From ed149f864398309d22fd44ea20a2931d7dd6577e Mon Sep 17 00:00:00 2001 From: rebecca <802632-arkandos@users.noreply.gitlab.com> Date: Sun, 1 Feb 2026 13:09:39 +0100 Subject: [PATCH] update to unicode 17, add is_tty --- data/DerivedCoreProperties.txt | 599 ++++++++++++++++++++++---------- data/DerivedGeneralCategory.txt | 203 ++++++----- data/EastAsianWidth.txt | 109 ++++-- data/HangulSyllableType.txt | 6 +- data/PropList.txt | 72 ++-- data/emoji-data.txt | 148 +++----- data/update.sh | 12 +- {test => dev}/benchmark.gleam | 3 +- flake.lock | 23 -- flake.nix | 89 ----- gleam.toml | 1 + manifest.toml | 10 +- src/string_width.gleam | 257 ++++---------- src/string_width_ffi.erl | 64 ++-- src/string_width_ffi.mjs | 66 ++-- test/columns.gleam | 4 +- test/generate.gleam | 14 +- test/string_width_test.gleam | 11 +- 18 files changed, 879 insertions(+), 812 deletions(-) rename {test => dev}/benchmark.gleam (88%) delete mode 100644 flake.lock delete mode 100644 flake.nix diff --git a/data/DerivedCoreProperties.txt b/data/DerivedCoreProperties.txt index 1075638..f327784 100644 --- a/data/DerivedCoreProperties.txt +++ b/data/DerivedCoreProperties.txt @@ -1,6 +1,6 @@ -# DerivedCoreProperties-16.0.0.txt -# Date: 2024-05-31, 18:09:32 GMT -# © 2024 Unicode®, Inc. +# DerivedCoreProperties-17.0.0.txt +# Date: 2025-07-30, 23:55:08 GMT +# © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html # @@ -178,6 +178,7 @@ FF5E ; Math # Sm FULLWIDTH TILDE FFE2 ; Math # Sm FULLWIDTH NOT SIGN FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 10D8E..10D8F ; Math # Sm [2] GARAY PLUS SIGN..GARAY MINUS SIGN +1CEF0 ; Math # Sm MEDIUM SMALL WHITE CIRCLE WITH HORIZONTAL BAR 1D400..1D454 ; Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G 1D456..1D49C ; Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A 1D49E..1D49F ; Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D @@ -253,8 +254,9 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1EEA5..1EEA9 ; Math # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; Math # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Math # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL +1F8D0..1F8D8 ; Math # Sm [9] LONG RIGHTWARDS ARROW OVER LONG LEFTWARDS ARROW..LONG LEFT RIGHT ARROW WITH DEPENDENT LOBE -# Total code points: 2312 +# Total code points: 2322 # ================================================ @@ -273,8 +275,8 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 01BC..01BF ; Alphabetic # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; Alphabetic # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; Alphabetic # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; Alphabetic # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; Alphabetic # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; Alphabetic # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; Alphabetic # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; Alphabetic # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; Alphabetic # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; Alphabetic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -344,7 +346,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; Alphabetic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; Alphabetic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; Alphabetic # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0897 ; Alphabetic # Mn ARABIC PEPET 08A0..08C8 ; Alphabetic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; Alphabetic # Lm ARABIC SMALL FARSI YEH @@ -477,7 +479,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0C4A..0C4C ; Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C55..0C56 ; Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Alphabetic # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; Alphabetic # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; Alphabetic # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Alphabetic # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C80 ; Alphabetic # Lo KANNADA SIGN SPACING CANDRABINDU @@ -497,7 +499,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CCA..0CCB ; Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; Alphabetic # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; Alphabetic # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -833,11 +835,8 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; Alphabetic # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Alphabetic # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; Alphabetic # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; Alphabetic # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; Alphabetic # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1020,6 +1019,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 108F4..108F5 ; Alphabetic # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; Alphabetic # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; Alphabetic # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..10959 ; Alphabetic # Lo [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..109B7 ; Alphabetic # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; Alphabetic # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; Alphabetic # Lo KHAROSHTHI LETTER A @@ -1053,7 +1053,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10EAB..10EAC ; Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; Alphabetic # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Alphabetic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC ; Alphabetic # Mn ARABIC COMBINING ALEF OVERLAY +10EC5 ; Alphabetic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6..10EC7 ; Alphabetic # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW +10EFA..10EFC ; Alphabetic # Mn [3] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1239,6 +1241,12 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA 11A9D ; Alphabetic # Lo SOYOMBO MARK PLUTA 11AB0..11AF8 ; Alphabetic # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL +11B60 ; Alphabetic # Mn SHARADA VOWEL SIGN OE +11B61 ; Alphabetic # Mc SHARADA VOWEL SIGN OOE +11B62..11B64 ; Alphabetic # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B65 ; Alphabetic # Mc SHARADA VOWEL SIGN SHORT O +11B66 ; Alphabetic # Mn SHARADA VOWEL SIGN CANDRA E +11B67 ; Alphabetic # Mc SHARADA VOWEL SIGN CANDRA O 11BC0..11BE0 ; Alphabetic # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO 11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA @@ -1274,6 +1282,9 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11D95 ; Alphabetic # Mn GUNJALA GONDI SIGN ANUSVARA 11D96 ; Alphabetic # Mc GUNJALA GONDI SIGN VISARGA 11D98 ; Alphabetic # Lo GUNJALA GONDI OM +11DB0..11DD8 ; Alphabetic # Lo [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DD9 ; Alphabetic # Lm TOLONG SIKI SIGN SELA +11DDA..11DDB ; Alphabetic # Lo [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA 11EE0..11EF2 ; Alphabetic # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; Alphabetic # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; Alphabetic # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O @@ -1311,6 +1322,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16D43..16D6A ; Alphabetic # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; Alphabetic # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; Alphabetic # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; Alphabetic # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; Alphabetic # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16F00..16F4A ; Alphabetic # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; Alphabetic # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F50 ; Alphabetic # Lo MIAO LETTER NASALIZATION @@ -1320,9 +1333,11 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16FE0..16FE1 ; Alphabetic # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Alphabetic # Lm OLD CHINESE ITERATION MARK 16FF0..16FF1 ; Alphabetic # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY -17000..187F7 ; Alphabetic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; Alphabetic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; Alphabetic # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +16FF2..16FF3 ; Alphabetic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; Alphabetic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..18CD5 ; Alphabetic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; Alphabetic # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; Alphabetic # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1AFF0..1AFF3 ; Alphabetic # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; Alphabetic # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; Alphabetic # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -1387,6 +1402,17 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1E4EB ; Alphabetic # Lm NAG MUNDARI SIGN OJOD 1E5D0..1E5ED ; Alphabetic # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG 1E5F0 ; Alphabetic # Lo OL ONAL SIGN HODDOND +1E6C0..1E6DE ; Alphabetic # Lo [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; Alphabetic # Lo [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E3 ; Alphabetic # Mn TAI YO SIGN UE +1E6E4..1E6E5 ; Alphabetic # Lo [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E6 ; Alphabetic # Mn TAI YO SIGN AU +1E6E7..1E6ED ; Alphabetic # Lo [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6EE..1E6EF ; Alphabetic # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F0..1E6F4 ; Alphabetic # Lo [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6F5 ; Alphabetic # Mn TAI YO SIGN OM +1E6FE ; Alphabetic # Lo TAI YO SYMBOL MUEANG +1E6FF ; Alphabetic # Lm TAI YO XAM LAI 1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1432,16 +1458,15 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1F150..1F169 ; Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z 20000..2A6DF ; Alphabetic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; Alphabetic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; Alphabetic # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; Alphabetic # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; Alphabetic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; Alphabetic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 142759 +# Total code points: 147421 # ================================================ @@ -1595,7 +1620,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 024B ; Lowercase # L& LATIN SMALL LETTER Q WITH HOOK TAIL 024D ; Lowercase # L& LATIN SMALL LETTER R WITH STROKE 024F..0293 ; Lowercase # L& [69] LATIN SMALL LETTER Y WITH STROKE..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Lowercase # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Lowercase # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02C0..02C1 ; Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP 02E0..02E4 ; Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -2073,13 +2098,14 @@ A7C3 ; Lowercase # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lowercase # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lowercase # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Lowercase # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Lowercase # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Lowercase # L& LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Lowercase # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Lowercase # L& LATIN SMALL LETTER SIGMOID S A7DB ; Lowercase # L& LATIN SMALL LETTER LAMBDA -A7F2..A7F4 ; Lowercase # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Lowercase # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F6 ; Lowercase # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2105,6 +2131,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 10D70..10D85 ; Lowercase # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Lowercase # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EBB..16ED3 ; Lowercase # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 1D41A..1D433 ; Lowercase # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z 1D44E..1D454 ; Lowercase # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G 1D456..1D467 ; Lowercase # L& [18] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL Z @@ -2139,7 +2166,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2569 +# Total code points: 2595 # ================================================ @@ -2750,7 +2777,10 @@ A7C2 ; Uppercase # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Uppercase # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Uppercase # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Uppercase # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Uppercase # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Uppercase # L& LATIN CAPITAL LETTER LAMBDA @@ -2767,6 +2797,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 10D50..10D65 ; Uppercase # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Uppercase # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Uppercase # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y +16EA0..16EB8 ; Uppercase # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY 1D400..1D419 ; Uppercase # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z 1D434..1D44D ; Uppercase # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z 1D468..1D481 ; Uppercase # L& [26] MATHEMATICAL BOLD ITALIC CAPITAL A..MATHEMATICAL BOLD ITALIC CAPITAL Z @@ -2803,7 +2834,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1978 +# Total code points: 2006 # ================================================ @@ -2821,7 +2852,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 00F8..01BA ; Cased # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL 01BC..01BF ; Cased # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C4..0293 ; Cased # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Cased # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Cased # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; Cased # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02C0..02C1 ; Cased # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP 02E0..02E4 ; Cased # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -2911,11 +2942,8 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7CD ; Cased # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; Cased # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; Cased # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; Cased # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2949,6 +2977,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 10D70..10D85 ; Cased # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118A0..118DF ; Cased # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Cased # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; Cased # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; Cased # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 1D400..1D454 ; Cased # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G 1D456..1D49C ; Cased # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A 1D49E..1D49F ; Cased # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D @@ -2988,7 +3018,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4578 +# Total code points: 4632 # ================================================ @@ -3194,7 +3224,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; Case_Ignorable # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ADD ; Case_Ignorable # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Case_Ignorable # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3274,7 +3305,7 @@ A720..A721 ; Case_Ignorable # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE.. A770 ; Case_Ignorable # Lm MODIFIER LETTER US A788 ; Case_Ignorable # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Case_Ignorable # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN -A7F2..A7F4 ; Case_Ignorable # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Case_Ignorable # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Case_Ignorable # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A802 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN HASANTA @@ -3350,7 +3381,8 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10D69..10D6D ; Case_Ignorable # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10D6F ; Case_Ignorable # Lm GARAY REDUPLICATION MARK 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Case_Ignorable # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; Case_Ignorable # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EFA..10EFF ; Case_Ignorable # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA @@ -3427,6 +3459,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11A59..11A5B ; Case_Ignorable # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK 11A8A..11A96 ; Case_Ignorable # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A98..11A99 ; Case_Ignorable # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11B60 ; Case_Ignorable # Mn SHARADA VOWEL SIGN OE +11B62..11B64 ; Case_Ignorable # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B66 ; Case_Ignorable # Mn SHARADA VOWEL SIGN CANDRA E 11C30..11C36 ; Case_Ignorable # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Case_Ignorable # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; Case_Ignorable # Mn BHAIKSUKI SIGN VIRAMA @@ -3442,6 +3477,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11D90..11D91 ; Case_Ignorable # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI 11D95 ; Case_Ignorable # Mn GUNJALA GONDI SIGN ANUSVARA 11D97 ; Case_Ignorable # Mn GUNJALA GONDI VIRAMA +11DD9 ; Case_Ignorable # Lm TOLONG SIKI SIGN SELA 11EF3..11EF4 ; Case_Ignorable # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11F00..11F01 ; Case_Ignorable # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA 11F36..11F3A ; Case_Ignorable # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R @@ -3464,6 +3500,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Case_Ignorable # Lm OLD CHINESE ITERATION MARK 16FE4 ; Case_Ignorable # Mn KHITAN SMALL SCRIPT FILLER +16FF2..16FF3 ; Case_Ignorable # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 1AFF0..1AFF3 ; Case_Ignorable # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; Case_Ignorable # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; Case_Ignorable # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -3497,6 +3534,11 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E4EB ; Case_Ignorable # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; Case_Ignorable # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E5EE..1E5EF ; Case_Ignorable # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E6E3 ; Case_Ignorable # Mn TAI YO SIGN UE +1E6E6 ; Case_Ignorable # Mn TAI YO SIGN AU +1E6EE..1E6EF ; Case_Ignorable # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F5 ; Case_Ignorable # Mn TAI YO SIGN OM +1E6FF ; Case_Ignorable # Lm TAI YO XAM LAI 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; Case_Ignorable # Lm ADLAM NASALIZATION MARK @@ -3505,13 +3547,14 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2749 +# Total code points: 2794 # ================================================ # Derived Property: Changes_When_Lowercased (CWL) # Characters whose normalized forms are not stable under a toLowercase mapping. -# For more information, see D139 in Section 3.13, "Default Case Algorithms". +# For more information, see the definition of "isLowercase(X)" +# in the "Conformance" / "Default Case Algorithms" section of the core specification. # Changes_When_Lowercased(X) is true when toLowercase(toNFD(X)) != toNFD(X) 0041..005A ; Changes_When_Lowercased # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -4110,7 +4153,10 @@ A7C2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER ANGLICAN A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Changes_When_Lowercased # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER LAMBDA @@ -4127,15 +4173,17 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 10D50..10D65 ; Changes_When_Lowercased # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Changes_When_Lowercased # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y +16EA0..16EB8 ; Changes_When_Lowercased # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1460 +# Total code points: 1488 # ================================================ # Derived Property: Changes_When_Uppercased (CWU) # Characters whose normalized forms are not stable under a toUppercase mapping. -# For more information, see D140 in Section 3.13, "Default Case Algorithms". +# For more information, see the definition of "isUppercase(X)" +# in the "Conformance" / "Default Case Algorithms" section of the core specification. # Changes_When_Uppercased(X) is true when toUppercase(toNFD(X)) != toNFD(X) 0061..007A ; Changes_When_Uppercased # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z @@ -4747,7 +4795,10 @@ A7C3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER ANGLICANA A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Changes_When_Uppercased # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Changes_When_Uppercased # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S A7DB ; Changes_When_Uppercased # L& LATIN SMALL LETTER LAMBDA @@ -4767,15 +4818,17 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 10D70..10D85 ; Changes_When_Uppercased # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Changes_When_Uppercased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EBB..16ED3 ; Changes_When_Uppercased # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1552 +# Total code points: 1580 # ================================================ # Derived Property: Changes_When_Titlecased (CWT) # Characters whose normalized forms are not stable under a toTitlecase mapping. -# For more information, see D141 in Section 3.13, "Default Case Algorithms". +# For more information, see the definition of "isTitlecase(X)" +# in the "Conformance" / "Default Case Algorithms" section of the core specification. # Changes_When_Titlecased(X) is true when toTitlecase(toNFD(X)) != toNFD(X) 0061..007A ; Changes_When_Titlecased # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z @@ -5386,7 +5439,10 @@ A7C3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER ANGLICANA A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Changes_When_Titlecased # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Changes_When_Titlecased # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S A7DB ; Changes_When_Titlecased # L& LATIN SMALL LETTER LAMBDA @@ -5406,15 +5462,17 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 10D70..10D85 ; Changes_When_Titlecased # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118C0..118DF ; Changes_When_Titlecased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EBB..16ED3 ; Changes_When_Titlecased # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1479 +# Total code points: 1507 # ================================================ # Derived Property: Changes_When_Casefolded (CWCF) # Characters whose normalized forms are not stable under case folding. -# For more information, see D142 in Section 3.13, "Default Case Algorithms". +# For more information, see the definition of "isCasefolded(X)" +# in the "Conformance" / "Default Case Algorithms" section of the core specification. # Changes_When_Casefolded(X) is true when toCasefold(toNFD(X)) != toNFD(X) 0041..005A ; Changes_When_Casefolded # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -6022,7 +6080,10 @@ A7C2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER ANGLICAN A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Changes_When_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER LAMBDA @@ -6042,15 +6103,17 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 10D50..10D65 ; Changes_When_Casefolded # L& [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 118A0..118BF ; Changes_When_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y +16EA0..16EB8 ; Changes_When_Casefolded # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1533 +# Total code points: 1561 # ================================================ # Derived Property: Changes_When_Casemapped (CWCM) # Characters whose normalized forms are not stable under case mapping. -# For more information, see D143 in Section 3.13, "Default Case Algorithms". +# For more information, see the definition of "isCased(X)" +# in the "Conformance" / "Default Case Algorithms" section of the core specification. # Changes_When_Casemapped(X) is true when CWL(X), or CWT(X), or CWU(X) 0041..005A ; Changes_When_Casemapped # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z @@ -6156,9 +6219,7 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7CD ; Changes_When_Casemapped # L& [30] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D6..A7DC ; Changes_When_Casemapped # L& [7] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7B0..A7DC ; Changes_When_Casemapped # L& [45] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -6183,9 +6244,11 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 10D70..10D85 ; Changes_When_Casemapped # L& [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 118A0..118DF ; Changes_When_Casemapped # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; Changes_When_Casemapped # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; Changes_When_Casemapped # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2981 +# Total code points: 3037 # ================================================ @@ -6210,8 +6273,8 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 01BC..01BF ; ID_Start # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; ID_Start # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; ID_Start # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; ID_Start # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; ID_Start # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; ID_Start # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; ID_Start # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ID_Start # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; ID_Start # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; ID_Start # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -6259,7 +6322,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; ID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; ID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; ID_Start # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; ID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; ID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -6327,7 +6390,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0C2A..0C39 ; ID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; ID_Start # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; ID_Start # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -6336,7 +6399,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0CAA..0CB3 ; ID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ID_Start # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; ID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; ID_Start # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; ID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -6561,11 +6624,8 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; ID_Start # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; ID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; ID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; ID_Start # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; ID_Start # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6702,6 +6762,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; ID_Start # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ID_Start # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ID_Start # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..10959 ; ID_Start # Lo [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..109B7 ; ID_Start # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ID_Start # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ID_Start # Lo KHAROSHTHI LETTER A @@ -6729,6 +6790,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10E80..10EA9 ; ID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; ID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6..10EC7 ; ID_Start # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -6821,6 +6884,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11D67..11D68 ; ID_Start # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI 11D6A..11D89 ; ID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; ID_Start # Lo GUNJALA GONDI OM +11DB0..11DD8 ; ID_Start # Lo [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DD9 ; ID_Start # Lm TOLONG SIKI SIGN SELA +11DDA..11DDB ; ID_Start # Lo [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA 11EE0..11EF2 ; ID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11F02 ; ID_Start # Lo KAWI SIGN REPHA 11F04..11F10 ; ID_Start # Lo [13] KAWI LETTER A..KAWI LETTER O @@ -6847,14 +6913,18 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16D43..16D6A ; ID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; ID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; ID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; ID_Start # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; ID_Start # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16F00..16F4A ; ID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; ID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; ID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; ID_Start # Lm OLD CHINESE ITERATION MARK -17000..187F7 ; ID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; ID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; ID_Start # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +16FF2..16FF3 ; ID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; ID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..18CD5 ; ID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; ID_Start # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; ID_Start # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1AFF0..1AFF3 ; ID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; ID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; ID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -6912,6 +6982,13 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E4EB ; ID_Start # Lm NAG MUNDARI SIGN OJOD 1E5D0..1E5ED ; ID_Start # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG 1E5F0 ; ID_Start # Lo OL ONAL SIGN HODDOND +1E6C0..1E6DE ; ID_Start # Lo [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; ID_Start # Lo [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E4..1E6E5 ; ID_Start # Lo [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E7..1E6ED ; ID_Start # Lo [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6F0..1E6F4 ; ID_Start # Lo [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6FE ; ID_Start # Lo TAI YO SYMBOL MUEANG +1E6FF ; ID_Start # Lm TAI YO XAM LAI 1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -6953,16 +7030,15 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1EEA5..1EEA9 ; ID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; ID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 20000..2A6DF ; ID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; ID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; ID_Start # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; ID_Start # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; ID_Start # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; ID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 141269 +# Total code points: 145916 # ================================================ @@ -6991,8 +7067,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 01BC..01BF ; ID_Continue # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; ID_Continue # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; ID_Continue # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; ID_Continue # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; ID_Continue # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; ID_Continue # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; ID_Continue # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ID_Continue # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; ID_Continue # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; ID_Continue # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -7068,7 +7144,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; ID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; ID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; ID_Continue # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0897..089F ; ID_Continue # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; ID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; ID_Continue # Lm ARABIC SMALL FARSI YEH @@ -7218,7 +7294,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C4A..0C4D ; ID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; ID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; ID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; ID_Continue # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; ID_Continue # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; ID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; ID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -7240,7 +7316,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CCA..0CCB ; ID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; ID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; ID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; ID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; ID_Continue # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; ID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -7457,7 +7533,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACE ; ID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ADD ; ID_Continue # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; ID_Continue # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -7646,11 +7723,8 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; ID_Continue # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; ID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; ID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; ID_Continue # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; ID_Continue # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -7857,6 +7931,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 108F4..108F5 ; ID_Continue # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ID_Continue # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ID_Continue # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..10959 ; ID_Continue # Lo [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..109B7 ; ID_Continue # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ID_Continue # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ID_Continue # Lo KHAROSHTHI LETTER A @@ -7895,7 +7970,9 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10EAB..10EAC ; ID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC..10EFF ; ID_Continue # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; ID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6..10EC7 ; ID_Continue # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW +10EFA..10EFF ; ID_Continue # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -8122,6 +8199,12 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; ID_Continue # Lo SOYOMBO MARK PLUTA 11AB0..11AF8 ; ID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL +11B60 ; ID_Continue # Mn SHARADA VOWEL SIGN OE +11B61 ; ID_Continue # Mc SHARADA VOWEL SIGN OOE +11B62..11B64 ; ID_Continue # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B65 ; ID_Continue # Mc SHARADA VOWEL SIGN SHORT O +11B66 ; ID_Continue # Mn SHARADA VOWEL SIGN CANDRA E +11B67 ; ID_Continue # Mc SHARADA VOWEL SIGN CANDRA O 11BC0..11BE0 ; ID_Continue # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO 11BF0..11BF9 ; ID_Continue # Nd [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE 11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L @@ -8162,6 +8245,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11D97 ; ID_Continue # Mn GUNJALA GONDI VIRAMA 11D98 ; ID_Continue # Lo GUNJALA GONDI OM 11DA0..11DA9 ; ID_Continue # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11DB0..11DD8 ; ID_Continue # Lo [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DD9 ; ID_Continue # Lm TOLONG SIKI SIGN SELA +11DDA..11DDB ; ID_Continue # Lo [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA +11DE0..11DE9 ; ID_Continue # Nd [10] TOLONG SIKI DIGIT ZERO..TOLONG SIKI DIGIT NINE 11EE0..11EF2 ; ID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; ID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; ID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O @@ -8212,6 +8299,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16D6B..16D6C ; ID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D70..16D79 ; ID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; ID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; ID_Continue # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; ID_Continue # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16F00..16F4A ; ID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; ID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F50 ; ID_Continue # Lo MIAO LETTER NASALIZATION @@ -8222,9 +8311,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16FE3 ; ID_Continue # Lm OLD CHINESE ITERATION MARK 16FE4 ; ID_Continue # Mn KHITAN SMALL SCRIPT FILLER 16FF0..16FF1 ; ID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY -17000..187F7 ; ID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; ID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; ID_Continue # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +16FF2..16FF3 ; ID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; ID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..18CD5 ; ID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; ID_Continue # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; ID_Continue # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1AFF0..1AFF3 ; ID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; ID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; ID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -8315,6 +8406,17 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1E5EE..1E5EF ; ID_Continue # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E5F0 ; ID_Continue # Lo OL ONAL SIGN HODDOND 1E5F1..1E5FA ; ID_Continue # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E6C0..1E6DE ; ID_Continue # Lo [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; ID_Continue # Lo [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E3 ; ID_Continue # Mn TAI YO SIGN UE +1E6E4..1E6E5 ; ID_Continue # Lo [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E6 ; ID_Continue # Mn TAI YO SIGN AU +1E6E7..1E6ED ; ID_Continue # Lo [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6EE..1E6EF ; ID_Continue # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F0..1E6F4 ; ID_Continue # Lo [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6F5 ; ID_Continue # Mn TAI YO SIGN OM +1E6FE ; ID_Continue # Lo TAI YO SYMBOL MUEANG +1E6FF ; ID_Continue # Lm TAI YO XAM LAI 1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -8360,17 +8462,16 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1EEAB..1EEBB ; ID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; ID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 20000..2A6DF ; ID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; ID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; ID_Continue # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; ID_Continue # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; ID_Continue # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; ID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144541 +# Total code points: 149240 # ================================================ @@ -8393,8 +8494,8 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 01BC..01BF ; XID_Start # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; XID_Start # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; XID_Start # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; XID_Start # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; XID_Start # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; XID_Start # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; XID_Start # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; XID_Start # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; XID_Start # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; XID_Start # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -8441,7 +8542,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; XID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; XID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; XID_Start # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; XID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; XID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -8509,7 +8610,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0C2A..0C39 ; XID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; XID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; XID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; XID_Start # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; XID_Start # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; XID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; XID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -8518,7 +8619,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0CAA..0CB3 ; XID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; XID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; XID_Start # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; XID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; XID_Start # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; XID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; XID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; XID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -8742,11 +8843,8 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; XID_Start # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; XID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; XID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; XID_Start # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; XID_Start # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -8888,6 +8986,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 108F4..108F5 ; XID_Start # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; XID_Start # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; XID_Start # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..10959 ; XID_Start # Lo [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..109B7 ; XID_Start # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; XID_Start # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; XID_Start # Lo KHAROSHTHI LETTER A @@ -8915,6 +9014,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10E80..10EA9 ; XID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; XID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; XID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6..10EC7 ; XID_Start # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -9007,6 +9108,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11D67..11D68 ; XID_Start # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI 11D6A..11D89 ; XID_Start # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; XID_Start # Lo GUNJALA GONDI OM +11DB0..11DD8 ; XID_Start # Lo [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DD9 ; XID_Start # Lm TOLONG SIKI SIGN SELA +11DDA..11DDB ; XID_Start # Lo [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA 11EE0..11EF2 ; XID_Start # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11F02 ; XID_Start # Lo KAWI SIGN REPHA 11F04..11F10 ; XID_Start # Lo [13] KAWI LETTER A..KAWI LETTER O @@ -9033,14 +9137,18 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16D43..16D6A ; XID_Start # Lo [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16D6B..16D6C ; XID_Start # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16E40..16E7F ; XID_Start # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; XID_Start # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; XID_Start # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16F00..16F4A ; XID_Start # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; XID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; XID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; XID_Start # Lm OLD CHINESE ITERATION MARK -17000..187F7 ; XID_Start # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; XID_Start # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; XID_Start # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +16FF2..16FF3 ; XID_Start # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; XID_Start # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..18CD5 ; XID_Start # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; XID_Start # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; XID_Start # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1AFF0..1AFF3 ; XID_Start # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; XID_Start # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; XID_Start # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -9098,6 +9206,13 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1E4EB ; XID_Start # Lm NAG MUNDARI SIGN OJOD 1E5D0..1E5ED ; XID_Start # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG 1E5F0 ; XID_Start # Lo OL ONAL SIGN HODDOND +1E6C0..1E6DE ; XID_Start # Lo [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; XID_Start # Lo [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E4..1E6E5 ; XID_Start # Lo [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E7..1E6ED ; XID_Start # Lo [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6F0..1E6F4 ; XID_Start # Lo [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6FE ; XID_Start # Lo TAI YO SYMBOL MUEANG +1E6FF ; XID_Start # Lm TAI YO XAM LAI 1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -9139,16 +9254,15 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1EEA5..1EEA9 ; XID_Start # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; XID_Start # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 20000..2A6DF ; XID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; XID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; XID_Start # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; XID_Start # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; XID_Start # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; XID_Start # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 141246 +# Total code points: 145893 # ================================================ @@ -9174,8 +9288,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 01BC..01BF ; XID_Continue # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; XID_Continue # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; XID_Continue # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; XID_Continue # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; XID_Continue # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; XID_Continue # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; XID_Continue # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; XID_Continue # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; XID_Continue # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; XID_Continue # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -9250,7 +9364,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; XID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; XID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; XID_Continue # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0897..089F ; XID_Continue # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; XID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; XID_Continue # Lm ARABIC SMALL FARSI YEH @@ -9400,7 +9514,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C4A..0C4D ; XID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; XID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; XID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; XID_Continue # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; XID_Continue # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; XID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; XID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -9422,7 +9536,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CCA..0CCB ; XID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; XID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; XID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; XID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; XID_Continue # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; XID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -9639,7 +9753,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACE ; XID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ADD ; XID_Continue # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; XID_Continue # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -9827,11 +9942,8 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; XID_Continue # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; XID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; XID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; XID_Continue # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; XID_Continue # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -10044,6 +10156,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 108F4..108F5 ; XID_Continue # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; XID_Continue # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; XID_Continue # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..10959 ; XID_Continue # Lo [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..109B7 ; XID_Continue # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; XID_Continue # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; XID_Continue # Lo KHAROSHTHI LETTER A @@ -10082,7 +10195,9 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10EAB..10EAC ; XID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC..10EFF ; XID_Continue # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; XID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6..10EC7 ; XID_Continue # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW +10EFA..10EFF ; XID_Continue # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -10309,6 +10424,12 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11A9D ; XID_Continue # Lo SOYOMBO MARK PLUTA 11AB0..11AF8 ; XID_Continue # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL +11B60 ; XID_Continue # Mn SHARADA VOWEL SIGN OE +11B61 ; XID_Continue # Mc SHARADA VOWEL SIGN OOE +11B62..11B64 ; XID_Continue # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B65 ; XID_Continue # Mc SHARADA VOWEL SIGN SHORT O +11B66 ; XID_Continue # Mn SHARADA VOWEL SIGN CANDRA E +11B67 ; XID_Continue # Mc SHARADA VOWEL SIGN CANDRA O 11BC0..11BE0 ; XID_Continue # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO 11BF0..11BF9 ; XID_Continue # Nd [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE 11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L @@ -10349,6 +10470,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11D97 ; XID_Continue # Mn GUNJALA GONDI VIRAMA 11D98 ; XID_Continue # Lo GUNJALA GONDI OM 11DA0..11DA9 ; XID_Continue # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11DB0..11DD8 ; XID_Continue # Lo [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DD9 ; XID_Continue # Lm TOLONG SIKI SIGN SELA +11DDA..11DDB ; XID_Continue # Lo [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA +11DE0..11DE9 ; XID_Continue # Nd [10] TOLONG SIKI DIGIT ZERO..TOLONG SIKI DIGIT NINE 11EE0..11EF2 ; XID_Continue # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; XID_Continue # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; XID_Continue # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O @@ -10399,6 +10524,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16D6B..16D6C ; XID_Continue # Lm [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 16D70..16D79 ; XID_Continue # Nd [10] KIRAT RAI DIGIT ZERO..KIRAT RAI DIGIT NINE 16E40..16E7F ; XID_Continue # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y +16EA0..16EB8 ; XID_Continue # L& [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; XID_Continue # L& [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16F00..16F4A ; XID_Continue # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; XID_Continue # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F50 ; XID_Continue # Lo MIAO LETTER NASALIZATION @@ -10409,9 +10536,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16FE3 ; XID_Continue # Lm OLD CHINESE ITERATION MARK 16FE4 ; XID_Continue # Mn KHITAN SMALL SCRIPT FILLER 16FF0..16FF1 ; XID_Continue # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY -17000..187F7 ; XID_Continue # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; XID_Continue # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; XID_Continue # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +16FF2..16FF3 ; XID_Continue # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; XID_Continue # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..18CD5 ; XID_Continue # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; XID_Continue # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; XID_Continue # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1AFF0..1AFF3 ; XID_Continue # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; XID_Continue # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; XID_Continue # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -10502,6 +10631,17 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1E5EE..1E5EF ; XID_Continue # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E5F0 ; XID_Continue # Lo OL ONAL SIGN HODDOND 1E5F1..1E5FA ; XID_Continue # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E6C0..1E6DE ; XID_Continue # Lo [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; XID_Continue # Lo [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E3 ; XID_Continue # Mn TAI YO SIGN UE +1E6E4..1E6E5 ; XID_Continue # Lo [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E6 ; XID_Continue # Mn TAI YO SIGN AU +1E6E7..1E6ED ; XID_Continue # Lo [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6EE..1E6EF ; XID_Continue # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F0..1E6F4 ; XID_Continue # Lo [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6F5 ; XID_Continue # Mn TAI YO SIGN OM +1E6FE ; XID_Continue # Lo TAI YO SYMBOL MUEANG +1E6FF ; XID_Continue # Lm TAI YO XAM LAI 1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -10547,17 +10687,16 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1EEAB..1EEBB ; XID_Continue # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1FBF0..1FBF9 ; XID_Continue # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 20000..2A6DF ; XID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; XID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; XID_Continue # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; XID_Continue # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; XID_Continue # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; XID_Continue # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144522 +# Total code points: 149221 # ================================================ @@ -10778,7 +10917,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 085F ; Cn # 086B..086F ; Cn # [5] .. -088F ; Cn # 0892..0896 ; Cn # [5] .. 0984 ; Cn # 098D..098E ; Cn # [2] .. @@ -120,7 +119,7 @@ 0C49 ; Cn # 0C4E..0C54 ; Cn # [7] .. 0C57 ; Cn # -0C5B..0C5C ; Cn # [2] .. +0C5B ; Cn # 0C5E..0C5F ; Cn # [2] .. 0C64..0C65 ; Cn # [2] .. 0C70..0C76 ; Cn # [7] .. @@ -132,7 +131,7 @@ 0CC5 ; Cn # 0CC9 ; Cn # 0CCE..0CD4 ; Cn # [7] .. -0CD7..0CDC ; Cn # [6] .. +0CD7..0CDB ; Cn # [5] .. 0CDF ; Cn # 0CE4..0CE5 ; Cn # [2] .. 0CF0 ; Cn # @@ -228,7 +227,8 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1ACF..1AFF ; Cn # [49] .. +1ADE..1ADF ; Cn # [2] .. +1AEC..1AFF ; Cn # [20] .. 1B4D ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. @@ -257,13 +257,12 @@ 2072..2073 ; Cn # [2] .. 208F ; Cn # 209D..209F ; Cn # [3] .. -20C1..20CF ; Cn # [15] .. +20C2..20CF ; Cn # [14] .. 20F1..20FF ; Cn # [15] .. 218C..218F ; Cn # [4] .. 242A..243F ; Cn # [22] .. 244B..245F ; Cn # [21] .. 2B74..2B75 ; Cn # [2] .. -2B96 ; Cn # 2CF4..2CF8 ; Cn # [5] .. 2D26 ; Cn # 2D28..2D2C ; Cn # [5] .. @@ -294,10 +293,7 @@ A48D..A48F ; Cn # [3] .. A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. -A7CE..A7CF ; Cn # [2] .. -A7D2 ; Cn # -A7D4 ; Cn # -A7DD..A7F1 ; Cn # [21] .. +A7DD..A7F0 ; Cn # [20] .. A82D..A82F ; Cn # [3] .. A83A..A83F ; Cn # [6] .. A878..A87F ; Cn # [8] .. @@ -333,9 +329,6 @@ FB3D ; Cn # FB3F ; Cn # FB42 ; Cn # FB45 ; Cn # -FBC3..FBD2 ; Cn # [16] .. -FD90..FD91 ; Cn # [2] .. -FDC8..FDCE ; Cn # [7] .. FDD0..FDEF ; Cn # [32] .. FE1A..FE1F ; Cn # [6] .. FE53 ; Cn # @@ -407,7 +400,7 @@ FFFE..FFFF ; Cn # [2] .. 108F6..108FA ; Cn # [5] .. 1091C..1091E ; Cn # [3] .. 1093A..1093E ; Cn # [5] .. -10940..1097F ; Cn # [64] .. +1095A..1097F ; Cn # [38] .. 109B8..109BB ; Cn # [4] .. 109D0..109D1 ; Cn # [2] .. 10A04 ; Cn # @@ -439,7 +432,8 @@ FFFE..FFFF ; Cn # [2] .. 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. 10EB2..10EC1 ; Cn # [16] .. -10EC5..10EFB ; Cn # [55] .. +10EC8..10ECF ; Cn # [8] .. +10ED9..10EF9 ; Cn # [33] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. 10F8A..10FAF ; Cn # [38] .. @@ -522,7 +516,8 @@ FFFE..FFFF ; Cn # [2] .. 11A48..11A4F ; Cn # [8] .. 11AA3..11AAF ; Cn # [13] .. 11AF9..11AFF ; Cn # [7] .. -11B0A..11BBF ; Cn # [182] .. +11B0A..11B5F ; Cn # [86] .. +11B68..11BBF ; Cn # [88] .. 11BE2..11BEF ; Cn # [14] .. 11BFA..11BFF ; Cn # [6] .. 11C09 ; Cn # @@ -544,7 +539,9 @@ FFFE..FFFF ; Cn # [2] .. 11D8F ; Cn # 11D92 ; Cn # 11D99..11D9F ; Cn # [7] .. -11DAA..11EDF ; Cn # [310] .. +11DAA..11DAF ; Cn # [6] .. +11DDC..11DDF ; Cn # [4] .. +11DEA..11EDF ; Cn # [246] .. 11EF9..11EFF ; Cn # [7] .. 11F11 ; Cn # 11F3B..11F3D ; Cn # [3] .. @@ -573,15 +570,17 @@ FFFE..FFFF ; Cn # [2] .. 16B78..16B7C ; Cn # [5] .. 16B90..16D3F ; Cn # [432] .. 16D7A..16E3F ; Cn # [198] .. -16E9B..16EFF ; Cn # [101] .. +16E9B..16E9F ; Cn # [5] .. +16EB9..16EBA ; Cn # [2] .. +16ED4..16EFF ; Cn # [44] .. 16F4B..16F4E ; Cn # [4] .. 16F88..16F8E ; Cn # [7] .. 16FA0..16FDF ; Cn # [64] .. 16FE5..16FEF ; Cn # [11] .. -16FF2..16FFF ; Cn # [14] .. -187F8..187FF ; Cn # [8] .. +16FF7..16FFF ; Cn # [9] .. 18CD6..18CFE ; Cn # [41] .. -18D09..1AFEF ; Cn # [8935] .. +18D1F..18D7F ; Cn # [97] .. +18DF3..1AFEF ; Cn # [8701] .. 1AFF4 ; Cn # 1AFFC ; Cn # 1AFFF ; Cn # @@ -596,8 +595,10 @@ FFFE..FFFF ; Cn # [2] .. 1BC89..1BC8F ; Cn # [7] .. 1BC9A..1BC9B ; Cn # [2] .. 1BCA4..1CBFF ; Cn # [3932] .. -1CCFA..1CCFF ; Cn # [6] .. -1CEB4..1CEFF ; Cn # [76] .. +1CCFD..1CCFF ; Cn # [3] .. +1CEB4..1CEB9 ; Cn # [6] .. +1CED1..1CEDF ; Cn # [15] .. +1CEF1..1CEFF ; Cn # [15] .. 1CF2E..1CF2F ; Cn # [2] .. 1CF47..1CF4F ; Cn # [9] .. 1CFC4..1CFFF ; Cn # [60] .. @@ -650,7 +651,10 @@ FFFE..FFFF ; Cn # [2] .. 1E300..1E4CF ; Cn # [464] .. 1E4FA..1E5CF ; Cn # [214] .. 1E5FB..1E5FE ; Cn # [4] .. -1E600..1E7DF ; Cn # [480] .. +1E600..1E6BF ; Cn # [192] .. +1E6DF ; Cn # +1E6F6..1E6FD ; Cn # [8] .. +1E700..1E7DF ; Cn # [224] .. 1E7E7 ; Cn # 1E7EC ; Cn # 1E7EF ; Cn # @@ -708,10 +712,9 @@ FFFE..FFFF ; Cn # [2] .. 1F249..1F24F ; Cn # [7] .. 1F252..1F25F ; Cn # [14] .. 1F266..1F2FF ; Cn # [154] .. -1F6D8..1F6DB ; Cn # [4] .. +1F6D9..1F6DB ; Cn # [3] .. 1F6ED..1F6EF ; Cn # [3] .. 1F6FD..1F6FF ; Cn # [3] .. -1F777..1F77A ; Cn # [4] .. 1F7DA..1F7DF ; Cn # [6] .. 1F7EC..1F7EF ; Cn # [4] .. 1F7F1..1F7FF ; Cn # [15] .. @@ -721,33 +724,34 @@ FFFE..FFFF ; Cn # [2] .. 1F888..1F88F ; Cn # [8] .. 1F8AE..1F8AF ; Cn # [2] .. 1F8BC..1F8BF ; Cn # [4] .. -1F8C2..1F8FF ; Cn # [62] .. -1FA54..1FA5F ; Cn # [12] .. +1F8C2..1F8CF ; Cn # [14] .. +1F8D9..1F8FF ; Cn # [39] .. +1FA58..1FA5F ; Cn # [8] .. 1FA6E..1FA6F ; Cn # [2] .. 1FA7D..1FA7F ; Cn # [3] .. -1FA8A..1FA8E ; Cn # [5] .. -1FAC7..1FACD ; Cn # [7] .. +1FA8B..1FA8D ; Cn # [3] .. +1FAC7 ; Cn # +1FAC9..1FACC ; Cn # [4] .. 1FADD..1FADE ; Cn # [2] .. -1FAEA..1FAEF ; Cn # [6] .. +1FAEB..1FAEE ; Cn # [4] .. 1FAF9..1FAFF ; Cn # [7] .. 1FB93 ; Cn # -1FBFA..1FFFF ; Cn # [1030] .. +1FBFB..1FFFF ; Cn # [1029] .. 2A6E0..2A6FF ; Cn # [32] .. -2B73A..2B73F ; Cn # [6] .. 2B81E..2B81F ; Cn # [2] .. -2CEA2..2CEAF ; Cn # [14] .. +2CEAE..2CEAF ; Cn # [2] .. 2EBE1..2EBEF ; Cn # [15] .. 2EE5E..2F7FF ; Cn # [2466] .. 2FA1E..2FFFF ; Cn # [1506] .. 3134B..3134F ; Cn # [5] .. -323B0..E0000 ; Cn # [711761] .. +3347A..E0000 ; Cn # [707463] .. E0002..E001F ; Cn # [30] .. E0080..E00FF ; Cn # [128] .. E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819533 +# Total code points: 814730 # ================================================ @@ -1355,7 +1359,10 @@ 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 A7CB..A7CC ; Lu # [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Lu # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Lu # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Lu # LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Lu # LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S A7DA ; Lu # LATIN CAPITAL LETTER LAMBDA @@ -1372,6 +1379,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 10D50..10D65 ; Lu # [22] GARAY CAPITAL LETTER A..GARAY CAPITAL LETTER OLD NA 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 +16EA0..16EB8 ; Lu # [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY 1D400..1D419 ; Lu # [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z 1D434..1D44D ; Lu # [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z 1D468..1D481 ; Lu # [26] MATHEMATICAL BOLD ITALIC CAPITAL A..MATHEMATICAL BOLD ITALIC CAPITAL Z @@ -1405,7 +1413,7 @@ 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: 1858 +# Total code points: 1886 # ================================================ @@ -1556,7 +1564,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 024B ; Ll # LATIN SMALL LETTER Q WITH HOOK TAIL 024D ; Ll # LATIN SMALL LETTER R WITH STROKE 024F..0293 ; Ll # [69] LATIN SMALL LETTER Y WITH STROKE..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Ll # [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Ll # [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 0371 ; Ll # GREEK SMALL LETTER HETA 0373 ; Ll # GREEK SMALL LETTER ARCHAIC SAMPI 0377 ; Ll # GREEK SMALL LETTER PAMPHYLIAN DIGAMMA @@ -2017,6 +2025,7 @@ 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 A7CD ; Ll # LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Ll # LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Ll # LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Ll # LATIN SMALL LETTER DOUBLE THORN A7D5 ; Ll # LATIN SMALL LETTER DOUBLE WYNN @@ -2041,6 +2050,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 10D70..10D85 ; Ll # [22] GARAY SMALL LETTER A..GARAY SMALL LETTER OLD NA 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 +16EBB..16ED3 ; Ll # [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 1D41A..1D433 ; Ll # [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z 1D44E..1D454 ; Ll # [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G 1D456..1D467 ; Ll # [18] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL Z @@ -2074,7 +2084,7 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 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: 2258 +# Total code points: 2283 # ================================================ @@ -2143,7 +2153,7 @@ 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 +A7F1..A7F4 ; Lm # [4] MODIFIER LETTER CAPITAL S..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 @@ -2159,21 +2169,25 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 107B2..107BA ; Lm # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10D4E ; Lm # GARAY VOWEL LENGTH MARK 10D6F ; Lm # GARAY REDUPLICATION MARK +10EC5 ; Lm # ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +11DD9 ; Lm # TOLONG SIKI SIGN SELA 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16D40..16D42 ; Lm # [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D6B..16D6C ; Lm # [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT 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 +16FF2..16FF3 ; Lm # [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 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 +1E6FF ; Lm # TAI YO XAM LAI 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 404 +# Total code points: 410 # ================================================ @@ -2183,7 +2197,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 00BA ; Lo # MASCULINE ORDINAL INDICATOR 01BB ; Lo # LATIN LETTER TWO WITH STROKE 01C0..01C3 ; Lo # [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK -0294 ; Lo # LATIN LETTER GLOTTAL STOP +0294..0295 ; Lo # [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE 05D0..05EA ; Lo # [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; Lo # [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0620..063F ; Lo # [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE @@ -2203,7 +2217,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Lo # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 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 +0889..088F ; Lo # [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 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 @@ -2269,7 +2283,7 @@ 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 +0C5C..0C5D ; Lo # [2] TELUGU ARCHAIC SHRII..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 @@ -2278,7 +2292,7 @@ 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 -0CDD..0CDE ; Lo # [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; Lo # [3] KANNADA ARCHAIC SHRII..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 @@ -2504,6 +2518,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 108F4..108F5 ; Lo # [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; Lo # [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; Lo # [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..10959 ; Lo # [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..109B7 ; Lo # [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; Lo # [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; Lo # KHAROSHTHI LETTER A @@ -2525,6 +2540,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10E80..10EA9 ; Lo # [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; Lo # [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Lo # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC6..10EC7 ; Lo # [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 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 @@ -2616,6 +2632,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11D67..11D68 ; Lo # [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI 11D6A..11D89 ; Lo # [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; Lo # GUNJALA GONDI OM +11DB0..11DD8 ; Lo # [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DDA..11DDB ; Lo # [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA 11EE0..11EF2 ; Lo # [19] MAKASAR LETTER KA..MAKASAR ANGKA 11F02 ; Lo # KAWI SIGN REPHA 11F04..11F10 ; Lo # [13] KAWI LETTER A..KAWI LETTER O @@ -2639,9 +2657,9 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16D43..16D6A ; Lo # [40] KIRAT RAI LETTER A..KIRAT RAI VOWEL SIGN AU 16F00..16F4A ; Lo # [75] MIAO LETTER PA..MIAO LETTER RTE 16F50 ; Lo # MIAO LETTER NASALIZATION -17000..187F7 ; Lo # [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; Lo # [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; Lo # [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +17000..18CD5 ; Lo # [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; Lo # [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; Lo # [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 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 @@ -2660,6 +2678,12 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1E4D0..1E4EA ; Lo # [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E5D0..1E5ED ; Lo # [30] OL ONAL LETTER O..OL ONAL LETTER EG 1E5F0 ; Lo # OL ONAL SIGN HODDOND +1E6C0..1E6DE ; Lo # [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; Lo # [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E4..1E6E5 ; Lo # [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E7..1E6ED ; Lo # [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6F0..1E6F4 ; Lo # [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6FE ; Lo # TAI YO SYMBOL MUEANG 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 @@ -2699,16 +2723,15 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 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..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 +2A700..2B81D ; Lo # [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; Lo # [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 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 +31350..33479 ; Lo # [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 136477 +# Total code points: 141062 # ================================================ @@ -2856,7 +2879,8 @@ 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..1ACE ; Mn # [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ADD ; Mn # [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Mn # [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 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 @@ -2938,7 +2962,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 10D24..10D27 ; Mn # [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Mn # [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Mn # [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Mn # [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFA..10EFF ; Mn # [6] ARABIC DOUBLE VERTICAL BAR BELOW..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 @@ -3013,6 +3037,9 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 11A59..11A5B ; Mn # [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK 11A8A..11A96 ; Mn # [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A98..11A99 ; Mn # [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11B60 ; Mn # SHARADA VOWEL SIGN OE +11B62..11B64 ; Mn # [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B66 ; Mn # SHARADA VOWEL SIGN CANDRA E 11C30..11C36 ; Mn # [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Mn # [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA 11C3F ; Mn # BHAIKSUKI SIGN VIRAMA @@ -3068,11 +3095,15 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E2EC..1E2EF ; Mn # [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Mn # [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E5EE..1E5EF ; Mn # [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E6E3 ; Mn # TAI YO SIGN UE +1E6E6 ; Mn # TAI YO SIGN AU +1E6EE..1E6EF ; Mn # [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F5 ; Mn # TAI YO SIGN OM 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: 2020 +# Total code points: 2059 # ================================================ @@ -3262,6 +3293,9 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 11A39 ; Mc # ZANABAZAR SQUARE SIGN VISARGA 11A57..11A58 ; Mc # [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU 11A97 ; Mc # SOYOMBO SIGN VISARGA +11B61 ; Mc # SHARADA VOWEL SIGN OOE +11B65 ; Mc # SHARADA VOWEL SIGN SHORT O +11B67 ; Mc # SHARADA VOWEL SIGN CANDRA O 11C2F ; Mc # BHAIKSUKI VOWEL SIGN AA 11C3E ; Mc # BHAIKSUKI SIGN VISARGA 11CA9 ; Mc # MARCHEN SUBJOINED LETTER YA @@ -3281,7 +3315,7 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 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: 468 +# Total code points: 471 # ================================================ @@ -3344,6 +3378,7 @@ 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 +11DE0..11DE9 ; Nd # [10] TOLONG SIKI DIGIT ZERO..TOLONG SIKI DIGIT NINE 11F50..11F59 ; Nd # [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 16130..16139 ; Nd # [10] GURUNG KHEMA DIGIT ZERO..GURUNG KHEMA DIGIT NINE 16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE @@ -3359,7 +3394,7 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH 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: 760 +# Total code points: 770 # ================================================ @@ -3377,8 +3412,9 @@ A6E6..A6EF ; Nl # [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM 1034A ; Nl # GOTHIC LETTER NINE HUNDRED 103D1..103D5 ; Nl # [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 12400..1246E ; Nl # [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM +16FF4..16FF6 ; Nl # [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS -# Total code points: 236 +# Total code points: 239 # ================================================ @@ -3900,6 +3936,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 10AF0..10AF6 ; Po # [7] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION LINE FILLER 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 +10ED0 ; Po # ARABIC BIBLICAL END OF VERSE 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 @@ -3951,7 +3988,7 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 1E5FF ; Po # OL ONAL ABBREVIATION SIGN 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 640 +# Total code points: 641 # ================================================ @@ -4011,6 +4048,7 @@ FF5E ; Sm # FULLWIDTH TILDE FFE2 ; Sm # FULLWIDTH NOT SIGN FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 10D8E..10D8F ; Sm # [2] GARAY PLUS SIGN..GARAY MINUS SIGN +1CEF0 ; Sm # MEDIUM SMALL WHITE CIRCLE WITH HORIZONTAL BAR 1D6C1 ; Sm # MATHEMATICAL BOLD NABLA 1D6DB ; Sm # MATHEMATICAL BOLD PARTIAL DIFFERENTIAL 1D6FB ; Sm # MATHEMATICAL ITALIC NABLA @@ -4022,8 +4060,9 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 1D7A9 ; Sm # MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA 1D7C3 ; Sm # MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1EEF0..1EEF1 ; Sm # [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL +1F8D0..1F8D8 ; Sm # [9] LONG RIGHTWARDS ARROW OVER LONG LEFTWARDS ARROW..LONG LEFT RIGHT ARROW WITH DEPENDENT LOBE -# Total code points: 950 +# Total code points: 960 # ================================================ @@ -4040,7 +4079,7 @@ 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..20C0 ; Sc # [33] EURO-CURRENCY SIGN..SOM SIGN +20A0..20C1 ; Sc # [34] EURO-CURRENCY SIGN..SAUDI RIYAL SIGN A838 ; Sc # NORTH INDIC RUPEE MARK FDFC ; Sc # RIAL SIGN FE69 ; Sc # SMALL DOLLAR SIGN @@ -4051,7 +4090,7 @@ FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 1E2FF ; Sc # WANCHO NGUN SIGN 1ECB0 ; Sc # INDIC SIYAQ RUPEE MARK -# Total code points: 63 +# Total code points: 64 # ================================================ @@ -4174,8 +4213,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 2B00..2B2F ; So # [48] NORTH EAST WHITE ARROW..WHITE VERTICAL ELLIPSE 2B45..2B46 ; So # [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B4D..2B73 ; So # [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; So # [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; So # [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; So # [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2CE5..2CEA ; So # [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2E50..2E51 ; So # [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR 2E80..2E99 ; So # [26] CJK RADICAL REPEAT..CJK RADICAL RAP @@ -4203,8 +4241,10 @@ 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 +FBC3..FBD2 ; So # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FD40..FD4F ; So # [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH -FDCF ; So # ARABIC LIGATURE SALAAMUHU ALAYNAA +FD90..FD91 ; So # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FDC8..FDCF ; So # [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..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 @@ -4218,6 +4258,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 101D0..101FC ; So # [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 10877..10878 ; So # [2] PALMYRENE LEFT-POINTING FLEURON..PALMYRENE RIGHT-POINTING FLEURON 10AC8 ; So # MANICHAEAN SIGN UD +10ED1..10ED8 ; So # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 1173F ; So # AHOM SYMBOL VI 11FD5..11FDC ; So # [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI 11FE1..11FF1 ; So # [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA @@ -4225,7 +4266,10 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16B45 ; So # PAHAWH HMONG SIGN CIM TSOV ROG 1BC9C ; So # DUPLOYAN SIGN O WITH CROSS 1CC00..1CCEF ; So # [240] UP-POINTING GO-KART..OUTLINED LATIN CAPITAL LETTER Z +1CCFA..1CCFC ; So # [3] SNAKE SYMBOL..NOSE SYMBOL 1CD00..1CEB3 ; So # [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET +1CEBA..1CED0 ; So # [23] FRAGILE SYMBOL..LEUKOTHEA +1CEE0..1CEEF ; So # [16] GEOMANTIC FIGURE POPULUS..GEOMANTIC FIGURE VIA 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 @@ -4258,11 +4302,10 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F250..1F251 ; So # [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT 1F260..1F265 ; So # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; So # [251] CYCLONE..AMPHORA -1F400..1F6D7 ; So # [728] RAT..ELEVATOR +1F400..1F6D8 ; So # [729] RAT..LANDSLIDE 1F6DC..1F6EC ; So # [17] WIRELESS..AIRPLANE ARRIVING 1F6F0..1F6FC ; So # [13] SATELLITE..ROLLER SKATE -1F700..1F776 ; So # [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F7D9 ; So # [95] HAUMEA..NINE POINTED WHITE STAR +1F700..1F7D9 ; So # [218] ALCHEMICAL SYMBOL FOR QUINTESSENCE..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 @@ -4272,18 +4315,20 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8BB ; So # [12] ARROW POINTING UPWARDS THEN NORTH WEST..SOUTH WEST ARROW FROM BAR 1F8C0..1F8C1 ; So # [2] LEFTWARDS ARROW FROM DOWNWARDS ARROW..RIGHTWARDS ARROW FROM DOWNWARDS ARROW -1F900..1FA53 ; So # [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP +1F900..1FA57 ; So # [344] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS ALFIL 1FA60..1FA6D ; So # [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; So # [13] BALLET SHOES..CRUTCH -1FA80..1FA89 ; So # [10] YO-YO..HARP -1FA8F..1FAC6 ; So # [56] SHOVEL..FINGERPRINT -1FACE..1FADC ; So # [15] MOOSE..ROOT VEGETABLE -1FADF..1FAE9 ; So # [11] SPLATTER..FACE WITH BAGS UNDER EYES -1FAF0..1FAF8 ; So # [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND +1FA80..1FA8A ; So # [11] YO-YO..TROMBONE +1FA8E..1FAC6 ; So # [57] TREASURE CHEST..FINGERPRINT +1FAC8 ; So # HAIRY CREATURE +1FACD..1FADC ; So # [16] ORCA..ROOT VEGETABLE +1FADF..1FAEA ; So # [12] SPLATTER..DISTORTED FACE +1FAEF..1FAF8 ; So # [10] FIGHT CLOUD..RIGHTWARDS PUSHING HAND 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; So # [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE +1FBFA ; So # ALARM BELL SYMBOL -# Total code points: 7376 +# Total code points: 7468 # ================================================ diff --git a/data/EastAsianWidth.txt b/data/EastAsianWidth.txt index 99f7a31..3e46eb6 100644 --- a/data/EastAsianWidth.txt +++ b/data/EastAsianWidth.txt @@ -1,6 +1,6 @@ -# EastAsianWidth-16.0.0.txt -# Date: 2024-04-30, 21:48:20 GMT -# © 2024 Unicode®, Inc. +# EastAsianWidth-17.0.0.txt +# Date: 2025-07-24, 00:12:54 GMT +# © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html # @@ -180,8 +180,8 @@ 0252..0260 ; N # Ll [15] LATIN SMALL LETTER TURNED ALPHA..LATIN SMALL LETTER G WITH HOOK 0261 ; A # Ll LATIN SMALL LETTER SCRIPT G 0262..0293 ; N # Ll [50] LATIN LETTER SMALL CAPITAL G..LATIN SMALL LETTER EZH WITH CURL -0294 ; N # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; N # Ll [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; N # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; N # Ll [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; N # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C3 ; N # Sk [2] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER RIGHT ARROWHEAD 02C4 ; A # Sk MODIFIER LETTER UP ARROWHEAD @@ -332,7 +332,7 @@ 0860..086A ; N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; N # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; N # Sk ARABIC RAISED ROUND DOT -0889..088E ; N # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; N # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; N # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0897..089F ; N # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; N # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF @@ -502,7 +502,7 @@ 0C4A..0C4D ; N # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; N # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; N # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; N # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; N # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; N # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; N # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -528,7 +528,7 @@ 0CCA..0CCB ; N # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; N # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; N # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; N # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; N # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; N # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -806,7 +806,8 @@ 1AA8..1AAD ; N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; N # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ADD ; N # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; N # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -976,7 +977,7 @@ 20A9 ; H # Sc WON SIGN 20AA..20AB ; N # Sc [2] NEW SHEQEL SIGN..DONG SIGN 20AC ; A # Sc EURO SIGN -20AD..20C0 ; N # Sc [20] KIP SIGN..SOM SIGN +20AD..20C1 ; N # Sc [21] KIP SIGN..SAUDI RIYAL SIGN 20D0..20DC ; N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; N # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1351,8 +1352,7 @@ 2B55 ; W # So HEAVY LARGE CIRCLE 2B56..2B59 ; A # So [4] HEAVY OVAL WITH OVAL INSIDE..HEAVY CIRCLED SALTIRE 2B5A..2B73 ; N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; N # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; N # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C5F ; N # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60..2C7B ; N # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; N # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V @@ -1548,11 +1548,8 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; N # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; N # Ll LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1..A7F4 ; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1709,13 +1706,15 @@ FB43..FB44 ; N # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETT FB46..FB4F ; N # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1 ; N # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; N # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; N # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; N # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; N # Pe ORNATE LEFT PARENTHESIS FD3F ; N # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD90..FD91 ; N # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; N # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; N # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; N # Sc RIAL SIGN FDFD..FDFF ; N # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL @@ -1904,6 +1903,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1091F ; N # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; N # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; N # Po LYDIAN TRIANGULAR MARK +10940..10959 ; N # Lo [26] SIDETIC LETTER N01..SIDETIC LETTER N26 10980..1099F ; N # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; N # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; N # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF @@ -1964,7 +1964,11 @@ FFFD ; A # So REPLACEMENT CHARACTER 10EAD ; N # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC..10EFF ; N # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6..10EC7 ; N # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW +10ED0 ; N # Po ARABIC BIBLICAL END OF VERSE +10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH +10EFA..10EFF ; N # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; N # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -2235,6 +2239,12 @@ FFFD ; A # So REPLACEMENT CHARACTER 11AB0..11ABF ; N # Lo [16] CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11AC0..11AF8 ; N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL 11B00..11B09 ; N # Po [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU +11B60 ; N # Mn SHARADA VOWEL SIGN OE +11B61 ; N # Mc SHARADA VOWEL SIGN OOE +11B62..11B64 ; N # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B65 ; N # Mc SHARADA VOWEL SIGN SHORT O +11B66 ; N # Mn SHARADA VOWEL SIGN CANDRA E +11B67 ; N # Mc SHARADA VOWEL SIGN CANDRA O 11BC0..11BE0 ; N # Lo [33] SUNUWAR LETTER DEVI..SUNUWAR LETTER KLOKO 11BE1 ; N # Po SUNUWAR SIGN PVO 11BF0..11BF9 ; N # Nd [10] SUNUWAR DIGIT ZERO..SUNUWAR DIGIT NINE @@ -2279,6 +2289,10 @@ FFFD ; A # So REPLACEMENT CHARACTER 11D97 ; N # Mn GUNJALA GONDI VIRAMA 11D98 ; N # Lo GUNJALA GONDI OM 11DA0..11DA9 ; N # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11DB0..11DD8 ; N # Lo [41] TOLONG SIKI LETTER I..TOLONG SIKI LETTER RRH +11DD9 ; N # Lm TOLONG SIKI SIGN SELA +11DDA..11DDB ; N # Lo [2] TOLONG SIKI SIGN HECAKA..TOLONG SIKI UNGGA +11DE0..11DE9 ; N # Nd [10] TOLONG SIKI DIGIT ZERO..TOLONG SIKI DIGIT NINE 11EE0..11EF2 ; N # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA 11EF3..11EF4 ; N # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; N # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O @@ -2349,6 +2363,8 @@ FFFD ; A # So REPLACEMENT CHARACTER 16E40..16E7F ; N # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 16E80..16E96 ; N # No [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM 16E97..16E9A ; N # Po [4] MEDEFAIDRIN COMMA..MEDEFAIDRIN EXCLAMATION OH +16EA0..16EB8 ; N # Lu [25] BERIA ERFE CAPITAL LETTER ARKAB..BERIA ERFE CAPITAL LETTER AY +16EBB..16ED3 ; N # Ll [25] BERIA ERFE SMALL LETTER ARKAB..BERIA ERFE SMALL LETTER AY 16F00..16F4A ; N # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 16F4F ; N # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F50 ; N # Lo MIAO LETTER NASALIZATION @@ -2360,11 +2376,14 @@ FFFD ; A # So REPLACEMENT CHARACTER 16FE3 ; W # Lm OLD CHINESE ITERATION MARK 16FE4 ; W # Mn KHITAN SMALL SCRIPT FILLER 16FF0..16FF1 ; W # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY -17000..187F7 ; W # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 +16FF2..16FF3 ; W # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; W # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..187FF ; W # Lo [6144] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187FF 18800..18AFF ; W # Lo [768] TANGUT COMPONENT-001..TANGUT COMPONENT-768 18B00..18CD5 ; W # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CFF ; W # Lo KHITAN SMALL SCRIPT CHARACTER-18CFF -18D00..18D08 ; W # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 +18D00..18D1E ; W # Lo [31] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; W # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1AFF0..1AFF3 ; W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -2385,7 +2404,12 @@ FFFD ; A # So REPLACEMENT CHARACTER 1BCA0..1BCA3 ; N # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1CC00..1CCEF ; N # So [240] UP-POINTING GO-KART..OUTLINED LATIN CAPITAL LETTER Z 1CCF0..1CCF9 ; N # Nd [10] OUTLINED DIGIT ZERO..OUTLINED DIGIT NINE +1CCFA..1CCFC ; N # So [3] SNAKE SYMBOL..NOSE SYMBOL 1CD00..1CEB3 ; N # So [436] BLOCK OCTANT-3..BLACK RIGHT TRIANGLE CARET +1CEBA..1CEBF ; N # So [6] FRAGILE SYMBOL..STRAWBERRY SYMBOL +1CEC0..1CED0 ; N # So [17] HEBE..LEUKOTHEA +1CEE0..1CEEF ; N # So [16] GEOMANTIC FIGURE POPULUS..GEOMANTIC FIGURE VIA +1CEF0 ; N # Sm MEDIUM SMALL WHITE CIRCLE WITH HORIZONTAL BAR 1CF00..1CF2D ; N # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT 1CF30..1CF46 ; N # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 1CF50..1CFC3 ; N # So [116] ZNAMENNY NEUME KRYUK..ZNAMENNY NEUME PAUK @@ -2496,6 +2520,17 @@ FFFD ; A # So REPLACEMENT CHARACTER 1E5F0 ; N # Lo OL ONAL SIGN HODDOND 1E5F1..1E5FA ; N # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E5FF ; N # Po OL ONAL ABBREVIATION SIGN +1E6C0..1E6DE ; N # Lo [31] TAI YO LETTER LOW KO..TAI YO LETTER HIGH KVO +1E6E0..1E6E2 ; N # Lo [3] TAI YO LETTER AA..TAI YO LETTER UE +1E6E3 ; N # Mn TAI YO SIGN UE +1E6E4..1E6E5 ; N # Lo [2] TAI YO LETTER U..TAI YO LETTER AE +1E6E6 ; N # Mn TAI YO SIGN AU +1E6E7..1E6ED ; N # Lo [7] TAI YO LETTER O..TAI YO LETTER AUE +1E6EE..1E6EF ; N # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F0..1E6F4 ; N # Lo [5] TAI YO LETTER AN..TAI YO LETTER AP +1E6F5 ; N # Mn TAI YO SIGN OM +1E6FE ; N # Lo TAI YO SYMBOL MUEANG +1E6FF ; N # Lm TAI YO XAM LAI 1E7E0..1E7E6 ; N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2623,14 +2658,13 @@ FFFD ; A # So REPLACEMENT CHARACTER 1F6CD..1F6CF ; N # So [3] SHOPPING BAGS..BED 1F6D0..1F6D2 ; W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY 1F6D3..1F6D4 ; N # So [2] STUPA..PAGODA -1F6D5..1F6D7 ; W # So [3] HINDU TEMPLE..ELEVATOR +1F6D5..1F6D8 ; W # So [4] HINDU TEMPLE..LANDSLIDE 1F6DC..1F6DF ; W # So [4] WIRELESS..RING BUOY 1F6E0..1F6EA ; N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE 1F6EB..1F6EC ; W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING 1F6F0..1F6F3 ; N # So [4] SATELLITE..PASSENGER SHIP 1F6F4..1F6FC ; W # So [9] SCOOTER..ROLLER SKATE -1F700..1F776 ; N # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE -1F77B..1F77F ; N # So [5] HAUMEA..ORCUS +1F700..1F77F ; N # So [128] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ORCUS 1F780..1F7D9 ; N # So [90] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NINE POINTED WHITE STAR 1F7E0..1F7EB ; W # So [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7F0 ; W # So HEAVY EQUALS SIGN @@ -2641,31 +2675,32 @@ FFFD ; A # So REPLACEMENT CHARACTER 1F890..1F8AD ; N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS 1F8B0..1F8BB ; N # So [12] ARROW POINTING UPWARDS THEN NORTH WEST..SOUTH WEST ARROW FROM BAR 1F8C0..1F8C1 ; N # So [2] LEFTWARDS ARROW FROM DOWNWARDS ARROW..RIGHTWARDS ARROW FROM DOWNWARDS ARROW +1F8D0..1F8D8 ; N # Sm [9] LONG RIGHTWARDS ARROW OVER LONG LEFTWARDS ARROW..LONG LEFT RIGHT ARROW WITH DEPENDENT LOBE 1F900..1F90B ; N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT 1F90C..1F93A ; W # So [47] PINCHED FINGERS..FENCER 1F93B ; N # So MODERN PENTATHLON 1F93C..1F945 ; W # So [10] WRESTLERS..GOAL NET 1F946 ; N # So RIFLE 1F947..1F9FF ; W # So [185] FIRST PLACE MEDAL..NAZAR AMULET -1FA00..1FA53 ; N # So [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP +1FA00..1FA57 ; N # So [88] NEUTRAL CHESS KING..BLACK CHESS ALFIL 1FA60..1FA6D ; N # So [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER 1FA70..1FA7C ; W # So [13] BALLET SHOES..CRUTCH -1FA80..1FA89 ; W # So [10] YO-YO..HARP -1FA8F..1FAC6 ; W # So [56] SHOVEL..FINGERPRINT -1FACE..1FADC ; W # So [15] MOOSE..ROOT VEGETABLE -1FADF..1FAE9 ; W # So [11] SPLATTER..FACE WITH BAGS UNDER EYES -1FAF0..1FAF8 ; W # So [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND +1FA80..1FA8A ; W # So [11] YO-YO..TROMBONE +1FA8E..1FAC6 ; W # So [57] TREASURE CHEST..FINGERPRINT +1FAC8 ; W # So HAIRY CREATURE +1FACD..1FADC ; W # So [16] ORCA..ROOT VEGETABLE +1FADF..1FAEA ; W # So [12] SPLATTER..DISTORTED FACE +1FAEF..1FAF8 ; W # So [10] FIGHT CLOUD..RIGHTWARDS PUSHING HAND 1FB00..1FB92 ; N # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; N # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE 1FBF0..1FBF9 ; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE +1FBFA ; N # So ALARM BELL SYMBOL 20000..2A6DF ; W # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A6E0..2A6FF ; W # Cn [32] .. -2A700..2B739 ; W # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B73A..2B73F ; W # Cn [6] .. -2B740..2B81D ; W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D +2A700..2B81D ; W # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; W # Cn [2] .. -2B820..2CEA1 ; W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2CEAF ; W # Cn [14] .. +2B820..2CEAD ; W # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD +2CEAE..2CEAF ; W # Cn [2] .. 2CEB0..2EBE0 ; W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBE1..2EBEF ; W # Cn [15] .. 2EBF0..2EE5D ; W # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D @@ -2675,8 +2710,8 @@ FFFD ; A # So REPLACEMENT CHARACTER 2FA20..2FFFD ; W # Cn [1502] .. 30000..3134A ; W # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 3134B..3134F ; W # Cn [5] .. -31350..323AF ; W # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -323B0..3FFFD ; W # Cn [56398] .. +31350..33479 ; W # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 +3347A..3FFFD ; W # Cn [52100] .. E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; A # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 diff --git a/data/HangulSyllableType.txt b/data/HangulSyllableType.txt index 56b5eea..8c3cf4a 100644 --- a/data/HangulSyllableType.txt +++ b/data/HangulSyllableType.txt @@ -1,6 +1,6 @@ -# HangulSyllableType-16.0.0.txt -# Date: 2024-04-30, 21:48:21 GMT -# © 2024 Unicode®, Inc. +# HangulSyllableType-17.0.0.txt +# Date: 2025-01-27, 18:09:16 GMT +# © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html # diff --git a/data/PropList.txt b/data/PropList.txt index fae2831..e64b422 100644 --- a/data/PropList.txt +++ b/data/PropList.txt @@ -1,6 +1,6 @@ -# PropList-16.0.0.txt -# Date: 2024-05-31, 18:09:48 GMT -# © 2024 Unicode®, Inc. +# PropList-17.0.0.txt +# Date: 2025-06-30, 06:19:01 GMT +# © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html # @@ -702,7 +702,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69 ; Other_Alphabetic # Mn GARAY VOWEL SIGN E 10EAB..10EAC ; Other_Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC ; Other_Alphabetic # Mn ARABIC COMBINING ALEF OVERLAY +10EFA..10EFC ; Other_Alphabetic # Mn [3] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC COMBINING ALEF OVERLAY 11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU 11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA 11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA @@ -809,6 +809,12 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11A59..11A5B ; Other_Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK 11A8A..11A96 ; Other_Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA 11A97 ; Other_Alphabetic # Mc SOYOMBO SIGN VISARGA +11B60 ; Other_Alphabetic # Mn SHARADA VOWEL SIGN OE +11B61 ; Other_Alphabetic # Mc SHARADA VOWEL SIGN OOE +11B62..11B64 ; Other_Alphabetic # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B65 ; Other_Alphabetic # Mc SHARADA VOWEL SIGN SHORT O +11B66 ; Other_Alphabetic # Mn SHARADA VOWEL SIGN CANDRA E +11B67 ; Other_Alphabetic # Mc SHARADA VOWEL SIGN CANDRA O 11C2F ; Other_Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA 11C30..11C36 ; Other_Alphabetic # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L 11C38..11C3D ; Other_Alphabetic # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA @@ -853,12 +859,16 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1E023..1E024 ; Other_Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Other_Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E08F ; Other_Alphabetic # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E6E3 ; Other_Alphabetic # Mn TAI YO SIGN UE +1E6E6 ; Other_Alphabetic # Mn TAI YO SIGN AU +1E6EE..1E6EF ; Other_Alphabetic # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F5 ; Other_Alphabetic # Mn TAI YO SIGN OM 1E947 ; Other_Alphabetic # Mn ADLAM HAMZA 1F130..1F149 ; Other_Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1495 +# Total code points: 1510 # ================================================ @@ -871,21 +881,22 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 16FE4 ; Ideographic # Mn KHITAN SMALL SCRIPT FILLER -17000..187F7 ; Ideographic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 -18800..18CD5 ; Ideographic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 -18CFF..18D08 ; Ideographic # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +16FF2..16FF3 ; Ideographic # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER +16FF4..16FF6 ; Ideographic # Nl [3] YANGQIN SIGN SLOW ONE BEAT..YANGQIN SIGN SLOW TWO BEATS +17000..18CD5 ; Ideographic # Lo [7382] TANGUT IDEOGRAPH-17000..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18CFF..18D1E ; Ideographic # Lo [32] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D1E +18D80..18DF2 ; Ideographic # Lo [115] TANGUT COMPONENT-769..TANGUT COMPONENT-883 1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 20000..2A6DF ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; Ideographic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; Ideographic # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; Ideographic # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; Ideographic # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; Ideographic # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 106477 +# Total code points: 110943 # ================================================ @@ -915,11 +926,11 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0384..0385 ; Diacritic # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS 0483..0487 ; Diacritic # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE 0559 ; Diacritic # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0591..05A1 ; Diacritic # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER -05A3..05BD ; Diacritic # Mn [27] HEBREW ACCENT MUNAH..HEBREW POINT METEG +0591..05BD ; Diacritic # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG 05BF ; Diacritic # Mn HEBREW POINT RAFE 05C1..05C2 ; Diacritic # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT -05C4 ; Diacritic # Mn HEBREW MARK UPPER DOT +05C4..05C5 ; Diacritic # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; Diacritic # Mn HEBREW POINT QAMATS QATAN 064B..0652 ; Diacritic # Mn [8] ARABIC FATHATAN..ARABIC SUKUN 0657..0658 ; Diacritic # Mn [2] ARABIC INVERTED DAMMA..ARABIC MARK NOON GHUNNA 06DF..06E0 ; Diacritic # Mn [2] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH UPRIGHT RECTANGULAR ZERO @@ -990,6 +1001,8 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1AB0..1ABD ; Diacritic # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Diacritic # Me COMBINING PARENTHESES OVERLAY 1AC1..1ACB ; Diacritic # Mn [11] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING TRIPLE ACUTE ACCENT +1ACF..1ADD ; Diacritic # Mn [15] COMBINING DOUBLE CARON..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Diacritic # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B34 ; Diacritic # Mn BALINESE SIGN REREKAN 1B44 ; Diacritic # Mc BALINESE ADEG ADEG 1B6B..1B73 ; Diacritic # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG @@ -1009,6 +1022,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1CF7 ; Diacritic # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Diacritic # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI +1D9B..1DBE ; Diacritic # Lm [36] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL EZH 1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW 1DF5..1DFF ; Diacritic # Mn [11] COMBINING UP TACK ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Diacritic # Sk GREEK KORONIS @@ -1034,6 +1048,7 @@ A717..A71F ; Diacritic # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER A720..A721 ; Diacritic # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE A788 ; Diacritic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Diacritic # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN +A7F1 ; Diacritic # Lm MODIFIER LETTER CAPITAL S A7F8..A7F9 ; Diacritic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A806 ; Diacritic # Mn SYLOTI NAGRI SIGN HASANTA A82C ; Diacritic # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA @@ -1077,6 +1092,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 10D24..10D27 ; Diacritic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D4E ; Diacritic # Lm GARAY VOWEL LENGTH MARK 10D69..10D6D ; Diacritic # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10EFA ; Diacritic # Mn ARABIC DOUBLE VERTICAL BAR BELOW 10EFD..10EFF ; Diacritic # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Diacritic # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Diacritic # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW @@ -1120,6 +1136,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA 11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA 11D97 ; Diacritic # Mn GUNJALA GONDI VIRAMA +11DD9 ; Diacritic # Lm TOLONG SIKI SIGN SELA 11F41 ; Diacritic # Mc KAWI SIGN KILLER 11F42 ; Diacritic # Mn KAWI CONJOINER 11F5A ; Diacritic # Mn KAWI SIGN NUKTA @@ -1150,7 +1167,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1178 +# Total code points: 1247 # ================================================ @@ -1190,14 +1207,16 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 113D3 ; Extender # Lo TULU-TIGALARI SIGN PLUTA 115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3 11A98 ; Extender # Mn SOYOMBO GEMINATION MARK +11DD9 ; Extender # Lm TOLONG SIKI SIGN SELA 16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM 16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Extender # Lm OLD CHINESE ITERATION MARK +16FF2..16FF3 ; Extender # Lm [2] CHINESE SMALL SIMPLIFIED ER..CHINESE SMALL TRADITIONAL ER 1E13C..1E13D ; Extender # Lm [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E5EF ; Extender # Mn OL ONAL SIGN IKIR 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 59 +# Total code points: 62 # ================================================ @@ -1220,7 +1239,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V A69C..A69D ; Other_Lowercase # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; Other_Lowercase # Lm MODIFIER LETTER US -A7F2..A7F4 ; Other_Lowercase # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Other_Lowercase # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Other_Lowercase # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W @@ -1230,7 +1249,7 @@ AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W 107B2..107BA ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1E030..1E06D ; Other_Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE -# Total code points: 311 +# Total code points: 312 # ================================================ @@ -1359,15 +1378,14 @@ FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21 FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24 FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29 20000..2A6DF ; Unified_Ideograph # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF -2A700..2B739 ; Unified_Ideograph # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 -2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D -2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2A700..2B81D ; Unified_Ideograph # Lo [4382] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEAD ; Unified_Ideograph # Lo [5774] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEAD 2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2EBF0..2EE5D ; Unified_Ideograph # Lo [622] CJK UNIFIED IDEOGRAPH-2EBF0..CJK UNIFIED IDEOGRAPH-2EE5D 30000..3134A ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -31350..323AF ; Unified_Ideograph # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +31350..33479 ; Unified_Ideograph # Lo [8490] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-33479 -# Total code points: 97680 +# Total code points: 101996 # ================================================ @@ -1809,9 +1827,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2B47..2B4C ; Pattern_Syntax # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B73 ; Pattern_Syntax # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B74..2B75 ; Pattern_Syntax # Cn [2] .. -2B76..2B95 ; Pattern_Syntax # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B96 ; Pattern_Syntax # Cn -2B97..2BFF ; Pattern_Syntax # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; Pattern_Syntax # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER 2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET 2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET diff --git a/data/emoji-data.txt b/data/emoji-data.txt index ff99028..450252c 100644 --- a/data/emoji-data.txt +++ b/data/emoji-data.txt @@ -1,11 +1,11 @@ # emoji-data.txt -# Date: 2024-05-01, 21:25:24 GMT -# © 2024 Unicode®, Inc. +# Date: 2025-07-25, 17:54:31 GMT +# © 2025 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html # # Emoji Data for UTS #51 -# Used with Emoji Version 16.0 and subsequent minor revisions (if any) +# Version: 17.0 # # For documentation and usage, see https://www.unicode.org/reports/tr51 # @@ -340,6 +340,7 @@ 1F6D1..1F6D2 ; Emoji # E3.0 [2] (🛑..🛒) stop sign..shopping cart 1F6D5 ; Emoji # E12.0 [1] (🛕) hindu temple 1F6D6..1F6D7 ; Emoji # E13.0 [2] (🛖..🛗) hut..elevator +1F6D8 ; Emoji # E17.0 [1] (🛘) landslide 1F6DC ; Emoji # E15.0 [1] (🛜) wireless 1F6DD..1F6DF ; Emoji # E14.0 [3] (🛝..🛟) playground slide..ring buoy 1F6E0..1F6E5 ; Emoji # E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat @@ -408,6 +409,8 @@ 1FA83..1FA86 ; Emoji # E13.0 [4] (🪃..🪆) boomerang..nesting dolls 1FA87..1FA88 ; Emoji # E15.0 [2] (🪇..🪈) maracas..flute 1FA89 ; Emoji # E16.0 [1] (🪉) harp +1FA8A ; Emoji # E17.0 [1] (🪊) trombone +1FA8E ; Emoji # E17.0 [1] (🪎) treasure chest 1FA8F ; Emoji # E16.0 [1] (🪏) shovel 1FA90..1FA95 ; Emoji # E12.0 [6] (🪐..🪕) ringed planet..banjo 1FA96..1FAA8 ; Emoji # E13.0 [19] (🪖..🪨) military helmet..rock @@ -421,6 +424,8 @@ 1FAC0..1FAC2 ; Emoji # E13.0 [3] (🫀..🫂) anatomical heart..people hugging 1FAC3..1FAC5 ; Emoji # E14.0 [3] (🫃..🫅) pregnant man..person with crown 1FAC6 ; Emoji # E16.0 [1] (🫆) fingerprint +1FAC8 ; Emoji # E17.0 [1] (🫈) hairy creature +1FACD ; Emoji # E17.0 [1] (🫍) orca 1FACE..1FACF ; Emoji # E15.0 [2] (🫎..🫏) moose..donkey 1FAD0..1FAD6 ; Emoji # E13.0 [7] (🫐..🫖) blueberries..teapot 1FAD7..1FAD9 ; Emoji # E14.0 [3] (🫗..🫙) pouring liquid..jar @@ -430,10 +435,12 @@ 1FAE0..1FAE7 ; Emoji # E14.0 [8] (🫠..🫧) melting face..bubbles 1FAE8 ; Emoji # E15.0 [1] (🫨) shaking face 1FAE9 ; Emoji # E16.0 [1] (🫩) face with bags under eyes +1FAEA ; Emoji # E17.0 [1] (🫪) distorted face +1FAEF ; Emoji # E17.0 [1] (🫯) fight cloud 1FAF0..1FAF6 ; Emoji # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands 1FAF7..1FAF8 ; Emoji # E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand -# Total elements: 1431 +# Total elements: 1438 # ================================================ @@ -640,6 +647,7 @@ 1F6D1..1F6D2 ; Emoji_Presentation # E3.0 [2] (🛑..🛒) stop sign..shopping cart 1F6D5 ; Emoji_Presentation # E12.0 [1] (🛕) hindu temple 1F6D6..1F6D7 ; Emoji_Presentation # E13.0 [2] (🛖..🛗) hut..elevator +1F6D8 ; Emoji_Presentation # E17.0 [1] (🛘) landslide 1F6DC ; Emoji_Presentation # E15.0 [1] (🛜) wireless 1F6DD..1F6DF ; Emoji_Presentation # E14.0 [3] (🛝..🛟) playground slide..ring buoy 1F6EB..1F6EC ; Emoji_Presentation # E1.0 [2] (🛫..🛬) airplane departure..airplane arrival @@ -704,6 +712,8 @@ 1FA83..1FA86 ; Emoji_Presentation # E13.0 [4] (🪃..🪆) boomerang..nesting dolls 1FA87..1FA88 ; Emoji_Presentation # E15.0 [2] (🪇..🪈) maracas..flute 1FA89 ; Emoji_Presentation # E16.0 [1] (🪉) harp +1FA8A ; Emoji_Presentation # E17.0 [1] (🪊) trombone +1FA8E ; Emoji_Presentation # E17.0 [1] (🪎) treasure chest 1FA8F ; Emoji_Presentation # E16.0 [1] (🪏) shovel 1FA90..1FA95 ; Emoji_Presentation # E12.0 [6] (🪐..🪕) ringed planet..banjo 1FA96..1FAA8 ; Emoji_Presentation # E13.0 [19] (🪖..🪨) military helmet..rock @@ -717,6 +727,8 @@ 1FAC0..1FAC2 ; Emoji_Presentation # E13.0 [3] (🫀..🫂) anatomical heart..people hugging 1FAC3..1FAC5 ; Emoji_Presentation # E14.0 [3] (🫃..🫅) pregnant man..person with crown 1FAC6 ; Emoji_Presentation # E16.0 [1] (🫆) fingerprint +1FAC8 ; Emoji_Presentation # E17.0 [1] (🫈) hairy creature +1FACD ; Emoji_Presentation # E17.0 [1] (🫍) orca 1FACE..1FACF ; Emoji_Presentation # E15.0 [2] (🫎..🫏) moose..donkey 1FAD0..1FAD6 ; Emoji_Presentation # E13.0 [7] (🫐..🫖) blueberries..teapot 1FAD7..1FAD9 ; Emoji_Presentation # E14.0 [3] (🫗..🫙) pouring liquid..jar @@ -726,10 +738,12 @@ 1FAE0..1FAE7 ; Emoji_Presentation # E14.0 [8] (🫠..🫧) melting face..bubbles 1FAE8 ; Emoji_Presentation # E15.0 [1] (🫨) shaking face 1FAE9 ; Emoji_Presentation # E16.0 [1] (🫩) face with bags under eyes +1FAEA ; Emoji_Presentation # E17.0 [1] (🫪) distorted face +1FAEF ; Emoji_Presentation # E17.0 [1] (🫯) fight cloud 1FAF0..1FAF6 ; Emoji_Presentation # E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands 1FAF7..1FAF8 ; Emoji_Presentation # E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand -# Total elements: 1212 +# Total elements: 1219 # ================================================ @@ -827,7 +841,6 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 21A9..21AA ; Extended_Pictographic# E0.6 [2] (↩️..↪️) right arrow curving left..left arrow curving right 231A..231B ; Extended_Pictographic# E0.6 [2] (⌚..⌛) watch..hourglass done 2328 ; Extended_Pictographic# E1.0 [1] (⌨️) keyboard -2388 ; Extended_Pictographic# E0.0 [1] (⎈) HELM SYMBOL 23CF ; Extended_Pictographic# E1.0 [1] (⏏️) eject button 23E9..23EC ; Extended_Pictographic# E0.6 [4] (⏩..⏬) fast-forward button..fast down button 23ED..23EE ; Extended_Pictographic# E0.7 [2] (⏭️..⏮️) next track button..last track button @@ -844,106 +857,63 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 2600..2601 ; Extended_Pictographic# E0.6 [2] (☀️..☁️) sun..cloud 2602..2603 ; Extended_Pictographic# E0.7 [2] (☂️..☃️) umbrella..snowman 2604 ; Extended_Pictographic# E1.0 [1] (☄️) comet -2605 ; Extended_Pictographic# E0.0 [1] (★) BLACK STAR -2607..260D ; Extended_Pictographic# E0.0 [7] (☇..☍) LIGHTNING..OPPOSITION 260E ; Extended_Pictographic# E0.6 [1] (☎️) telephone -260F..2610 ; Extended_Pictographic# E0.0 [2] (☏..☐) WHITE TELEPHONE..BALLOT BOX 2611 ; Extended_Pictographic# E0.6 [1] (☑️) check box with check -2612 ; Extended_Pictographic# E0.0 [1] (☒) BALLOT BOX WITH X 2614..2615 ; Extended_Pictographic# E0.6 [2] (☔..☕) umbrella with rain drops..hot beverage -2616..2617 ; Extended_Pictographic# E0.0 [2] (☖..☗) WHITE SHOGI PIECE..BLACK SHOGI PIECE 2618 ; Extended_Pictographic# E1.0 [1] (☘️) shamrock -2619..261C ; Extended_Pictographic# E0.0 [4] (☙..☜) REVERSED ROTATED FLORAL HEART BULLET..WHITE LEFT POINTING INDEX 261D ; Extended_Pictographic# E0.6 [1] (☝️) index pointing up -261E..261F ; Extended_Pictographic# E0.0 [2] (☞..☟) WHITE RIGHT POINTING INDEX..WHITE DOWN POINTING INDEX 2620 ; Extended_Pictographic# E1.0 [1] (☠️) skull and crossbones -2621 ; Extended_Pictographic# E0.0 [1] (☡) CAUTION SIGN 2622..2623 ; Extended_Pictographic# E1.0 [2] (☢️..☣️) radioactive..biohazard -2624..2625 ; Extended_Pictographic# E0.0 [2] (☤..☥) CADUCEUS..ANKH 2626 ; Extended_Pictographic# E1.0 [1] (☦️) orthodox cross -2627..2629 ; Extended_Pictographic# E0.0 [3] (☧..☩) CHI RHO..CROSS OF JERUSALEM 262A ; Extended_Pictographic# E0.7 [1] (☪️) star and crescent -262B..262D ; Extended_Pictographic# E0.0 [3] (☫..☭) FARSI SYMBOL..HAMMER AND SICKLE 262E ; Extended_Pictographic# E1.0 [1] (☮️) peace symbol 262F ; Extended_Pictographic# E0.7 [1] (☯️) yin yang -2630..2637 ; Extended_Pictographic# E0.0 [8] (☰..☷) TRIGRAM FOR HEAVEN..TRIGRAM FOR EARTH 2638..2639 ; Extended_Pictographic# E0.7 [2] (☸️..☹️) wheel of dharma..frowning face 263A ; Extended_Pictographic# E0.6 [1] (☺️) smiling face -263B..263F ; Extended_Pictographic# E0.0 [5] (☻..☿) BLACK SMILING FACE..MERCURY 2640 ; Extended_Pictographic# E4.0 [1] (♀️) female sign -2641 ; Extended_Pictographic# E0.0 [1] (♁) EARTH 2642 ; Extended_Pictographic# E4.0 [1] (♂️) male sign -2643..2647 ; Extended_Pictographic# E0.0 [5] (♃..♇) JUPITER..PLUTO 2648..2653 ; Extended_Pictographic# E0.6 [12] (♈..♓) Aries..Pisces -2654..265E ; Extended_Pictographic# E0.0 [11] (♔..♞) WHITE CHESS KING..BLACK CHESS KNIGHT 265F ; Extended_Pictographic# E11.0 [1] (♟️) chess pawn 2660 ; Extended_Pictographic# E0.6 [1] (♠️) spade suit -2661..2662 ; Extended_Pictographic# E0.0 [2] (♡..♢) WHITE HEART SUIT..WHITE DIAMOND SUIT 2663 ; Extended_Pictographic# E0.6 [1] (♣️) club suit -2664 ; Extended_Pictographic# E0.0 [1] (♤) WHITE SPADE SUIT 2665..2666 ; Extended_Pictographic# E0.6 [2] (♥️..♦️) heart suit..diamond suit -2667 ; Extended_Pictographic# E0.0 [1] (♧) WHITE CLUB SUIT 2668 ; Extended_Pictographic# E0.6 [1] (♨️) hot springs -2669..267A ; Extended_Pictographic# E0.0 [18] (♩..♺) QUARTER NOTE..RECYCLING SYMBOL FOR GENERIC MATERIALS 267B ; Extended_Pictographic# E0.6 [1] (♻️) recycling symbol -267C..267D ; Extended_Pictographic# E0.0 [2] (♼..♽) RECYCLED PAPER SYMBOL..PARTIALLY-RECYCLED PAPER SYMBOL 267E ; Extended_Pictographic# E11.0 [1] (♾️) infinity 267F ; Extended_Pictographic# E0.6 [1] (♿) wheelchair symbol -2680..2685 ; Extended_Pictographic# E0.0 [6] (⚀..⚅) DIE FACE-1..DIE FACE-6 -2690..2691 ; Extended_Pictographic# E0.0 [2] (⚐..⚑) WHITE FLAG..BLACK FLAG 2692 ; Extended_Pictographic# E1.0 [1] (⚒️) hammer and pick 2693 ; Extended_Pictographic# E0.6 [1] (⚓) anchor 2694 ; Extended_Pictographic# E1.0 [1] (⚔️) crossed swords 2695 ; Extended_Pictographic# E4.0 [1] (⚕️) medical symbol 2696..2697 ; Extended_Pictographic# E1.0 [2] (⚖️..⚗️) balance scale..alembic -2698 ; Extended_Pictographic# E0.0 [1] (⚘) FLOWER 2699 ; Extended_Pictographic# E1.0 [1] (⚙️) gear -269A ; Extended_Pictographic# E0.0 [1] (⚚) STAFF OF HERMES 269B..269C ; Extended_Pictographic# E1.0 [2] (⚛️..⚜️) atom symbol..fleur-de-lis -269D..269F ; Extended_Pictographic# E0.0 [3] (⚝..⚟) OUTLINED WHITE STAR..THREE LINES CONVERGING LEFT 26A0..26A1 ; Extended_Pictographic# E0.6 [2] (⚠️..⚡) warning..high voltage -26A2..26A6 ; Extended_Pictographic# E0.0 [5] (⚢..⚦) DOUBLED FEMALE SIGN..MALE WITH STROKE SIGN 26A7 ; Extended_Pictographic# E13.0 [1] (⚧️) transgender symbol -26A8..26A9 ; Extended_Pictographic# E0.0 [2] (⚨..⚩) VERTICAL MALE WITH STROKE SIGN..HORIZONTAL MALE WITH STROKE SIGN 26AA..26AB ; Extended_Pictographic# E0.6 [2] (⚪..⚫) white circle..black circle -26AC..26AF ; Extended_Pictographic# E0.0 [4] (⚬..⚯) MEDIUM SMALL WHITE CIRCLE..UNMARRIED PARTNERSHIP SYMBOL 26B0..26B1 ; Extended_Pictographic# E1.0 [2] (⚰️..⚱️) coffin..funeral urn -26B2..26BC ; Extended_Pictographic# E0.0 [11] (⚲..⚼) NEUTER..SESQUIQUADRATE 26BD..26BE ; Extended_Pictographic# E0.6 [2] (⚽..⚾) soccer ball..baseball -26BF..26C3 ; Extended_Pictographic# E0.0 [5] (⚿..⛃) SQUARED KEY..BLACK DRAUGHTS KING 26C4..26C5 ; Extended_Pictographic# E0.6 [2] (⛄..⛅) snowman without snow..sun behind cloud -26C6..26C7 ; Extended_Pictographic# E0.0 [2] (⛆..⛇) RAIN..BLACK SNOWMAN 26C8 ; Extended_Pictographic# E0.7 [1] (⛈️) cloud with lightning and rain -26C9..26CD ; Extended_Pictographic# E0.0 [5] (⛉..⛍) TURNED WHITE SHOGI PIECE..DISABLED CAR 26CE ; Extended_Pictographic# E0.6 [1] (⛎) Ophiuchus 26CF ; Extended_Pictographic# E0.7 [1] (⛏️) pick -26D0 ; Extended_Pictographic# E0.0 [1] (⛐) CAR SLIDING 26D1 ; Extended_Pictographic# E0.7 [1] (⛑️) rescue worker’s helmet -26D2 ; Extended_Pictographic# E0.0 [1] (⛒) CIRCLED CROSSING LANES 26D3 ; Extended_Pictographic# E0.7 [1] (⛓️) chains 26D4 ; Extended_Pictographic# E0.6 [1] (⛔) no entry -26D5..26E8 ; Extended_Pictographic# E0.0 [20] (⛕..⛨) ALTERNATE ONE-WAY LEFT WAY TRAFFIC..BLACK CROSS ON SHIELD 26E9 ; Extended_Pictographic# E0.7 [1] (⛩️) shinto shrine 26EA ; Extended_Pictographic# E0.6 [1] (⛪) church -26EB..26EF ; Extended_Pictographic# E0.0 [5] (⛫..⛯) CASTLE..MAP SYMBOL FOR LIGHTHOUSE 26F0..26F1 ; Extended_Pictographic# E0.7 [2] (⛰️..⛱️) mountain..umbrella on ground 26F2..26F3 ; Extended_Pictographic# E0.6 [2] (⛲..⛳) fountain..flag in hole 26F4 ; Extended_Pictographic# E0.7 [1] (⛴️) ferry 26F5 ; Extended_Pictographic# E0.6 [1] (⛵) sailboat -26F6 ; Extended_Pictographic# E0.0 [1] (⛶) SQUARE FOUR CORNERS 26F7..26F9 ; Extended_Pictographic# E0.7 [3] (⛷️..⛹️) skier..person bouncing ball 26FA ; Extended_Pictographic# E0.6 [1] (⛺) tent -26FB..26FC ; Extended_Pictographic# E0.0 [2] (⛻..⛼) JAPANESE BANK SYMBOL..HEADSTONE GRAVEYARD SYMBOL 26FD ; Extended_Pictographic# E0.6 [1] (⛽) fuel pump -26FE..2701 ; Extended_Pictographic# E0.0 [4] (⛾..✁) CUP ON BLACK SQUARE..UPPER BLADE SCISSORS 2702 ; Extended_Pictographic# E0.6 [1] (✂️) scissors -2703..2704 ; Extended_Pictographic# E0.0 [2] (✃..✄) LOWER BLADE SCISSORS..WHITE SCISSORS 2705 ; Extended_Pictographic# E0.6 [1] (✅) check mark button 2708..270C ; Extended_Pictographic# E0.6 [5] (✈️..✌️) airplane..victory hand 270D ; Extended_Pictographic# E0.7 [1] (✍️) writing hand -270E ; Extended_Pictographic# E0.0 [1] (✎) LOWER RIGHT PENCIL 270F ; Extended_Pictographic# E0.6 [1] (✏️) pencil -2710..2711 ; Extended_Pictographic# E0.0 [2] (✐..✑) UPPER RIGHT PENCIL..WHITE NIB 2712 ; Extended_Pictographic# E0.6 [1] (✒️) black nib 2714 ; Extended_Pictographic# E0.6 [1] (✔️) check mark 2716 ; Extended_Pictographic# E0.6 [1] (✖️) multiply @@ -959,7 +929,6 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 2757 ; Extended_Pictographic# E0.6 [1] (❗) red exclamation mark 2763 ; Extended_Pictographic# E1.0 [1] (❣️) heart exclamation 2764 ; Extended_Pictographic# E0.6 [1] (❤️) red heart -2765..2767 ; Extended_Pictographic# E0.0 [3] (❥..❧) ROTATED HEAVY BLACK HEART BULLET..ROTATED FLORAL HEART BULLET 2795..2797 ; Extended_Pictographic# E0.6 [3] (➕..➗) plus..divide 27A1 ; Extended_Pictographic# E0.6 [1] (➡️) right arrow 27B0 ; Extended_Pictographic# E0.6 [1] (➰) curly loop @@ -973,19 +942,19 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 303D ; Extended_Pictographic# E0.6 [1] (〽️) part alternation mark 3297 ; Extended_Pictographic# E0.6 [1] (㊗️) Japanese “congratulations” button 3299 ; Extended_Pictographic# E0.6 [1] (㊙️) Japanese “secret” button -1F000..1F003 ; Extended_Pictographic# E0.0 [4] (🀀..🀃) MAHJONG TILE EAST WIND..MAHJONG TILE NORTH WIND 1F004 ; Extended_Pictographic# E0.6 [1] (🀄) mahjong red dragon -1F005..1F0CE ; Extended_Pictographic# E0.0 [202] (🀅..🃎) MAHJONG TILE GREEN DRAGON..PLAYING CARD KING OF DIAMONDS +1F02C..1F02F ; Extended_Pictographic# E0.0 [4] (🀬..🀯) .. +1F094..1F09F ; Extended_Pictographic# E0.0 [12] (🂔..🂟) .. +1F0AF..1F0B0 ; Extended_Pictographic# E0.0 [2] (🂯..🂰) .. +1F0C0 ; Extended_Pictographic# E0.0 [1] (🃀) 1F0CF ; Extended_Pictographic# E0.6 [1] (🃏) joker -1F0D0..1F0FF ; Extended_Pictographic# E0.0 [48] (🃐..🃿) .. -1F10D..1F10F ; Extended_Pictographic# E0.0 [3] (🄍..🄏) CIRCLED ZERO WITH SLASH..CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH -1F12F ; Extended_Pictographic# E0.0 [1] (🄯) COPYLEFT SYMBOL -1F16C..1F16F ; Extended_Pictographic# E0.0 [4] (🅬..🅯) RAISED MR SIGN..CIRCLED HUMAN FIGURE +1F0D0 ; Extended_Pictographic# E0.0 [1] (🃐) +1F0F6..1F0FF ; Extended_Pictographic# E0.0 [10] (🃶..🃿) .. 1F170..1F171 ; Extended_Pictographic# E0.6 [2] (🅰️..🅱️) A button (blood type)..B button (blood type) 1F17E..1F17F ; Extended_Pictographic# E0.6 [2] (🅾️..🅿️) O button (blood type)..P button 1F18E ; Extended_Pictographic# E0.6 [1] (🆎) AB button (blood type) 1F191..1F19A ; Extended_Pictographic# E0.6 [10] (🆑..🆚) CL button..VS button -1F1AD..1F1E5 ; Extended_Pictographic# E0.0 [57] (🆭..🇥) MASK WORK SYMBOL.. +1F1AE..1F1E5 ; Extended_Pictographic# E0.0 [56] (🆮..🇥) .. 1F201..1F202 ; Extended_Pictographic# E0.6 [2] (🈁..🈂️) Japanese “here” button..Japanese “service charge” button 1F203..1F20F ; Extended_Pictographic# E0.0 [13] (🈃..🈏) .. 1F21A ; Extended_Pictographic# E0.6 [1] (🈚) Japanese “free of charge” button @@ -994,7 +963,8 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F23C..1F23F ; Extended_Pictographic# E0.0 [4] (🈼..🈿) .. 1F249..1F24F ; Extended_Pictographic# E0.0 [7] (🉉..🉏) .. 1F250..1F251 ; Extended_Pictographic# E0.6 [2] (🉐..🉑) Japanese “bargain” button..Japanese “acceptable” button -1F252..1F2FF ; Extended_Pictographic# E0.0 [174] (🉒..🋿) .. +1F252..1F25F ; Extended_Pictographic# E0.0 [14] (🉒..🉟) .. +1F266..1F2FF ; Extended_Pictographic# E0.0 [154] (🉦..🋿) .. 1F300..1F30C ; Extended_Pictographic# E0.6 [13] (🌀..🌌) cyclone..milky way 1F30D..1F30E ; Extended_Pictographic# E0.7 [2] (🌍..🌎) globe showing Europe-Africa..globe showing Americas 1F30F ; Extended_Pictographic# E0.6 [1] (🌏) globe showing Asia-Australia @@ -1010,7 +980,6 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F31D..1F31E ; Extended_Pictographic# E1.0 [2] (🌝..🌞) full moon face..sun with face 1F31F..1F320 ; Extended_Pictographic# E0.6 [2] (🌟..🌠) glowing star..shooting star 1F321 ; Extended_Pictographic# E0.7 [1] (🌡️) thermometer -1F322..1F323 ; Extended_Pictographic# E0.0 [2] (🌢..🌣) BLACK DROPLET..WHITE SUN 1F324..1F32C ; Extended_Pictographic# E0.7 [9] (🌤️..🌬️) sun behind small cloud..wind face 1F32D..1F32F ; Extended_Pictographic# E1.0 [3] (🌭..🌯) hot dog..burrito 1F330..1F331 ; Extended_Pictographic# E0.6 [2] (🌰..🌱) chestnut..seedling @@ -1026,11 +995,8 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F37D ; Extended_Pictographic# E0.7 [1] (🍽️) fork and knife with plate 1F37E..1F37F ; Extended_Pictographic# E1.0 [2] (🍾..🍿) bottle with popping cork..popcorn 1F380..1F393 ; Extended_Pictographic# E0.6 [20] (🎀..🎓) ribbon..graduation cap -1F394..1F395 ; Extended_Pictographic# E0.0 [2] (🎔..🎕) HEART WITH TIP ON THE LEFT..BOUQUET OF FLOWERS 1F396..1F397 ; Extended_Pictographic# E0.7 [2] (🎖️..🎗️) military medal..reminder ribbon -1F398 ; Extended_Pictographic# E0.0 [1] (🎘) MUSICAL KEYBOARD WITH JACKS 1F399..1F39B ; Extended_Pictographic# E0.7 [3] (🎙️..🎛️) studio microphone..control knobs -1F39C..1F39D ; Extended_Pictographic# E0.0 [2] (🎜..🎝) BEAMED ASCENDING MUSICAL NOTES..BEAMED DESCENDING MUSICAL NOTES 1F39E..1F39F ; Extended_Pictographic# E0.7 [2] (🎞️..🎟️) film frames..admission tickets 1F3A0..1F3C4 ; Extended_Pictographic# E0.6 [37] (🎠..🏄) carousel horse..person surfing 1F3C5 ; Extended_Pictographic# E1.0 [1] (🏅) sports medal @@ -1045,11 +1011,9 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F3E0..1F3E3 ; Extended_Pictographic# E0.6 [4] (🏠..🏣) house..Japanese post office 1F3E4 ; Extended_Pictographic# E1.0 [1] (🏤) post office 1F3E5..1F3F0 ; Extended_Pictographic# E0.6 [12] (🏥..🏰) hospital..castle -1F3F1..1F3F2 ; Extended_Pictographic# E0.0 [2] (🏱..🏲) WHITE PENNANT..BLACK PENNANT 1F3F3 ; Extended_Pictographic# E0.7 [1] (🏳️) white flag 1F3F4 ; Extended_Pictographic# E1.0 [1] (🏴) black flag 1F3F5 ; Extended_Pictographic# E0.7 [1] (🏵️) rosette -1F3F6 ; Extended_Pictographic# E0.0 [1] (🏶) BLACK ROSETTE 1F3F7 ; Extended_Pictographic# E0.7 [1] (🏷️) label 1F3F8..1F3FA ; Extended_Pictographic# E1.0 [3] (🏸..🏺) badminton..amphora 1F400..1F407 ; Extended_Pictographic# E1.0 [8] (🐀..🐇) rat..rabbit @@ -1086,7 +1050,6 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F4F8 ; Extended_Pictographic# E1.0 [1] (📸) camera with flash 1F4F9..1F4FC ; Extended_Pictographic# E0.6 [4] (📹..📼) video camera..videocassette 1F4FD ; Extended_Pictographic# E0.7 [1] (📽️) film projector -1F4FE ; Extended_Pictographic# E0.0 [1] (📾) PORTABLE STEREO 1F4FF..1F502 ; Extended_Pictographic# E1.0 [4] (📿..🔂) prayer beads..repeat single button 1F503 ; Extended_Pictographic# E0.6 [1] (🔃) clockwise vertical arrows 1F504..1F507 ; Extended_Pictographic# E1.0 [4] (🔄..🔇) counterclockwise arrows button..muted speaker @@ -1097,51 +1060,30 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F516..1F52B ; Extended_Pictographic# E0.6 [22] (🔖..🔫) bookmark..water pistol 1F52C..1F52D ; Extended_Pictographic# E1.0 [2] (🔬..🔭) microscope..telescope 1F52E..1F53D ; Extended_Pictographic# E0.6 [16] (🔮..🔽) crystal ball..downwards button -1F546..1F548 ; Extended_Pictographic# E0.0 [3] (🕆..🕈) WHITE LATIN CROSS..CELTIC CROSS 1F549..1F54A ; Extended_Pictographic# E0.7 [2] (🕉️..🕊️) om..dove 1F54B..1F54E ; Extended_Pictographic# E1.0 [4] (🕋..🕎) kaaba..menorah -1F54F ; Extended_Pictographic# E0.0 [1] (🕏) BOWL OF HYGIEIA 1F550..1F55B ; Extended_Pictographic# E0.6 [12] (🕐..🕛) one o’clock..twelve o’clock 1F55C..1F567 ; Extended_Pictographic# E0.7 [12] (🕜..🕧) one-thirty..twelve-thirty -1F568..1F56E ; Extended_Pictographic# E0.0 [7] (🕨..🕮) RIGHT SPEAKER..BOOK 1F56F..1F570 ; Extended_Pictographic# E0.7 [2] (🕯️..🕰️) candle..mantelpiece clock -1F571..1F572 ; Extended_Pictographic# E0.0 [2] (🕱..🕲) BLACK SKULL AND CROSSBONES..NO PIRACY 1F573..1F579 ; Extended_Pictographic# E0.7 [7] (🕳️..🕹️) hole..joystick 1F57A ; Extended_Pictographic# E3.0 [1] (🕺) man dancing -1F57B..1F586 ; Extended_Pictographic# E0.0 [12] (🕻..🖆) LEFT HAND TELEPHONE RECEIVER..PEN OVER STAMPED ENVELOPE 1F587 ; Extended_Pictographic# E0.7 [1] (🖇️) linked paperclips -1F588..1F589 ; Extended_Pictographic# E0.0 [2] (🖈..🖉) BLACK PUSHPIN..LOWER LEFT PENCIL 1F58A..1F58D ; Extended_Pictographic# E0.7 [4] (🖊️..🖍️) pen..crayon -1F58E..1F58F ; Extended_Pictographic# E0.0 [2] (🖎..🖏) LEFT WRITING HAND..TURNED OK HAND SIGN 1F590 ; Extended_Pictographic# E0.7 [1] (🖐️) hand with fingers splayed -1F591..1F594 ; Extended_Pictographic# E0.0 [4] (🖑..🖔) REVERSED RAISED HAND WITH FINGERS SPLAYED..REVERSED VICTORY HAND 1F595..1F596 ; Extended_Pictographic# E1.0 [2] (🖕..🖖) middle finger..vulcan salute -1F597..1F5A3 ; Extended_Pictographic# E0.0 [13] (🖗..🖣) WHITE DOWN POINTING LEFT HAND INDEX..BLACK DOWN POINTING BACKHAND INDEX 1F5A4 ; Extended_Pictographic# E3.0 [1] (🖤) black heart 1F5A5 ; Extended_Pictographic# E0.7 [1] (🖥️) desktop computer -1F5A6..1F5A7 ; Extended_Pictographic# E0.0 [2] (🖦..🖧) KEYBOARD AND MOUSE..THREE NETWORKED COMPUTERS 1F5A8 ; Extended_Pictographic# E0.7 [1] (🖨️) printer -1F5A9..1F5B0 ; Extended_Pictographic# E0.0 [8] (🖩..🖰) POCKET CALCULATOR..TWO BUTTON MOUSE 1F5B1..1F5B2 ; Extended_Pictographic# E0.7 [2] (🖱️..🖲️) computer mouse..trackball -1F5B3..1F5BB ; Extended_Pictographic# E0.0 [9] (🖳..🖻) OLD PERSONAL COMPUTER..DOCUMENT WITH PICTURE 1F5BC ; Extended_Pictographic# E0.7 [1] (🖼️) framed picture -1F5BD..1F5C1 ; Extended_Pictographic# E0.0 [5] (🖽..🗁) FRAME WITH TILES..OPEN FOLDER 1F5C2..1F5C4 ; Extended_Pictographic# E0.7 [3] (🗂️..🗄️) card index dividers..file cabinet -1F5C5..1F5D0 ; Extended_Pictographic# E0.0 [12] (🗅..🗐) EMPTY NOTE..PAGES 1F5D1..1F5D3 ; Extended_Pictographic# E0.7 [3] (🗑️..🗓️) wastebasket..spiral calendar -1F5D4..1F5DB ; Extended_Pictographic# E0.0 [8] (🗔..🗛) DESKTOP WINDOW..DECREASE FONT SIZE SYMBOL 1F5DC..1F5DE ; Extended_Pictographic# E0.7 [3] (🗜️..🗞️) clamp..rolled-up newspaper -1F5DF..1F5E0 ; Extended_Pictographic# E0.0 [2] (🗟..🗠) PAGE WITH CIRCLED TEXT..STOCK CHART 1F5E1 ; Extended_Pictographic# E0.7 [1] (🗡️) dagger -1F5E2 ; Extended_Pictographic# E0.0 [1] (🗢) LIPS 1F5E3 ; Extended_Pictographic# E0.7 [1] (🗣️) speaking head -1F5E4..1F5E7 ; Extended_Pictographic# E0.0 [4] (🗤..🗧) THREE RAYS ABOVE..THREE RAYS RIGHT 1F5E8 ; Extended_Pictographic# E2.0 [1] (🗨️) left speech bubble -1F5E9..1F5EE ; Extended_Pictographic# E0.0 [6] (🗩..🗮) RIGHT SPEECH BUBBLE..LEFT ANGER BUBBLE 1F5EF ; Extended_Pictographic# E0.7 [1] (🗯️) right anger bubble -1F5F0..1F5F2 ; Extended_Pictographic# E0.0 [3] (🗰..🗲) MOOD BUBBLE..LIGHTNING MOOD 1F5F3 ; Extended_Pictographic# E0.7 [1] (🗳️) ballot box with ballot -1F5F4..1F5F9 ; Extended_Pictographic# E0.0 [6] (🗴..🗹) BALLOT SCRIPT X..BALLOT BOX WITH BOLD CHECK 1F5FA ; Extended_Pictographic# E0.7 [1] (🗺️) world map 1F5FB..1F5FF ; Extended_Pictographic# E0.6 [5] (🗻..🗿) mount fuji..moai 1F600 ; Extended_Pictographic# E1.0 [1] (😀) grinning face @@ -1210,26 +1152,22 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F6BF ; Extended_Pictographic# E1.0 [1] (🚿) shower 1F6C0 ; Extended_Pictographic# E0.6 [1] (🛀) person taking bath 1F6C1..1F6C5 ; Extended_Pictographic# E1.0 [5] (🛁..🛅) bathtub..left luggage -1F6C6..1F6CA ; Extended_Pictographic# E0.0 [5] (🛆..🛊) TRIANGLE WITH ROUNDED CORNERS..GIRLS SYMBOL 1F6CB ; Extended_Pictographic# E0.7 [1] (🛋️) couch and lamp 1F6CC ; Extended_Pictographic# E1.0 [1] (🛌) person in bed 1F6CD..1F6CF ; Extended_Pictographic# E0.7 [3] (🛍️..🛏️) shopping bags..bed 1F6D0 ; Extended_Pictographic# E1.0 [1] (🛐) place of worship 1F6D1..1F6D2 ; Extended_Pictographic# E3.0 [2] (🛑..🛒) stop sign..shopping cart -1F6D3..1F6D4 ; Extended_Pictographic# E0.0 [2] (🛓..🛔) STUPA..PAGODA 1F6D5 ; Extended_Pictographic# E12.0 [1] (🛕) hindu temple 1F6D6..1F6D7 ; Extended_Pictographic# E13.0 [2] (🛖..🛗) hut..elevator -1F6D8..1F6DB ; Extended_Pictographic# E0.0 [4] (🛘..🛛) .. +1F6D8 ; Extended_Pictographic# E17.0 [1] (🛘) landslide +1F6D9..1F6DB ; Extended_Pictographic# E0.0 [3] (🛙..🛛) .. 1F6DC ; Extended_Pictographic# E15.0 [1] (🛜) wireless 1F6DD..1F6DF ; Extended_Pictographic# E14.0 [3] (🛝..🛟) playground slide..ring buoy 1F6E0..1F6E5 ; Extended_Pictographic# E0.7 [6] (🛠️..🛥️) hammer and wrench..motor boat -1F6E6..1F6E8 ; Extended_Pictographic# E0.0 [3] (🛦..🛨) UP-POINTING MILITARY AIRPLANE..UP-POINTING SMALL AIRPLANE 1F6E9 ; Extended_Pictographic# E0.7 [1] (🛩️) small airplane -1F6EA ; Extended_Pictographic# E0.0 [1] (🛪) NORTHEAST-POINTING AIRPLANE 1F6EB..1F6EC ; Extended_Pictographic# E1.0 [2] (🛫..🛬) airplane departure..airplane arrival 1F6ED..1F6EF ; Extended_Pictographic# E0.0 [3] (🛭..🛯) .. 1F6F0 ; Extended_Pictographic# E0.7 [1] (🛰️) satellite -1F6F1..1F6F2 ; Extended_Pictographic# E0.0 [2] (🛱..🛲) ONCOMING FIRE ENGINE..DIESEL LOCOMOTIVE 1F6F3 ; Extended_Pictographic# E0.7 [1] (🛳️) passenger ship 1F6F4..1F6F6 ; Extended_Pictographic# E3.0 [3] (🛴..🛶) kick scooter..canoe 1F6F7..1F6F8 ; Extended_Pictographic# E5.0 [2] (🛷..🛸) sled..flying saucer @@ -1237,8 +1175,7 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F6FA ; Extended_Pictographic# E12.0 [1] (🛺) auto rickshaw 1F6FB..1F6FC ; Extended_Pictographic# E13.0 [2] (🛻..🛼) pickup truck..roller skate 1F6FD..1F6FF ; Extended_Pictographic# E0.0 [3] (🛽..🛿) .. -1F774..1F77F ; Extended_Pictographic# E0.0 [12] (🝴..🝿) LOT OF FORTUNE..ORCUS -1F7D5..1F7DF ; Extended_Pictographic# E0.0 [11] (🟕..🟟) CIRCLED TRIANGLE.. +1F7DA..1F7DF ; Extended_Pictographic# E0.0 [6] (🟚..🟟) .. 1F7E0..1F7EB ; Extended_Pictographic# E12.0 [12] (🟠..🟫) orange circle..brown square 1F7EC..1F7EF ; Extended_Pictographic# E0.0 [4] (🟬..🟯) .. 1F7F0 ; Extended_Pictographic# E14.0 [1] (🟰) heavy equals sign @@ -1247,7 +1184,10 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F848..1F84F ; Extended_Pictographic# E0.0 [8] (🡈..🡏) .. 1F85A..1F85F ; Extended_Pictographic# E0.0 [6] (🡚..🡟) .. 1F888..1F88F ; Extended_Pictographic# E0.0 [8] (🢈..🢏) .. -1F8AE..1F8FF ; Extended_Pictographic# E0.0 [82] (🢮..🣿) .. +1F8AE..1F8AF ; Extended_Pictographic# E0.0 [2] (🢮..🢯) .. +1F8BC..1F8BF ; Extended_Pictographic# E0.0 [4] (🢼..🢿) .. +1F8C2..1F8CF ; Extended_Pictographic# E0.0 [14] (🣂..🣏) .. +1F8D9..1F8FF ; Extended_Pictographic# E0.0 [39] (🣙..🣿) .. 1F90C ; Extended_Pictographic# E13.0 [1] (🤌) pinched fingers 1F90D..1F90F ; Extended_Pictographic# E12.0 [3] (🤍..🤏) white heart..pinching hand 1F910..1F918 ; Extended_Pictographic# E1.0 [9] (🤐..🤘) zipper-mouth face..sign of the horns @@ -1293,7 +1233,8 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1F9CD..1F9CF ; Extended_Pictographic# E12.0 [3] (🧍..🧏) person standing..deaf person 1F9D0..1F9E6 ; Extended_Pictographic# E5.0 [23] (🧐..🧦) face with monocle..socks 1F9E7..1F9FF ; Extended_Pictographic# E11.0 [25] (🧧..🧿) red envelope..nazar amulet -1FA00..1FA6F ; Extended_Pictographic# E0.0 [112] (🨀..🩯) NEUTRAL CHESS KING.. +1FA58..1FA5F ; Extended_Pictographic# E0.0 [8] (🩘..🩟) .. +1FA6E..1FA6F ; Extended_Pictographic# E0.0 [2] (🩮..🩯) .. 1FA70..1FA73 ; Extended_Pictographic# E12.0 [4] (🩰..🩳) ballet shoes..shorts 1FA74 ; Extended_Pictographic# E13.0 [1] (🩴) thong sandal 1FA75..1FA77 ; Extended_Pictographic# E15.0 [3] (🩵..🩷) light blue heart..pink heart @@ -1304,7 +1245,9 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1FA83..1FA86 ; Extended_Pictographic# E13.0 [4] (🪃..🪆) boomerang..nesting dolls 1FA87..1FA88 ; Extended_Pictographic# E15.0 [2] (🪇..🪈) maracas..flute 1FA89 ; Extended_Pictographic# E16.0 [1] (🪉) harp -1FA8A..1FA8E ; Extended_Pictographic# E0.0 [5] (🪊..🪎) .. +1FA8A ; Extended_Pictographic# E17.0 [1] (🪊) trombone +1FA8B..1FA8D ; Extended_Pictographic# E0.0 [3] (🪋..🪍) .. +1FA8E ; Extended_Pictographic# E17.0 [1] (🪎) treasure chest 1FA8F ; Extended_Pictographic# E16.0 [1] (🪏) shovel 1FA90..1FA95 ; Extended_Pictographic# E12.0 [6] (🪐..🪕) ringed planet..banjo 1FA96..1FAA8 ; Extended_Pictographic# E13.0 [19] (🪖..🪨) military helmet..rock @@ -1318,7 +1261,10 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1FAC0..1FAC2 ; Extended_Pictographic# E13.0 [3] (🫀..🫂) anatomical heart..people hugging 1FAC3..1FAC5 ; Extended_Pictographic# E14.0 [3] (🫃..🫅) pregnant man..person with crown 1FAC6 ; Extended_Pictographic# E16.0 [1] (🫆) fingerprint -1FAC7..1FACD ; Extended_Pictographic# E0.0 [7] (🫇..🫍) .. +1FAC7 ; Extended_Pictographic# E0.0 [1] (🫇) +1FAC8 ; Extended_Pictographic# E17.0 [1] (🫈) hairy creature +1FAC9..1FACC ; Extended_Pictographic# E0.0 [4] (🫉..🫌) .. +1FACD ; Extended_Pictographic# E17.0 [1] (🫍) orca 1FACE..1FACF ; Extended_Pictographic# E15.0 [2] (🫎..🫏) moose..donkey 1FAD0..1FAD6 ; Extended_Pictographic# E13.0 [7] (🫐..🫖) blueberries..teapot 1FAD7..1FAD9 ; Extended_Pictographic# E14.0 [3] (🫗..🫙) pouring liquid..jar @@ -1329,12 +1275,14 @@ E0020..E007F ; Emoji_Component # E0.0 [96] (󠀠..󠁿) tag space..c 1FAE0..1FAE7 ; Extended_Pictographic# E14.0 [8] (🫠..🫧) melting face..bubbles 1FAE8 ; Extended_Pictographic# E15.0 [1] (🫨) shaking face 1FAE9 ; Extended_Pictographic# E16.0 [1] (🫩) face with bags under eyes -1FAEA..1FAEF ; Extended_Pictographic# E0.0 [6] (🫪..🫯) .. +1FAEA ; Extended_Pictographic# E17.0 [1] (🫪) distorted face +1FAEB..1FAEE ; Extended_Pictographic# E0.0 [4] (🫫..🫮) .. +1FAEF ; Extended_Pictographic# E17.0 [1] (🫯) fight cloud 1FAF0..1FAF6 ; Extended_Pictographic# E14.0 [7] (🫰..🫶) hand with index finger and thumb crossed..heart hands 1FAF7..1FAF8 ; Extended_Pictographic# E15.0 [2] (🫷..🫸) leftwards pushing hand..rightwards pushing hand 1FAF9..1FAFF ; Extended_Pictographic# E0.0 [7] (🫹..🫿) .. 1FC00..1FFFD ; Extended_Pictographic# E0.0[1022] (🰀..🿽) .. -# Total elements: 3537 +# Total elements: 2848 #EOF diff --git a/data/update.sh b/data/update.sh index a556cab..ed86106 100755 --- a/data/update.sh +++ b/data/update.sh @@ -5,11 +5,11 @@ cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" rm *.txt -wget https://www.unicode.org/Public/UCD/latest/ucd/DerivedCoreProperties.txt -wget https://www.unicode.org/Public/UCD/latest/ucd/extracted/DerivedGeneralCategory.txt -wget https://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt -wget https://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt -wget https://www.unicode.org/Public/UCD/latest/ucd/HangulSyllableType.txt -wget https://www.unicode.org/Public/UCD/latest/ucd/PropList.txt +curl https://www.unicode.org/Public/UCD/latest/ucd/DerivedCoreProperties.txt > DerivedCoreProperties.txt +curl https://www.unicode.org/Public/UCD/latest/ucd/extracted/DerivedGeneralCategory.txt > DerivedGeneralCategory.txt +curl https://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt > EastAsianWidth.txt +curl https://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt > emoji-data.txt +curl https://www.unicode.org/Public/UCD/latest/ucd/HangulSyllableType.txt > HangulSyllableType.txt +curl https://www.unicode.org/Public/UCD/latest/ucd/PropList.txt > PropList.txt popd diff --git a/test/benchmark.gleam b/dev/benchmark.gleam similarity index 88% rename from test/benchmark.gleam rename to dev/benchmark.gleam index 158e9a7..9101292 100644 --- a/test/benchmark.gleam +++ b/dev/benchmark.gleam @@ -1,8 +1,7 @@ -import gleam/io import string_width pub fn main() { - io.debug(loop(1_000_000, 0)) + echo loop(1_000_000, 0) } fn loop(i, sum) { diff --git a/flake.lock b/flake.lock deleted file mode 100644 index dd93f6c..0000000 --- a/flake.lock +++ /dev/null @@ -1,23 +0,0 @@ -{ - "nodes": { - "nixpkgs": { - "locked": { - "lastModified": 0, - "narHash": "sha256-NOiTvBbRLIOe5F6RbHaAh6++BNjsb149fGZd1T4+KBg=", - "path": "/nix/store/sdzpqjwx7pdx6lsq6llyfqqf7hspp83c-source", - "type": "path" - }, - "original": { - "id": "nixpkgs", - "type": "indirect" - } - }, - "root": { - "inputs": { - "nixpkgs": "nixpkgs" - } - } - }, - "root": "root", - "version": 7 -} diff --git a/flake.nix b/flake.nix deleted file mode 100644 index 62ca517..0000000 --- a/flake.nix +++ /dev/null @@ -1,89 +0,0 @@ -{ - outputs = { self, nixpkgs }: - let - lib = nixpkgs.lib; - systems = ["x86_64-linux" "aarch64-linux" "x86_64-darwin" "aarch64-darwin"]; - forAllSystems = f: lib.genAttrs systems (system: f system); - in - { - devShell = forAllSystems (system: - with import nixpkgs { inherit system; config.allowUnfree = true; }; - let - erlang_28 = - let - - src = fetchFromGitHub { - rev = "lukas/kernel/shell-improvements"; - sha256 = "sha256-D7XblZX78M0BlFkzUK1w1lIM+sE1QgZ73MHTJ6d84iI="; - owner = "garazdawi"; - repo = "otp"; - }; - opensslPackage = pkgs.openssl; - in - stdenv.mkDerivation ({ - # name is used instead of pname to - # - not have to pass pnames as argument - # - have a separate pname for erlang (main module) - name = "erlang-28.0"; - - inherit src; - version = "28.0"; - - nativeBuildInputs = with pkgs; [ autoconf makeWrapper perl gnum4 libxslt libxml2 ]; - buildInputs = with pkgs; [ ncurses opensslPackage systemd ]; - debugInfo = false; - - # On some machines, parallel build reliably crashes on `GEN asn1ct_eval_ext.erl` step - enableParallelBuilding = false; - - postPatch = '' - patchShebangs make - ''; - - # For OTP 27+ we need ex_doc to build the documentation - # When ex_docSupport is enabled, grab the raw ex_doc executable from the ex_doc - # derivation. Next, patch the first line to use the escript that will be - # built during the build phase of this derivation. Finally, building the - # documentation requires the erlang-logo.png asset. - preConfigure = '' - ./otp_build autoconf - ''; - - configureFlags = [ - "--with-ssl=${lib.getOutput "out" opensslPackage}" - "--with-ssl-incl=${lib.getDev opensslPackage}" # This flag was introduced in R24 - "--enable-threads" - "--enable-smp-support" - "--enable-kernel-poll" - "--enable-hipe" - # ++ optional wxSupport "--enable-wx" - "--enable-systemd" - ]; - - # install-docs will generate and install manpages and html docs - # (PDFs are generated only when fop is available). - - postInstall = '' - ln -s $out/lib/erlang/lib/erl_interface*/bin/erl_call $out/bin/erl_call - ''; - - # Some erlang bin/ scripts run sed and awk - postFixup = '' - wrapProgram $out/lib/erlang/bin/erl --prefix PATH ":" "${gnused}/bin/" - wrapProgram $out/lib/erlang/bin/start_erl --prefix PATH ":" "${lib.makeBinPath [ gnused gawk ]}" - ''; - - installTargets = ["install"]; - }); - in - pkgs.mkShell { - nativeBuildInputs = [ - erlang_28 - rebar3 - gleam - taplo - ]; - } - ); - }; -} diff --git a/gleam.toml b/gleam.toml index 4eb26d4..34c0211 100644 --- a/gleam.toml +++ b/gleam.toml @@ -32,3 +32,4 @@ gleam_stdlib = ">= 0.40.0 and < 2.0.0" [dev-dependencies] gleeunit = ">= 1.0.0 and < 2.0.0" simplifile = ">= 2.1.0 and < 3.0.0" +gleam_regexp = ">= 1.1.1 and < 2.0.0" diff --git a/manifest.toml b/manifest.toml index 311e5b4..5966ab6 100644 --- a/manifest.toml +++ b/manifest.toml @@ -2,13 +2,15 @@ # You typically do not need to edit this file packages = [ - { name = "filepath", version = "1.0.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "filepath", source = "hex", outer_checksum = "EFB6FF65C98B2A16378ABC3EE2B14124168C0CE5201553DE652E2644DCFDB594" }, - { name = "gleam_stdlib", version = "0.40.0", build_tools = ["gleam"], requirements = [], otp_app = "gleam_stdlib", source = "hex", outer_checksum = "86606B75A600BBD05E539EB59FABC6E307EEEA7B1E5865AFB6D980A93BCB2181" }, - { name = "gleeunit", version = "1.2.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleeunit", source = "hex", outer_checksum = "F7A7228925D3EE7D0813C922E062BFD6D7E9310F0BEE585D3A42F3307E3CFD13" }, - { name = "simplifile", version = "2.1.0", build_tools = ["gleam"], requirements = ["filepath", "gleam_stdlib"], otp_app = "simplifile", source = "hex", outer_checksum = "BDD04F5D31D6D34E2EDFAEF0B68A6297AEC939888C3BFCE61133DE13857F6DA2" }, + { name = "filepath", version = "1.1.2", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "filepath", source = "hex", outer_checksum = "B06A9AF0BF10E51401D64B98E4B627F1D2E48C154967DA7AF4D0914780A6D40A" }, + { name = "gleam_regexp", version = "1.1.1", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_regexp", source = "hex", outer_checksum = "9C215C6CA84A5B35BB934A9B61A9A306EC743153BE2B0425A0D032E477B062A9" }, + { name = "gleam_stdlib", version = "0.68.1", build_tools = ["gleam"], requirements = [], otp_app = "gleam_stdlib", source = "hex", outer_checksum = "F7FAEBD8EF260664E86A46C8DBA23508D1D11BB3BCC6EE1B89B3BC3E5C83FF1E" }, + { name = "gleeunit", version = "1.9.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleeunit", source = "hex", outer_checksum = "DA9553CE58B67924B3C631F96FE3370C49EB6D6DC6B384EC4862CC4AAA718F3C" }, + { name = "simplifile", version = "2.3.2", build_tools = ["gleam"], requirements = ["filepath", "gleam_stdlib"], otp_app = "simplifile", source = "hex", outer_checksum = "E049B4DACD4D206D87843BCF4C775A50AE0F50A52031A2FFB40C9ED07D6EC70A" }, ] [requirements] +gleam_regexp = { version = ">= 1.1.1 and < 2.0.0" } gleam_stdlib = { version = ">= 0.40.0 and < 2.0.0" } gleeunit = { version = ">= 1.0.0 and < 2.0.0" } simplifile = { version = ">= 2.1.0 and < 3.0.0" } diff --git a/src/string_width.gleam b/src/string_width.gleam index 0db57c9..a14b336 100644 --- a/src/string_width.gleam +++ b/src/string_width.gleam @@ -3,7 +3,62 @@ //// font-size: 0.7em; //// opacity: 0.75; //// } +//// +//// .goto-top { +//// display: block; +//// font-size: 0.85em; +//// text-align: right; +//// } //// +//// +//// //// //// The `with` variants of all functions additionally work with custom options. //// @@ -12,7 +67,8 @@ //// #### Measure //// [line](#line "Width of a line")[[_with](#line_with)] //// [dimensions](#dimensions "Size of a string")[[_with](#dimensions_with)], -//// [get_terminal_size](#get_terminal_size "Size of the terminal window") +//// [get_terminal_size](#get_terminal_size "Size of the terminal window"), +//// [is_tty](#is_tty "Check if this is an interactive terminal") //// //// #### Layout & Positioning //// @@ -70,13 +126,13 @@ import string_width/internal/tables // https://github.com/muesli/reflow/ // https://github.com/charmbracelet/x/ -// v3.3.2: +// v3.4.1: // - test ansi sequences during truncation // - try poslen -> split for binary states (align, limit) // so far, switching away from string.append was never worth it. // - cprof, eprof, eflamb`e -// v3.4.0: +// v3.5.0: // - what about grid?? // I don't have a design right now that I like. // - `length` variant for measure that works more like the old line @@ -124,11 +180,6 @@ const default_options = Options( /// Start building up new options. /// -/// pub fn new() -> Options { default_options } @@ -150,11 +201,6 @@ pub fn new() -> Options { /// See also [Grapheme Clusters and Terminal Emulators](https://mitchellh.com/writing/grapheme-clusters-in-terminals) /// for a better explanation on how terminals behave. /// -/// pub fn mode_2027(options: Options) -> Options { Options(..options, mode: Mode2027) } @@ -170,11 +216,6 @@ pub fn mode_2027(options: Options) -> Options { /// /// See `mode_2027` for more explanation on the implications. /// -/// pub fn mode_2027_ext(options: Options) -> Options { Options(..options, mode: Mode2027Ext) } @@ -187,11 +228,6 @@ pub fn mode_2027_ext(options: Options) -> Options { /// Note that except for `fold_raw`, this library will still always process /// grapheme clusters as a unit. /// -/// pub fn mode_wcwidth(options: Options) -> Options { Options(..options, mode: ModeWcwidth) } @@ -203,11 +239,6 @@ pub fn mode_wcwidth(options: Options) -> Options { /// Unicode recommends treating these characters as narrow by default, /// but you can change this behaviour using this option. /// -/// pub fn ambiguous_as_wide(options: Options) -> Options { Options(..options, ambiguous_as_wide: True) } @@ -217,11 +248,6 @@ pub fn ambiguous_as_wide(options: Options) -> Options { /// You can enable this option as an optimisation if you are sure that your /// string doesn't contain any ansi escape codes. /// -/// pub fn count_ansi_codes(options: Options) -> Options { Options(..options, count_ansi_codes: True) } @@ -231,11 +257,6 @@ pub fn count_ansi_codes(options: Options) -> Options { /// Whenever a tab character `\t` is encountered, the current column number will /// be rounded up to the next multiple of this number. /// -/// pub fn with_tab_width(options: Options, tab_width: Int) -> Options { Options(..options, tab_width:) } @@ -246,11 +267,6 @@ pub fn with_tab_width(options: Options, tab_width: Int) -> Options { /// indented somehow, you can set this option to this number to make sure tab /// stops are correctly calculated. /// -/// pub fn at_tab_offset(options: Options, tab_offset: Int) -> Options { Options(..options, tab_offset:) } @@ -268,11 +284,6 @@ pub type Size { /// Checks the built-in methods for the target, as well as the `LINES` and /// `COLUMNS` environment variables. /// -/// pub fn get_terminal_size() -> Result(Size, Nil) { case do_get_terminal_size() { Ok(#(rows, columns)) -> Ok(Size(rows:, columns:)) @@ -284,6 +295,11 @@ pub fn get_terminal_size() -> Result(Size, Nil) { @external(javascript, "./string_width_ffi.mjs", "get_terminal_size") fn do_get_terminal_size() -> Result(#(Int, Int), Nil) +/// Checks whether the program is running in an interactive terminal (TTY). +@external(erlang, "string_width_ffi", "is_tty") +@external(javascript, "./string_width_ffi.mjs", "is_tty") +pub fn is_tty() -> Bool + /// Get the number of columns required to print a line in a terminal. /// /// If multiple lines are given, the length of the longest line is returned. @@ -304,11 +320,6 @@ fn do_get_terminal_size() -> Result(#(Int, Int), Nil) /// // --> 5 /// ``` /// -/// pub fn line(str: String) -> Int { let Size(rows: _, columns:) = dimensions_with(str, default_options) columns @@ -327,11 +338,6 @@ pub fn line(str: String) -> Int { /// // --> 2 /// ``` /// -/// pub fn line_with(str: String, options: Options) -> Int { let Size(rows: _, columns:) = dimensions_with(str, options) columns @@ -352,22 +358,12 @@ pub fn line_with(str: String, options: Options) -> Int { /// // --> Size(rows: 2, columns: 10) /// ``` /// -/// pub fn dimensions(str: String) -> Size { dimensions_with(str, default_options) } /// Like `dimensions`, but use custom options. /// -/// pub fn dimensions_with(str: String, options: Options) -> Size { let #(str, ranges, range_width) = prepare_measure(options, str) @@ -450,11 +446,6 @@ fn prepare_measure( /// // --> "Hello\nWorld" /// ``` /// -/// pub fn limit( str: String, to max_size: Size, @@ -465,11 +456,6 @@ pub fn limit( /// Like `limit`, but also customise the options used for measuring. /// -/// pub fn limit_with( str: String, to max_size: Size, @@ -550,11 +536,6 @@ pub fn limit_with( /// for your text format, for example using the awesome /// [glam](https://hexdocs.pm/glam/) package! /// -/// pub fn soft_wrap( str: String, to max_size: Size, @@ -568,11 +549,6 @@ pub fn soft_wrap( /// Like `soft_wrap`, but using custom options to measure the strings and indents. /// -/// pub fn soft_wrap_with( str: String, to max_size: Size, @@ -1212,11 +1188,6 @@ fn limit_state_commit( /// // --> "Hello World" // 3 spaces /// ``` /// -/// pub fn tabs_to_spaces(str: String) -> String { tabs_to_spaces_with(str, default_options) } @@ -1232,11 +1203,6 @@ pub fn tabs_to_spaces(str: String) -> String { /// // --> "hi cutie~" /// ``` /// -/// pub fn tabs_to_spaces_with(str: String, using options: Options) -> String { use acc, piece <- fold_raw_pieces(str, options, from: "") case piece.piece { @@ -1279,11 +1245,6 @@ pub type Placement { /// // --> " Trans \n rights\n are \n human \n rights" /// ``` /// -/// pub fn position( str: String, in bounding_box: Size, @@ -1296,11 +1257,6 @@ pub fn position( /// Like `position`, but use custom options to measure each line. /// -/// pub fn position_with( str: String, in bounding_box: Size, @@ -1355,11 +1311,6 @@ pub fn position_with( /// // --> " Trans\n rights\n are\n human\n rights" /// ``` /// -/// pub fn align( str: String, to max_width: Int, @@ -1371,11 +1322,6 @@ pub fn align( /// Like `align`, bu use custom options for measure. /// -/// pub fn align_with( str: String, to max_width: Int, @@ -1429,11 +1375,6 @@ pub fn align_with( /// // --> "-------------\n-------------\n-Trans-------\n-rights!-----\n-------------" /// ``` /// -/// pub fn padding( str: String, top top: Int, @@ -1453,11 +1394,6 @@ pub fn padding( /// Like `padding`, but use custom options for measuring. /// -/// pub fn padding_with( str: String, top top: Int, @@ -1496,11 +1432,6 @@ pub fn padding_with( /// // --> "ow:--\ntrans\n-----" /// ``` /// -/// pub fn scroll( str: String, top top: Int, @@ -1515,11 +1446,6 @@ pub fn scroll( /// Like `scroll`, but provide custom options for measuring. /// -/// pub fn scroll_with( str: String, top top: Int, @@ -1550,11 +1476,6 @@ pub fn scroll_with( /// // <> "I hope you are feeling fantastic today!" /// ``` /// -/// pub fn stack_vertical( blocks: List(String), align horizontal: Alignment, @@ -1566,11 +1487,6 @@ pub fn stack_vertical( /// Like `stack_vertical`, but using custom options for measure. /// -/// pub fn stack_vertical_with( blocks: List(String), align horizontal: Alignment, @@ -1630,11 +1546,6 @@ pub fn stack_vertical_with( /// // <> " This option is enabled by default in a terminal." /// ``` /// -/// pub fn stack_horizontal( blocks: List(String), place vertical: Placement, @@ -1646,11 +1557,6 @@ pub fn stack_horizontal( /// Like `stack_horizontal`, but using custom options for measure. /// -/// pub fn stack_horizontal_with( blocks: List(String), place vertical: Placement, @@ -1927,11 +1833,6 @@ fn guard_list(list: List(a), empty: b, non_empty: fn(a, List(a)) -> b) -> b { /// // --> "\u{1b}[31mhello" <> "\u{1b}[m\n" <> "\u{1b}[31mworld" <> "\u{1b}[m" /// ``` /// -/// pub fn inline_styles(str: String) -> String { let ansi_ranges = ansi.match(str) @@ -1993,11 +1894,6 @@ pub fn inline_styles(str: String) -> String { /// // --> "check out Gleam!" /// ``` /// -/// pub fn strip_ansi(str: String) -> String { ansi.strip(str) } @@ -2005,11 +1901,6 @@ pub fn strip_ansi(str: String) -> String { /// Returns true if a given component string recieved in `fold` is an ANSI /// escape sequence. /// -/// pub fn is_ansi_component(str: String, options: Options) -> Bool { case options.count_ansi_codes { True -> False @@ -2043,11 +1934,6 @@ pub type Piece { /// // --> [Piece("h", 0, 0, 1), Piece("i", 0, 1, 1), Piece(" ", 0, 2, 1), Piece("😊", 0, 3, 2)] /// ``` /// -/// pub fn fold( over str: String, from state: state, @@ -2064,11 +1950,6 @@ pub fn fold( /// /// Intended to be used as a basis for custom layout algorithms. /// -/// pub fn fold_with( over str: String, using options: Options, @@ -2133,11 +2014,6 @@ pub fn fold_with( /// } /// ``` /// -/// pub fn fold_raw( over string: String, using options: Options, @@ -2174,11 +2050,6 @@ pub fn fold_raw( /// // --> [Piece("h", 0, 0, 1), Piece("i", 0, 1, 1), Piece("!", 0, 2, 1)] /// ``` /// -/// pub fn fold_raw_pieces( over string: String, using options: Options, diff --git a/src/string_width_ffi.erl b/src/string_width_ffi.erl index 23e9afd..cb2cbcb 100644 --- a/src/string_width_ffi.erl +++ b/src/string_width_ffi.erl @@ -1,30 +1,50 @@ -module(string_width_ffi). --export([ - fold_bytes/3, - fold_codepoints/3, - utf_codepoint_to_string/1, - get_terminal_size/0 -]). -fold_bytes(<>, State, Fun) -> fold_bytes(Rest, Fun(State, Byte), Fun); -fold_bytes(_Binary, State, _Fun) -> State. +-export([fold_bytes/3, fold_codepoints/3, utf_codepoint_to_string/1, get_terminal_size/0, + is_tty/0]). -fold_codepoints(<>, State, Fun) -> fold_codepoints(Rest, Fun(State, Cp), Fun); -fold_codepoints(_Binary, State, _Fun) -> State. +fold_bytes(<>, State, Fun) -> + fold_bytes(Rest, Fun(State, Byte), Fun); +fold_bytes(_Binary, State, _Fun) -> + State. -utf_codepoint_to_string(Cp) -> <>. +fold_codepoints(<>, State, Fun) -> + fold_codepoints(Rest, Fun(State, Cp), Fun); +fold_codepoints(_Binary, State, _Fun) -> + State. + +utf_codepoint_to_string(Cp) -> + <>. get_terminal_size() -> case {io:rows(), io:columns()} of - {{ok, Rows}, {ok, Cols}} -> {ok, {Rows, Cols}}; - _ -> case {os:getenv("LINES"), os:getenv("COLUMNS")} of - {false, _} -> {error, nil}; - {_, false} -> {error, nil}; - {LinesStr, ColumnsStr} -> - case catch {list_to_integer(LinesStr), list_to_integer(ColumnsStr)} of - {EnvRows, EnvCols} when is_integer(EnvRows) andalso is_integer(EnvCols) -> - {ok, {EnvRows, EnvCols}}; - _ -> {error, nil} - end - end + {{ok, Rows}, {ok, Cols}} -> + {ok, {Rows, Cols}}; + _ -> + case {os:getenv("LINES"), os:getenv("COLUMNS")} of + {false, _} -> + {error, nil}; + {_, false} -> + {error, nil}; + {LinesStr, ColumnsStr} -> + case catch {list_to_integer(LinesStr), list_to_integer(ColumnsStr)} of + {EnvRows, EnvCols} when is_integer(EnvRows) andalso is_integer(EnvCols) -> + {ok, {EnvRows, EnvCols}}; + _ -> + {error, nil} + end + end + end. + +is_tty() -> + case io:columns() of + {ok, _} -> + % Check io:getopts for stdin, stdout, and terminal flags + Opts = io:getopts(), + HasStdin = proplists:get_value(stdin, Opts, false), + HasStdout = proplists:get_value(stdout, Opts, false), + IsDumb = os:getenv("TERM") == "DUMB", + HasStdin and HasStdout and not IsDumb; + {error, _} -> + false end. diff --git a/src/string_width_ffi.mjs b/src/string_width_ffi.mjs index f64a3f2..dd609f3 100644 --- a/src/string_width_ffi.mjs +++ b/src/string_width_ffi.mjs @@ -1,6 +1,7 @@ -import { toList, Ok, Error } from './gleam.mjs' +import { toList, Ok, Error } from "./gleam.mjs"; -const ANSI_RE = /\x1b(?:[\x30-\x4f\x51-\x57\x59-\x5a\x60-\x7e]|(?:\[[\x20-\x3f]*?[\x40-\x7e])|(?:[\x50\x58\x5d\x5e\x5f].*?(?:\x07|\x1b\\)))/mg +const ANSI_RE = + /\x1b(?:[\x30-\x4f\x51-\x57\x59-\x5a\x60-\x7e]|(?:\[[\x20-\x3f]*?[\x40-\x7e])|(?:[\x50\x58\x5d\x5e\x5f].*?(?:\x07|\x1b\\)))/gm; const ASCII_RE = /[\x20-\x7e]+(?=[\x20-\x7e]|$)/g; const SEGMENTER = new Intl.Segmenter(); @@ -13,10 +14,10 @@ export function get_terminal_size() { } } catch {} - const envRows = parseInt(Deno.env.get("LINES"), 10) - const envCols = parseInt(Deno.env.get("COLUMNS"), 10) - if(envRows && envCols) { - return new Ok([envRows, envCols]) + const envRows = parseInt(Deno.env.get("LINES"), 10); + const envCols = parseInt(Deno.env.get("COLUMNS"), 10); + if (envRows && envCols) { + return new Ok([envRows, envCols]); } } @@ -31,22 +32,29 @@ export function get_terminal_size() { return new Ok([process.stdin.rows, process.stdin.columns]); } - const envRows = parseInt(process.env.LINES, 10) - const envCols = parseInt(process.env.COLUMNS, 10) + const envRows = parseInt(process.env.LINES, 10); + const envCols = parseInt(process.env.COLUMNS, 10); if (envRows && envCols) { - return new Ok([envRows, envCols]) + return new Ok([envRows, envCols]); } } - return new Error() + return new Error(); } +export function is_tty() { + return ( + process.stdin.isTTY === true && + process.stdout.isTTY === true && + process.env["TERM"] != "DUMB" + ); +} export function prepare_measure(options, str) { if (!options.count_ansi_codes) { - str = str.replaceAll(ANSI_RE, '') + str = str.replaceAll(ANSI_RE, ""); } - const ascii_ranges = scan_poslen(ASCII_RE, str) - return [str, ascii_ranges, 1] + const ascii_ranges = scan_poslen(ASCII_RE, str); + return [str, ascii_ranges, 1]; } export function table_lookup(table, value) { @@ -61,50 +69,50 @@ export function table_lookup(table, value) { } export function match_ansi(str) { - return scan_poslen(ANSI_RE, str) + return scan_poslen(ANSI_RE, str); } export function strip_ansi(str) { - return str.replaceAll(ANSI_RE, '') + return str.replaceAll(ANSI_RE, ""); } export function unsafe_split(str, at) { - return [str.slice(0, at), str.slice(at)] + return [str.slice(0, at), str.slice(at)]; } export function fold_bytes(str, state, fun) { for (let i = 0; i < str.length; ++i) { - state = fun(state, str.charCodeAt(i)) + state = fun(state, str.charCodeAt(i)); } - return state + return state; } export function fold_codepoints(str, state, fun) { for (const codePoint of str) { - state = fun(state, codePoint.codePointAt(0)) + state = fun(state, codePoint.codePointAt(0)); } - return state + return state; } export function fold_graphemes(str, state, fun) { - for(const { segment } of SEGMENTER.segment(str)) { - state = fun(state, segment) + for (const { segment } of SEGMENTER.segment(str)) { + state = fun(state, segment); } - return state + return state; } export function utf_codepoint_to_string(cp) { - return String.fromCodePoint(cp) + return String.fromCodePoint(cp); } function scan_poslen(re, str) { - let match - let matches = [] + let match; + let matches = []; - re.lastIndex = 0 + re.lastIndex = 0; while (null !== (match = re.exec(str))) { - matches.push([match.index, re.lastIndex-match.index]) + matches.push([match.index, re.lastIndex - match.index]); } - return toList(matches) + return toList(matches); } diff --git a/test/columns.gleam b/test/columns.gleam index 9122b20..e9e3f09 100644 --- a/test/columns.gleam +++ b/test/columns.gleam @@ -1,6 +1,6 @@ import gleam/io import gleam/list -import string_width.{type Size, Left, Size, Top} +import string_width.{Left, Size, Top} const max_width = 49 @@ -37,7 +37,7 @@ pub fn main() { // loop(10_000) } -fn loop(i) { +pub fn loop(i) { case i { 0 -> Nil _ -> { diff --git a/test/generate.gleam b/test/generate.gleam index d4418bd..408f037 100644 --- a/test/generate.gleam +++ b/test/generate.gleam @@ -4,12 +4,12 @@ import gleam/bit_array import gleam/bool -import gleam/bytes_builder +import gleam/bytes_tree as bytes_builder import gleam/dict import gleam/int import gleam/io import gleam/list -import gleam/regex +import gleam/regexp as regex import gleam/string import simplifile @@ -76,10 +76,10 @@ pub fn main() { print_table_info(wide, "Wide", 17) io.println("Ambiguous table:") - io.debug(bit_array.byte_size(io.debug(generate_table(ambiguous, 16)))) + echo bit_array.byte_size(echo generate_table(ambiguous, 16)) io.println("Wide table:") - io.debug(bit_array.byte_size(io.debug(generate_table(wide, 17)))) + echo bit_array.byte_size(echo generate_table(wide, 17)) io.println("Narrows:") io.println(ranges_to_string(narrow)) @@ -145,7 +145,7 @@ pub fn main() { }) let nonspacing = - list.concat([ + list.flatten([ default_ignorable, custom_ignored, hangul_vowel_or_trailing_jamo, @@ -156,7 +156,7 @@ pub fn main() { |> compress_ranges(fn(_, _) { [] }) print_table_info(nonspacing, "Ignorable", 17) - io.debug(bit_array.byte_size(io.debug(generate_table(nonspacing, 17)))) + echo bit_array.byte_size(echo generate_table(nonspacing, 17)) let spacing_modifiers = parse_unicode_data("./data/DerivedGeneralCategory.txt", fn(prop) { @@ -168,7 +168,7 @@ pub fn main() { |> compress_ranges(fn(_, _) { [] }) print_table_info(spacing_modifiers, "Spacing Modifieres", 17) - io.debug(bit_array.byte_size(io.debug(generate_table(spacing_modifiers, 17)))) + echo bit_array.byte_size(echo generate_table(spacing_modifiers, 17)) Nil } diff --git a/test/string_width_test.gleam b/test/string_width_test.gleam index 7a1d5d0..9e149bc 100644 --- a/test/string_width_test.gleam +++ b/test/string_width_test.gleam @@ -1,11 +1,10 @@ -import gleam/io import gleam/list import gleeunit import gleeunit/should import string_width.{Piece, Size, dimensions, line as sw} pub fn main() { - io.debug(#("Terminal Size: ", string_width.get_terminal_size())) + let _ = echo string_width.get_terminal_size() as "Terminal size" gleeunit.main() } @@ -113,13 +112,9 @@ pub fn pedantic_test() { swg("葛󠄀") |> should.equal(2) // Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞ 6 6 | 6 6 6 6 6 6 - sw( - "Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞", - ) + sw("Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞") |> should.equal(6) - swg( - "Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞", - ) + swg("Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞") |> should.equal(6) // バ| :L 1 2 | 2 2 2 2 1 -- 2.51.2