diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index d77f62385..5056da3dd 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-16.0.0.txt -# Date: 2024-04-25, 16:53:41 GMT +# Date: 2024-04-25, 10:18:46 GMT [KW] # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2553,14 +2553,26 @@ FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN FDFC ; PO # Sc RIAL SIGN FDFD..FDFF ; AL # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE00..FE0F ; CM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE10 ; IS # Po PRESENTATION FORM FOR VERTICAL COMMA -FE11..FE12 ; CL # Po [2] PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP -FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON +FE10..FE12 ; CL # Po [3] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP +FE13..FE14 ; NS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON FE15..FE16 ; EX # Po [2] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; OP # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET FE18 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS -FE20..FE2F ; CM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FE20 ; GL # Mn COMBINING LIGATURE LEFT HALF +FE21 ; CM # Mn COMBINING LIGATURE RIGHT HALF +FE22 ; GL # Mn COMBINING DOUBLE TILDE LEFT HALF +FE23 ; CM # Mn COMBINING DOUBLE TILDE RIGHT HALF +FE24 ; GL # Mn COMBINING MACRON LEFT HALF +FE25 ; CM # Mn COMBINING MACRON RIGHT HALF +FE26..FE27 ; GL # Mn [2] COMBINING CONJOINING MACRON..COMBINING LIGATURE LEFT HALF BELOW +FE28 ; CM # Mn COMBINING LIGATURE RIGHT HALF BELOW +FE29 ; GL # Mn COMBINING TILDE LEFT HALF BELOW +FE2A ; CM # Mn COMBINING TILDE RIGHT HALF BELOW +FE2B ; GL # Mn COMBINING MACRON LEFT HALF BELOW +FE2C ; CM # Mn COMBINING MACRON RIGHT HALF BELOW +FE2D..FE2E ; GL # Mn [2] COMBINING CONJOINING MACRON BELOW..COMBINING CYRILLIC TITLO LEFT HALF +FE2F ; CM # Mn COMBINING CYRILLIC TITLO RIGHT HALF FE30 ; ID # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER FE31..FE32 ; ID # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH FE33..FE34 ; ID # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE diff --git a/unicodetools/data/ucd/dev/NameAliases.txt b/unicodetools/data/ucd/dev/NameAliases.txt index 49769d705..9023e8218 100644 --- a/unicodetools/data/ucd/dev/NameAliases.txt +++ b/unicodetools/data/ucd/dev/NameAliases.txt @@ -1,5 +1,5 @@ # NameAliases-16.0.0.txt -# Date: 2024-02-02 +# Date: 2024-04-24 # © 2024 Unicode®, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # @@ -328,6 +328,8 @@ FEFF;ZWNBSP;abbreviation 16E77;MEDEFAIDRIN SMALL LETTER NG;correction 1B001;HENTAIGANA LETTER E-1;correction 1D0C5;BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS;correction +1E899;MENDE KIKAKUI SYLLABLE M172 MBO;correction +1E89A;MENDE KIKAKUI SYLLABLE M174 MBOO;correction E0100;VS17;abbreviation E0101;VS18;abbreviation E0102;VS19;abbreviation diff --git a/unicodetools/data/ucd/dev/NamesList.txt b/unicodetools/data/ucd/dev/NamesList.txt index a14f921c3..7cf781bf3 100644 --- a/unicodetools/data/ucd/dev/NamesList.txt +++ b/unicodetools/data/ucd/dev/NamesList.txt @@ -1,12 +1,18 @@ ; charset=UTF-8 @@@ The Unicode Standard 16.0.0 @@@+ NamesList-16.0.0.txt -@+ Generation Date: 2024-04-24, 09:09:06 GMT +@+ Generation Date: 2024-04-26, 11:55:14 GMT Unicode 16.0.0 names list. - Repertoire synched with UnicodeData-16.0.0d14.txt. + Repertoire synched with UnicodeData-16.0.0d16.txt. Pre-beta rollup of various fixes. Add xref between 131A6 and 13DEE. Add xrefs between 01C3, A71D, 107B9. + Added xrefs from 1DF0A to A71D and 107B9. + Added formal aliases and annotation for 1E899, 1E89A + Removed unneeded subheads for two postponed archaic SHRII characters. + Added formal alias for 12327. + Added xrefs between 050F and 1C8A. + Added an annotation about Amerindian orthographic use for 00B7. This file is semi-automatically derived from UnicodeData.txt and a set of manually created annotations using a script to select or suppress information from the data file. The rules used @@ -735,6 +741,7 @@ = Georgian comma = Greek middle dot (ano teleia) * also used as a raised decimal point or to denote multiplication; for multiplication 22C5 is preferred + * used as a vowel length mark (part of words) in many Amerindian orthographies x (full stop - 002E) x (dot above - 02D9) x (greek ano teleia - 0387) @@ -3689,7 +3696,6 @@ 04FF CYRILLIC SMALL LETTER HA WITH STROKE @@ 0500 Cyrillic Supplement 052F @ Komi letters -@+ These letters are for the obsolete Molodtsov alphabet, used in the 1920s. 0500 CYRILLIC CAPITAL LETTER KOMI DE 0501 CYRILLIC SMALL LETTER KOMI DE 0502 CYRILLIC CAPITAL LETTER KOMI DJE @@ -3706,6 +3712,8 @@ 050D CYRILLIC SMALL LETTER KOMI SJE 050E CYRILLIC CAPITAL LETTER KOMI TJE 050F CYRILLIC SMALL LETTER KOMI TJE + x (cyrillic small letter tje - 1C8A) +@+ These letters are for the obsolete Molodtsov alphabet, used in the 1920s. @ Khanty letters 0510 CYRILLIC CAPITAL LETTER REVERSED ZE 0511 CYRILLIC SMALL LETTER REVERSED ZE @@ -6253,8 +6261,6 @@ 0C59 TELUGU LETTER DZA 0C5A TELUGU LETTER RRRA * letter for an alveolar consonant whose exact phonetic value is not known -@ Historic syllable -0C5C TELUGU ARCHAIC SHRII @ Consonant 0C5D TELUGU LETTER NAKAARA POLLU * vowelless form of na @@ -6389,8 +6395,6 @@ @ Various signs 0CD5 KANNADA LENGTH MARK 0CD6 KANNADA AI LENGTH MARK -@ Historic syllable -0CDC KANNADA ARCHAIC SHRII @ Additional consonants 0CDD KANNADA LETTER NAKAARA POLLU * vowelless form of na @@ -11269,6 +11273,7 @@ @ Khanty letters 1C89 CYRILLIC CAPITAL LETTER TJE 1C8A CYRILLIC SMALL LETTER TJE + x (cyrillic small letter komi tje - 050F) @@ 1C90 Georgian Extended 1CBF @ Capital letters (Mtavruli) @+ This is the special uppercase of the modern secular alphabet. Modern Georgian orthography uses these letters to emphasize words and phrases analogously to Latin "all caps" style. See the Georgian block for lowercase Mkhedruli. @@ -37503,6 +37508,7 @@ FFFF 12325 CUNEIFORM SIGN UMUM TIMES PA 12326 CUNEIFORM SIGN UN 12327 CUNEIFORM SIGN UN GUNU + % CUNEIFORM SIGN KALAM 12328 CUNEIFORM SIGN UR 12329 CUNEIFORM SIGN UR CROSSING UR 1232A CUNEIFORM SIGN UR SHESHIG @@ -58449,6 +58455,8 @@ FFFF 1DF09 LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK x (latin small letter t with hook - 01AD) 1DF0A LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK + x (modifier letter raised exclamation mark - A71D) + x (modifier letter retroflex click with retroflex hook - 107B9) @ Clicks 1DF0B LATIN SMALL LETTER ESH WITH DOUBLE BAR x (integral with double stroke - 2A0E) @@ -59233,7 +59241,10 @@ FFFF 1E897 MENDE KIKAKUI SYLLABLE M188 MBEE 1E898 MENDE KIKAKUI SYLLABLE M072 MBE 1E899 MENDE KIKAKUI SYLLABLE M172 MBOO + % MENDE KIKAKUI SYLLABLE M172 MBO + * this and the following character had swapped transliterations of the vowels in their names 1E89A MENDE KIKAKUI SYLLABLE M174 MBO + % MENDE KIKAKUI SYLLABLE M174 MBOO 1E89B MENDE KIKAKUI SYLLABLE M187 MBUU 1E89C MENDE KIKAKUI SYLLABLE M161 LONG MBE 1E89D MENDE KIKAKUI SYLLABLE M105 LONG MBOO diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 3da704c9f..64258a373 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -34630,7 +34630,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D6BE;MATHEMATICAL BOLD CAPITAL CHI;Lu;0;L; 03A7;;;;N;;;;; 1D6BF;MATHEMATICAL BOLD CAPITAL PSI;Lu;0;L; 03A8;;;;N;;;;; 1D6C0;MATHEMATICAL BOLD CAPITAL OMEGA;Lu;0;L; 03A9;;;;N;;;;; -1D6C1;MATHEMATICAL BOLD NABLA;Sm;0;L; 2207;;;;N;;;;; +1D6C1;MATHEMATICAL BOLD NABLA;Sm;0;ON; 2207;;;;N;;;;; 1D6C2;MATHEMATICAL BOLD SMALL ALPHA;Ll;0;L; 03B1;;;;N;;;;; 1D6C3;MATHEMATICAL BOLD SMALL BETA;Ll;0;L; 03B2;;;;N;;;;; 1D6C4;MATHEMATICAL BOLD SMALL GAMMA;Ll;0;L; 03B3;;;;N;;;;; @@ -34688,7 +34688,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D6F8;MATHEMATICAL ITALIC CAPITAL CHI;Lu;0;L; 03A7;;;;N;;;;; 1D6F9;MATHEMATICAL ITALIC CAPITAL PSI;Lu;0;L; 03A8;;;;N;;;;; 1D6FA;MATHEMATICAL ITALIC CAPITAL OMEGA;Lu;0;L; 03A9;;;;N;;;;; -1D6FB;MATHEMATICAL ITALIC NABLA;Sm;0;L; 2207;;;;N;;;;; +1D6FB;MATHEMATICAL ITALIC NABLA;Sm;0;ON; 2207;;;;N;;;;; 1D6FC;MATHEMATICAL ITALIC SMALL ALPHA;Ll;0;L; 03B1;;;;N;;;;; 1D6FD;MATHEMATICAL ITALIC SMALL BETA;Ll;0;L; 03B2;;;;N;;;;; 1D6FE;MATHEMATICAL ITALIC SMALL GAMMA;Ll;0;L; 03B3;;;;N;;;;; @@ -34746,7 +34746,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D732;MATHEMATICAL BOLD ITALIC CAPITAL CHI;Lu;0;L; 03A7;;;;N;;;;; 1D733;MATHEMATICAL BOLD ITALIC CAPITAL PSI;Lu;0;L; 03A8;;;;N;;;;; 1D734;MATHEMATICAL BOLD ITALIC CAPITAL OMEGA;Lu;0;L; 03A9;;;;N;;;;; -1D735;MATHEMATICAL BOLD ITALIC NABLA;Sm;0;L; 2207;;;;N;;;;; +1D735;MATHEMATICAL BOLD ITALIC NABLA;Sm;0;ON; 2207;;;;N;;;;; 1D736;MATHEMATICAL BOLD ITALIC SMALL ALPHA;Ll;0;L; 03B1;;;;N;;;;; 1D737;MATHEMATICAL BOLD ITALIC SMALL BETA;Ll;0;L; 03B2;;;;N;;;;; 1D738;MATHEMATICAL BOLD ITALIC SMALL GAMMA;Ll;0;L; 03B3;;;;N;;;;; @@ -34804,7 +34804,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D76C;MATHEMATICAL SANS-SERIF BOLD CAPITAL CHI;Lu;0;L; 03A7;;;;N;;;;; 1D76D;MATHEMATICAL SANS-SERIF BOLD CAPITAL PSI;Lu;0;L; 03A8;;;;N;;;;; 1D76E;MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA;Lu;0;L; 03A9;;;;N;;;;; -1D76F;MATHEMATICAL SANS-SERIF BOLD NABLA;Sm;0;L; 2207;;;;N;;;;; +1D76F;MATHEMATICAL SANS-SERIF BOLD NABLA;Sm;0;ON; 2207;;;;N;;;;; 1D770;MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA;Ll;0;L; 03B1;;;;N;;;;; 1D771;MATHEMATICAL SANS-SERIF BOLD SMALL BETA;Ll;0;L; 03B2;;;;N;;;;; 1D772;MATHEMATICAL SANS-SERIF BOLD SMALL GAMMA;Ll;0;L; 03B3;;;;N;;;;; @@ -34862,7 +34862,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1D7A6;MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL CHI;Lu;0;L; 03A7;;;;N;;;;; 1D7A7;MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL PSI;Lu;0;L; 03A8;;;;N;;;;; 1D7A8;MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA;Lu;0;L; 03A9;;;;N;;;;; -1D7A9;MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA;Sm;0;L; 2207;;;;N;;;;; +1D7A9;MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA;Sm;0;ON; 2207;;;;N;;;;; 1D7AA;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA;Ll;0;L; 03B1;;;;N;;;;; 1D7AB;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL BETA;Ll;0;L; 03B2;;;;N;;;;; 1D7AC;MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL GAMMA;Ll;0;L; 03B3;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 12f20edf2..9574a73a5 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2024-04-25, 17:07:58 GMT +# Date: 2024-04-27, 01:25:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1381,14 +1381,12 @@ FF1A ; MidLetter # Po FULLWIDTH COLON 066C ; MidNum # Po ARABIC THOUSANDS SEPARATOR 07F8 ; MidNum # Po NKO COMMA 2044 ; MidNum # Sm FRACTION SLASH -FE10 ; MidNum # Po PRESENTATION FORM FOR VERTICAL COMMA -FE14 ; MidNum # Po PRESENTATION FORM FOR VERTICAL SEMICOLON FE50 ; MidNum # Po SMALL COMMA FE54 ; MidNum # Po SMALL SEMICOLON FF0C ; MidNum # Po FULLWIDTH COMMA FF1B ; MidNum # Po FULLWIDTH SEMICOLON -# Total code points: 15 +# Total code points: 13 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 443177f93..53f749d75 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2024-04-25, 17:06:05 GMT +# Date: 2024-04-27, 01:24:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1155,19 +1155,14 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1D54A..1D550 ; L # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y 1D552..1D6A5 ; L # L& [340] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J 1D6A8..1D6C0 ; L # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA -1D6C1 ; L # Sm MATHEMATICAL BOLD NABLA 1D6C2..1D6DA ; L # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA 1D6DC..1D6FA ; L # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA -1D6FB ; L # Sm MATHEMATICAL ITALIC NABLA 1D6FC..1D714 ; L # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA 1D716..1D734 ; L # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA -1D735 ; L # Sm MATHEMATICAL BOLD ITALIC NABLA 1D736..1D74E ; L # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA 1D750..1D76E ; L # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA -1D76F ; L # Sm MATHEMATICAL SANS-SERIF BOLD NABLA 1D770..1D788 ; L # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA 1D78A..1D7A8 ; L # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA -1D7A9 ; L # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA 1D7AA..1D7C2 ; L # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; L # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1D800..1D9FF ; L # So [512] SIGNWRITING HAND-FIST INDEX..SIGNWRITING HEAD @@ -1220,7 +1215,7 @@ F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. # The above property value applies to 815351 code points not listed here. -# Total code points: 1095518 +# Total code points: 1095513 # ================================================ @@ -1952,10 +1947,15 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; ON # So GREEK MUSICAL LEIMMA 1D300..1D356 ; ON # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING +1D6C1 ; ON # Sm MATHEMATICAL BOLD NABLA 1D6DB ; ON # Sm MATHEMATICAL BOLD PARTIAL DIFFERENTIAL +1D6FB ; ON # Sm MATHEMATICAL ITALIC NABLA 1D715 ; ON # Sm MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL +1D735 ; ON # Sm MATHEMATICAL BOLD ITALIC NABLA 1D74F ; ON # Sm MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL +1D76F ; ON # Sm MATHEMATICAL SANS-SERIF BOLD NABLA 1D789 ; ON # Sm MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL +1D7A9 ; ON # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA 1D7C3 ; ON # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1EEF0..1EEF1 ; ON # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL 1F000..1F02B ; ON # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK @@ -1997,7 +1997,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; ON # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 6746 +# Total code points: 6751 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 250ad855b..38f0bbb53 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2024-04-25, 17:06:19 GMT +# Date: 2024-04-27, 01:24:33 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -232,7 +232,7 @@ FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET 301B ; CL # Pe RIGHT WHITE SQUARE BRACKET 301E..301F ; CL # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK FD3E ; CL # Pe ORNATE LEFT PARENTHESIS -FE11..FE12 ; CL # Po [2] PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP +FE10..FE12 ; CL # Po [3] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP FE18 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET FE36 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS FE38 ; CL # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET @@ -267,7 +267,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 1343F ; CL # Cf EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 145CF ; CL # Lo ANATOLIAN HIEROGLYPH A410A END LOGOGRAM MARK -# Total code points: 97 +# Total code points: 98 # ================================================ @@ -321,12 +321,19 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 2007 ; GL # Zs FIGURE SPACE 2011 ; GL # Pd NON-BREAKING HYPHEN 202F ; GL # Zs NARROW NO-BREAK SPACE +FE20 ; GL # Mn COMBINING LIGATURE LEFT HALF +FE22 ; GL # Mn COMBINING DOUBLE TILDE LEFT HALF +FE24 ; GL # Mn COMBINING MACRON LEFT HALF +FE26..FE27 ; GL # Mn [2] COMBINING CONJOINING MACRON..COMBINING LIGATURE LEFT HALF BELOW +FE29 ; GL # Mn COMBINING TILDE LEFT HALF BELOW +FE2B ; GL # Mn COMBINING MACRON LEFT HALF BELOW +FE2D..FE2E ; GL # Mn [2] COMBINING CONJOINING MACRON BELOW..COMBINING CYRILLIC TITLO LEFT HALF 1107F ; GL # Mn BRAHMI NUMBER JOINER 13430..13436 ; GL # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE 13439..1343B ; GL # Cf [3] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH INSERT AT BOTTOM 16FE4 ; GL # Mn KHITAN SMALL SCRIPT FILLER -# Total code points: 32 +# Total code points: 41 # ================================================ @@ -345,6 +352,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 30FB ; NS # Po KATAKANA MIDDLE DOT 30FD..30FE ; NS # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK A015 ; NS # Lm YI SYLLABLE WU +FE13..FE14 ; NS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON FE54..FE55 ; NS # Po [2] SMALL SEMICOLON..SMALL COLON FF1A..FF1B ; NS # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON FF65 ; NS # Po HALFWIDTH KATAKANA MIDDLE DOT @@ -354,7 +362,7 @@ FF9E..FF9F ; NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KA 16FE3 ; NS # Lm OLD CHINESE ITERATION MARK 1F679..1F67B ; NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT -# Total code points: 33 +# Total code points: 35 # ================================================ @@ -408,10 +416,8 @@ FF1F ; EX # Po FULLWIDTH QUESTION MARK 060C..060D ; IS # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR 07F8 ; IS # Po NKO COMMA 2044 ; IS # Sm FRACTION SLASH -FE10 ; IS # Po PRESENTATION FORM FOR VERTICAL COMMA -FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION FORM FOR VERTICAL SEMICOLON -# Total code points: 13 +# Total code points: 10 # ================================================ @@ -2163,7 +2169,13 @@ ABEC ; CM # Mc MEETEI MAYEK LUM IYEK ABED ; CM # Mn MEETEI MAYEK APUN IYEK FB1E ; CM # Mn HEBREW POINT JUDEO-SPANISH VARIKA FE00..FE0F ; CM # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE20..FE2F ; CM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FE21 ; CM # Mn COMBINING LIGATURE RIGHT HALF +FE23 ; CM # Mn COMBINING DOUBLE TILDE RIGHT HALF +FE25 ; CM # Mn COMBINING MACRON RIGHT HALF +FE28 ; CM # Mn COMBINING LIGATURE RIGHT HALF BELOW +FE2A ; CM # Mn COMBINING TILDE RIGHT HALF BELOW +FE2C ; CM # Mn COMBINING MACRON RIGHT HALF BELOW +FE2F ; CM # Mn COMBINING CYRILLIC TITLO RIGHT HALF FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR 101FD ; CM # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE 102E0 ; CM # Mn COPTIC EPACT THOUSANDS MARK @@ -2382,7 +2394,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2479 +# Total code points: 2470 # ================================================