 0x01dd, 0x0259, 0x025b, 0x0192, 0x0260, 0x0263, 0x0269, 0x0268, 0x0199, 0x026f, 0x0272, 0x0275, + 0x01a1, 0x01a5, 0x0280, 0x01a8, 0x0283, 0x01ad, 0x0288, 0x01b0, 0x028a, 0x028b, 0x01b4, 0x01b6, 0x0292, + 0x01b9, 0x01bd, 0x01c6, 0x01c6, 0x01c9, 0x01c9, 0x01cc, 0x01cc, 0x01dc, 0x01df, 0x01ef, 0x01f3, 0x01f3, + 0x01f5, 0x0195, 0x01bf, 0x01f9, 0x021f, 0x019e, 0x0223, 0x0233, 0x2c65, 0x023c, 0x019a, 0x2c66, 0x0242, + 0x0180, 0x0289, 0x028c, 0x0247, 0x024f, 0x03b9, 0x0371, 0x0373, 0x0377, 0x03f3, 0x03ac, 0x03ad, 0x03af, + 0x03cc, 0x03cd, 0x03ce, 0x03b1, 0x03c1, 0x03c3, 0x03cb, 0x03c3, 0x03d7, 0x03b2, 0x03b8, 0x03c6, 0x03c0, + 0x03d9, 0x03ef, 0x03ba, 0x03c1, 0x03b8, 0x03b5, 0x03f8, 0x03f2, 0x03fb, 0x037b, 0x037d, 0x0450, 0x045f, + 0x0430, 0x044f, 0x0461, 0x0481, 0x048b, 0x04bf, 0x04cf, 0x04c2, 0x04ce, 0x04d1, 0x052f, 0x0561, 0x0586, + 0x2d00, 0x2d25, 0x2d27, 0x2d2d, 0x13f0, 0x13f5, 0x0432, 0x0434, 0x043e, 0x0441, 0x0442, 0x0442, 0x044a, + 0x0463, 0xa64b, 0x10d0, 0x10fa, 0x10fd, 0x10ff, 0x1e01, 0x1e95, 0x1e61, 0x1ea1, 0x1eff, 0x1f00, 0x1f07, + 0x1f10, 0x1f15, 0x1f20, 0x1f27, 0x1f30, 0x1f37, 0x1f40, 0x1f45, 0x1f51, 0x1f53, 0x1f55, 0x1f57, 0x1f60, + 0x1f67, 0x1fb0, 0x1fb1, 0x1f70, 0x1f71, 0x03b9, 0x1f72, 0x1f75, 0x1fd0, 0x1fd1, 0x1f76, 0x1f77, 0x1fe0, + 0x1fe1, 0x1f7a, 0x1f7b, 0x1fe5, 0x1f78, 0x1f79, 0x1f7c, 0x1f7d, 0x03c9, 0x006b, 0x00e5, 0x214e, 0x2170, + 0x217f, 0x2184, 0x24d0, 0x24e9, 0x2c30, 0x2c5f, 0x2c61, 0x026b, 0x1d7d, 0x027d, 0x2c68, 0x2c6c, 0x0251, + 0x0271, 0x0250, 0x0252, 0x2c73, 0x2c76, 0x023f, 0x0240, 0x2c81, 0x2ce3, 0x2cec, 0x2cee, 0x2cf3, 0xa641, + 0xa66d, 0xa681, 0xa69b, 0xa723, 0xa72f, 0xa733, 0xa76f, 0xa77a, 0xa77c, 0x1d79, 0xa77f, 0xa787, 0xa78c, + 0x0265, 0xa791, 0xa793, 0xa797, 0xa7a9, 0x0266, 0x025c, 0x0261, 0x026c, 0x026a, 0x029e, 0x0287, 0x029d, + 0xab53, 0xa7b5, 0xa7c3, 0xa794, 0x0282, 0x1d8e, 0xa7c8, 0xa7ca, 0xa7d1, 0xa7d7, 0xa7d9, 0xa7f6, 0x13a0, + 0x13ef, 0xff41, 0xff5a, 0x10428, 0x1044f, 0x104d8, 0x104fb, 0x10597, 0x105a1, 0x105a3, 0x105b1, 0x105b3, + 0x105b9, 0x105bb, 0x105bc, 0x10cc0, 0x10cf2, 0x118c0, 0x118df, 0x16e60, 0x16e7f, 0x1e922, 0x1e943 +}; +static const unsigned FOLD_MAP_2[] = { + S(0x00df), S(0x0130), S(0x0149), S(0x01f0), S(0x0587), S(0x1e96), S(0x1e97), S(0x1e98), S(0x1e99), + S(0x1e9a), S(0x1e9e), S(0x1f50), R(0x1f80,0x1f87), R(0x1f88,0x1f8f), R(0x1f90,0x1f97), R(0x1f98,0x1f9f), + R(0x1fa0,0x1fa7), R(0x1fa8,0x1faf), S(0x1fb2), S(0x1fb3), S(0x1fb4), S(0x1fb6), S(0x1fbc), S(0x1fc2), + S(0x1fc3), S(0x1fc4), S(0x1fc6), S(0x1fcc), S(0x1fd6), S(0x1fe4), S(0x1fe6), S(0x1ff2), S(0x1ff3), + S(0x1ff4), S(0x1ff6), S(0x1ffc), S(0xfb00), S(0xfb01), S(0xfb02), S(0xfb05), S(0xfb06), S(0xfb13), + S(0xfb14), S(0xfb15), S(0xfb16), S(0xfb17) +}; +static const unsigned FOLD_MAP_2_DATA[] = { + 0x0073,0x0073, 0x0069,0x0307, 0x02bc,0x006e, 0x006a,0x030c, 0x0565,0x0582, 0x0068,0x0331, 0x0074,0x0308, + 0x0077,0x030a, 0x0079,0x030a, 0x0061,0x02be, 0x0073,0x0073, 0x03c5,0x0313, 0x1f00,0x03b9, 0x1f07,0x03b9, + 0x1f00,0x03b9, 0x1f07,0x03b9, 0x1f20,0x03b9, 0x1f27,0x03b9, 0x1f20,0x03b9, 0x1f27,0x03b9, 0x1f60,0x03b9, + 0x1f67,0x03b9, 0x1f60,0x03b9, 0x1f67,0x03b9, 0x1f70,0x03b9, 0x03b1,0x03b9, 0x03ac,0x03b9, 0x03b1,0x0342, + 0x03b1,0x03b9, 0x1f74,0x03b9, 0x03b7,0x03b9, 0x03ae,0x03b9, 0x03b7,0x0342, 0x03b7,0x03b9, 0x03b9,0x0342, + 0x03c1,0x0313, 0x03c5,0x0342, 0x1f7c,0x03b9, 0x03c9,0x03b9, 0x03ce,0x03b9, 0x03c9,0x0342, 0x03c9,0x03b9, + 0x0066,0x0066, 0x0066,0x0069, 0x0066,0x006c, 0x0073,0x0074, 0x0073,0x0074, 0x0574,0x0576, 0x0574,0x0565, + 0x0574,0x056b, 0x057e,0x0576, 0x0574,0x056d +}; +static const unsigned FOLD_MAP_3[] = { + S(0x0390), S(0x03b0), S(0x1f52), S(0x1f54), S(0x1f56), S(0x1fb7), S(0x1fc7), S(0x1fd2), S(0x1fd3), + S(0x1fd7), S(0x1fe2), S(0x1fe3), S(0x1fe7), S(0x1ff7), S(0xfb03), S(0xfb04) +}; +static const unsigned FOLD_MAP_3_DATA[] = { + 0x03b9,0x0308,0x0301, 0x03c5,0x0308,0x0301, 0x03c5,0x0313,0x0300, 0x03c5,0x0313,0x0301, + 0x03c5,0x0313,0x0342, 0x03b1,0x0342,0x03b9, 0x03b7,0x0342,0x03b9, 0x03b9,0x0308,0x0300, + 0x03b9,0x0308,0x0301, 0x03b9,0x0308,0x0342, 0x03c5,0x0308,0x0300, 0x03c5,0x0308,0x0301, + 0x03c5,0x0308,0x0342, 0x03c9,0x0342,0x03b9, 0x0066,0x0066,0x0069, 0x0066,0x0066,0x006c +}; #undef R #undef S static const struct {