diff options
Diffstat (limited to 'util/unicode/data/SentenceBreakProperty.txt')
-rw-r--r-- | util/unicode/data/SentenceBreakProperty.txt | 232 |
1 files changed, 195 insertions, 37 deletions
diff --git a/util/unicode/data/SentenceBreakProperty.txt b/util/unicode/data/SentenceBreakProperty.txt index d714d59d3a..19752103f9 100644 --- a/util/unicode/data/SentenceBreakProperty.txt +++ b/util/unicode/data/SentenceBreakProperty.txt @@ -1,8 +1,8 @@ -# SentenceBreakProperty-6.3.0.txt -# Date: 2013-09-25, 18:59:01 GMT [MD] +# SentenceBreakProperty-7.0.0.txt +# Date: 2014-02-19, 15:51:38 GMT [MD] # # Unicode Character Database -# Copyright (c) 1991-2013 Unicode, Inc. +# Copyright (c) 1991-2014 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see http://www.unicode.org/reports/tr44/ @@ -53,8 +53,7 @@ 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08E4..08FE ; Extend # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT -0900..0902 ; Extend # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +08E4..0902 ; Extend # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE 093B ; Extend # Mc DEVANAGARI VOWEL SIGN OOE @@ -117,6 +116,7 @@ 0BCA..0BCC ; Extend # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU 0BCD ; Extend # Mn TAMIL SIGN VIRAMA 0BD7 ; Extend # Mc TAMIL AU LENGTH MARK +0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA 0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C41..0C44 ; Extend # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR @@ -124,6 +124,7 @@ 0C4A..0C4D ; Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; Extend # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C62..0C63 ; Extend # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; Extend # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; Extend # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0CBC ; Extend # Mn KANNADA SIGN NUKTA 0CBE ; Extend # Mc KANNADA VOWEL SIGN AA @@ -135,6 +136,7 @@ 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -231,6 +233,8 @@ 1A6D..1A72 ; Extend # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI 1A73..1A7C ; Extend # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -249,8 +253,7 @@ 1BA6..1BA7 ; Extend # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG 1BA8..1BA9 ; Extend # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG 1BAA ; Extend # Mc SUNDANESE SIGN PAMAAEH -1BAB ; Extend # Mn SUNDANESE SIGN VIRAMA -1BAC..1BAD ; Extend # Mc [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BAB..1BAD ; Extend # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA 1BE6 ; Extend # Mn BATAK SIGN TOMPI 1BE7 ; Extend # Mc BATAK VOWEL SIGN E 1BE8..1BE9 ; Extend # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE @@ -270,7 +273,8 @@ 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE -1DC0..1DE6 ; Extend # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE 1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -310,6 +314,7 @@ A9B6..A9B9 ; Extend # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN A9BA..A9BB ; Extend # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE A9BC ; Extend # Mn JAVANESE VOWEL SIGN PEPET A9BD..A9C0 ; Extend # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON +A9E5 ; Extend # Mn MYANMAR SIGN SHAN SAW AA29..AA2E ; Extend # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE AA2F..AA30 ; Extend # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI AA31..AA32 ; Extend # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE @@ -319,6 +324,8 @@ AA43 ; Extend # Mn CHAM CONSONANT SIGN FINAL NG AA4C ; Extend # Mn CHAM CONSONANT SIGN FINAL M AA4D ; Extend # Mc CHAM CONSONANT SIGN FINAL H AA7B ; Extend # Mc MYANMAR SIGN PAO KAREN TONE +AA7C ; Extend # Mn MYANMAR SIGN TAI LAING TONE-2 +AA7D ; Extend # Mc MYANMAR SIGN TAI LAING TONE-5 AAB0 ; Extend # Mn TAI VIET MAI KANG AAB2..AAB4 ; Extend # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U AAB7..AAB8 ; Extend # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA @@ -338,19 +345,22 @@ ABEC ; Extend # Mc MEETEI MAYEK LUM IYEK ABED ; Extend # Mn MEETEI MAYEK APUN IYEK FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE20..FE26 ; Extend # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FE20..FE2D ; Extend # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK 101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; Extend # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII 10A01..10A03 ; Extend # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R 10A05..10A06 ; Extend # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O 10A0C..10A0F ; Extend # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA 10A38..10A3A ; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; Extend # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA 11002 ; Extend # Mc BRAHMI SIGN VISARGA 11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA -11080..11081 ; Extend # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA 11082 ; Extend # Mc KAITHI SIGN VISARGA 110B0..110B2 ; Extend # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B3..110B6 ; Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI @@ -360,11 +370,53 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Extend # Mc CHAKMA VOWEL SIGN E 1112D..11134 ; Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; Extend # Mn MAHAJANI SIGN NUKTA 11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA 11182 ; Extend # Mc SHARADA SIGN VISARGA 111B3..111B5 ; Extend # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II 111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O 111BF..111C0 ; Extend # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA +1122C..1122E ; Extend # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II +1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11232..11233 ; Extend # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU +11234 ; Extend # Mn KHOJKI SIGN ANUSVARA +11235 ; Extend # Mc KHOJKI SIGN VIRAMA +11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA +112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II +112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11301 ; Extend # Mn GRANTHA SIGN CANDRABINDU +11302..11303 ; Extend # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA +1133C ; Extend # Mn GRANTHA SIGN NUKTA +1133E..1133F ; Extend # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I +11340 ; Extend # Mn GRANTHA VOWEL SIGN II +11341..11344 ; Extend # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR +11347..11348 ; Extend # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI +1134B..1134D ; Extend # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA +11357 ; Extend # Mc GRANTHA AU LENGTH MARK +11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II +114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E +114BA ; Extend # Mn TIRHUTA VOWEL SIGN SHORT E +114BB..114BE ; Extend # Mc [4] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN AU +114BF..114C0 ; Extend # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C1 ; Extend # Mc TIRHUTA SIGN VISARGA +114C2..114C3 ; Extend # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115AF..115B1 ; Extend # Mc [3] SIDDHAM VOWEL SIGN AA..SIDDHAM VOWEL SIGN II +115B2..115B5 ; Extend # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115B8..115BB ; Extend # Mc [4] SIDDHAM VOWEL SIGN E..SIDDHAM VOWEL SIGN AU +115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BE ; Extend # Mc SIDDHAM SIGN VISARGA +115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +11630..11632 ; Extend # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II +11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163B..1163C ; Extend # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU +1163D ; Extend # Mn MODI SIGN ANUSVARA +1163E ; Extend # Mc MODI SIGN VISARGA +1163F..11640 ; Extend # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA 116AB ; Extend # Mn TAKRI SIGN ANUSVARA 116AC ; Extend # Mc TAKRI SIGN VISARGA 116AD ; Extend # Mn TAKRI VOWEL SIGN AA @@ -372,8 +424,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 116B0..116B5 ; Extend # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU 116B6 ; Extend # Mc TAKRI SIGN VIRAMA 116B7 ; Extend # Mn TAKRI SIGN NUKTA +16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1D165..1D166 ; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; Extend # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -381,9 +436,10 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO 1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1649 +# Total code points: 1834 # ================================================ @@ -396,7 +452,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 # ================================================ 00AD ; Format # Cf SOFT HYPHEN -0600..0604 ; Format # Cf [5] ARABIC NUMBER SIGN..ARABIC SIGN SAMVAT +0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE 061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK @@ -409,11 +465,12 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR 110BD ; Format # Cf KAITHI NUMBER SIGN +1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Format # Cf LANGUAGE TAG E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 143 +# Total code points: 148 # ================================================ @@ -702,6 +759,10 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG 0523 ; Lower # L& CYRILLIC SMALL LETTER EN WITH MIDDLE HOOK 0525 ; Lower # L& CYRILLIC SMALL LETTER PE WITH DESCENDER 0527 ; Lower # L& CYRILLIC SMALL LETTER SHHA WITH DESCENDER +0529 ; Lower # L& CYRILLIC SMALL LETTER EN WITH LEFT HOOK +052B ; Lower # L& CYRILLIC SMALL LETTER DZZHE +052D ; Lower # L& CYRILLIC SMALL LETTER DCHE +052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Lower # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN 1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Lower # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -969,6 +1030,9 @@ A691 ; Lower # L& CYRILLIC SMALL LETTER TSSE A693 ; Lower # L& CYRILLIC SMALL LETTER TCHE A695 ; Lower # L& CYRILLIC SMALL LETTER HWE A697 ; Lower # L& CYRILLIC SMALL LETTER SHWE +A699 ; Lower # L& CYRILLIC SMALL LETTER DOUBLE O +A69B ; Lower # L& CYRILLIC SMALL LETTER CROSSED O +A69C..A69D ; Lower # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A723 ; Lower # L& LATIN SMALL LETTER EGYPTOLOGICAL ALEF A725 ; Lower # L& LATIN SMALL LETTER EGYPTOLOGICAL AIN A727 ; Lower # L& LATIN SMALL LETTER HENG @@ -1019,7 +1083,12 @@ A787 ; Lower # L& LATIN SMALL LETTER INSULAR T A78C ; Lower # L& LATIN SMALL LETTER SALTILLO A78E ; Lower # L& LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A791 ; Lower # L& LATIN SMALL LETTER N WITH DESCENDER -A793 ; Lower # L& LATIN SMALL LETTER C WITH BAR +A793..A795 ; Lower # L& [3] LATIN SMALL LETTER C WITH BAR..LATIN SMALL LETTER H WITH PALATAL HOOK +A797 ; Lower # L& LATIN SMALL LETTER B WITH FLOURISH +A799 ; Lower # L& LATIN SMALL LETTER F WITH STROKE +A79B ; Lower # L& LATIN SMALL LETTER VOLAPUK AE +A79D ; Lower # L& LATIN SMALL LETTER VOLAPUK OE +A79F ; Lower # L& LATIN SMALL LETTER VOLAPUK UE A7A1 ; Lower # L& LATIN SMALL LETTER G WITH OBLIQUE STROKE A7A3 ; Lower # L& LATIN SMALL LETTER K WITH OBLIQUE STROKE A7A5 ; Lower # L& LATIN SMALL LETTER N WITH OBLIQUE STROKE @@ -1027,10 +1096,14 @@ A7A7 ; Lower # L& LATIN SMALL LETTER R WITH OBLIQUE STROKE A7A9 ; Lower # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M +AB30..AB5A ; Lower # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG +AB5C..AB5F ; Lower # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK +AB64..AB65 ; Lower # L& [2] LATIN SMALL LETTER INVERTED ALPHA..GREEK LETTER SMALL CAPITAL OMEGA FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z 1D44E..1D454 ; Lower # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G 1D456..1D467 ; Lower # L& [18] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL Z @@ -1060,7 +1133,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA -# Total code points: 1933 +# Total code points: 2029 # ================================================ @@ -1211,6 +1284,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0370 ; Upper # L& GREEK CAPITAL LETTER HETA 0372 ; Upper # L& GREEK CAPITAL LETTER ARCHAIC SAMPI 0376 ; Upper # L& GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA +037F ; Upper # L& GREEK CAPITAL LETTER YOT 0386 ; Upper # L& GREEK CAPITAL LETTER ALPHA WITH TONOS 0388..038A ; Upper # L& [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS 038C ; Upper # L& GREEK CAPITAL LETTER OMICRON WITH TONOS @@ -1330,6 +1404,10 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0522 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH MIDDLE HOOK 0524 ; Upper # L& CYRILLIC CAPITAL LETTER PE WITH DESCENDER 0526 ; Upper # L& CYRILLIC CAPITAL LETTER SHHA WITH DESCENDER +0528 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK +052A ; Upper # L& CYRILLIC CAPITAL LETTER DZZHE +052C ; Upper # L& CYRILLIC CAPITAL LETTER DCHE +052E ; Upper # L& CYRILLIC CAPITAL LETTER EL WITH DESCENDER 0531..0556 ; Upper # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 10A0..10C5 ; Upper # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10C7 ; Upper # L& GEORGIAN CAPITAL LETTER YN @@ -1589,6 +1667,8 @@ A690 ; Upper # L& CYRILLIC CAPITAL LETTER TSSE A692 ; Upper # L& CYRILLIC CAPITAL LETTER TCHE A694 ; Upper # L& CYRILLIC CAPITAL LETTER HWE A696 ; Upper # L& CYRILLIC CAPITAL LETTER SHWE +A698 ; Upper # L& CYRILLIC CAPITAL LETTER DOUBLE O +A69A ; Upper # L& CYRILLIC CAPITAL LETTER CROSSED O A722 ; Upper # L& LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF A724 ; Upper # L& LATIN CAPITAL LETTER EGYPTOLOGICAL AIN A726 ; Upper # L& LATIN CAPITAL LETTER HENG @@ -1638,14 +1718,21 @@ A78B ; Upper # L& LATIN CAPITAL LETTER SALTILLO A78D ; Upper # L& LATIN CAPITAL LETTER TURNED H A790 ; Upper # L& LATIN CAPITAL LETTER N WITH DESCENDER A792 ; Upper # L& LATIN CAPITAL LETTER C WITH BAR +A796 ; Upper # L& LATIN CAPITAL LETTER B WITH FLOURISH +A798 ; Upper # L& LATIN CAPITAL LETTER F WITH STROKE +A79A ; Upper # L& LATIN CAPITAL LETTER VOLAPUK AE +A79C ; Upper # L& LATIN CAPITAL LETTER VOLAPUK OE +A79E ; Upper # L& LATIN CAPITAL LETTER VOLAPUK UE A7A0 ; Upper # L& LATIN CAPITAL LETTER G WITH OBLIQUE STROKE A7A2 ; Upper # L& LATIN CAPITAL LETTER K WITH OBLIQUE STROKE A7A4 ; Upper # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Upper # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA ; Upper # L& LATIN CAPITAL LETTER H WITH HOOK +A7AA..A7AD ; Upper # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7B0..A7B1 ; Upper # L& [2] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER TURNED T FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z 1D434..1D44D ; Upper # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z 1D468..1D481 ; Upper # L& [26] MATHEMATICAL BOLD ITALIC CAPITAL A..MATHEMATICAL BOLD ITALIC CAPITAL Z @@ -1677,8 +1764,11 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1D756..1D76E ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA 1D790..1D7A8 ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7CA ; Upper # L& MATHEMATICAL BOLD CAPITAL DIGAMMA +1F130..1F149 ; Upper # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z +1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z +1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1514 +# Total code points: 1641 # ================================================ @@ -1716,15 +1806,13 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN -08A0 ; OLetter # Lo ARABIC LETTER BEH WITH SMALL V BELOW -08A2..08AC ; OLetter # Lo [11] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER ROHINGYA YEH +08A0..08B2 ; OLetter # Lo [19] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE 0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; OLetter # Lo DEVANAGARI OM 0958..0961 ; OLetter # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL 0971 ; OLetter # Lm DEVANAGARI SIGN HIGH SPACING DOT -0972..0977 ; OLetter # Lo [6] DEVANAGARI LETTER CANDRA A..DEVANAGARI LETTER UUE -0979..097F ; OLetter # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA +0972..0980 ; OLetter # Lo [15] DEVANAGARI LETTER CANDRA A..BENGALI ANJI 0985..098C ; OLetter # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L 098F..0990 ; OLetter # Lo [2] BENGALI LETTER E..BENGALI LETTER AI 0993..09A8 ; OLetter # Lo [22] BENGALI LETTER O..BENGALI LETTER NA @@ -1779,8 +1867,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0C05..0C0C ; OLetter # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L 0C0E..0C10 ; OLetter # Lo [3] TELUGU LETTER E..TELUGU LETTER AI 0C12..0C28 ; OLetter # Lo [23] TELUGU LETTER O..TELUGU LETTER NA -0C2A..0C33 ; OLetter # Lo [10] TELUGU LETTER PA..TELUGU LETTER LLA -0C35..0C39 ; OLetter # Lo [5] TELUGU LETTER VA..TELUGU LETTER HA +0C2A..0C39 ; OLetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C59 ; OLetter # Lo [2] TELUGU LETTER TSA..TELUGU LETTER DZA 0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL @@ -1864,6 +1951,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1681..169A ; OLetter # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH 16A0..16EA ; OLetter # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; OLetter # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL +16F1..16F8 ; OLetter # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC 1700..170C ; OLetter # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA 170E..1711 ; OLetter # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA 1720..1731 ; OLetter # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA @@ -1879,7 +1967,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1880..18A8 ; OLetter # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; OLetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; OLetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S -1900..191C ; OLetter # Lo [29] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER HA +1900..191E ; OLetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA 1950..196D ; OLetter # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI 1970..1974 ; OLetter # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 1980..19AB ; OLetter # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA @@ -1949,6 +2037,7 @@ A6A0..A6E5 ; OLetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI A6E6..A6EF ; OLetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM A717..A71F ; OLetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A788 ; OLetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A7F7 ; OLetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7FB..A801 ; OLetter # Lo [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I A803..A805 ; OLetter # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O A807..A80A ; OLetter # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO @@ -1962,6 +2051,10 @@ A930..A946 ; OLetter # Lo [23] REJANG LETTER KA..REJANG LETTER A A960..A97C ; OLetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH A984..A9B2 ; OLetter # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA A9CF ; OLetter # Lm JAVANESE PANGRANGKEP +A9E0..A9E4 ; OLetter # Lo [5] MYANMAR LETTER SHAN GHA..MYANMAR LETTER SHAN BHA +A9E6 ; OLetter # Lm MYANMAR MODIFIER LETTER SHAN REDUPLICATION +A9E7..A9EF ; OLetter # Lo [9] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING NNA +A9FA..A9FE ; OLetter # Lo [5] MYANMAR LETTER TAI LAING LLA..MYANMAR LETTER TAI LAING BHA AA00..AA28 ; OLetter # Lo [41] CHAM LETTER A..CHAM LETTER HA AA40..AA42 ; OLetter # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG AA44..AA4B ; OLetter # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS @@ -1969,7 +2062,7 @@ AA60..AA6F ; OLetter # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAM AA70 ; OLetter # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION AA71..AA76 ; OLetter # Lo [6] MYANMAR LETTER KHAMTI XA..MYANMAR LOGOGRAM KHAMTI HM AA7A ; OLetter # Lo MYANMAR LETTER AITON RA -AA80..AAAF ; OLetter # Lo [48] TAI VIET LETTER LOW KO..TAI VIET LETTER HIGH O +AA7E..AAAF ; OLetter # Lo [50] MYANMAR LETTER SHWE PALAUNG CHA..TAI VIET LETTER HIGH O AAB1 ; OLetter # Lo TAI VIET VOWEL AA AAB5..AAB6 ; OLetter # Lo [2] TAI VIET VOWEL E..TAI VIET VOWEL O AAB9..AABD ; OLetter # Lo [5] TAI VIET VOWEL UEA..TAI VIET VOWEL AN @@ -2023,22 +2116,30 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10140..10174 ; OLetter # Nl [53] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ACROPHONIC STRATIAN FIFTY MNAS 10280..1029C ; OLetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; OLetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 -10300..1031E ; OLetter # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU +10300..1031F ; OLetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10330..10340 ; OLetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA 10341 ; OLetter # Nl GOTHIC LETTER NINETY 10342..10349 ; OLetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; OLetter # Nl GOTHIC LETTER NINE HUNDRED +10350..10375 ; OLetter # Lo [38] OLD PERMIC LETTER AN..OLD PERMIC LETTER IA 10380..1039D ; OLetter # Lo [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU 103A0..103C3 ; OLetter # Lo [36] OLD PERSIAN SIGN A..OLD PERSIAN SIGN HA 103C8..103CF ; OLetter # Lo [8] OLD PERSIAN SIGN AURAMAZDAA..OLD PERSIAN SIGN BUUMISH 103D1..103D5 ; OLetter # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 10450..1049D ; OLetter # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +10500..10527 ; OLetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE +10530..10563 ; OLetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10600..10736 ; OLetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 +10740..10755 ; OLetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE +10760..10767 ; OLetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 10800..10805 ; OLetter # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; OLetter # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; OLetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO 10837..10838 ; OLetter # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE 1083C ; OLetter # Lo CYPRIOT SYLLABLE ZA 1083F..10855 ; OLetter # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW +10860..10876 ; OLetter # Lo [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW +10880..1089E ; OLetter # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW 10900..10915 ; OLetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; OLetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 10980..109B7 ; OLetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA @@ -2048,25 +2149,62 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10A15..10A17 ; OLetter # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA 10A19..10A33 ; OLetter # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA 10A60..10A7C ; OLetter # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH +10A80..10A9C ; OLetter # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH +10AC0..10AC7 ; OLetter # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW +10AC9..10AE4 ; OLetter # Lo [28] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER TAW 10B00..10B35 ; OLetter # Lo [54] AVESTAN LETTER A..AVESTAN LETTER HE 10B40..10B55 ; OLetter # Lo [22] INSCRIPTIONAL PARTHIAN LETTER ALEPH..INSCRIPTIONAL PARTHIAN LETTER TAW 10B60..10B72 ; OLetter # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW +10B80..10B91 ; OLetter # Lo [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW 10C00..10C48 ; OLetter # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH 11003..11037 ; OLetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA 11083..110AF ; OLetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; OLetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; OLetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA +11150..11172 ; OLetter # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA +11176 ; OLetter # Lo MAHAJANI LIGATURE SHRI 11183..111B2 ; OLetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA 111C1..111C4 ; OLetter # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM +111DA ; OLetter # Lo SHARADA EKAM +11200..11211 ; OLetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA +11213..1122B ; OLetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +112B0..112DE ; OLetter # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA +11305..1130C ; OLetter # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L +1130F..11310 ; OLetter # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI +11313..11328 ; OLetter # Lo [22] GRANTHA LETTER OO..GRANTHA LETTER NA +1132A..11330 ; OLetter # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA +11332..11333 ; OLetter # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA +11335..11339 ; OLetter # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA +1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA +1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA +114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG +114C7 ; OLetter # Lo TIRHUTA OM +11580..115AE ; OLetter # Lo [47] SIDDHAM LETTER A..SIDDHAM LETTER HA +11600..1162F ; OLetter # Lo [48] MODI LETTER A..MODI LETTER LLA +11644 ; OLetter # Lo MODI SIGN HUVA 11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA -12000..1236E ; OLetter # Lo [879] CUNEIFORM SIGN A..CUNEIFORM SIGN ZUM -12400..12462 ; OLetter # Nl [99] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN OLD ASSYRIAN ONE QUARTER +118FF ; OLetter # Lo WARANG CITI OM +11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +12000..12398 ; OLetter # Lo [921] CUNEIFORM SIGN A..CUNEIFORM SIGN UM TIMES ME +12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 13000..1342E ; OLetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 16800..16A38 ; OLetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ +16A40..16A5E ; OLetter # Lo [31] MRO LETTER TA..MRO LETTER TEK +16AD0..16AED ; OLetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I +16B00..16B2F ; OLetter # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU +16B40..16B43 ; OLetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM +16B63..16B77 ; OLetter # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS +16B7D..16B8F ; OLetter # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ 16F00..16F44 ; OLetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 1B000..1B001 ; OLetter # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M +1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK +1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL +1BC90..1BC99 ; OLetter # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1E800..1E8C4 ; OLetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1EE00..1EE03 ; OLetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; OLetter # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; OLetter # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -2105,7 +2243,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 97841 +# Total code points: 99420 # ================================================ @@ -2123,6 +2261,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C66..0C6F ; Numeric # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0CE6..0CEF ; Numeric # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0D66..0D6F ; Numeric # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE +0DE6..0DEF ; Numeric # Nd [10] SINHALA LITH DIGIT ZERO..SINHALA LITH DIGIT NINE 0E50..0E59 ; Numeric # Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE 0ED0..0ED9 ; Numeric # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE 0F20..0F29 ; Numeric # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE @@ -2142,6 +2281,7 @@ A620..A629 ; Numeric # Nd [10] VAI DIGIT ZERO..VAI DIGIT NINE A8D0..A8D9 ; Numeric # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A900..A909 ; Numeric # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE A9D0..A9D9 ; Numeric # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE +A9F0..A9F9 ; Numeric # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DIGIT NINE AA50..AA59 ; Numeric # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE @@ -2149,10 +2289,16 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N 110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE 11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE +112F0..112F9 ; Numeric # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE +11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE +118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE -# Total code points: 452 +# Total code points: 532 # ================================================ @@ -2167,8 +2313,6 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP 0021 ; STerm # Po EXCLAMATION MARK 003F ; STerm # Po QUESTION MARK -055C ; STerm # Po ARMENIAN EXCLAMATION MARK -055E ; STerm # Po ARMENIAN QUESTION MARK 0589 ; STerm # Po ARMENIAN FULL STOP 061F ; STerm # Po ARABIC QUESTION MARK 06D4 ; STerm # Po ARABIC FULL STOP @@ -2191,6 +2335,7 @@ FF0E ; ATerm # Po FULLWIDTH FULL STOP 203C..203D ; STerm # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG 2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK 2E2E ; STerm # Po REVERSED QUESTION MARK +2E3C ; STerm # Po STENOGRAPHIC FULL STOP 3002 ; STerm # Po IDEOGRAPHIC FULL STOP A4FF ; STerm # Po LISU PUNCTUATION FULL STOP A60E..A60F ; STerm # Po [2] VAI FULL STOP..VAI QUESTION MARK @@ -2212,8 +2357,19 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK 111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA +111CD ; STerm # Po SHARADA SUTRA MARK +11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA +1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK +115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA +115C9 ; STerm # Po SIDDHAM END OF TEXT MARK +11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA +16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA +16AF5 ; STerm # Po BASSA VAH FULL STOP +16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB +16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS +1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP -# Total code points: 80 +# Total code points: 96 # ================================================ @@ -2254,7 +2410,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 230B ; Close # Pe RIGHT FLOOR 2329 ; Close # Ps LEFT-POINTING ANGLE BRACKET 232A ; Close # Pe RIGHT-POINTING ANGLE BRACKET -275B..275E ; Close # So [4] HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT +275B..2760 ; Close # So [6] HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT..HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT 2768 ; Close # Ps MEDIUM LEFT PARENTHESIS ORNAMENT 2769 ; Close # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT 276A ; Close # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT @@ -2332,6 +2488,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 2E27 ; Close # Pe RIGHT SIDEWAYS U BRACKET 2E28 ; Close # Ps LEFT DOUBLE PARENTHESIS 2E29 ; Close # Pe RIGHT DOUBLE PARENTHESIS +2E42 ; Close # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK 3008 ; Close # Ps LEFT ANGLE BRACKET 3009 ; Close # Pe RIGHT ANGLE BRACKET 300A ; Close # Ps LEFT DOUBLE ANGLE BRACKET @@ -2352,8 +2509,8 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 301B ; Close # Pe RIGHT WHITE SQUARE BRACKET 301D ; Close # Ps REVERSED DOUBLE PRIME QUOTATION MARK 301E..301F ; Close # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK -FD3E ; Close # Ps ORNATE LEFT PARENTHESIS -FD3F ; Close # Pe ORNATE RIGHT PARENTHESIS +FD3E ; Close # Pe ORNATE LEFT PARENTHESIS +FD3F ; Close # Ps ORNATE RIGHT PARENTHESIS FE17 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET FE18 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET FE35 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS @@ -2390,8 +2547,9 @@ FF5F ; Close # Ps FULLWIDTH LEFT WHITE PARENTHESIS FF60 ; Close # Pe FULLWIDTH RIGHT WHITE PARENTHESIS FF62 ; Close # Ps HALFWIDTH LEFT CORNER BRACKET FF63 ; Close # Pe HALFWIDTH RIGHT CORNER BRACKET +1F676..1F678 ; Close # So [3] SANS-SERIF HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT..SANS-SERIF HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT -# Total code points: 181 +# Total code points: 187 # ================================================ |